28th week of 2022 patent applcation highlights part 46 |
Patent application number | Title | Published |
20220222400 | SIMULATION APPARATUS, SIMULATION METHOD, AND COMPUTER READABLE MEDIUM STORING PROGRAM - There is provided a simulation apparatus that analyzes a flow of a fluid using a particle method, the apparatus including: a processing unit that develops a position of each of a plurality of particles in a time domain using the particle method based on a simulation condition. The processing unit divides an analysis space into a plurality of division regions, disposes, in each of the plurality of division regions, the plurality of particles having sizes different from each other for each division region, determines whether or not to add new particles to the division region and determines a portion to which particles are to be added, for each of the plurality of division regions, and adds new particles to a portion determined as the portion to which particles are to be added in a case where new particles are to be added. | 2022-07-14 |
20220222401 | INTELLIGENT BIT DESIGN - A method includes determining a bit design based on a design criterion, determining a cutter design to be mounted on the bit design at a bit design position based on cutter information, wherein the cutter information is based on a historical cutter performance metric of one or more cutters having the cutter design. The method also includes generating a drill bit model based on the bit design and the cutter design and determining that the drill bit model meets the design criterion. | 2022-07-14 |
20220222402 | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING PROGRAM - An information processing device includes processing circuitry configured to acquire a plurality of pieces of data, input the pieces of data to a model as input data, and in a case of obtaining output data output from the model, calculate an importance of each component of the input data with respect to the output data based on the input data and the output data, acquire a binding coefficient indicating a relevance among components of the input data, calculate a bound importance obtained by applying the binding coefficient to the importance, and create information indicating the bound importance of each input item. | 2022-07-14 |
20220222403 | Design Method, Design Device, and Program for Regenerator - A design method for an energy conversion device, the method causing a design device to execute processing comprising: a step of creating an equation showing a thermal efficiency with respect to a predetermined variable including a flow path diameter (equivalent flow path diameter), a frequency, a temperature gradient, and specific acoustic impedance of a flow path in a regenerator performing energy conversion based on an equation of fluid related to the oscillating flow; a step of selecting any one input parameter of the flow path diameter (equivalent flow path diameter), the frequency, the temperature gradient, and the specific acoustic impedance; a step of creating an equation related to the selected parameter based on the equation showing the thermal efficiency and an equation showing a shape of the flow path of the regenerator; and a step of uniquely calculating a value of the selected parameter maximizing the thermal efficiency based on the equation related to the selected parameter by applying a plurality of design values other than the selected parameter related to the energy conversion device which is a design target. | 2022-07-14 |
20220222404 | OPTIMIZATION OF PARAMETERS FOR SYNTHESIS OF A TOPOLOGY USING A DISCRIMINANT FUNCTION MODULE - A tool is disclosed that includes a discriminant module. The discriminant module finds one configuration, which is selected from many different possible and legal configurations, that is optimal. The optimal configuration is translated into a set of optimized parameters (identified from the library of parameters that the user can select from) and provided to the designer. The designer reviews (and can manually revise or change) the optimized parameters. The optimized parameters are translated into engineering parameters. The engineering parameters are passed, as an input, to the RTL generation module. The RTL generation module produces the RTL description of the hardware function that is optimal and meets the designer's defined requirements. | 2022-07-14 |
20220222405 | DESIGN SUPPORT SYSTEM AND COMPUTER READABLE MEDIUM - A software studying unit ( | 2022-07-14 |
20220222406 | Solver Creation Tool for System Simulation - A method for generating a simulator of a target system includes parsing data defining operational components and component parameters, searching for and obtaining model code definitions within a library database, customizing the model code definitions based on the component parameters, constructing a system model, and generating solver code based the customized model code definitions of the target system. The solver code may be indicative of input and output operation of the target system. The method may also include concatenating the system model with the solver code to form a solver function definition for the target system, and converting the solver function definition into an field programmable gate array (FPGA) core or central processing unit (CPU) core for execution on a simulation device for the target system. | 2022-07-14 |
20220222407 | CHIP DESIGN METHOD, CHIP DESIGN DEVICE, CHIP, AND ELECTRONIC DEVICE - A chip design method, a chip design device, a chip, and an electronic device are provided. The chip design method includes: determining at least one power state of the chip, one power state of the at least one power state including switch states of respective power domains on the chip in a chip operation mode, and the at least one power state including a first power state; determining control signals sent by changed power domains in the respective power domains in a case where a power state of the chip is switched to the first power state, in a case where the power state of the chip is switched to the first power state, switch states of the changed power domains changing; and analyzing timing dependency between the control signals to determine timing dependency between power domains to which the control signals act in the first power state. | 2022-07-14 |
20220222408 | SYSTEM ON CHIP ARCHITECTURE, INTERPOSER, FPGA AND METHOD OF DESIGN - A system on chip device, where the active interposer/chassis incorporates an FPGA/eFPGA, may be used to flexibly implement interposer/chassis operations such as a network on chip communication protocols, state machines, interfaces, or data conversion, digital interfaces operations, data filtering operations, data filtering operations, and the like, or any other digital operation as required, so that analogue and mixed signals only need be addressed in dedicated chiplets. | 2022-07-14 |
20220222409 | METHOD AND SYSTEM FOR PREDICTING REMAINING USEFUL LIFE OF ANALOG CIRCUIT - A method and a system for predicting remaining useful life of an analog circuit are provided. A simulation model of the analog circuit is built, and an output voltage is selected as a degradation variable. Different degradation cycles are set to extract degradation features of the output voltage. Key features that can reflect a degradation trend of a circuit component are selected. Multi-feature fusion and similarity model are adopted to construct a health indicator curve to characterize a degradation process of a full life cycle of different circuit components. A prediction model is established based on a temporal convolutional network and an attention mechanism, and preferably selected features and a constructed health indicator database are used as an input of a TCN-attention network to predict the remaining useful life of the circuit component. | 2022-07-14 |
20220222410 | SIMULATION MODEL AND SIMULATION METHOD - An object of the present disclosure is to accurately simulate the operation of a CSTBT. The simulation model of a CSTBT includes a MOSFET, a diode whose cathode is connected to the drain of the MOSFET, capacitance C | 2022-07-14 |
20220222411 | METHOD AND SYSTEM FOR DESIGNING AN INTEGRATED CIRCUIT, AND AN INTEGRATED CIRCUIT - A computer-implemented method for designing a floorplan for an integrated circuit includes determining a circuit design for the integrated circuit, wherein the circuit design for the integrated circuit has a system device and a logic device. Logical definitions for the system device and the logic device are determined. A plurality of interconnect devices are determined. A plurality of interconnect figures of merit (FOMs) associated with the plurality of interconnect devices are also determined. The method includes determining, with an optimization operation, a candidate floorplan for the circuit design based upon the logical definitions for the system device, the logic device, the plurality of interconnect devices, and the interconnect FOMs for the interconnect devices. The candidate floorplan is determined based upon parameters associated with computational performance, power consumption, and physical area of the candidate floorplan for the circuit design. The candidate floorplan is implemented as the integrated circuit. | 2022-07-14 |
20220222412 | ELECTRONIC GENERATION OF THREE-DIMENSIONAL QUANTUM CIRCUIT DIAGRAMS - Systems and techniques that facilitate electronic generation of three-dimensional quantum circuit diagrams are provided. In various embodiments, a system can comprise a data component that can access qubit topology data characterizing a quantum computing device. In various aspects, the system can further comprise a rendering component that can render a three-dimensional quantum circuit diagram based on the qubit topology data. In various instances, the qubit topology data can indicate which qubits of the quantum computing device are coupled together. In various cases, the rendering component can render the three-dimensional quantum circuit diagram by generating a two-dimensional qubit configuration model of the quantum computing device based on which qubits of the quantum computing device are coupled together, by extruding one or more qubit lines three-dimensionally outward from the two-dimensional qubit configuration model, and by rendering one or more quantum gates on the one or more qubit lines. | 2022-07-14 |
20220222413 | Apparatus, Device, Method and Computer Program for Generating a Circuit Design of Polynomial Interpolation Hardware - Examples relate to an apparatus, a device, a method, and a computer program for generating a circuit design of polynomial interpolation hardware. The apparatus comprises processing circuitry configured to sub-divide the range of input values of the polynomial interpolation hardware into a plurality of regions, determine, for each region of the plurality of regions, a set of polynomial approximations that are suitable in view of a desired accuracy of the polynomial interpolation hardware, remove, based on one or more user-defined objectives, polynomial approximations from the respective sets of polynomial approximations, and generate the circuit design of the polynomial interpolation hardware based on one polynomial approximation per region remaining in the respective sets of polynomial approximations after the iterative removal of polynomial approximations. | 2022-07-14 |
20220222414 | DESIGN AUTOMATION FOR MONOLITHIC 3D DEVICES - A method of designing a 3D Integrated Circuit including: partitioning at least one design into at least a first and a second level, where the first level includes logic and the second level includes memory; then performing a first placement of the second level using a placer executed by a computer, the placer is a part of a Computer Aided Design tool, where the 3D Integrated Circuit includes a plurality of connections between the first level and the second level; and performing a second placement of the first level based on the first placement, where memory includes a first memory array, the logic includes a first logic circuit configured so as to write data to first memory array. Performing the first placement includes placing the first memory array, and where performing the second placement includes placing the first logic circuit based on the first placement of the first memory array. | 2022-07-14 |
20220222415 | AUTOMATED DYNAMIC DOCUMENT GENERATOR - A method for automated dynamic document generation includes: storing, in a memory of a document generator, (i) a common pool of objects each defining document content and having respective object identifiers, (ii) a plurality of templates having respective template identifiers and containing respective template subsets of the object identifiers, and (iii) a plurality of master templates having respective master template identifiers and containing respective master template subsets of the object identifiers; establishing a connection to a data source; detecting document initiation data in the data source including a selected one of the template identifiers; responsive to the detection, retrieving a selected one of the master template identifiers associated with the selected template identifier; retrieving the template subset and the master template subset of objects corresponding to the selected template identifier and the selected master template identifier; and generating a document according to the template subset and the master template subset. | 2022-07-14 |
20220222416 | SIMULATED THUMBNAIL PREVIEWS FOR FILES - A thumbnail preview of a file enables a user to recognize the file without opening it. An algorithmic approach to generating simulated thumbnail previews is provided. This approach includes executing rules for determining and implementing one or more rendering schemas to simulate different content types within a portion of a file. A simulated thumbnail preview is generated from the simulated content types based on a file structure. Since users may rely on the general structure and distinguishing content elements of a thumbnail for recognizing a file, these distinguishing elements are maintained based on different rendering schemas used to create a simulated thumbnail. Moreover, the algorithmic approach promotes consistent simulated thumbnails across clients, regardless of client processing capabilities, form factors, customized theming, or the like. Based on the rules for rendering various content types, the simulated thumbnails are also consistently generated across documents. | 2022-07-14 |
20220222417 | ANNOTATION CONTROL FEATURES FOR SYSTEMS AND PLATFORMS THAT SUPPORT INFORMATION ANALYSIS, EDITING, AND STORAGE IN WEB BROWSERS - The present disclosure relates to systems for creating, organizing, viewing, and connecting annotations of web documents within web browsers that are made to be annotation capable. The rationale for designing systems using the principles disclosed herein is explained in detail. This rationale is illustrated using sequence diagrams and use case diagrams to elucidate the need for the design principles and data structures employed. The disclosure also provides exemplary hardware specifications and describes design tradeoffs. | 2022-07-14 |
20220222418 | GENERATING AND PRESENTING CUSTOMIZED INFORMATION CARDS - Methods, systems, apparatus, and computer-readable media for generating and presenting customized information cards. In some implementations, an indication of a data set is received. Data indicating a selection of an element of the data set is received. An indication of items in the data set that are associated with the selected element is received. Data is received indicating a selection of one or more of the items that are associated with the selected element of the data set. Card data defining an information card for the selected element of the data set is stored. The card definition data can indicate the selected one or more items and a reference to the data set. | 2022-07-14 |
20220222419 | Dynamic Web Content Based on Contextual Profile - Dynamic web content personalization may be used to alter a web page such that two different people who view that web page do not see the exact same content on that page. The present disclosure includes techniques that allow a web page to be structured, via underlying source code, so that content can be dynamically generated based on a user transaction history. Further, dynamic content customization can effectively change the layout and functionality of a web page in ways not previously contemplated. For example, different control elements may become accessible based on a particular contextual user profile assigned to a user based on a transaction history. Modular content modules may also have a different appearance for different users. | 2022-07-14 |
20220222420 | CONSTRUCTING A PATH FOR CHARACTER GLYPHS - Techniques described herein take character glyphs as input and generate a text-on-a-path text object that includes the character glyphs arranged in a determined order along a path. For instance, a method described herein includes accessing character glyphs in input data. The method further includes determining an order for the character glyphs based on relative positions and orientations of the character glyphs in the input data. The method further includes generating a path for the character glyphs, based on the order, and associating the path with the character glyphs. Further, the method includes generating a text object that includes the set of character glyphs arranged in the order along the path. | 2022-07-14 |
20220222421 | DIGITAL PROCESSING SYSTEMS AND METHODS FOR TAGGING EXTRACTION ENGINE FOR GENERATING NEW DOCUMENTS IN COLLABORATIVE WORK SYSTEMS - Systems, methods, and computer-readable media for tagging, extracting, and consolidating information from electronically stored files are disclosed. The systems and methods may involve presenting to an entity viewing at least one source document a tag interface for enabling selection and tagging of document segments with at least one characteristic associated with each document segment; identifying tagged segments within the at least one source document; accessing a consolidation rule containing instructions for combining the tagged segments; implementing the consolidation rule to associate document segments sharing common tags; and outputting for display at least one tagged-based consolidation document grouping together commonly tagged document segments. | 2022-07-14 |
20220222422 | SYSTEMS, METHODS, AND DEVICES FOR E-MAIL RENDERING - Systems, methods, and storage media for rendering and displaying e-mails are disclosed. Exemplary implementations may: receive a first file, wherein the first file comprises an e-mail written in HTML; determine a display structure of the contents of the email written in HTML; access a DOM structure of the first file; create a second file in a first file format by parsing the DOM structure, wherein the second file comprises a first object; create a third file comprising one or more first markup language blocks in a first markup language format; process the one or more first markup language blocks to create a plurality of second markup language components; identify a mapping between the first file and the plurality of second markup language components; create, based on the mapping, a fourth file in a HTML format; and render and display the fourth file in one or more email clients. | 2022-07-14 |
20220222423 | SYSTEM AND COMPUTER-IMPLEMENTED METHOD FOR IN-PAGE REPORTING OF USER FEEDBACK ON A WEBSITE OR MOBILE APP - Computer-implemented techniques are disclosed for presenting an in-page console on a website for reviewing interaction data captured during user interaction with one or more web pages of the website. The web browser activates the in-page console via an activation procedure. One or more of the web pages of the website are selected after activation of the in-page console. A feedback badge on the website can be replaced with a reporting badge upon activation of the in-page console and with the reporting badge displaying an indicator of interaction data captured for the selected web page. The in-page console is overlaid one or more of the selected web pages. The in-page console displays the interaction data, or recordings of user interaction, captured during user interaction with the selected web page to enable review of the captured interaction data for the selected web page overlaid on the selected web page. | 2022-07-14 |
20220222424 | CONVERSATIONAL USER INTERFACE SYSTEM AND METHOD OF OPERATION - Disclosed herein is a computer-implemented method of carrying on a conversation, the method including: during a conversation session, receiving an electronic query initiated by a user; based on query data associated with the query, automatically retrieving first result data from a hierarchical taxonomy; in the event that the first result data contains one or more user-selectable options, generating an electronic response to the query based at least on the one or more user-selectable options; and otherwise: based on the query data, automatically retrieving second result data from a tagged-content source and generating the electronic response to the query based at least on the second result data. | 2022-07-14 |
20220222425 | DIGITAL PROCESSING SYSTEMS AND METHODS FOR DYNAMICALLY UPDATING DOCUMENTS WITH DATA FROM LINKED FILES IN COLLABORATIVE WORK SYSTEMS - Systems, methods, and computer-readable media for automatically updating an electronic word processing document based on a change in a linked file and vice versa are disclosed. The systems and methods may involve accessing the electronic word processing document; identifying in the electronic word processing document a variable data element; accessing the external file identified in the link; pulling, from the external file, first replacement data corresponding to the current data; replacing the current data in the electronic word processing document with the first replacement data; identifying a change to the variable data element in the electronic word processing document; upon identification of the change, accessing the external file via the link; and updating the external file to reflect the change to the variable data element in the electronic word processing document. | 2022-07-14 |
20220222426 | DIGITAL PROCESSING SYSTEMS AND METHODS FOR DISPLAY PANE SCROLL LOCKING DURING COLLABORATIVE DOCUMENT EDITING IN COLLABORATIVE WORK SYSTEMS - Systems, methods, and computer-readable media for managing a display interference in an electronic collaborative word processing document are disclosed. The systems and methods may involve accessing a electronic collaborative word processing document; presenting a first and a second instance of the electronic collaborative word processing document via a first and a second hardware device running a first and a second editor, respectively; receiving from the first and the second editor during a common editing period, first and second edits to the electronic collaborative word processing document, respectively; locking a display associated with the second hardware device to suppress the pagination change caused by the first edits received by the second hardware device; and upon receipt of a scroll-up command via the second editor during the common editing period, causing the display associated with the second hardware device to reflect the pagination change caused by the first edits. | 2022-07-14 |
20220222427 | DIGITAL PROCESSING SYSTEMS AND METHODS FOR EMBEDDED LIVE APPLICATION IN-LINE IN A WORD PROCESSING DOCUMENT IN COLLABORATIVE WORK SYSTEMS - Systems, methods, and computer-readable media for causing dynamic activity in an electronic word processing document are disclosed. The systems and methods may involve accessing an electronic word processing document; presenting an interface enabling selection of a live application for embedding in the electronic word processing document; embedding, in-line with text of the electronic word processing document, a live active icon representative of the live application; presenting, in a first viewing mode, the live active icon; receiving a selection of the live active icon; in response to the selection, presenting in a second viewing mode, an expanded view of the live application; receiving a collapse instruction; and in response to the collapse instruction, reverting from the second viewing mode to the first viewing mode. | 2022-07-14 |
20220222428 | DIGITAL PROCESSING SYSTEMS AND METHODS FOR EMBEDDING A FUNCTIONING APPLICATION IN A WORD PROCESSING DOCUMENT IN COLLABORATIVE WORK SYSTEMS - Systems, methods, and computer-readable media for embedding and running an electronic non-word processing application within an electronic word processing document are disclosed. The systems and methods may involve accessing the electronic word processing document; opening the electronic word processing document within an electronic word processing application; accessing the electronic non-word processing application; embedding the electronic non-word processing application within the electronic word processing application in a manner enabling non-word processing functionality to occur from within the electronic word processing application; while the electronic non-word processing application is displayed within the electronic word processing application, receiving at least one of the inputs; and in response to receiving at least one of the inputs, causing functionality of the electronic non-word processing application to be displayed within the electronic word processing document presented by the electronic word processing application. | 2022-07-14 |
20220222429 | SELF-EXECUTING DOCUMENT REVISION - Self-executing document revision includes creating a current version of an electronic rendering of a collaborative document based on input received from a user via a communicative coupling with a data communications network. The current version's relevancy is determined by a self-executing document revisor and compared with the relevancy of a prior version of the collaborative document. In response to determining the relevancy of the current version is less than the relevancy of the prior version, one or more segments of one or more electronically stored versions of the collaborative document are selected based on a relevancy of each of the one or more segments, the relevancy of each determined by the self-executing document revisor. The self-executing document revisor generates a graphical representation of a revised version of the collaborative document by merging the one or more segments selected with the current version of the collaborative document. | 2022-07-14 |
20220222430 | PROVIDING USER-SPECIFIC PREVIEWS WITHIN TEXT - Examples described herein include systems and methods for providing user-specific previews for terms within text. An example method can include receiving tracked user behavior reflecting terms selected by a user and entered into a search. A representation of known words can be created based on the tracked user behavior. By training machine-learning models for each individual user, personalized previews can be presented when each user encounters a new body of text, such as in a webpage or email. The preview can apply to a term not previously known to the user but likely to be searched by the user, relying on content gathered from a search on a search medium that the user was likely to use. The content can be presented to the user in a graphical user interface allowing for interaction and feedback. | 2022-07-14 |
20220222431 | DIGITAL PROCESSING SYSTEMS AND METHODS FOR DYNAMIC WORK DOCUMENT UPDATES USING EMBEDDED IN-LINE LINKS IN COLLABORATIVE WORK SYSTEMS - Systems, methods, and computer-readable media for embedding within an electronic word processing document are disclosed. The systems and methods may involve accessing the electronic word processing document, wherein the electronic word processing document contains text; detecting an in-line object inserted into the text at a particular location, the in-line object including a URL-based rule linked to a portion of the text; executing the URL-based rule to retrieve internet located data corresponding to the URL-based rule; and inserting the retrieved internet-located data into the text at the particular location. | 2022-07-14 |
20220222432 | RECOMMENDING THEME PATTERNS OF A DOCUMENT - The disclosure provides a method for recommending theme patterns of a document. In some embodiments, a trigger for providing theme patterns may be detected. Current content of the document may be identified. At least one theme pattern related to the current content of the document may be provided. | 2022-07-14 |
20220222433 | SYSTEMS AND METHODS FOR CONSTRUCTING TEXTUAL OUTPUT OPTIONS - The presently disclosed embodiments may include a computer readable medium including instructions that when executed by one or more processing devices cause the one or more processing devices to perform a method. The method may include: analyzing an electronic document text; identifying in the electronic document text a first drafted text element to be modified; causing the first drafted text element to be highlighted to a user on a display; generating at least one text output option that conveys a meaning associated with the first drafted text element but includes one or more changes relative to the first drafted text element; and causing the at least one text output option to be shown to the user via the display. | 2022-07-14 |
20220222434 | ANALYZING PRESENTATIONS TO STRUCTURE METADATA FOR GENERATING QUESTIONS DIRECTED TO THE CONTENT OF THE PRESENTATIONS - A method for generating a series of questions from a presentation that includes receiving information materials for a presentation session, and converting the information materials into a text based data element. The method further includes comparing the text based data elements to a knowledge base directed to topics of interest to score the text based data elements for priority, and transforming text based data elements having a score above a threshold value into plurality of quiz metadata objects. The quiz metadata objects include context from the topics of interest. The method further includes generating quiz questions from the plurality of quiz metadata objects using the context and a set of templates of question types. | 2022-07-14 |
20220222435 | Task-Specific Text Generation Based On Multimodal Inputs - In one embodiment, a method includes accessing first sets of tokens associated with a desired task and one or more modalities associated with a context of the desired task, determining a second set of tokens for each of the one or more modalities using a classifier network associated with the modality, generating a number of embedding vectors by mapping the first sets of tokens and the second set of tokens associated with each of the one or more modalities to an embedding space, and producing a sequence of words addressing the desired task by processing the number of embedding vectors with an encoder-decoder network. | 2022-07-14 |
20220222436 | NEURAL REASONING PATH RETRIEVAL FOR MULTI-HOP TEXT COMPREHENSION - A question answering system includes: a neural network tokenizer module configured to determine a token representation of a question to be answered and token representations of candidate paragraphs of a present reasoning path for the question, respectively; a neural network module configured to: transform the token representation of the question and the token representations of the candidate paragraphs of the present reasoning path into vector representations; and append a first variable to the vector representations to produce a second variable; a search module configured to: select the candidate paragraphs from a knowledge database to extend a present reasoning path based on lexical relevance of the candidate paragraphs to the question; and selectively add ones of the candidate paragraphs to the present reasoning path; and an answer inference network module configured to selectively determine an answer to the question based on multiple different portions of the present reasoning path. | 2022-07-14 |
20220222437 | SYSTEMS AND METHODS FOR STRUCTURED PHRASE EMBEDDING AND USE THEREOF - A system and method for training and using a text embedding model may include creating structured phrases from an input text; creating turn input samples from the input text, each turn input sample based on only or consisting of input from a single turn within the text and being formed by removing structure from structured phrases; and training an embedding model using the structured phrases and turn input samples. Call input samples may be created based on input from more than one turn within the text. At each level of resolution (e.g. phrase, speaker, call), a different level of resolution may be used to create input samples. At inference an embedding may be based on a weighted combination of the sub-terms within an input phrase, each weight being based on an inverse document frequency measure for the sub-term associated with the weight. | 2022-07-14 |
20220222438 | CORPUS DATA AUGMENTATION AND DEBIASING - Machine learning model training corpus debiasing includes identifying an attribute of input text selected from the training corpus, the attribute including word(s) of the input text, and the attribute corresponding to an attribute class encompassing different possible class values, recognizing bias in the input text with respect to the attribute class, and generating output text corresponding to the attribute and imparting diversity with respect to the attribute class and relative to the input text, where generating the output text uses an optimization function based on loss objectives to minimize loss in the generated output text as compared to the input text. | 2022-07-14 |
20220222439 | GENERATING TIME-BASED RECAPS OF DOCUMENTS USING A DEEP LEARNING SEQUENCE TO SEQUENCE MODEL - Techniques are provided herein for generating improved document summaries that consider the amount of time that has passed since the user last accessed the document. The length of time that has passed since the user has accessed each previous portion of the document is used as a variable to determine how much the summary should focus on each of the previously read sections of the document. When a document is accessed by a user, a relevance score is assigned to content from previously accessed sections of that document, where the relevance score is weighted based on how long ago each of the sections was accessed by the user. Once the various content items of previous sections have been provided relevance scores, selected sentences with the highest relevance scores are fed to a deep learning sequence-to-sequence model is used to build the document summary. | 2022-07-14 |
20220222440 | SYSTEMS AND METHODS FOR ASSESSING RISK ASSOCIATED WITH A MACHINE LEARNING MODEL - Techniques for assessing risk associated with a machine learning model trained to perform a task. The techniques include: using at least one computer hardware processor to execute software to perform: obtaining natural language text including a plurality of answers to a respective plurality of questions for assessing risk for the machine learning model; identifying, using a second natural language processing (NLP) technique and from among a plurality of topics, the risk report indicating at least one risk associated with the machine learning model and at least one action to perform for mitigating the at least one risk associated with the machine learning model; and outputting the risk report to a user of the software. | 2022-07-14 |
20220222441 | MACHINE LEARNING BASED NAMED ENTITY RECOGNITION FOR NATURAL LANGUAGE PROCESSING - A system performs named entity recognition for performing natural language processing, for example, for conversation engines. The system uses context information in named entity recognition. The system includes the context of a sentence during model training and execution. The system generates high quality contextual data for training NER models. The system utilizes labeled and unlabeled contextual data for training NER models. The system provides NER models for execution in production environments. The system uses heuristics to determine whether to use a context-based NER model or a simple NER model that does not use context information. This allows the system to use simple NER models when the likelihood of improving the accuracy of prediction based on context is low. | 2022-07-14 |
20220222442 | PARAMETER LEARNING APPARATUS, PARAMETER LEARNING METHOD, AND COMPUTER READABLE RECORDING MEDIUM - A parameter learning apparatus | 2022-07-14 |
20220222443 | TECHNICAL DOCUMENT ISSUES SCANNER - A technical document scanner disclosed herein determines and categorizes various common issues among a large number of documents. An implementation of the technical document scanner is implemented using various computer process instructions including scanning a technical document to extract content, applying named entity recognition on the extracted content from the technical document to extract named entities, applying relation extraction on the named entities to extract relations between the named entities, and analyzing the relations between the entities to compose lists of high relevance entities for issue checking. | 2022-07-14 |
20220222444 | CHATBOT CONDUCTING A VIRTUAL SOCIAL DIALOGUE - Improved techniques for dialogue management are disclosed. In particular, disclosed systems facilitate improved autonomous agents that can generate a virtual social dialogue from a corpus of text. A virtual social dialogue is a dialogue between autonomous agents and user devices. For example, a virtual social dialogue can include viewpoints, concerns, or questions of various actors on a particular topic. By presenting textual content in this manner, disclosed techniques improve information comprehension and increase the practicality of autonomous agents. | 2022-07-14 |
20220222446 | PREDICTING SERVICE ISSUES - Examples are described herein for facilitating responses to computing device service requests. In various examples, natural language processing may be performed on a plurality of incoming computing device service requests associated with a plurality of computing devices. A plurality of embeddings corresponding to the plurality of computing device service requests may be generated based on the natural language processing. Based on distances between each of a particular subset of the embeddings in an embedding space, a trending service issue associated with the computing device service requests corresponding to the particular subset may be predicted. The trending service issue may be provided to a computing device servicer associated with resolving a new incoming computing device service request. | 2022-07-14 |
20220222447 | TRANSLATION METHOD AND APPARATUS, ELECTRONIC DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM - An electronic device obtains a to-be-translated sentence. The electronic device divides the to-be-translated sentence into a preset quantity of clauses. The electronic device separately translates each of the clauses to obtain a respective translation result corresponding to each of the clauses. The electronic device combines the respective translation results corresponding to each of the clauses according to semantics to obtain a target translation sentence corresponding to the to-be-translated sentence. | 2022-07-14 |
20220222448 | METHOD, APPARATUS, AND SYSTEM FOR PROVIDING INTERPRETATION RESULT USING VISUAL INFORMATION - Provided is a method of providing an interpretation result using visual information, and the method includes: acquiring a spatial domain image including line-of-sight information of a user and gaze position information in the spatial domain image; segmenting the acquired spatial domain image into a plurality of images; detecting text areas including text for each of the segmented images; generating text blocks, each of which is a text recognition result for each of the detected text areas, and determining the text block corresponding to the gaze position information; converting a first language included in the determined text block into a second language that is a target language; and providing the user with a conversion result of the second language. | 2022-07-14 |
20220222449 | PRESENTATION TRANSCRIPTS - An example system may include a processor and a non-transitory machine-readable storage medium storing instructions executable by the processer to generate a real-time transcript of a live delivery of a presentation; provide a unique identification to an attendee within a physical proximity to the live delivery of the presentation; and provide, responsive to receiving the unique identification from a device associated with the attendee, the real-time transcript to the device associated with the attendee for display. | 2022-07-14 |
20220222450 | DATA GENERATION MODEL LEARNING APPARATUS, LATENT VARIABLE GENERATION MODEL LEARNING APPARATUS, TRANSLATION DATA GENERATION APPARATUS, DATA GENERATION MODEL LEARNING METHOD, LATENT VARIABLE GENERATION MODEL LEARNING METHOD, TRANSLATION DATA GENERATION METHOD, AND PROGRAM - To provide translation techniques for translating a natural language representation in one language into a natural language representation in another language using sound. With L | 2022-07-14 |
20220222451 | AUDIO PROCESSING APPARATUS, METHOD FOR PRODUCING CORPUS OF AUDIO PAIR, AND STORAGE MEDIUM ON WHICH PROGRAM IS STORED - In order to solve a conventional problem that there has been no mechanism for accumulating first audio and second audio, which is audio obtained through simultaneous interpretation of the first audio, in association with each other, an audio processing apparatus includes: a first audio accepting unit that accepts first audio of speech uttered by a first speaker of a first language; a second audio accepting unit that accepts second audio, which is audio obtained through simultaneous interpretation of the first audio into a second language by a second speaker; and an accumulating unit that accumulates the first audio and the second audio in association with each other. Accordingly, it is possible to realize a mechanism for accumulating first audio and second audio, which is audio obtained through simultaneous interpretation of the first audio, in association with each other. | 2022-07-14 |
20220222452 | WIRELESS INDOOR CONSUMER TRACKING - In an example, a method comprises communicating with a radio frequency (RF)-enabled asset tag within a space, tracking a location of the RF-enabled asset tag within the space, determining location estimates of the asset tag as the asset tag moves within the space, and accepting identifying information from or about a selected user. The method additionally comprises determining, based on a predetermined correspondence criteria, a correspondence between the asset tag location and a position estimate of an electronic hardware device within the space. Further, in response to determining the correspondence between the asset tag and the electronic hardware device and based at least in part on the identifying information accepted via the electronic hardware device, the method includes associating tracked asset tag location information corresponding to the location estimates of the asset tag as the asset tag moved within the space to identification of the selected user. | 2022-07-14 |
20220222453 | SYSTEMS AND METHODS FOR VERIFYING REMOTE PURCHASES - Systems, methods, and computer readable media are disclosed for electronic security systems for an establishment offering in-store pick-up of previously purchased products. Embodiments may include an electronic article surveillance (EAS) gate, a receiver for receiving transmissions from the tags, and a processor. The processor may be configured to access a purchase transaction record of an out-of-store product purchase; receive a unique tag ID of a specific tag associated with a specific product corresponding to the purchased product, and assign the specific product to a record associated with the purchase transaction; receive, from a mobile communications device, a notification that the purchased product is being picked up at the establishment; authorize pick-up of the specific product based on the received information; and following the authorization of pick-up, disable an ability to initiate an alarm when the receiver receives a transmission from the specific tag in proximity to the EAS gate. | 2022-07-14 |
20220222454 | CONTACTLESS AND AUTOMATIC OPERATIONS OF A RETAIL STORE - Consistent with disclosed embodiments, systems, methods, and computer readable media for reading wireless transmitting tags and for automatically generating product distribution planograms may be provided. Embodiments may include at least one processor configured to receive, from a plurality of receivers in an establishment, wireless signals from a plurality of wirelessly tagged products; determine, from the wireless signals, locations in the establishment of each wirelessly tagged product; perform a lookup of an ID of each wirelessly tagged product to determine product classification information associated with each product; and generate a planogram for the establishment using the determined locations of the wirelessly tagged products and the determined product classification information, the planogram indicating on a map of the establishment locations of groups of the wirelessly tagged products sharing common classification information. | 2022-07-14 |
20220222455 | Industrial Digital Barcode Reader - A convertible slot scanner assembly for capturing at least one object appearing in a field of view (FOV) is provided that includes an imaging assembly, a controller, an image decoder, a chassis, a first window, and a housing. The chassis is configured to accommodate the imaging assembly and includes an optical cavity, an opening, and a flange portion at least partially surrounding the opening. The first window is configured to at least partially cover the opening of the chassis. The housing includes a housing cavity that is dimensioned to at least partially accommodate the chassis. The housing is positionable in a first, horizontal configuration and a second, vertical configuration. In the horizontal configuration, the first window is in a generally horizontal orientation. In the vertical configuration, the first window is in a generally upright orientation. | 2022-07-14 |
20220222456 | SAMPLE ANALYSIS SYSTEM AND SAMPLE MANAGEMENT METHOD - A sample analysis system and a sample management method are provided. The sample analysis system includes: one or more analysis devices configured to test a sample; a scanning component configured to scan the sample to obtain scanning information before testing the sample by the analysis devices; an image information obtaining component configured to acquire image information of a region in the sample containing a sample identifier; a processor configured to identify the sample identifier of the sample according to at least one of the scanning information or the image information of the sample. The system can obtain the sample identifier of a sample in two ways, thus improving the efficiency of sample test. | 2022-07-14 |
20220222457 | FACADE ELEMENT TRACKING SYSTEMS AND RELATED TECHNIQUES - An automated system can be used for tracking facade elements such as panels, glazing, or related structures, such as to help facilitate processing (e.g., fabrication) of such elements. Such a system can also facilitate management of other aspects of a life-cycle of a facade element, such as including one or more of design management or field monitoring. Such a system can include generating a unique identifier that is specific to a particular article, such as a panel or frame member, for example. Such a unique identifier can be used to track the article through the fabrication process. | 2022-07-14 |
20220222458 | METHODS AND APPARATUS FOR PROVIDING OUT-OF-RANGE INDICATIONS FOR IMAGING READERS - Methods and apparatus for providing out-of-range indications are disclosed. An example imaging reader includes an image sensor and an optical assembly. The imaging reader may include a distance determining module configured to determine a distance to a target. The imaging reader may include an indication determining module configured to determine an out-of-range indication when the distance satisfies a first condition. An indicator may be included and configured to present the out-of-range indication. The image sensor may be configured to capture a representation of an image of the target when the distance satisfies a second condition. The imaging reader may include an indicia decoder configured to decode an indicia in the representation to determine an indicia payload and/or a communication interface to convey the indicia payload to a host system. | 2022-07-14 |
20220222459 | Systems and Methods for Generating and Scanning Codes - A system and method enables computerized devices to scan the screens of their own device or to scan the screens of other devices with or without using a camera by a trigger using one or multiple methods. The system provides methods for scanning from a screen of a computerized device or a digital camera. The system provides a method that reduces the required details and size to scan a QR code or any other scannable element directly from the screen or by input into a scanning system. The system provides a method to scan single or multiple QR codes, barcodes, or any other scannable and identifiable elements singular or combined by one or multiple triggers. | 2022-07-14 |
20220222460 | ARTICLES OF MANUFACTURE BASED ON COLORSPACE TRANSFORMATION TECHNIQUES - An article of manufacture may include a matrix barcode on a physical medium and associated with an environment. The matrix barcode may include a plurality of colors, where at least one of the plurality of colors is a least prevalent color, of a plurality of prevalent colors in the environment. | 2022-07-14 |
20220222461 | DIGITAL PROCESSING SYSTEMS AND METHODS FOR DETECTABLE CODES IN PRESENTATION ENABLING TARGETED FEEDBACK IN COLLABORATIVE WORK SYSTEMS - Systems, methods, and computer-readable media for enabling a plurality of mobile communications devices to be used in parallel to comment on presentation slides within a deck are disclosed. The systems and methods may involve receiving a first and a second comment on a first slide; receiving a third and a fourth comment on a second slide; identifying a first and a second repository associated with the first and the second slide of the presentation, respectively; aggregating the first comment and the second comment in the first repository; aggregating the third comment and the fourth comment in the second repository; displaying to a presenter of the deck the first comment and the second comment in association with the first slide; and displaying to the presenter of the deck, the third comment and the fourth comment in association with the second slide. | 2022-07-14 |
20220222462 | PLURALITY OF CODE PORTION OPTIONS OF A MULTI-PART CODE SYSTEM - A method includes obtaining, by a first computing device of a multi-part code system, a first portion of a multi-part code from a second computing device. The multi-part code is representative of an interaction between the first and second computing devices. The method further includes obtaining a plurality of multi-part code portion options. A multi-part code portion option of the plurality of multi-part code portion options includes an amount of interaction information. Each of the plurality of multi-part code portion options is generated to align with the first portion of the multi-part code. The method further includes performing an alignment function to align a desired amount of multi-part code portion options with the first portion to produce a multi-part code having a desired amount of interaction information and sending the multi-part code having the desired amount of interaction information to a network computing device to complete the interaction. | 2022-07-14 |
20220222463 | UTILIZING ON-DEVICE SENSORS TO DETECT A SCAN - The present disclosure is directed towards systems and method for determining whether a scannable code displayed on a client device has been scanned. In particular, the systems and methods described herein involve activating one or more on-board sensors of the client device to capture output signals. Based on the output signals, the systems and methods include identifying discrete signals that indicate whether the scannable code has been scanned by a scanning device. Further, based on an analysis of the identified discrete signals, the systems and methods include determining whether the scannable code has been scanned by the scanning device. | 2022-07-14 |
20220222464 | MATERIAL SPECTROSCOPY - A computer, including a processor and a memory, the memory including instructions to be executed by the processor to acquire a first image by illuminating a first object with a first light beam, determine a first measure of pixel values in the image and perform a comparison of the first measure of pixel values to a second measure of pixel values determined from a second image of a second object, wherein the second image is previously acquired by illuminating the second object with a second light beam. The instructions include further instructions to, when the comparison determines that the first measure is equal to the second measure of pixel values within a tolerance, determine that the first object and the second object are a same object. | 2022-07-14 |
20220222465 | CAMERA ASSEMBLY FOR A FACIAL RECOGNITION SYSTEM OF A MOTOR VEHICLE - A camera assembly is provided for a facial recognition system of a motor vehicle. The camera assembly includes a cosmetic panel adapted to be attached to the motor vehicle. The cosmetic panel has an outboard side and an inboard side facing the motor vehicle. The cosmetic panel is opaque to visible light and transmissive to an infrared light. The camera assembly further includes a single infrared camera adapted to be disposed adjacent to the inboard side of the cosmetic panel. The single infrared camera generates an image signal, in response to the single infrared camera receiving the infrared light transmitted through cosmetic panel. | 2022-07-14 |
20220222466 | MATERIAL SPECTROSCOPY - A computer, including a processor and a memory, the memory including instructions to be executed by the processor to acquire a first image by illuminating a first object with a first light beam, segment the first image of the first object to determine regions that correspond to a first surface material and determine a first measure of pixel values in regions of the first image that correspond to the first surface material. The instructions include further instructions to perform a comparison of the first measure of pixel values to a second measure of pixel values determined from a second image of a second object, wherein the second image is previously acquired by illuminating the second object with a second light beam and when the comparison determines that the first measure is equal to the second measure of pixel values within a tolerance, determine that the first object and the second object are a same object. | 2022-07-14 |
20220222467 | MOTION RECOGNITION APPARATUS AND METHOD - A motion recognition apparatus extracts a plurality of first motion feature vectors within a period of time, and extracts a plurality of second motion feature vectors within another period of time closely next to the period of time. The apparatus calculates and sequences the distances between each of the plurality of first motion feature vectors and the plurality of cluster centroids to generate a corresponding first cluster centroid sequence respectively, and calculates and sequences the distances between each of the plurality of second motion feature vectors and the plurality of cluster centroids to generate a corresponding second cluster centroid sequence respectively. The apparatus recognizes a first segment motion, a second segment motion, and a whole motion based on the number of appearances of the cluster centroid in the first cluster centroid sequences, the second cluster centroid sequences and both of them respectively. | 2022-07-14 |
20220222468 | ADDITIVE MANUFACTURING COUNTERFEITING OBFUSCATION - A method of forming an additive manufactured part with obfuscated anti-counterfeiting features includes additive manufacturing the part using an approved additive manufacturing method and additive manufacturing a plurality of obfuscated anti-counterfeiting structures on a surface of the part using the approved additive manufacturing method. Each of the plurality of obfuscated anti-counterfeiting structures has at least one of a prohibitive physical dimension and a prohibitive physical shape that is prohibitive from being formed using at least one unapproved additive manufacturing method such that counterfeit manufacture of the part by the at least one unapproved additive manufacturing method is detected by inspecting the surface or observing a build failure by the at least one unapproved additive manufacturing method. The plurality of obfuscated anti-counterfeiting structures includes a plurality of hollow structures, a plurality of solid structures, and/or a plurality of truss structures. | 2022-07-14 |
20220222469 | SYSTEMS, DEVICES AND METHODS FOR DISTRIBUTED HIERARCHICAL VIDEO ANALYSIS - System and method of analyzing a video, comprising dividing the video into a set of successive basic units; generating semantic tags for the basic units using a set of hierarchical classifier nodes that comprise a parent classifier node and a plurality of child classifier nodes, wherein the basic units are each routed through selected child classifier nodes based on classification of the basic units by the parent classifier node; and generating a semantic topic for the video based on the semantic tags generated for the basic units. | 2022-07-14 |
20220222470 | AUTOMATIC CONTENT RECOGNITION AND INFORMATION IN LIVE STREAMING SUITABLE FOR VIDEO GAMES - In various examples, one or more Machine Learning Models (MLMs) are used to identify content items in a video stream and present information associated with the content items to viewers of the video stream. Video streamed to a user(s) may be applied to an MLM(s) trained to detect an object(s) therein. The MLM may directly detect particular content items or detect object types, where a detection may be narrowed to a particular content item using a twin neural network, and/or an algorithm. Metadata of an identified content item may be used to display a graphical element selectable to acquire the content item in the game or otherwise. In some examples, object detection coordinates from an object detector used to identify the content item may be used to determine properties of an interactive element overlaid on the video and presented on or in association with a frame of the video. | 2022-07-14 |
20220222471 | TELECOMMUNICATION NETWORK MONITORING - A method, system, and computer program product for monitoring a telecom network is provided. The method includes retrieving images associated with a transmission location of a telecom network. A communication channel is initialized for enabling transmission of a real time video stream comprising the images with respect to virtual network functions. The virtual network functions are enabled and a triggering signal of the virtual network functions is located. Image collector software and hardware components are activated for collecting the images for local cache storage and location and activation information is collected. Attributes of objects within the images are collected and detecting resulting obstruction characteristics associated with obstruction objects located within a coverage area of the telecom network are detected. The obstruction characteristics are mapped with login and disturbance patterns of the telecom network and an alternative transmission location within the telecom network is determined for providing improved transmission characteristics. | 2022-07-14 |
20220222472 | FRAUDULENT ACT RECOGNITION DEVICE, CONTROL PROGRAM THEREFOR, AND FRAUDULENT ACT RECOGNITION METHOD - A fraudulent act recognition device is configured to be operatively coupled to a camera that monitors operation of a settlement terminal by a purchaser. The fraudulent act recognition device includes a controller configured to recognize a commodity registration operation of the settlement terminal initiated by the purchaser. The controller is configured to review imaging data provided by the camera to recognize an action of the purchaser who performs the commodity registration operation. The controller is configured to determine whether an action of the purchaser is indicative of a fraudulent act. The controller is configured to provide a notification in response to a determination that the action of the purchaser is indicative of the fraudulent act. | 2022-07-14 |
20220222473 | VEHICLE COMMUNICATION SYSTEMS AND METHODS FOR DETECTING AND CAPTURING RELEVANT OBJECT DATA - Vehicle communication systems and methods for identifying and classifying objects as relevant to an occupant of a vehicle. A method includes capturing first object data at a first vehicle, classifying the first object data as relevant or non-relevant based on a first user profile associated with the first vehicle, and transmitting a transmission package including the first object data to a server in response to classifying the first object data as relevant. | 2022-07-14 |
20220222474 | MATERIAL SPECTROSCOPY - A computer, including a processor and a memory, the memory including instructions to be executed by the processor to acquire a first image by illuminating a first object with a first light beam, determine a first measure based on a first number of pixels corresponding to the first object in the first image and determine a relative distance measure by comparing the first measure based on the first number of pixels corresponding to the first object to a second measure based on a second number of pixels corresponding to a second object in the first image. The instructions can include instructions to modify the first measure of pixel values based on the relative distance measure, perform a comparison of the modified first measure of pixel values to a third measure of pixel values determined from a second image of a second object, and when the comparison determines that the first measure is equal to the third measure of pixel values within a tolerance, determine that the first object and the second object are a same object. | 2022-07-14 |
20220222475 | OBSTACLE DETECTION AND NOTIFICATION FOR MOTORCYCLES - An obstacle detection and notification system for a motorcycle. The system includes a forward looking camera and a backward looking camera mountable to the motorcycle and a processor in operable communication with the forward looking camera and the backward looking camera. The processor executes program instructions to execute processes including: receiving video from the of the forward looking camera and the backward looking camera, performing a computer vision and machine learning based object detection and tracking process to detect, classify and track obstacles in the video and to output detected object data, defining a blind spot region around one or more other vehicles using the detected object data, determining whether the motorcycle is located in the blind spot region, and outputting audible, tactile or visual feedback, via an output system, to a rider of the motorcycle when the motorcycle is determined to be located in the blind spot region. | 2022-07-14 |
20220222476 | METHOD FOR GENERATING HIGH-PRECISION MAP AND METHOD AND SYSTEM FOR RECOGNIZING TRAFFIC LIGHTS - A generation method of high-precision map for recognizing traffic lights is provided. The generation method comprised steps of: obtaining road test data comprising video data of traffic lights; marking the video data in order to obtain marked data of the traffic lights, the marked data comprising states of the traffic lights and traffic lights information; using the video data and the marked data to generate a recognition model of the traffic lights; and storing the recognition model and the traffic lights information in a high-precision map to generate a high-precision map for recognizing the traffic lights. Furthermore, a method and system for recognizing traffic lights using high-precision map are also provided. The recognition model is stored in the high-precision map, and cooperating with the high-precision map to effectively recognize the traffic lights. | 2022-07-14 |
20220222477 | PERFORMING NON-MAXIMUM SUPPRESSION IN PARALLEL - Apparatuses, systems, and techniques to perform non-maximum suppression (NMS) in parallel to remove redundant bounding boxes. In at least one embodiment, two or more parallel circuits to perform two or more portions of a NMS algorithm in parallel to remove one or more redundant bounding boxes corresponding to one or more objects within one or more digital images. | 2022-07-14 |
20220222478 | OPTICAL DEVICE - An optical device includes an optical sensor, one or more diffusive optical elements disposed on a surface of a display screen and configured to diffuse and to distribute a first portion of light associated with a subject across an array of sensor elements of the optical sensor, and one or more processors. The display screen includes one or more transmissive components that allow the first portion of light to pass through the display screen via the surface of the display screen, and one or more blocking components that prevent a second portion of light associated with the subject from passing through the display screen. The one or more processors are configured to obtain, from the optical sensor, sensor data associated with the first portion of light, process the sensor data to determine an image of the subject, and perform one or more actions based on the image of the subject. | 2022-07-14 |
20220222479 | MATERIAL SPECTROSCOPY - A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine a first measure of pixel values in the first image, acquire a second image, estimate ambient light illuminating the first object based on the second image and modify the first measure of pixel values based on a second measure of pixel values corresponding to estimated ambient light based on the second image. The instructions include further instructions to perform a comparison of the modified first measure of pixel values to a third measure of pixel values determined from a third image of a second object, wherein the third image is previously acquired by illuminating the second object with a second light beam and, when the comparison determines that the first measure is equal to the third measure of pixel values within a tolerance, determine whether the first object and the second object are a same object. | 2022-07-14 |
20220222480 | NEIGHBORING BOUNDING BOX AGGREGATION FOR NEURAL NETWORKS - Apparatuses, systems, and techniques to generate bounding box information. In at least one embodiment, for example, bounding box information is generated based, at least in part, on a plurality of candidate bounding box information. | 2022-07-14 |
20220222481 | IMAGE ANALYSIS FOR PROBLEM RESOLUTION - A method comprises receiving an input of at least one image associated with an issue. In the method, text is extracted from the at least one image, and an intent is determined from the extracted text. The method further includes recommending a response to the issue based at least in part on the determined intent, and transmitting the recommended response to a user. The extracting, determining and recommending are performed at least in part using one or more machine learning models. | 2022-07-14 |
20220222482 | PROVIDING AMBIENT INFORMATION BASED ON LEARNED USER CONTEXT AND INTERACTION, AND ASSOCIATED SYSTEMS AND DEVICES - Methods, computer readable media, and devices for auto scheduling of ambient information and apps based on learned user context and interaction are described. A method may include recording information corresponding to one or more ambient screens previously displayed to a user, building a probabilistic inference model based at least in part on the recorded information, ranking the one or more ambient screens based at least in part on the probabilistic inference model, selecting a candidate ambient screen from the ranked one or more ambient screens, and displaying the candidate ambient screen during an idle timeslot. | 2022-07-14 |
20220222483 | RANKED FACTOR SELECTION FOR MACHINE LEARNING MODEL - Described herein are techniques to a systematic approach to reduce the number of factors of an input dataset that impact a target prediction of a trained ML model. The techniques include obtaining a dataset of typed data points and ascertaining the factors of the data points based, at least in part, on the datatypes of the data points. The techniques also include obtaining an indicator of correlation of each factor ascertained in the dataset to a target prediction by a trained ML model and assigning a score to each respective factor ascertained in the dataset based on the indicator of correlation of each factor. The techniques further include ranking the factors ascertained in the dataset based on the score of each factor, selecting factors from the factors ascertained in the dataset, and providing the selected factors for making the target prediction by the trained ML model. | 2022-07-14 |
20220222484 | AI-ENHANCED DATA LABELING - An AI-enhanced data labeling tool assists a human operator in annotating image data. The tool may use a segmentation model to identify portions to be labeled. Initially, the operator manually annotates portions and once the operator has labeled a sufficient number of portions, a classifier is trained to predict labels for other portions. The predictions generated by the classifier are presented to the operator for approval or modification. The tool may also include an active learning model that recommends portions of the image data for the operator to annotate next. The active learning model may suggest one or more batches of portions based on the extent to which, once labeled, those batches will increase the diversity of the total set of labeled portions. | 2022-07-14 |
20220222485 | SYSTEM FOR DETECTING AND CLASSIFYING CONSUMER PACKAGED GOODS - A system is provided for identifying consumer packaged goods (CPGs). The system comprises an imaging device mounted on a mobile platform; a CPG detector which is equipped with a neural network and which (a) utilizes the imaging device to obtain an image containing a plurality of CPGs, (b) detects a set of CPG superclass features in the image, and (c) generates a CPG feature map which maps the location of CPG features in the image, wherein said neural network has been trained on a set of images of CPGs to recognize which of a set of superclasses a detected CPG belongs to; a region proposal network which accepts the CPG feature map as input and which returns a first set of regions in the image where a CPG could be located; a superclassifier which examines each region in the first set of regions to determine if the region contains an instance of a superclass of a CPG, and which outputs a second set of regions containing a CPG; and a superclass proposal layer which operates on each member of the second set of regions and returns a set of superclass proposals for each region. | 2022-07-14 |
20220222486 | Data Source Evaluation Platform for Improved Generation of Supervised Learning Models - Aspects of the disclosure relate to evaluating sources of training data for model generation. A computing platform may receive, from one or more data sources, a labelled data set. The computing platform may apply, to the labelled data set, an unsupervised learning algorithm, resulting in a clustered data set. The computing platform may compare, for each data point in the labelled data set, corresponding clustering information and labelling information to identify discrepancies. The computing platform may flag, for data points with identified discrepancies between the clustering information and labelling information, a labelling error. The computing platform may grade, based on the flagged labelling errors, each of the one or more data sources. Using remaining data of the labelled data set, not flagged with labelling errors, the computing platform may train a supervised learning model by weighting the remaining data based on: a corresponding data source and its grade. | 2022-07-14 |
20220222487 | Automated Prediction of Pixel Error Noticeability - A system includes a hardware processor and a memory storing a software code including a predictive model. The hardware processor executes the software code to receive an input including an image having a pixel anomaly, and image data identifying the location of the pixel anomaly in the image. The software code uses the predictive model to extract a global feature map of a global image region of the image, the pixel anomaly being located within the global image region; to extract a local feature map of a local image region of the image, the pixel anomaly being located within the local image region and the local image region being smaller than the global image region; and to predict, based on the global feature map and the local feature map, a distraction level of the pixel anomaly within the image. | 2022-07-14 |
20220222488 | INTELLIGENT VISUAL RECOGNITION TRANSLATION - A method, computer program product, and system include a processor(s) obtaining, captured image data. The processor(s) utilizes an image recognition agent and the captured image data from the defined vicinity to generate and train a model to provide artificial intelligence related to recognizing objects within the captured image data and to designate a location of the recognized objects within a mapped representation of physical space comprising the defined vicinity of the user; mapped representation comprises predefined locations. The processor(s) applies the model to identify one or more objects in the defined vicinity of the user and for each object, presence or absence of the object in each of the predefined locations. The processor(s) determines whether to trigger a notification to the user identifying each object and the predefined locations in which the object is present. | 2022-07-14 |
20220222489 | GENERATION OF TRAINING DATA FOR MACHINE LEARNING BASED MODELS FOR NAMED ENTITY RECOGNITION FOR NATURAL LANGUAGE PROCESSING - A system performs named entity recognition for performing natural language processing, for example, for conversation engines. The system uses context information in named entity recognition. The system includes the context of a sentence during model training and execution. The system generates high quality contextual data for training NER models. The system utilizes labeled and unlabeled contextual data for training NER models. The system provides NER models for execution in production environments. The system uses heuristics to determine whether to use a context-based NER model or a simple NER model that does not use context information. This allows the system to use simple NER models when the likelihood of improving the accuracy of prediction based on context is low. | 2022-07-14 |
20220222490 | INFORMATION PROCESSING DEVICE, METHOD AND PROGRAM - An information processing device performs machine learning utilizing a tree structure model configured by branching and hierarchically arranging a plurality of nodes respectively corresponding to hierarchically divided state spaces, the information processing device including: a learning object dataset reader configured to read a learning object dataset formed of a plurality of input columns and one or more output columns; an importance degree calculator configured to calculate importance degrees of the individual input columns based on the learning object dataset; an order generator configured to generate an order of the individual input columns to be a base of branch determination of the individual nodes, based on the individual importance degrees; and a machine learning circuitry configured to perform the machine learning based on the learning object dataset and the order. | 2022-07-14 |
20220222491 | SYSTEM AND METHOD FOR LIGHTWEIGHT SEMANTIC MASKING - A method includes performing, using at least one processor of an electronic device, semantic probing on a pre-trained model using one or more textual utterances. Performing the semantic probing includes processing each of the one or more textual utterances to determine a performance score for one or more targeted hidden layers of the pre-trained model. Performing the semantic probing also includes selecting a subset of the targeted hidden layers based on a comparison of the performance score to a predetermined threshold. The method also includes reconstructing, using the at least one processor, the pre-trained model based on the semantic probing to generate a reconstructed model. | 2022-07-14 |
20220222492 | METHODS AND SYSTEMS FOR BUDGETED AND SIMPLIFIED TRAINING OF DEEP NEURAL NETWORKS - Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example, a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example, in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps. The weighted feature maps are stored in the LSTM. A Q value is calculated for different actions based on the weighted feature maps stored in the LSTM. | 2022-07-14 |
20220222493 | DEVICE AND METHOD TO IMPROVE REINFORCEMENT LEARNING WITH SYNTHETIC ENVIRONMENT - A computer-implemented method for learning a strategy and/or method for learning a synthetic environment. The strategy is configured to control an agent, and the method includes: providing synthetic environment parameters and a real environment and a population of strategies. Subsequently, repeating the following steps for a predetermined number of repetitions as a first loop: carrying out for each strategy of the population of strategies subsequent steps as a second loop: disturb the synthetic environment parameters with random noise; train for a first given number of step the strategy on the disturbed synthetic environment; evaluate the trained strategy on the real environment by determining rewards of the trained strategies; updating the synthetic environment parameters depending on the noise and the rewards. Finally, outputting the evaluated strategy with the highest reward on the real environment or with the best trained strategy on the disturbed synthetic environment. | 2022-07-14 |
20220222494 | CLASSIFICATION ALGORITHM BASED ON MULTIFORM SEPARATION - The present invention provides a multiform separation classifier, including an input module, a data collection module, a multiform separation engine, and an output module. The input module is configured to receive sample data. The data collection module is connected to the input module and configured to store a collection of data from the input module. The collection of data includes a training set and/or a test set. The multiform separation engine is connected to the data collection module and configured to use at least two piecewise continuous functions to perform classification. The piecewise continuous functions are respectively trained with the training set through a learning process. The output module is connected to the multiform separation engine and configured to derive an output result after the sample data is processed through the multiform separation engine. | 2022-07-14 |
20220222495 | USING CONTEXTUAL TRANSFORMATION TO TRANSFER DATA BETWEEN TARGETS - A method, computer system, and a computer program product for contextual transformation is provided. The present invention may include providing a source application for transformation. The present invention may include transforming at least one selection within the source application. The present invention may include communicating the at least one transformed selection to a target application. | 2022-07-14 |
20220222496 | IMAGE PROCESSING SYSTEM - Disclosed is a multi-modal convolutional neural network (CNN) for fusing image information from a frame based camera, such as, a near infra-red (NIR) camera and an event camera for analysing facial characteristics in order to produce classifications such as head pose or eye gaze. The neural network processes image frames acquired from each camera through a plurality of convolutional layers to provide a respective set of one or more intermediate images. The network fuses at least one corresponding pair of intermediate images generated from each of image frames through an array of fusing cells. Each fusing cell is connected to at least a respective element of each intermediate image and is trained to weight each element from each intermediate image to provide the fused output. The neural network further comprises at least one task network configured to generate one or more task outputs for the region of interest. | 2022-07-14 |
20220222497 | METHOD FOR IDENTIFYING DRY SALT FLAT BASED ON SENTINEL-1 DATA - A method for identifying a dry salt flat based on the sentinel-1 data is provided. The method includes: carrying out field survey and acquiring data; processing sentinel-1 data; determining backscattering values, spectrum characteristics and colors of different polarization; and determining a classification criterion and carrying out threshold classification. | 2022-07-14 |
20220222498 | IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND STORAGE MEDIUM FOR GENERATING QUANTIZED DATA FOR FORMING AN IMAGE ON A PRINT MEDIUM - Provided is quantization processing that can reduce color development defect due to dot overlapping and can output an image with reduced granularity when the image is printed by using multiple kinds of colorants. To this end, dot arrangement information for a colorant for which dot arrangement is already determined among multiple kinds of colorants is acquired for a predetermined region of the image, and an evaluation value of each pixel included in the predetermined region is derived based on the arrangement information. In addition, for the predetermined region, a target value for a predetermined colorant for which dot arrangement is yet to be determined is derived based on the image. Then, whether or not to arrange a dot of the predetermined colorant in the predetermined region is determined based on the target value and the evaluation value. | 2022-07-14 |
20220222499 | IMAGE FORMING SYSTEM, CONTROL METHOD THEREOF, AND MEDIUM - An image forming system is provided. The image forming system comprises an image forming unit configured to execute a print job and form an image on a supplied sheet; and an inspection unit configured to inspect quality of the image formed in the sheet, wherein the inspection unit does not set a sheet discharged by the image forming unit without being used for the print job to a target of inspection. | 2022-07-14 |
20220222500 | DETERMINING SPATIAL DISTANCE USING ENCODING SIGNALS - The present disclosure relates generally to signal encoding for containers such as shipping boxes, food containers, wrapped items such as pallets. One aspect of the technology relates to an image processing method for determining spatial dimensions of an encoded surface. The method comprises: obtaining an image depicting the encoded surface, in which the encoded surface comprises one or more raw data signal tiles printed thereon, with each tile comprising a side length N in inches or centimeters; detecting each of the one or more raw data signal tiles from the obtained image; determining a total number of tiles in a vertical direction, and determining a total number of tiles in a horizontal direction; determining a height and length of the encoded surface by multiplying each of the total number of tiles in a vertical direction and the total number of tiles in a horizontal direction by the side length N. Other aspects are described as well. | 2022-07-14 |