Patent application number | Description | Published |
20080303949 | MANIPULATING VIDEO STREAMS - Methods, systems and apparatus, including computer program products, for manipulating video streams in videoconference session. A reference background image is identified from a first video frame in a video stream of a videoconferencing environment. A subsequent video frame from the video stream is received. Areas of the subsequent video frame corresponding to a foreground area are identified. The foreground area includes pixels of the subsequent video frame that are different from corresponding pixels in the first video frame. The foreground area is transformed based on a selected image transformation. The transformed foreground area is composited onto the reference background image into a composite video frame. | 12-11-2008 |
20120176401 | Gesture Mapping for Image Filter Input Parameters - This disclosure pertains to systems, methods, and computer readable medium for mapping particular user interactions, e.g., gestures, to the input parameters of various image processing routines, e.g., image filters, in a way that provides a seamless, dynamic, and intuitive experience for both the user and the software developer. Such techniques may handle the processing of both “relative” gestures, i.e., those gestures having values dependent on how much an input to the device has changed relative to a previous value of the input, and “absolute” gestures, i.e., those gestures having values dependent only on the instant value of the input to the device. Additionally, inputs to the device beyond user-input gestures may be utilized as input parameters to one or more image processing routines. For example, the device's orientation, acceleration, and/or position in three-dimensional space may be used as inputs to particular image processing routines. | 07-12-2012 |
20120242852 | Gesture-Based Configuration of Image Processing Techniques - This disclosure pertains to apparatuses, methods, and computer readable medium for mapping particular user interactions, e.g., gestures, to the input parameters of various image filters, while simultaneously setting auto exposure, auto focus, auto white balance, and/or other image processing technique input parameters based on the appropriate underlying image sensor data in a way that provides a seamless, dynamic, and intuitive experience for both the user and the client application software developer. Such techniques may handle the processing of image filters applying location-based distortions as well as those image filters that do not apply location-based distortions to the captured image data. Additionally, techniques are provided for increasing the performance and efficiency of various image processing systems when employed in conjunction with image filters that do not require all of an image sensor's captured image data to produce their desired image filtering effects. | 09-27-2012 |
20140240539 | GESTURE MAPPING FOR IMAGE FILTER INPUT PARAMETERS - This disclosure pertains to systems, methods, and computer readable medium for mapping particular user interactions, e.g., gestures, to the input parameters of various image processing routines, e.g., image filters, in a way that provides a seamless, dynamic, and intuitive experience for both the user and the software developer. Such techniques may handle the processing of both “relative” gestures, i.e., those gestures having values dependent on how much an input to the device has changed relative to a previous value of the input, and “absolute” gestures, i.e., those gestures having values dependent only on the instant value of the input to the device. Additionally, inputs to the device beyond user-input gestures may be utilized as input parameters to one or more image processing routines. For example, the device's orientation, acceleration, and/or position in three-dimensional space may be used as inputs to particular image processing routines. | 08-28-2014 |
20150346970 | Systems And Methods For Managing Authority Designation And Event Handling For Hierarchical Graphical User Interfaces - Prior art attempts to manage authority designation in GUI-based computer systems have set up various “handshaking” schemes between a graphics management system, such as a window server, and the various processes that are attempting to offer and accept access to each other. However, these schemes have certain limitations. In particular, when windows are used as the “fundamental basis” for implementing authority designation, events that should treat all content within a window identically can't do so because, even though all content in the window may appear to be “owned” by the window, there may be some other process that is actually rendering the content to some portion of the window. Thus, described herein are systems and methods to manage authority designation and event handling within “hierarchical” GUIs using “handshaking” schemes that are secure, sub-window granular, and that generalize recursively when applied to the various graphical layers used to construct the windows. | 12-03-2015 |
Patent application number | Description | Published |
20090304029 | VIRTUAL MEMORY PROTOCOL SEGMENTATION OFFLOADING - Methods and systems for a more efficient transmission of network traffic are provided. According to one embodiment, a method is provided for performing segmentation offloading, such as TCP segmentation offloading (TSO). An interface performs direct virtual memory addressing of a user memory space of a system memory on behalf of a network processor to fetch payload data originated by a user process running on a host processor. Then, the network processor segments the payload data across one or more packets. | 12-10-2009 |
20090307363 | NETWORK PROTOCOL REASSEMBLY ACCELARATION - Methods and systems are provided for network protocol reassembly acceleration. According to one embodiment, an incoming packet is received at a network interface. Payload data from the packet is written by a memory interface to a physical page within a system memory on behalf of the network interface based on a sequence number associated with the incoming packet and by obtaining a physical address from a virtual memory map corresponding to an incoming session with which the packet is associated. After the physical page is full, the physical page is made accessible to a user process being executed by a processor associated with the system memory by remapping the physical page through a paging table used by the user process. | 12-10-2009 |
20130215904 | VIRTUAL MEMORY PROTOCOL SEGMENTATION OFFLOADING - Methods and systems for a more efficient transmission of network traffic are provided. According to one embodiment, a user process of a host processor requests a network driver to store payload data within a system memory. The network driver stores (i) payload buffers each containing therein at least a subset of the payload data and (ii) buffer descriptors each containing therein information indicative of a starting address of a corresponding payload buffer within a user memory space. A network processor transmits onto a network the payload data within multiple transport layer protocol packets by (i) causing a network interface to retrieve the payload data from the payload buffers by performing direct virtual memory addressing of the user memory space using the buffer descriptors and information contained within a translation data structure stored within the system memory; and (ii) segmenting the payload data across the transport layer protocol packets. | 08-22-2013 |
20150110125 | VIRTUAL MEMORY PROTOCOL SEGMENTATION OFFLOADING - Methods and systems for a more efficient transmission of network traffic are provided. According to one embodiment, payload data originated by a user process running on a host processor of the computer system is fetched by an interface of the computer system by performing direct virtual memory addressing of a user memory space of a system memory of the computer system on behalf of a network processor of the computer system. The direct virtual memory addressing maps a physical address of the payload data to a virtual address. The payload data is segmented by the network processor across one or more packets. | 04-23-2015 |
Patent application number | Description | Published |
20140256357 | PROVIDING POINTS OF INTEREST TO USER DEVICES IN VARIABLE ZONES - Receiving point of interest zones and alerts on user devices comprises communicating, by a user computing device to a remote computing device, a request for point of interest data corresponding to points of interest within a proximity of the user device; presenting the received point of interest data; identifying a particular point of interest; and outputting an alert regarding the particular point of interest. Receiving point of interest zones on user devices comprises communicating a request for point of interest data; receiving the point of interest data from the remote network device wherein a size of the point of interest zone is determined based on a density of points of interest in the proximity of the user, and wherein the shape of the point of interest zone is expanded in a direction of travel and contracted in the opposite direction; and presenting the received point of interest data. | 09-11-2014 |
20140257747 | CONFIGURABLE POINT OF INTEREST ALERTS - Receiving point of interest zones and alerts on user devices comprises communicating, by a user computing device to a remote computing device, a request for point of interest data corresponding to points of interest within a proximity of the user device; presenting the received point of interest data; identifying a particular point of interest; and outputting an alert regarding the particular point of interest. Receiving point of interest zones on user devices comprises communicating a request for point of interest data; receiving the point of interest data from the remote network device wherein a size of the point of interest zone is determined based on a density of points of interest in the proximity of the user, and wherein the shape of the point of interest zone is expanded in a direction of travel and contracted in the opposite direction; and presenting the received point of interest data. | 09-11-2014 |
20150100271 | PROVIDING POINTS OF INTEREST TO USER DEVICES IN VARIABLE ZONES - Receiving point of interest zones and alerts on user devices comprises communicating, by a user computing device to a remote computing device, a request for point of interest data corresponding to points of interest within a proximity of the user device; presenting the received point of interest data; identifying a particular point of interest; and outputting an alert regarding the particular point of interest. Receiving point of interest zones on user devices comprises communicating a request for point of interest data; receiving the point of interest data from the remote network device wherein a size of the point of interest zone is determined based on a density of points of interest in the proximity of the user, and wherein the shape of the point of interest zone is expanded in a direction of travel and contracted in the opposite direction; and presenting the received point of interest data. | 04-09-2015 |
20150264527 | CLUSTERING GEOFENCE-BASED ALERTS FOR MOBILE DEVICES - A geofence management system obtains location data for points of interest. The geofence management system determines, at the option of the user, the location of a user mobile computing device relative to specific points of interest and alerts the user when the user nears the points of interest. The geofence management system, however, determines relationships among the identified points of interest, and associates or “clusters” the points of interest together based on the determined relationships. Rather than establishing separate geofences for multiple points of interest, and then alerting the user each time the user's mobile device enters each geofence boundary, the geofence management system establishes a single geofence boundary for the associated points of interest. When the user's mobile device enters the clustered geofence boundary, the geofence management system notifies the user device to alert the user of the entrance event. The user then receives the clustered, geofence-based alert. | 09-17-2015 |
Patent application number | Description | Published |
20130027990 | VARYING SWITCHING FREQUENCY AND PERIOD OF A POWER SUPPLY CONTROLLER - An example integrated circuit controller for use in a switching power supply includes a pulse width modulation (PWM) circuit and a timing circuit. The PWM circuit controls a switch to regulate an output of the power supply in response to a switch current flowing through the switch and in response to a clock signal having a switching period. The timing circuit provides the clock signal and increases the switching period in response to an on time of the switch exceeding a threshold time. | 01-31-2013 |
20130083566 | MULTI-STAGE SAMPLING CIRCUIT FOR A POWER CONVERTER CONTROLLER - An example controller for a power converter includes a track and hold circuit, a sample and hold circuit, and drive logic. The track and hold circuit receives a signal from a terminal of the controller that is representative of an output voltage of the power converter. The track and hold circuit includes a first capacitor that provides a first voltage that tracks the signal and then holds the first voltage. The sample and hold circuit samples the first voltage when the first voltage is held on the first capacitor. The sample and hold circuit includes a second capacitor coupled to hold a second voltage representative of the first voltage after a sample period, where the second capacitor has a capacitance value larger than that of the first capacitor. The drive logic controls the first switch to regulate an output of the power converter in response to the second voltage. | 04-04-2013 |
20140063862 | VARYING SWITCHING FREQUENCY AND PERIOD OF A POWER SUPPLY CONTROLLER - A controller includes a PWM circuit and a timing circuit. The PWM circuit controls a switch in response to a clock signal. A switching period of the clock signal is based on a charging and discharging time of a capacitor included in the timing circuit. Both first and second current sinks discharge the capacitor while the timing circuit is in a normal discharging mode that is when an on time of the switch is less than a threshold time. The second current sink is prevented from discharging the capacitor such that the capacitor is discharged with the first current sink and not the second current sink while the timing circuit is in an alternative discharging mode that is when the on time of the switch exceeds the threshold time. The discharging of the capacitor in the alternative discharging mode increases the switching period of the clock signal. | 03-06-2014 |
20140204628 | MULTI-STAGE SAMPLING CIRCUIT FOR A POWER CONVERTER CONTROLLER - An example controller for a power converter includes a track and hold circuit, a sample and hold circuit, and drive logic. The track and hold circuit receives a signal that is representative of an output voltage of the power converter. The track and hold circuit includes a first capacitor that provides a first voltage that tracks the signal and then holds the first voltage. The sample and hold circuit then samples the first voltage that is held on the first capacitor. The sample and hold circuit includes a second capacitor that holds a second voltage representative of the first voltage after a fixed sample period. The second capacitor is larger than that of the first capacitor. The drive logic controlling the first switch to regulate the output of the power converter includes disabling the first switch during an on time of the first switch responsive to the second voltage. | 07-24-2014 |
20140328089 | ON TIME SAMPLING PREVENTION - An example controller circuit includes a feedback sampling circuit, an oscillator, a drive logic, and a false sampling prevention circuit. The feedback sampling circuit generates a sample signal in response to a sampling of a feedback signal. The oscillator generates an on-time signal that transitions from a first logic state to a second logic state during each period of the on-time signal. The drive logic controls a switch to regulate the output of a power converter. The drive logic turns on the switch to end an off-time of the switch in response to the on-time signal transitioning from the first logic state to the second logic state. The false sampling prevention circuit prevents the on-time signal from transitioning from the first logic state to the second logic state to extend the off-time of the switch until a sampling complete signal indicates that sampling of the feedback signal is complete. | 11-06-2014 |
20150303812 | DIMMING EDGE DETECTION FOR POWER CONVERTER - A controller for a power converter includes an edge detection circuit and a drive circuit. The edge detection circuit includes a comparator, a count module, and an edge checking module. The comparator is coupled to output a compare signal in response to comparing an input sense signal and a count signal. The input sense signal is representative of an input voltage of the power converter. The count module is coupled to adjust the count signal to track the input sense signal in response to receiving the compare signal. The edge checking module is coupled to output at least one edge signal in response to the compare signal. The drive circuit is coupled to output a drive signal in response to the at least one edge signal. The drive signal is for controlling a switch coupled to regulate an output of the power converter. | 10-22-2015 |
Patent application number | Description | Published |
20120026776 | MEMORY RESISTOR HAVING PLURAL DIFFERENT ACTIVE MATERIALS - Methods and means related to memory resistors are provided. A memristor includes at least two different active materials disposed between a pair of electrodes. The active materials are selected to exhibit respective and opposite changes in electrical resistance in response to changes in oxygen ion content. The active materials are subject to oxygen ion reconfiguration under the influence of an applied electric field. An electrical resistance of the memristor is thus adjustable by way of applied programming voltages and is non-volatile between programming events. | 02-02-2012 |
20120085985 | ELECTRICALLY ACTUATED DEVICE - An electrically actuated device includes a reactive metal layer, a first electrode established in contact with the reactive metal layer, an insulating material layer established in contact with the first electrode or the reactive metal layer, an active region established on the insulating material layer, and a second electrode established on the active region. A conductive nano-channel is formed through a thickness of the insulating material layer. | 04-12-2012 |
20120249252 | OSCILLATOR CIRCUITRY HAVING NEGATIVE DIFFERENTIAL RESISTANCE - Circuitry is provided that closely emulates biological neural responses. Two astable multivibrator circuits (AMCs), each including a negative differential resistance device, are coupled in series-circuit relationship. Each AMC is characterized by a distinct voltage-dependant time constant. The circuitry exhibits oscillations in electrical current when subjected to a voltage equal to or greater than a threshold value. Various oscillating waveforms can be produced in accordance with voltages applied to the circuitry. | 10-04-2012 |
20130044525 | ASYMMETRIC SWITCHING RECTIFIER - An asymmetric switching rectifier includes a first switching device to allow electric current to flow while in a first state and inhibit electric current in a second state and a second switching device connected in a head-to-head formation to said first switching device, said second switching to allow electric current to flow while in a first state and inhibit electric current in a second state. A first electric current to turn said switching devices to said first state is different than a second electric current to turn said switching devices to said second state. The rectifier further includes a bypass segment to draw a bypass electric current from a center electrode between said first switching device and said second switching device. | 02-21-2013 |
20130175497 | DEVICE STRUCTURE FOR LONG ENDURANCE MEMRISTORS - A memristor includes a first electrode formed of a first metal, a second electrode formed of a second material, wherein the second material comprises a different material from the first metal, and a switching layer positioned between the first electrode and the second electrode. The switching layer is formed of a composition of a first material comprising the first metal and a second nonmetal material, in which the switching layer is in direct contact with the first electrode and in which at least one conduction channel is configured to be formed in the switching layer from an interaction between the first metal and the second nonmetal material. | 07-11-2013 |
20130242637 | Memelectronic Device - A memelectronic device may have a first and a second electrode spaced apart by a plurality of materials. A first material may have a memory characteristic exhibited by the first material maintaining a magnitude of an electrically controlled physical property after discontinuing an electrical stimulus on the first material. A second material may have an auxiliary characteristic. | 09-19-2013 |
20130334485 | MEMRISTIVE ELEMENTS THAT EXHIBIT MINIMAL SNEAK PATH CURRENT - Memristive elements are provided that include an active region disposed between a first electrode and a second electrode, the active region including two switching layers formed of a switching material capable of carrying a species of dopants and a conductive layer formed of a dopant source material. Memristive elements also are provided that include two active regions disposed between a first electrode and a second electrode, and a third electrode being disposed between and in electrical contact with both of the active regions. Each of the active regions include a switching layer formed of a switching material capable of carrying a species of dopants and a conductive layer formed of a dopant source material. Multilayer structures including the memristive elements also are provided. | 12-19-2013 |
20140091270 | LOW ENERGY MEMRISTORS WITH ENGINEERED SWITCHING CHANNEL MATERIALS - Low energy memristors with engineered switching channel materials include: a first electrode; a second electrode; and a switching layer positioned between the first electrode and the second electrode, wherein the switching layer includes a first phase comprising an insulating matrix in which is dispersed a second phase comprising an electrically conducting compound material for forming a switching channel. | 04-03-2014 |
20140145142 | MEMRISTOR STRUCTURE WITH A DOPANT SOURCE - A memristor including a dopant source is disclosed. The structure includes an electrode, a conductive alloy including a conducting material, a dopant source material, and a dopant, and a switching layer positioned between the electrode and the conductive alloy, wherein the switching layer includes an electronically semiconducting or nominally insulating and weak ionic switching material. A method for fabricating the memristor including a dopant source is also disclosed. | 05-29-2014 |
20140167042 | MEMRISTORS HAVING MIXED OXIDE PHASES - A memristor includes a first electrode; a second electrode; and a switching layer interposed between the first electrode and the second electrode, wherein the switching layer includes an electrically semiconducting or nominally insulating and weak ionic switching mixed metal oxide phase for forming at least one switching channel in the switching layer. A method of forming the memristor is also provided. | 06-19-2014 |
20150041751 | CUSTOMIZABLE NONLINEAR ELECTRICAL DEVICES - In one example, a customizable nonlinear electrical device includes a first conductive layer, a second conductive layer, and a thin film metal-oxide layer sandwiched between the first conductive layer and the second conductive layer to form a first rectifying interface between the metal-oxide layer and the first conductive layer and a second rectifying interface between the metal-oxide layer and the second conductive layer. The metal-oxide layer includes an electrically conductive mixture of co-existing metal and metal oxides. A method forming a nonlinear electrical device is also provided. | 02-12-2015 |
Patent application number | Description | Published |
20090265148 | MODELING A SECTOR-POLARIZED-ILLUMINATION SOURCE IN AN OPTICAL LITHOGRAPHY SYSTEM - One embodiment of the present invention provides a system that constructs a source polarization model to simulate a piecewise-constant-linear polarization-configuration of an illumination source in an optical lithography system. During operation, the system starts by partitioning an illumination pupil plane of the illumination source into a set of sectors to match a physical implementation of the illumination source. Next, the system constructs the source polarization model for the illumination source by individually specifying a constant-linear polarization-state within each sector to match the polarization-configuration of the illumination source. | 10-22-2009 |
20100058280 | BULK IMAGE MODELING FOR OPTICAL PROXIMITY CORRECTION - A method is described herein for predicting lateral position information about a feature represented in an integrated circuit layout for use with an integrated circuit fabrication process, where the process projects an image onto a resist. The method includes providing a lateral distribution of intensity values of the image at different depths with the resist. Next, the lateral position of an edge point of the feature is predicted in dependence upon a particular resist development time, and further in dependence upon the image intensity values at more than one depth within the resist. | 03-04-2010 |
20100280812 | Modeling critical-dimension (CD) scanning-electron-microscopy (CD-SEM) CD extraction - One embodiment of the present invention relates to a process that models critical-dimension (CD) scanning-electron-microscopy (CD-SEM) extraction during photolithography process model calibration. During operation, the process receives measured CD values which were obtained using a CD-SEM extraction process, wherein the CD-SEM extraction process determines a measured CD value for a feature by measuring multiple CD values of the feature along multiple electron beam scans. The process then determines simulated CD values, wherein a simulated CD value is determined based at least on a set of CD extraction cut-lines evenly placed around the target feature. During subsequent photolithography process model calibration, the process fits a parameter that models an aspect of the photolithography process based at least on both the measured CD values and the simulated CD values. | 11-04-2010 |
20110029940 | METHOD AND APPARATUS FOR MODELING THIN-FILM TOPOGRAPHY EFFECT ON A PHOTOLITHOGRAPHY PROCESS - One embodiment of the present invention provides a system that determines image intensity at a location in a photoresist (PR) layer on a wafer. During operation, the system receives a set of masks which were used to generate one or more patterned layers of a multilayer structure on the wafer, wherein a patterned layer includes a set of reflectors on a top surface of the patterned layer, which correspond to patterns in a patterned-layer mask in the set of masks, wherein a reflector reflects light from a light source during a photolithography process. The system then generates a first virtual mask based on the first mask and the patterned-layer mask, wherein the first virtual mask uses a clear area to model a reflector in the set of reflectors. Next, the system determines the image intensity value at the location on the PR layer based at least on the first mask and the first virtual mask. | 02-03-2011 |
Patent application number | Description | Published |
20120084142 | BID LANDSCAPE FORECASTING IN ONLINE ADVERTISING - Techniques are provided for advertiser bid forecasting in online advertising, including display advertising. Methods are provided in which key targeting-related user segments are determined from bidding statistics. A feature set is extracted from an impression opportunity, based at least in part on the bidding statistics. A gradient boosting descent tree technique is utilized in determining an initial bid forecasting result. A linear regression-based model is used in post-tuning to arrive at a post-tuned result. For short-term forecasting, this may be the final result. For long-term forecasting, a hybrid approach may be utilized with further processing including utilization of a publisher-specific model. | 04-05-2012 |
20130085865 | CONTEXT-CONTINGENT TARGETING IN ONLINE ADVERTISING - An advertising exchange server for context-contingent targeting of online advertisements may include a processor, memory, a communication interface, and a database saved in system storage to store advertisements saved in relation to advertising attributes. The processor may be configured to work with the communication interface to provide an option for an advertiser to express a targeting profile using a freeform mixture of logical operations including a plurality of targeting attributes, the freeform mixture of logical operations excluding solely a series of conjunctive combinations. The processor may receive, and store in memory, the expressed targeting profile and at least one associated advertisement from the advertiser. The processor may receive and match an advertising opportunity with one or more targeting attributes of the targeting profile. The processor may deliver the advertisement associated with the targeting profile that substantially matches the advertising opportunity to fill the advertising opportunity. | 04-04-2013 |
20130339126 | CAMPAIGN PERFORMANCE FORECASTING FOR NON-GUARANTEED DELIVERY ADVERTISING - Advertisement (“ad”) campaign forecasting may predict results for the campaign and the ads included in the campaign. The results may include a forecast for impressions, clicks, conversions, and/or interactions with the ads. The forecasting may be utilized for display advertising with non-guaranteed delivery (“NGD”) systems in which a bidding platform allows advertisers to bid for ad impressions, clicks, and/or conversions. Forecasting results may be used by advertisers to manage and optimize campaigns. | 12-19-2013 |
20130346182 | MULTIMEDIA FEATURES FOR CLICK PREDICTION OF NEW ADVERTISEMENTS - Multimedia features extracted from display advertisements may be integrated into a click prediction model for improving click prediction accuracy. Multimedia features may help capture the attractiveness of ads with similar contents or aesthetics. Numerous multimedia features (in addition to user, advertiser and publisher features) may be utilized for the purposes of improving click prediction in ads with limited or no history. | 12-26-2013 |
20150186938 | SEARCH SERVICE ADVERTISEMENT SELECTION - Methods, computer systems, and computer storage media are provided for evaluating information retrieval (IR) such as search query results (including advertisements) by a machine learning scorer. In an embodiment, a set of features is derived from a query and a machine learning algorithm is applied to construct a linear model of (query, ads) for scoring by maximizing a relevance metric. In an embodiment, the machine learned scorer is adapted for use with WAND algorithm based ad selection. | 07-02-2015 |
20150262220 | Dynamic Advertising Based on User Preferences - Systems and methods for responding to an advertisement request with a personalized advertisement are provided. More particularly, in response to an advertisement request from a requesting computer user, a plurality of candidate advertisements are identified and an advertisement is selected. A plurality of potential modifications for the selected advertisement are then identified. A modification, from the plurality of potential modifications, is selected as a function of a user preference vector associated with the requesting computer user. The user preference vector comprises a plurality of user preference items, each item indicating a likelihood of interaction of the requesting computer user with an advertisement having a modification according to a corresponding preference classification. Modification content corresponding to the selected modification is obtained and the modification content is added the selected advertisement. The modified selected advertisement is returned as a personalized advertisement to the advertisement request. | 09-17-2015 |
20150278200 | Convolutional Latent Semantic Models and their Applications - Functionality is described herein for transforming first and second symbolic linguistic items into respective first and second continuous-valued concept vectors, using a deep learning model, such as a convolutional latent semantic model. The model is designed to capture both the local and global linguistic contexts of the linguistic items. The functionality then compares the first concept vector with the second concept vector to produce a similarity measure. More specifically, the similarity measure expresses the closeness between the first and second linguistic items in a high-level semantic space. In one case, the first linguistic item corresponds to a query, and the second linguistic item may correspond to a phrase, or a document, or a keyword, or an ad, etc. In one implementation, the convolutional latent semantic model is produced in a training phase based on click-through data. | 10-01-2015 |
Patent application number | Description | Published |
20120150626 | System and Method for Automated Recommendation of Advertisement Targeting Attributes - A system and method for recommending targeting attributes for advertising campaigns are provided. The system and method comprise receiving at least one advertizing campaign, receiving historical targeting data and historical click-through data, selecting a machine learning model, and determining recommended targeting attributes for the advertising campaign using the machine learning model and the received data. The machine learning model may be a collaborative filtering model or a performance oriented model. The collaborative filtering model may rely on matrix factorization or Boltzmann Machines. The performance-oriented model may rely on a local regression. | 06-14-2012 |
20120158456 | Forecasting Ad Traffic Based on Business Metrics in Performance-based Display Advertising - A method, advertising network, and computer readable medium for forecasting ad traffic based on business metrics in performance-based display advertising. The method commences by defining a set of advertising campaign parameters, the advertising campaign parameters comprising target predicates, a campaign pricing model, and a campaign performance model. The method continues by forecasting a supply of impressions satisfying target predicates, based on a statistical analysis of a historical dataset containing impressions satisfying target predicates. Once a measure of forecasted supply is known, an auction model serves for calculating the likelihood of winning the forecasted impression at auction, based the campaign pricing model and the campaign performance model. Having a forecasted supply, and also an assessment of the likelihood of winning at auction, the method proceeds by determining values for various performance metrics. The performance metrics are displayed; the user makes changes to any one or more of the advertising campaign parameters. | 06-21-2012 |