29th week of 2022 patent applcation highlights part 45 |
Patent application number | Title | Published |
20220229966 | Method and Apparatus for Locating and Identifying Physical Blocks Within a Grid - An apparatus for showing an arrangement having a plurality of physical blocks which includes a first block having a vertical axis and a second block having a vertical axis. The apparatus includes a grid upon which the plurality of blocks is placed to form an arrangement of blocks with respect to the grid. The apparatus includes a computer in communication with the grid. The computer receiving signals from the grid which reveal a location and an identity of the first block about its vertical axis and the second block about its vertical axis. The signals used by the computer to drive an interactive computer graphic visualization of the arrangement of physical blocks with respect to the grid. The present invention pertains to a method for showing an arrangement. | 2022-07-21 |
20220229967 | Method and apparatus for printing electrical circuit directly on target surface having 3-dimensional shape, 3D printer used for the same and electrical device having electrical circuit printed by the same - A method and apparatus for printing an electric circuit directly on a target surface having a three-dimensional shape are provided. In this method, a 3D printing apparatus that can be attached to a target surface is used. In this printing method, two-dimensional information about the shape of the electric circuit to be printed and information about the three-dimensional shape of the target surface are input. Two-dimensional information about the shape of the electric circuit to be printed is adjusted based on the information about the three-dimensional shape of the target surface to generate three-dimensional information about the electric circuit to be printed. Based on this, a tool path for controlling the 3D printing apparatus is generated. | 2022-07-21 |
20220229968 | VERTEX-BASED OPC FOR OPENING PATTERNING - A method of enhancing a layout pattern includes determining a target layout pattern comprising a disk shape associated with a hole. The method includes defining a polygon having a plurality of vertices on the disk shape. The plurality of vertices coincide with a boundary of the disk shape and the polygon is an initial layout pattern of the hole. The method includes performing an iterative correction of the initial layout pattern. The iterative correction includes projecting the layout pattern of the hole onto a substrate, determining an error between the target layout pattern and the projected layout pattern, and adjusting the layout pattern by moving the vertices of the polygon to generate a next iteration of the layout pattern. The method includes continuing the adjusting, projecting, and determining until a criterion is satisfied and a final iteration of the layout pattern of the hole is generated. | 2022-07-21 |
20220229969 | AUTOMATIC DOCUMENT GENERATION AND SEGMENTATION SYSTEM - Methods and systems are provided for generating a corpus of documents from an original document or document corpus. Original documents are processed to extract document layout and elements. Elements are clustered and processed by neural networks, such as GANs, to generate additional elements that are then combined with the extracted layout to produce new documents, such as for training automated document processing systems. | 2022-07-21 |
20220229970 | MULTI-FACETED SITE EVALUATOR INTEGRATING USER DEFINED EVALUATION ENGINES - A website building system (WBS) includes at least one hardware processor and a site evaluator running on the at least one hardware processor to evaluate at least one application area of a website according to at least one user category of the WBS. The site evaluator includes at least one evaluation engine to evaluate the at least one application area according to rules and at least one of: scripts and machine learning (ML) models, a site modifier to implement at least one of automatic and manual modifications to the website according to recommendations from the at least one evaluation engine and an evaluation engine handler to enable user creation and editing of the at least one evaluation engine. | 2022-07-21 |
20220229971 | SUPPORTING PIECEWISE UPDATE OF JSON DOCUMENT EFFICIENTLY - Herein are fine grained updates to pieces of JavaScript object notation (JSON) documents by database statements that can update, delete, and insert parts of JSON documents. In an embodiment, a computer receives a request that specifies a modification of a JSON document that is stored in a compressed format in persistent storage. The modification adds additional content to the JSON document, and/or replaces an old value in the JSON document with a new value that is not a same size as the old value. The modification is recorded in a change log. The change log is eventually applied to the compressed format of the JSON document in the persistent storage without entirely rewriting the compressed format of the JSON document in the persistent storage. | 2022-07-21 |
20220229972 | SYSTEM AND METHODS FOR CONTEXT SPECIFIC ANNOTATION OF ELECTRONIC FILES - Embodiments described herein are directed to an annotation system having a remote processor, and a client processor in data communication with the remote processor. The client processor is adapted to send a first request for an electronic file to the remote processor, receive the electronic file from the remote processor, define at least one new annotation about the electronic file, and define at least one anchor associated with the at least one annotation. The at least one of the remote processor and the client processor is adapted to store the at least one anchor and the at least one annotation in an annotation file that is separate from the electronic file. | 2022-07-21 |
20220229973 | INTERACTIVE TOOL FOR MODIFYING AN AUTOMATICALLY GENERATED ELECTRONIC FORM - In some aspects, a method includes receiving data corresponding to a source document. The source document has an input file format. The method includes generating an intermediate file representing an electronic form based on the data. The intermediate file includes metadata indicating one or more elements of the source document, the intermediate file having an intermediate file format. The method includes providing an interactive tool configured to enable display and modification of the electronic form based on user input. The modification includes adding an additional element, deleting at least one of the one or more elements, modifying at least one of the one or more elements, or a combination thereof. The method includes converting the modified intermediate file to an output file having a target output file format. The output file represents the electronic form configured to support user entry of input information. The method includes outputting the output file. | 2022-07-21 |
20220229974 | FORMULA GENERATION BY EXAMPLE - A system includes an interface configured to receive a user input string for a data cell and a processor configured to: determine a lexicon from data related to the data cell; determine an efficient formula from the lexicon; and provide the efficient formula to a formula cell. The system further includes a memory coupled to the processor and configured to provide the processor with instructions. | 2022-07-21 |
20220229975 | COPY-PASTE TRIGGERED FORMULA GENERATION - A system includes an interface configured to receive a paste-to data cell. The system includes a processor configured to: determine whether there is an exact match key for a copy-from data set; in response to there not being the exact match key for the copy-from data set, determine whether there is a smart formula for the copy-from data set; and in response to there being the smart formula for the copy-from data set, provide the smart formula for the copy-from data set to a formula cell. The system includes a memory coupled to the processor and configured to provide the processor with instructions. | 2022-07-21 |
20220229976 | Infinite Canvas - Providing an infinite or seemingly infinite canvas as a workspace is disclosed. In some embodiments, an ability to add to a displayed canvas and view simultaneously one or more table objects, each of which has associated with it an ability to define the content of a first cell by reference to one or more other cells such that the content of the first cell is updated automatically and without further human intervention if the content of one or more of the one or more other cells is changed, is provided. | 2022-07-21 |
20220229977 | DATA NORMALIZATION AND EXTRACTION SYSTEM - A data ingestion system normalizes ingested documents and extracts data based on a template that is applied to the documents. In an aspect, the system accesses a document of a document type and determines a template to apply to the document. The system normalizes the document, extracts data values from the document based at least in part on the template, and generates structured data based at least partly on the extracted data. | 2022-07-21 |
20220229978 | SYSTEM FOR COLLABORATION ON THE DRAFTING OF A SHARED DIGITAL CONTRACT - The system and method for providing clause-based tailored editing in a collaborative digital contract drafting system. The collaborative digital contract drafting system allows multiple users from different parties to collaborate on the digital drafting, editing, and virtual negotiation of a digital contract. The system allows users to collaborate in real time during the drafting process and provides version control of the digital contract that is siloed between clauses and stored and tracked separately in a tracking database. Siloing the version control between clauses allows toggling between different versions of different clauses independent of one another. | 2022-07-21 |
20220229979 | PLATFORM INTERPRETATION OF USER INPUT CONVERTED INTO STANDARDIZED INPUT - Disclosed herein is a platform for translating various user input into a standardized input used to cause a database to sort data in a specified manner and present the data in a graphic user interface according to user instruction. User input is a text string that includes a first set of characters and a second set of characters split by a dividing symbol. Based on the choice of dividing symbol and the arrangement of the first set of character and second set of characters the system converts the input into a standardized form. | 2022-07-21 |
20220229980 | SYSTEMS AND METHODS FOR DATA PARSING - Systems and methods for data parsing are disclosed. In one aspect, a method of parsing raw data associated with one or more transactions involves receiving a text string including raw data for a transaction, matching the text string to a plurality of locations within a location corpus to extract location information from the text string, and identifying a candidate entity from the text string based on a similarity score with respect to a plurality of entities within an entity corpus. The method further involves in response to the similarity score of the identified candidate entity being less than a threshold score, generating entity information using the tokens indicative of entity information, and generating normalized transaction data including the extracted location information and one of the identified candidate entity or the generated entity information. | 2022-07-21 |
20220229981 | GENERATING MESSAGE EFFECTIVENESS PREDICTIONS AND INSIGHTS - Messages are processed to generate effectiveness predictions and/or other insights associated with the messages. Candidate messages are processed through a natural language processing (NLP) component to parse the candidate message into message elements for further processing. The message elements are converted to a vector or set of vectors, which are provided as input to a machine learning model to make predictions of message effectiveness. A contribution score can be made for each message element of the candidate message, which may be indicative of the importance or relevance for the individual message element to the overall predicted message effectiveness. Other message elements not originally within the message can be provided as candidates to replace message elements already located within the message. In this way, a message that is likely to be effective, such being likely to have a high conversion rate, can be published or otherwise distributed. | 2022-07-21 |
20220229982 | INFORMATION PROCESSING APPARATUS, INFORMATION LEARNING APPARATUS, INFORMATION PROCESSING METHOD, INFORMATION LEARNING METHOD AND PROGRAM - An information processing apparatus includes a memory and a processor configured to perform generating subword units of a plurality of layers for each of processing units constituting an input sequence and generating an embedded vector based on the subword units of the plurality of layers for each of the processing units; and executing a process based on a learned parameter, with the embedded vector generated for each of the processing units as an input. | 2022-07-21 |
20220229983 | GLOBAL, MODEL-AGNOSTIC MACHINE LEARNING EXPLANATION TECHNIQUE FOR TEXTUAL DATA - A model-agnostic global explainer for textual data processing (NLP) machine learning (ML) models, “NLP-MLX”, is described herein. NLP-MLX explains global behavior of arbitrary NLP ML models by identifying globally-important tokens within a textual dataset containing text data. NLP-MLX accommodates any arbitrary combination of training dataset pre-processing operations used by the NLP ML model. NLP-MLX includes four main stages. A Text Analysis stage converts text in documents of a target dataset into tokens. A Token Extraction stage uses pre-processing techniques to efficiently pre-filter the complete list of tokens into a smaller set of candidate important tokens. A Perturbation Generation stage perturbs tokens within documents of the dataset to help evaluate the effect of different tokens, and combinations of tokens, on the model's predictions. Finally, a Token Evaluation stage uses the ML model and perturbed documents to evaluate the impact of each candidate token relative to predictions for the original documents. | 2022-07-21 |
20220229984 | SYSTEMS AND METHODS FOR SEMI-SUPERVISED EXTRACTION OF TEXT CLASSIFICATION INFORMATION - Disclosed embodiments relate to extracting classification information from input text. Techniques can include obtaining input text, identifying a plurality of tokens in the input text, pre-training a machine learning model, determining tagging information of the plurality of tokens using a first classification layer of the machine learning model, pairing sequences of tokens using the tagging information associated with the plurality of tokens, wherein the paired sequences of tokens are determined by a second classification layer, determining one or more attribute classifiers to apply to the one or more paired sequences, wherein the attribute classifiers are determined by a third classification layer of the machine learning model, evaluating sentiments of the paired sequences, wherein the sentiments of the paired sequences are determined by a fourth classification layer of the language machine learning model, aggregating sentiments of the paired sequences associated with an attribute classifier, and storing the aggregated sentiments. | 2022-07-21 |
20220229985 | ADVERSARIAL DISCRIMINATIVE NEURAL LANGUAGE MODEL ADAPTATION - Systems and methods for updating a language model are provided. One example method includes, at an electronic device with one or more processors and memory, training a first language model using a training data set comprising user-generated and user-relevant data, and storing a reference version of the first language model including a first overall probability distribution. Based on the reference version of the first language model, a second language model including a second overall probability distribution is updated (i.e., adapted) using the first overall probability distribution as a constraint on the second overall probability distribution. | 2022-07-21 |
20220229986 | SYSTEM AND METHOD FOR COMPILING AND USING TAXONOMY LOOKUP SOURCES IN A NATURAL LANGUAGE UNDERSTANDING (NLU) FRAMEWORK - A natural language understanding (NLU) framework includes a lookup source framework, which enables a lookup source system to be defined having one or more lookup sources. In particular, taxonomy lookup sources can be compiled from suitable taxonomy source data that represents relationships between various entities within a domain of a client. These taxonomy lookup sources can extract taxonomy segmentations from utterances, such as received user utterances and sample utterances of an intent-entity model. The taxonomy segmentations can then be leveraged by the NLU system to perform vocabulary injection to expand the number of meaning representations in the utterance meaning model and/or the understanding model, increasing the likelihood of matches being located during a meaning search operation. Additionally, the taxonomy lookup sources can be leveraged by the NLU system to enable validation of sample utterances submitted for inclusion in the intent-entity model. | 2022-07-21 |
20220229987 | SYSTEM AND METHOD FOR REPOSITORY-AWARE NATURAL LANGUAGE UNDERSTANDING (NLU) USING A LOOKUP SOURCE FRAMEWORK - A natural language understanding (NLU) framework includes a lookup source framework, which enables a lookup source system to be defined having one or more lookup sources. The lookup source system can operate in a number of different manners to facilitate repository-aware inference of user utterances, for example, by facilitating vocabulary injection during compilation of an utterance meaning model and/or an understanding model. Additionally, the lookup source system can be leveraged to cleanse client-specific training data of sensitive values to generate generic training data that can be used to train the NLU framework of other clients. The lookup sources can be compiled in a synchronous or asynchronous manner, which enables lookup sources to be compiled in an on-demand basis from test source data. Additionally, understanding models that reference lookup sources can be periodically recompiled while leveraging the latest versions of the lookup sources for vocabulary injection. | 2022-07-21 |
20220229988 | Touch Keyboard Using a Trained Model - A computing device outputs for display at a presence-sensitive display, a graphical keyboard comprising a plurality of keys, receives an indication of at least one gesture to select a group of keys of the plurality of keys, and determines at least one characteristic associated with the at least one gesture to select the group of keys of the plurality of keys. The computing device modifies a spatial model based at least in part on the at least one characteristic and determines a candidate word based at least in part on data provided by the spatial model and a language model, wherein the spatial model provides data based at least in part on the indication of the at least one gesture and wherein the language model provides data based at least in part on a lexicon. The computing device outputs for display at the presence-sensitive display, the candidate word. | 2022-07-21 |
20220229989 | MACHINE LEARNING PREDICTION OF TEXT TO HIGHLIGHT DURING LIVE AUTOMATED TEXT TRANSCRIPTION - A method including transcribing, automatically, an ongoing stream of voice data into text phrases. The method also includes receiving an indication of a selected text phrase in the text phrases. The method also includes converting the selected text phrase to a selected phrase vector. The method also includes generating a subsequent text phrase, after the selected text phrase, from the ongoing stream of voice data, and adding the subsequent text phrase to the text phrases. The method also includes converting the subsequent text phrase to a subsequent phrase vector. The method also includes generating a similarity confidence score from the selected phrase vector and the subsequent phrase vector, using a machine learning model. The method also includes highlighting, responsive to the similarity confidence score exceeding a threshold value, the subsequent text phrase in the text phrases. | 2022-07-21 |
20220229990 | SYSTEM AND METHOD FOR LOOKUP SOURCE SEGMENTATION SCORING IN A NATURAL LANGUAGE UNDERSTANDING (NLU) FRAMEWORK - A natural language understanding (NLU) framework includes a lookup source system having one or more lookup sources. Each lookup source includes a respective source data representation that is compiled from respective source data. Once compiled, a user utterance can be submitted to the lookup source system, which generates segmentations of the user utterance. Each segmentation generally includes a collection of non-overlapping segments, and each segment generally describes how tokens of the user utterance can be grouped together and matched to the states of the source data representations. During lookup source inference, matches can be made to produced states or using fuzzy matchers that have corresponding of scoring adjustments. These scoring adjustments may be used by a segmentation scoring subsystem, potentially in combination with one or more additional segmentation scoring plugins, to score and rank the segmentations determined by the lookup source system for the user utterance. | 2022-07-21 |
20220229991 | MULTI-FEATURE BALANCING FOR NATURAL LANGUAGE PROCESSORS - Techniques are disclosed for systems including techniques for multi-feature balancing for natural langue processors. In an embodiment, a method includes receiving a natural language query to be processed by a machine learning model, the machine learning model utilizing a dataset of natural language phrases for processing natural language queries, determining, based on the machine learning model and the natural language query, a feature dropout value, generating, and based on the natural language query, one or more contextual features and one or more expressional features that may be input to the machine learning model, modifying at least one or the one or more contextual features and the one or more expressional features based on the feature dropout value to generate a set of input features for the machine learning model, and processing the set of input features to cause generating an output dataset for corresponding to the natural language query. | 2022-07-21 |
20220229992 | WORD LATTICE AUGMENTATION FOR AUTOMATIC SPEECH RECOGNITION - Speech processing techniques are disclosed that enable determining a text representation of named entities in captured audio data. Various implementations include determining the location of a carrier phrase in a word lattice representation of the captured audio data, where the carrier phrase provides an indication of a named entity. Additional or alternative implementations include matching a candidate named entity with the portion of the word lattice, and augmenting the word lattice with the matched candidate named entity. | 2022-07-21 |
20220229993 | CONTEXT TAG INTEGRATION WITH NAMED ENTITY RECOGNITION MODELS - Techniques are provided for using context tags in named-entity recognition (NER) models. In one particular aspect, a method is provided that includes receiving an utterance, generating embeddings for words of the utterance, generating a regular expression and gazetteer feature vector for the utterance, generating a context tag distribution feature vector for the utterance, concatenating or interpolating the embeddings with the regular expression and gazetteer feature vector and the context tag distribution feature vector to generate a set of feature vectors, generating an encoded form of the utterance based on the set of feature vectors, generating log-probabilities based on the encoded form of the utterance, and identifying one or more constraints for the utterance. | 2022-07-21 |
20220229994 | OPERATIONAL MODELING AND OPTIMIZATION SYSTEM FOR A NATURAL LANGUAGE UNDERSTANDING (NLU) FRAMEWORK - A natural language understanding (NLU) framework includes a modeling and optimization system that enables enhanced understanding and explainability to the operation of the NLU framework. The NLU framework includes a configuration vector storing settings of various components that may be applied during NLU inference of an utterance, such as which components should be activated or deactivated, as well as which numerical values (e.g., threshold values, coefficients, weight values) that are used by these components during operation. By using this configuration vector to systematically disable and adjust numerical parameters of the components of the NLU framework, and then determining the performance of the NLU framework in these configurations, the modeling and optimization system determines relationships between, as well as the relative importance of, the components of the NLU framework. The modeling and optimization system automatically determines or optimizes configurations for the NLU framework to accommodate various NLU performance and/or resource constraints. | 2022-07-21 |
20220229995 | INTERPRETATION OF DEEP NEURAL MODEL BASED DIALOGUE AGENTS - Techniques facilitating interpretation of deep neural model based dialogue agents are provided. In one example, a computer-implemented method comprises extracting, by a device operatively coupled to a processor, features from a dialogue model independently from the dialogue model, the features comprising input features provided to the dialogue model and output features produced via the dialogue model in response to the input features, resulting in extracted features; and analyzing, by the device, a dialogue context associated with the extracted features by identifying pairwise interactions between respective ones of the extracted features. | 2022-07-21 |
20220229996 | INTERACTIVE SYSTEM - The purpose of the present invention is to provide an interactive system that allows addition of appropriate response content. An interactive system | 2022-07-21 |
20220229997 | DIALOGUE PROCESSING APPARATUS, LEARNING APPARATUS, DIALOGUE PROCESSING METHOD, LEARNING METHOD AND PROGRAM - A generation unit that takes a question Q | 2022-07-21 |
20220229998 | LOOKUP SOURCE FRAMEWORK FOR A NATURAL LANGUAGE UNDERSTANDING (NLU) FRAMEWORK - A natural language understanding (NLU) framework includes a lookup source framework, which enables a lookup source system to be defined having one or more lookup sources. Each lookup source of the lookup source system includes a respective source data representation that is compiled from respective source data. For example, a source data representation may include source data arranged in a finite state transducer (IFST) structure as a set of finite-state automata (FSA) states, wherein each state is associated with a token that represents underlying source data. Different producers can be applied during compilation of a source data representation to derive additional states within the source data representation from the source data. Certain states of the source data representation that contain sensitive data can be selectively protected through encryption and/or obfuscation, while other portions of the source data representation that are not sensitive may remain in clear-text form. | 2022-07-21 |
20220229999 | SERVICE PLATFORM FOR GENERATING CONTEXTUAL, STYLE-CONTROLLED RESPONSE SUGGESTIONS FOR AN INCOMING MESSAGE - An apparatus ( | 2022-07-21 |
20220230000 | MULTI-FACTOR MODELLING FOR NATURAL LANGUAGE PROCESSING - Techniques are disclosed for systems including techniques for multi-factor modelling for training and utilizing chatbot systems for natural language processing. In an embodiment, a method includes receiving a set of utterance data corresponding to a natural language-based query, determining one or more intents for the chatbot corresponds to a possible context for the natural language-based query and associated with a skill for the chatbot, generating one or more intent classification datasets, each intent classification dataset associated with a probability that the natural language query corresponds to an intent of the one or more intents, generating one or more transformed datasets each corresponding to a skill of one or more skills, determining a first skill of the one or more skills based on the one or more transformed datasets and processing, based on the determined first skill, the set of utterance data to resolve the natural language-based query. | 2022-07-21 |
20220230001 | Apparatuses, Systems, and Methods for Providing Automated Question Generation For Documents - Apparatuses, systems, and methods are provided for parallel construction for question generation (QG) corresponding to a content item. Text of at least a portion of the content item may be extracted as a source language text, at least a portion of which may be translated to generate a parallel text having a primary language different from the source language. The source and primary language texts may be aligned to create an aligned source language text and an aligned primary language text. A QG strategy may be determined and at least one step to be performed on the aligned primary language text may be generated based at least in part upon the determined QG strategy. At least one parallel operation corresponding to the at least one step to be performed on the aligned primary language text may be constructed, and a source language question may be generated. | 2022-07-21 |
20220230002 | MULTI STREAM RFID TAG APPLICATOR - A radio frequency identification (RFID) tag applicator including a spool system for holding and guiding a tape including a plurality of RFID tags from a first spool to a second spool, an RFID programmer coupled to spool system to send a programming signal to each of the tags passing from the first spool to the second spool, an RFID reader coupled to the spool system for reading a return signal from a programmed RFID tag in order to reject or accept the programmed tag, and an applicator member operatively coupled to the RFID reader to cause an RFID tag to peel away from the tape onto a passing substrate if the RFID tag is accepted by the RFID reader or pass to the second spool if rejected. | 2022-07-21 |
20220230003 | DEVICE ARCHITECTURE - A device for contactless communication with a terminal, the device comprising: an antenna for receiving a wireless signal emitted by the terminal; an embedded chip configured to generate data for communication to the terminal to perform a first function associated with the device; and a module separate from the chip configured to perform processes as part of a second function associated with the device, the module being connected to the antenna and comprising a power-harvesting unit configured to harvest power from the received wireless signal to power at least the module. | 2022-07-21 |
20220230004 | DAISY CHAIN ANTENNA - An RFID system ( | 2022-07-21 |
20220230005 | SYSTEM FOR ENCODING RESOURCE ACCESS CREDENTIAL IN BARCODE - Systems for encoding resource access credentials in barcodes displayed on user devices, such as mobile phones, are described. A resource access credential authorising payment for a transaction relating to the purchase of goods or services is obtained, and a barcode encoding barcode data is generated, including at least a purchasing entity identifier, the resource access credential, and a user supplied transaction identifier. The barcode is displayed on the display of the user device, and read by an optical reader of merchant computing system. The merchant computing system requests payment for the transaction using the resource access credential, and produces a transaction data packet containing transaction data relating to the transaction, together with at least the purchasing entity identifier and user supplied transaction identifier. | 2022-07-21 |
20220230006 | COLOR BAR CODE AND CODE DETERMINING SYSTEM - A color bar code comprising a code block is disclosed. The code block comprises: a header region, comprising a specific color; and a code region, comprising at least two code color bars with different color kinds, wherein a color sequence of the code color bars indicates a code. The code color bars form concentric layers surrounding the header region. Such color bar code can comprise more information and the contained therein is more easily to be acquired. A code determining system which can determine the code in the color bar code is also disclosed. | 2022-07-21 |
20220230007 | Systems and Methods for Labeling, Identifying, and Tracking Data Related to Consumable Product - Systems and methods for labeling, identifying, and tracking data related to consumable substance include encoded information related to the substance itself, its container, and/or an animal (e.g., human, feline, canine, livestock) intended to receive the substance in vivo. | 2022-07-21 |
20220230008 | System Integrating UI for Manual Input with Scanning of Encoded Data Markings - A device includes: an image sensor to capture images of an object within an FOV, a guide projector and a processor. The processor is to analyze some of the images to detect entry of an encoded data marking carried by the object into the FOV, and in response to detecting such entry into the FOV: operate the guide projector to project a visual guide onto the object to guide movement of the encoded data marking to a first location indicated by the visual guide within the FOV; analyze more of the images to detect such movement to the first location, and then to a second location within the FOV; and in response to the movement to the second location, interpret the movement to the second location as receipt of manual input; and in response to the manual input, transmit data decoded from the encoded data marking to another device. | 2022-07-21 |
20220230009 | FINGERPRINT RECOGNITION MODULE, DISPLAY PANEL AND DRIVING METHOD, AND DISPLAY DEVICE - A fingerprint recognition module, a display panel and driving method, and a display device are provided. The fingerprint recognition module includes a first electrode layer including a plurality of first electrodes, and a piezoelectric layer disposed on a side of the first electrode layer. The fingerprint recognition module also includes a second electrode layer disposed on a side of the piezoelectric layer facing away from the first electrode layer. The second electrode layer includes a plurality of second electrodes that are arranged along a first direction, and one second electrode overlaps at least two first electrodes. Moreover, the fingerprint recognition module includes a flexible circuit board bonded and connected to the plurality of second electrodes. In a plane parallel to the first electrode layer, the plurality of second electrodes and the flexible circuit board are arranged along a second direction, and the first direction intersects the second direction. | 2022-07-21 |
20220230010 | BIOLOGICAL INFORMATION IDENTIFICATION APPARATUS AND ELECTRONIC DEVICE - A biological information identification apparatus is provided, including: a fingerprint identification module and a packaging layer disposed on a surface of the fingerprint identification module facing a user, and configured to package the fingerprint identification module to insulate the fingerprint identification module from an outside environment, a top surface of the packaging layer being an arc surface. The fingerprint identification module includes: a fingerprint identification chip configured to identify fingerprint information of the user, where a plurality of capacitive pixel units are disposed on an upper surface of the fingerprint identification chip, and the capacitive pixel units are configured to form capacitance with a finger of the user; and a plurality of conductive elements disposed above the capacitive pixel units. An electronic device including the aforementioned biological information identification apparatus is provided. | 2022-07-21 |
20220230011 | THIN, MULTI-LENS, OPTICAL FINGERPRINT SENSOR ADAPTED TO IMAGE THROUGH CELL PHONE DISPLAYS - A multiple-lens optical fingerprint reader for reading fingerprints through a display has an image sensor integrated circuit with photosensor array(s); a spacer; and multiple lenses in a microlens array, each lens of multiple lenses focuses light arriving at that lens from a finger adjacent the display through the spacer to form an image on associated photosensors on a photosensor array of the integrated circuit. A method of verifying identity of a user includes illuminating a finger of the user with an OLED display; focusing light from the fingerprint through arrayed microlenses onto a photosensor array of an integrated circuit, reading the array to overlapping electronic fingerprint images; extracting features from the overlapping electronic fingerprint images or from a stitched fingerprint image, and comparing the features to features of at least one user in a library of features and associated with one or more fingers of one or more authorized users. | 2022-07-21 |
20220230012 | PRE-PROCESSING A TABLE IN A DOCUMENT FOR NATURAL LANGUAGE PROCESSING - Provided are a computer program product, system, and method for pre-processing a table in a document for natural language processing. A table in a document is parsed to extract column headers, row headers, and data cells, which are processed to determine an initial set of a main element comprising an entity whose value is to be extracted, a conditional element that refines the entity, and a value element comprising a value for the entity. A user selection is received of at least one of the column headers, row headers, and data cells for at least one of the main element, conditional element, and the value element in the initial set to produce a modified set of the main element, conditional element, and value element. The modified set is provided to a natural language processing engine to perform natural language processing of the document including the table, using the modified set. | 2022-07-21 |
20220230013 | NEURAL NETWORK ARCHITECTURE FOR EXTRACTING INFORMATION FROM DOCUMENTS - A system to extract data from regions of interest on a document is provided. The system includes a storage device storing an image derived from a document having text information. The system includes a document importer operable to perform optical character recognition to convert image data in the image to machine readable data. The system includes a neural network that identifies at least one region of interest on the image to classify an area of the at least one region of interest as a table. The neural network is operable to take as input the machine readable data and the image and combine both the machine readable data and the image to determine that the classified area is the table. | 2022-07-21 |
20220230014 | METHODS AND SYSTEMS FOR TRANSFER LEARNING OF DEEP LEARNING MODEL BASED ON DOCUMENT SIMILARITY LEARNING - Disclosed is a method and system for transfer learning of a deep learning model based on a document similarity learning. A transfer learning method may include pre-training, by the at least one processor, a similarity model to output a similarity between documents, generating, by the at least one processor, a fine tuning model by replacing a first output function of the pre-trained similarity model with a second output function, and training, by the at least one processor, the fine tuning model to output a score for a document input to the fine tuning model. | 2022-07-21 |
20220230015 | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM - An information processing apparatus includes: a processor configured to: when existence of predetermined information is detected, inquire a user whether to display contents of the information before the contents of the information are displayed as an augmented-reality image in front of a user's field of view; and control the displaying of the contents of the information by the augmented-reality image according to a user's instruction in response to the inquiry. | 2022-07-21 |
20220230016 | LANDMARK-LESS SIMULTANEOUS LOCALIZATION AND MAPPING - A simultaneous localization and mapping system for a motor vehicle is disclosed and includes a plurality of sensors disposed within a vehicle operable to detect an object proximate the vehicle and generate a plurality of data points representing sensor returns corresponding to the detected objects surrounding the vehicle, and a controller configured to receive the data points representing the sensor returns of the detected objects surrounding the vehicle, to define an occupancy grid based on the data points and to generate vehicle operating instructions based on the defined occupancy grid, wherein the controller is configured to define at least one geometric anchor from the detected data points and localizing the vehicle based on the at least one geometric anchor. | 2022-07-21 |
20220230017 | ROBUST LANE-BOUNDARY ASSOCIATION FOR ROAD MAP GENERATION - Association algorithms of newly-detected lane boundaries to lane boundaries can be made more robust through the use of generated or “dummy” states. Different types of dummy states can be used to identify outlier/erroneous detections and/or new, legitimate lane boundaries. Therefore, depending on a type of dummy state a newly-detected lane boundary is associated with, the newly-detected lane boundary can be ignored, or the associated dummy state can be added to the lane boundary states of the filter. | 2022-07-21 |
20220230018 | COMBINING VISIBLE LIGHT CAMERA AND THERMAL CAMERA INFORMATION - In some examples, one or more processors may receive at least one first visible light image and a first thermal image. Further, the processor(s) may generate, from the at least one first visible light image, an edge image that identifies edge regions in the at least one first visible light image. At least one of a lane marker or road edge region may be determined based at least in part on information from the edge image. In addition, one or more first regions of interest in the first thermal image may be determined based on at least one of the lane marker or the road edge region. Furthermore, a gain of a thermal sensor may be adjusted based on the one or more first regions of interest in the first thermal image. | 2022-07-21 |
20220230019 | LANE MAPPING AND LOCALIZATION USING PERIODICALLY-UPDATED ANCHOR FRAMES - A hybrid approach for using reference frames is presented in which a series of anchor frames is used, effectively resetting a global frame upon a trigger event. With each new anchor frame, parameter values for lane boundary estimates (known as lane boundary states) can be recalculated with respect to the new anchor frame. Triggering events may a based on a length of time, distance traveled, and/or an uncertainty value. | 2022-07-21 |
20220230020 | INFORMATION EXTRACTION FROM IMAGES USING NEURAL NETWORK TECHNIQUES AND ANCHOR WORDS - Scene text information extraction of desired text information from an image can be performed and managed. An information management component (IMC) can determine an anchor word based on analysis of an image. To facilitate determining desired text information in the image, WIC can re-orient the image to zero or substantially zero degrees if it determines that the orientation is skewed. IMC can utilize a neural network to determine and apply bounding boxes to text strings in the image. Using a rules-based approach or machine learning techniques, employing a trained machine learning component, IMC can utilize the anchor word along with inline grouping of textual information in the image, deep text recognition analysis, or bounding box prediction to determine or predict the desired text information in the image. IMC can facilitate presenting the desired text information, anchor word, or other information obtained from the image in an editable format. | 2022-07-21 |
20220230021 | AUTONOMOUS VEHICLE SYSTEM FOR INTELLIGENT ON-BOARD SELECTION OF DATA FOR BUILDING A REMOTE MACHINE LEARNING MODEL - Systems and methods for on-board selection of data logs for training a machine learning model are disclosed. The system includes an autonomous vehicle having a plurality of sensors and a processor. The processor receives a plurality of unlabeled images from the plurality of sensors, a machine learning model, and a loss function corresponding to the machine learning model. For each of the plurality of images, the processor then determines one or more predictions using the machine learning model, compute an importance function based on the loss function and the one or more predictions, and transmit that image to a remote server for updating the machine learning model when a value of the importance function is greater than a threshold. | 2022-07-21 |
20220230022 | Method for Acquiring Object Information and Apparatus for Performing Same - The present invention relates to a method for acquiring an object information, the method comprising: obtaining an input image acquired by capturing a sea; obtaining a noise level of the input image; when the noise level indicates a noise lower than a predetermined level, acquiring an object information related to an obstacle included in the input image from the input image by using a first artificial neural network, and when the noise level indicates a noise higher than the predetermined level, obtaining a noise-reduced image of which the environmental noise is reduced from the input image by using a second artificial neural network, and acquiring an object information related to an obstacle included in the sea from the noise-reduced image by using the first artificial neural network. | 2022-07-21 |
20220230023 | ANOMALY DETECTION METHOD, STORAGE MEDIUM, AND ANOMALY DETECTION DEVICE - An anomaly detection method for a computer to execute a process includes obtaining a plurality of waveform data detected by a plurality of sensors arranged on a monitoring target; specifying a plurality of target waveform data from among the plurality of waveform data based on a correlation of a shape of the obtained plurality of waveform data; combining the plurality of target waveform data into combined waveform data; clustering the combined waveform data by dividing into clusters for a time unit; and detecting an anomaly of the monitoring target based on a size of each of the clusters. | 2022-07-21 |
20220230024 | ARTIFICIAL INTELLIGENCE OPTIMIZATION PLATFORM - Systems and methods are provided for reusing machine learning models. For example, the applicability of prior models may be compared using one or more assessment values, including a similarity threshold and/or an accuracy threshold. The similarity threshold may identify a similarity of data between a first data set used to generate a first model and a new data set that is received by the system. When the similarity between these two data sets is exceeded, the system may reuse a model with the highest similarity value. When an accuracy value of the data set does not exceed an accuracy threshold, the system may initiate a retraining process to generate a second ML model associated with the second data. | 2022-07-21 |
20220230025 | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING PROGRAM, AND INFORMATION PROCESSING METHOD - An information processing device includes a memory, and processing circuitry coupled to the memory. The processing circuitry is configured to acquire gradation processing target image data, and perform gradation processing on the gradation processing target image data based on a learned model learned in advance. | 2022-07-21 |
20220230026 | Generating Labeled Training Instances for Autonomous Vehicles - In techniques disclosed herein, machine learning models can be utilized in the control of autonomous vehicle(s), where the machine learning models are trained using automatically generated training instances. In some such implementations, a label corresponding to an object in a labeled instance of training data can be mapped to the corresponding instance of unlabeled training data. For example, an instance of sensor data can be captured using one or more sensors of a first sensor suite of a first vehicle can be labeled. The label(s) can be mapped to an instance of data captured using one or more sensors of a second sensor suite of a second vehicle. | 2022-07-21 |
20220230027 | DETECTION METHOD, STORAGE MEDIUM, AND INFORMATION PROCESSING APPARATUS - A detection method for a computer to execute a process includes when data is input to a first detection model among a plurality of detection models trained with boundaries that classify a feature space of data into a plurality of application regions based on a plurality of pieces of training data that corresponds to a plurality of classes, acquiring a first output result that indicates which application region among the plurality of application regions the input data is located in; when data is input to a second detection model, acquiring a second output result; and detecting data that is a factor of an accuracy deterioration of an output result of a trained model based on a time change of data to be data streamed based on the first and the second output result. | 2022-07-21 |
20220230028 | DETERMINATION METHOD, NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM, AND INFORMATION PROCESSING DEVICE - A determination method performed by a computer, the determination method includes acquiring a first output result when data generated under second environment different from a first environment that is a training environment is input to a trained model, acquiring a second output result when the data is input to a detection model that detects decrease in a correct answer rate of a trained model when the trained model is converted into the second environment, and determining whether or not to retrain the trained model when the trained model is converted into the second environment based on the first output result and the second output result. | 2022-07-21 |
20220230029 | IMAGE FORMING APPARATUS, IMAGE FORMING SYSTEM AND CONTROL METHOD OF IMAGE FORMING APPARATUS - An image forming apparatus has an office direct print function, and when a non-installed font that is not installed in the image forming apparatus is included in application data, a font substitution guidance screen is displayed on a display. A drop-down list that is an operator for selecting a substitute font is provided in the font substitution guidance screen, whereby a user can arbitrarily select a substitute font. The font substitution guidance screen displays also a sample character group having a typeface according to the selected substitute font. | 2022-07-21 |
20220230030 | IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND STORAGE MEDIUM - It is made possible to perform appropriate color matching between devices irrespective of whether a printed material is print-output in color or monochrome from a destination device. The color characteristic of the destination device is obtained by printing a chart in which a predetermined density pattern is formed in the destination device and reading the color of the chart. Next, whether the chart output from the destination device is color or monochrome is determined. Then, color conversion parameters for reproducing the color characteristic of the destination device in an adjustment device are determined by printing the color chart in a case where the printed material is determined that formed in color or printing the monochrome chart in a case where the printed material is determined that formed in monochrome in the adjustment device. | 2022-07-21 |
20220230031 | RASTER IMAGE PROCESSOR - A raster image processor (RIP) for digital binary halftoning a continuous tone image (CT) by a threshold tile (TT) into a halftone raster image (RT) for a printing device capable of printing on a plurality of substrates (S | 2022-07-21 |
20220230032 | WIRELESS TAG READER AND BASKET DEVICE - A wireless tag reader includes a casing, an antenna in the casing and through which a radio wave is transmitted to and received from a wireless tag on an article, a control device in the casing and configured to read tag information stored in the wireless tag based on a radio wave received by the antenna, and an elastic member between the casing and the antenna so as to permit the antenna to be movable with respect to the casing. | 2022-07-21 |
20220230033 | SMART LABELS - Smart labels, methods of operating smart labels, and associated contexts in which such smart labels may be used are disclosed. The smart label, for use in conjunction with consumer product packaging, comprises an energy harvester to capture ambient energy to provide a source of electrical energy and electronic circuitry powered by the electrical energy. A fuse provides an electrical connection between the energy harvester and the electronic circuitry and destruction of the fuse permanently disconnects the energy harvester from the electronic circuitry. Unnecessary continued operation of the electronic circuitry powered by the energy harvester can therefore be prevented, for example when the consumer product packaging is disposed of or recycled, which may be an undesirable heat source. Smart labelling, and a connected network of smart bins which can read the smart labelling, may also be used to promote consumer recycling of consumer product packaging. | 2022-07-21 |
20220230034 | ADAPTABLE TRACKING TAG - A tracking tag system includes a tag case, a first tag case back plate and a second tag case back plate. The tag case has a mating surface and is configured to house a PCB having a transmitter and circuitry for controlling the transmitter. The first tag case back plate is configured to mate with the tag case to enclose and totally protect the PCB, the transmitter, the circuitry and a battery of a first type against ingress of water during immersion and against dust ingress. The second tag case back plate configured to enclose and totally protect the PCB, the transmitter, the circuitry and a battery of a second type against ingress of water during immersion and against dust ingress. | 2022-07-21 |
20220230035 | TRANSPONDER - A transponder with a disrupting signal source to shut down the transponder. The transponder may use an RFID chip. The disrupting signal source can be an electrical signal source electrically coupled to the RFID chip, for example capacitively coupled. The disruptive signal source can also be a radiation source, for example an infrared source. The disrupting signal source can be connected to a receiver to allow the transponder to be shut down remotely. Multiple transponders as described can be combined to form a multi-transponder device in which transponders can be shut down selectively. | 2022-07-21 |
20220230036 | INDIRECT ELECTRONIC BADGE TRACKING - A control system for an industrial vehicle includes a badge communicator and an information linking device. The badge communicator has a transceiver for short range communication with electronic badges that are within a fixed short range of the badge communicator, defining a first zone. The information linking device is programmed to execute program code. The program code extracts a current state of an operating parameter read from an industrial vehicle network bus, generates a second zone within the first zone that is defined based upon the extracted industrial vehicle operating parameter, detects a presence of an electronic badge within the first zone, determines whether the electronic badge is within the second zone, performs a first action if the detected electronic badge is not within the second zone, and performs a second action if the electronic badge is within the second zone. | 2022-07-21 |
20220230037 | ENROLMENT DEVICE FOR A BIOMETRIC SMART CARD - The application provides an enrolment card for a biometric card with a first card body. The enrolment card includes a battery for providing electrical power, a microcontroller unit that is electrically connected to the battery, and a plurality of contact pins that are electrically connected to the battery and to the microcontroller unit. The enrolment card further includes a second card body with a card engagement element. The second card body is sized to correspond to the first card body. The battery and the second microcontroller unit are embedded in the second card body. The enrolment card provides an enrolment mode, wherein the card engagement element engages with the first card body for allowing the contact pins to contact corresponding contact pads of the biometric card and the battery provides the electrical power to the biometric card. | 2022-07-21 |
20220230038 | SELF-ADHESIVE STRAPS FOR RFID DEVICES - An RFID device includes an antenna defining a gap, with an RFID strap electrically coupled to the antenna across the gap. The RFID strap is secured to the antenna by a self-adhesive substance, such as a pressure-sensitive adhesive, an isotropic conductive adhesive, or an anisotropic conductive adhesive. The use of a self-adhesive substance allows for such an RFID device to be assembled at facilities other than dedicated RFID device manufacturing facilities, which may include a packaging supplier factory. Additionally, such an RFID device allows for the creation of a flexible “build on demand” system capable of producing a smaller number of RFID devices than are typically produced using conventional approaches. Such a system may further test, program, apply print to, and/or cut an RFID device that it has assembled. | 2022-07-21 |
20220230039 | RADIO-FREQUENCY IDENTIFICATION WRISTBAND WITH SURFACE ACOUSTIC WAVE SENSOR - An apparatus for automatic radio-frequency identification (RFID). In an embodiment, the apparatus comprises a flexible strap comprising a plurality of holes and a buckle configured to buckle to any one of the plurality of holes, such that, when the buckle is buckled to one of the plurality of holes, the strap forms a closed loop. The apparatus further comprises one or more tag enclosures. Each tag enclosure comprises one or more buckles and a RFID tag configured to communicate identifying data to a reader device. The one or more buckles of each tag enclosure are each configured to buckle to any one of the plurality of holes on the strap such that the tag enclosure may be attached to the strap at any one of a plurality of positions on the strap. | 2022-07-21 |
20220230040 | RADIO FREQUENCY IDENTIFICATION (RFID) TAG WITH DEACTIVATABLE LINK - An electronic article surveillance (“EAS”) tag for an EAS system, comprising an antenna, a radio frequency identification (“RFID”) chip configured to transmit and/or receive a wireless signal via the antenna; and a magnetically-actuatable switch configured to move between a first position and a second position. The switch is configured to electrically couple the RFID chip to the antenna in the first position. The switch is further configured to electrically decouple the RFID chip from the antenna in the second position. | 2022-07-21 |
20220230041 | LOCATION OF FASTENER ACCESSORY USING SACRIFICIAL RF TAG - A fastener accessory includes a fastener body and a sacrificial radio frequency (RF) tag. A dielectric substrate of the tag is affixed to a contact surface of the fastener body. An RF antenna trace is connected to or printed on the substrate. The antenna trace transmits an RF response signal when energized by an external RF tracking circuit. The substrate is plastically deformed by an installation force to prevent transmission of the response signal. A method for locating the fastener body within a search area includes exciting a receiver trace of the tag using an interrogation signal, frequency-modulating an interrogation frequency using an RF modulating circuit, transmitting a response signal at a response frequency via a transmitting antenna trace of the tag, and detecting the response signal using an RF tracking circuit to locate the fastener body within the search area. | 2022-07-21 |
20220230042 | COMBINATION OF RADIO FREQUENCY IDENTIFICATION TECHNOLOGY WITH OPTICAL AND/OR QUASI-OPTICAL IDENTIFICATION TECHNOLOGIES - RFID devices are provided with an antenna coupled to an RFID chip by a direct or indirect connection. A data-carrying pattern that is visible at one or more wavelengths is incorporated into and/or onto the antenna. The pattern may comprise a plurality of apertures defined in the antenna or a material applied onto the antenna and having a property or properties different from a property or properties of the material used to form the antenna at one or more wavelengths. The pattern may carry data that is optically readable at one wavelength and quasi-optically readable at another wavelength. The pattern may include at least one sensing material configured to cause the pattern to present different data depending on whether a condition is existent or not. The antenna may include a plurality of layers, each with patterns or portions of a pattern or patterns that are visible at different wavelengths. | 2022-07-21 |
20220230043 | RFID DEVICE AND METHOD OF MANUFACTURING THE SAME - An RFID device that can be connected to a piece of material, in particular, a piece of fabric ( | 2022-07-21 |
20220230044 | DI CAPACITIVE EMBEDDED METAL CARD - A transaction card having a metal layer, an opening in the metal layer for a transponder chip, and at least one discontinuity extending from an origin on the card periphery to a terminus in the opening. The card has a greater flex resistance than a card having a comparative discontinuity with the terminus and the origin the same distance from a line defined by a first long side of the card periphery in an absence of one or more strengthening features. Strengthening features include a discontinuity wherein one of the terminus or the origin are located relatively closer to the first long side of the card periphery than the other, a plurality of discontinuities wherein fewer than all extend from the card periphery to the opening, a self-supporting, non-metal layer disposed on at least one surface of the card, or one or more ceramic reinforcing tabs surrounding the opening. | 2022-07-21 |
20220230045 | MONITORING OF PRODUCTS - The invention relates to the monitoring of products by means of active radio tags. According to the invention, packagings of products are provided with an active radio tag that detects at least one environmental condition and/or at least one packaging state, and which emits a signal at time intervals, which provides information about a unique identifier and at least one state in which the respective product is found. The signal is picked up by a receiver that extracts the unique identifier and the state information and transmits together with location information to a computer system. | 2022-07-21 |
20220230046 | INFORMATION PROCESSING SYSTEM, INFORMATION CODE GENERATING SYSTEM, INFORMATION PROCESSING METHOD, AND INFORMATION CODE GENERATING METHOD - To easily determine whether an information code has been replaced, an information processing device obtains, based on original information obtained by photographing an optically readable information code and decoding the same, first class information indicating a class into which an object visually represented by first visual information which should be displayed together with an information code is classified. The information processing device obtains second class information indicating a class into which an object visually represented by second visual information photographed together with the information code because of display together with the information code is classified. The information processing device compares the first class information with the second class information. The information processing device controls, based on a result of the comparison, execution of predetermined processing using the original information. | 2022-07-21 |
20220230047 | OPTIMISTIC DATA RETRIEVAL IN A PROCESS CONTROL ENVIRONMENT - Processing raw data stored in an historian device for determining an amount of products passed through a process element in a process control environment is described. A count value is incremented by a counter at a rate at which products pass through the process element. The count value rolls over to zero when the count value reaches a rollover value R. An historian device periodically receives count value data points from the counter. A deadband value D is set in the historian device for distinguishing between rollovers, resets, and reversals. A client device queries the historian device for an amount of products passed through the process element for a timeframe. The historian device selects a set of count value data points from within the queried timeframe. The historian device determines, based on the selected data points and their quality, an amount of products passed through the process element. | 2022-07-21 |
20220230048 | Neural Architecture Scaling For Hardware Accelerators - Methods, systems, and apparatus, including computer-readable media, for scaling neural network architectures on hardware accelerators. A method includes receiving training data and information specifying target computing resources, and performing using the training data, a neural architecture search over a search space to identify an architecture for a base neural network. A plurality of scaling parameter values for scaling the base neural network can be identified, which can include repeatedly selecting a plurality of candidate scaling parameter values, and determining a measure of performance for the base neural network scaled according to the plurality of candidate scaling parameter values, in accordance with a plurality of second objectives including a latency objective. An architecture for a scaled neural network can be determined using the architecture of the base neural network scaled according to the plurality of scaling parameter values. | 2022-07-21 |
20220230049 | SYSTEMS AND METHODS FOR IDENTIFYING ANOMALOUS NUCLEAR RADIOACTIVE SOURCES - A system for identifying anomalous nuclear radioactive sources can include: a radiation detector configured to collect spectra data corresponding to a radioactive source; a multi-channel analyzer configured to convert the collected spectra data to at least one two-dimensional (2D) image; and a neuromorphic architecture that includes a plurality of neurons configured to detect a radioactive anomaly based on the at least one 2D image. | 2022-07-21 |
20220230050 | FACT VALIDATION METHOD AND SYSTEM, COMPUTER DEVICE AND STORAGE MEDIUM - The disclosure relates to a fact validation method and system, a computer device and a storage medium. The method includes following steps: a statement to be validated is inputted and a searching is made for the statement to obtain an evidence set of the statement; a hierarchical heterogeneous graph consisting of an entity node, a sentence node and a context node is constructed based on the evidence set; the statement and the evidence set are spliced and a node is initialized to obtain feature representation of the node; the feature representation of the node is updated based on inference according to a propagation direction of a neural network of the node in the hierarchical heterogeneous graph; and an inference path for the updated feature representation of the node is built and a prediction result of the statement is output according to the inference path. | 2022-07-21 |
20220230051 | Spiking Neural Network - A spiking neural network for classifying input pattern signals, comprising a plurality of spiking neurons implemented in hardware or a combination of hardware and software, and a plurality of synaptic elements interconnecting the spiking neurons to form the network. Each synaptic element is adapted to receive a synaptic input signal and apply a weight to the synaptic input signal to generate a synaptic output signal, the synaptic elements being configurable to adjust the weight applied by each synaptic element, and each of the spiking neurons is adapted to receive one or more of the synaptic output signals from one or more of the synaptic elements, and generate a spatio-temporal spike train output signal in response to the received one or more synaptic output signals. | 2022-07-21 |
20220230052 | SIMPLIFICATION OF NEURAL NETWORK MODELS - The simplification of neural network models is described. For example, a method for simplifying a neural network model includes providing the neural network model to be simplified, defining a first temporal filter for the conveyance of input from a neuron to an other spatially-extended neuron along the arborized projection, defining a second temporal filter for the conveyance of input from yet another neuron to the spatially-extended neuron along the arborized projection, replacing, in the neural network model, the first, spatially-extended neuron with a first, spatially-constrained neuron and the arborized projection with a first connection extending between the first, spatially-constrained neuron and the second neuron, wherein the first connection filters input from the second neuron in accordance with the first temporal filter and a second connection extending between the first spatially-constrained neuron and the third neuron. | 2022-07-21 |
20220230053 | GRAPH NEURAL NETWORK FOR SIGNAL PROCESSING - Creating a machine learning graph neural network configured to process signals. A method includes identifying a plurality of machine learning graphs where each of the machine learning graphs are for different types of data. The method further includes receiving input identifying shared content of different machine learning graph nodes from different graphs in the plurality of machine learning graphs. The method further includes creating a combined machine learning graph neural network, configured to process signals, using the plurality of machine learning graphs based on the shared content, the combined machine learning graph neural network comprising nodes corresponding to nodes in the plurality of machine learning graphs such that output from the combined machine learning graph neural network comprises outputs generated based on relationships of nodes in the combined machine learning graph corresponding to nodes in different machine learning graphs in the plurality of machine learning graphs. | 2022-07-21 |
20220230054 | OPERATION OF TRAINABLE MODULES, INCLUDING MONITORING AS TO WHETHER THE RANGE OF APPLICATION OF THE TRAINING IS ABANDONED - A method for operating a trainable module. At least one input variable value is supplied to variations of the trainable module, the variations differing so much from each other, that they may not be converted into each other in a congruent manner, using progressive learning. A measure of the uncertainty of the output variable values is ascertained from the difference of the output variable values, into which the variations translate, in each instance, the input variable value. The uncertainty is compared to a distribution of uncertainties, which is ascertained for input variable learning values used during training of the trainable module and/or for further input variable test values, to which relationships learned during the training of the trainable module are applicable. The extent to which the relationships learned during the training of the trainable module are applicable to the input variable value, is evaluated from the result of the comparison. | 2022-07-21 |
20220230055 | COMPUTING CIRCUIT AND DATA PROCESSING METHOD BASED ON CONVOLUTIONAL NEURAL NETWORK AND COMPUTER READABLE STORAGE MEDIUM - A computing circuit and a data processing method based on a convolutional neural network and a computer readable storage medium are provided. Input data is obtained from a memory. A first computation is performed on first part data of the input data to obtain first output data. The first output data is buffered in a first buffer. When the buffered first output data is greater than a first predetermined data amount, a second computation is performed on the first output data to obtain second output data. The second output data is buffered in a second buffer. Third output data obtained by performing a third computation on the second output data is output to the memory. When performing the second computation on the first output data, the first computation is continuously performed on the input data. Accordingly, the number of accesses of the memory can be reduced. | 2022-07-21 |
20220230056 | NEUROMORPHIC HARDWARE FOR PROCESSING A KNOWLEDGE GRAPH REPRESENTED BY OBSERVED TRIPLE STATEMENTS AND METHOD FOR TRAINING A LEARNING COMPONENT - Provided is neuromorphic hardware for processing a knowledge graph, with a learning component, having an input layer containing node embedding populations of neurons, with each node embedding populations representing an entity contained in the observed statements, and an output layer, containing output neurons configured for representing a likelihood for each possible triple statement, and modeling a probabilistic, sampling-based model derived from an energy function, wherein the observed statements have minimal energy, and with a control component, configured for switching the learning component into a data-driven learning mode, configured for training the component with a maximum likelihood learning algorithm minimizing energy in the probabilistic, sampling-based model, using only the observed statements, which are assigned low energy values, in which the learning component supports generation of triple statements, and into a model-driven learning mode, configured for training the component, with the learning component learning to assign high energy values. | 2022-07-21 |
20220230057 | HYPERBOLIC FUNCTIONS FOR MACHINE LEARNING ACCELERATION - The present disclosure relates generally to techniques for enhancing recurrent neural networks (RNNs) implemented on an integrated circuit. In particular, approximations of activation functions used in an RNN, such as sigmoid and hyperbolic tangent, may be implemented in an integrated circuit, which may result in increased efficiencies, reduced latency, increased accuracy, and reduced resource consumption involved with implementing machine learning. | 2022-07-21 |
20220230058 | NEURAL PROCESSING UNIT (NPU) DIRECT MEMORY ACCESS (NDMA) MEMORY BANDWIDTH OPTIMIZATION - A neural processing unit (NPU) is described. The NPU includes an NPU direct memory access (NDMA) core. The NDMA core includes a read engine having a read buffer. The NDMA core also includes a write engine having a write buffer. The NPU also includes a controller. The controller is configured to direct the NDMA core to perform hardware memory bandwidth optimization for reading/writing NDMA data in the read buffer and/or NDMA data in the write buffer. The NDMA core is also configured to transparently combine NDMA transaction requests for a data stripe to increase local access to available tensors in artificial neural networks. | 2022-07-21 |
20220230059 | NEURON CORE WITH TIME-EMBEDDED FLOATING POINT ARITHMETIC - Provided is a method of operating a neuron in a neuromorphic system. The method includes evaluating a membrane potential value at a corresponding time when receiving an input spike, time-modulating a synaptic weight of the membrane potential value and converting the time-modulated synaptic weight into a membrane potential value at a reference time, and generating an output spike when the membrane potential value at the reference time exceeds a certain threshold value. The membrane potential value at the reference time is represented by a floating point number including a predetermined bit of exponent and mantissa, and the floating point number includes time information. The method further includes accessing a memory and scanning a neural state variable when a timer is updated to “0” to update the neural state variable to an updated value at a reference time. | 2022-07-21 |
20220230060 | NEUROMORPHIC DEVICE - A neuromorphic device includes: a neuron block unit including a plurality of neurons; a synapse block unit including a plurality of synapses; and a topology block unit including a plurality of parallel Look-Up Table (LUT) modules including pre and post neuron elements configured with addresses of a presynaptic neuron and a postsynaptic neuron. Each of the plurality of neurons has an intrinsic address, each of the plurality of synapses has an intrinsic address. The parallel LUT module is partitioned based on a first synapse address among synapse addresses, and each of the partitions is indexed based on a second synapse address among the synapse addresses. | 2022-07-21 |
20220230061 | MODALITY ADAPTIVE INFORMATION RETRIEVAL - In some embodiments, a multimodal computing system receives a query and identifies, from source documents, text passages and images that are relevant to the query. The multimodal computing system accesses a multimodal question-answering model that includes a textual stream of language models and a visual stream of language models. Each of the textual stream and the visual stream contains a set of transformer-based models and each transformer-based model includes a cross-attention layer using data generated by both the textual stream and visual stream of language models as an input. The multimodal computing system identifies text relevant to the query by applying the textual stream to the text passages and computes, using the visual stream, relevance scores of the images to the query, respectively. The multimodal computing system further generates a response to the query by including the text and/or an image according to the relevance scores. | 2022-07-21 |
20220230062 | DYNAMIC NETWORK CONFIGURATION - A method for dynamically configuring a network is proposed for training a machine learning model. The network includes a server computing device and a plurality of client computing devices. The method is performed at a computing device communicatively coupled to the network and includes the following: selecting client computing devices to participate in training the model; determining a first value of an evaluation metric of the model based on the selected client computing devices; determining the presence of an adjustment trigger; adjusting the number of client computing devices used to determine the value of the evaluation metric in response to the adjustment trigger; determining a second value of the evaluation metric based on the adjusted number of client computing devices; and setting the number of client computing devices participating in training the model accordingly. | 2022-07-21 |
20220230063 | ELECTRONIC APPARATUS AND CONTROLLING METHOD THEREOF - An electronic apparatus includes a communication interface; a memory configured to store at least one instruction; and a processor configured to execute the at least one instruction to: receive a text corresponding to a user utterance and information regarding a first external device; obtain a plurality of weights of a plurality of elements related to the first external device; identify a second external device for obtaining response information; control the communication interface to transmit the text corresponding to the user utterance to the second external device; receive first response information regarding the user utterance from the second external device; obtain second response information; and control the communication interface to transmit the second response information to the first external device. | 2022-07-21 |
20220230064 | CALIBRATION OF ANALOG CIRCUITS FOR NEURAL NETWORK COMPUTING - An analog circuit is calibrated to perform neural network computing. Calibration input is provided to a pre-trained neural network that includes at least a given layer having pre-trained weights stored in the analog circuit. The analog circuit performs tensor operations of the given layer using the pre-trained weights. Statistics of calibration output from the analog circuit is calculated. Normalization operations to be performed during neural network inference are determined. The normalization operations incorporate the statistics of the calibration output and are performed at a normalization layer that follows the given layer. A configuration of the normalization operations is written into memory while the pre-trained weights stay unchanged. | 2022-07-21 |
20220230065 | SEMI-SUPERVISED TRAINING OF MACHINE LEARNING MODELS USING LABEL GUESSING - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. One of the methods includes receiving an unlabeled batch; receiving a labeled batch; generating, from the unlabeled batch and the labeled batch, a processed unlabeled batch and a processed labeled batch, the generating comprising: for each unlabeled training input of the plurality of unlabeled training inputs: generating, from the unlabeled training input, a plurality of augmented unlabeled training inputs; processing each of the augmented unlabeled training inputs using the machine learning model to generate a respective model output for each augmented unlabeled training input; generating, from the model outputs for the augmented unlabeled training inputs, a guessed model output; and associating the guessed model output with each of the augmented unlabeled training inputs; and training the machine learning model on the processed labeled batch and the processed unlabeled batch. | 2022-07-21 |