Patent application number | Description | Published |
20110282925 | DIRECTIONAL OPTIMIZATION VIA EBW - An optimization system and method includes determining a best gradient as a sparse direction in a function having a plurality of parameters. The sparse direction includes a direction that maximizes change of the function. This maximum change of the function is determined by performing an optimization process that gives maximum growth subject to a sparsity regularized constraint. An extended Baum Welch (EBW) method can be used to identify the sparse direction. A best step size is determined along the sparse direction by finding magnitudes of entries of direction that maximizes the function restricted to the sparse direction. A solution is recursively refined for the function optimization using a processor and storage media. | 11-17-2011 |
20110283226 | WINDOW DISPLAY MANAGEMENT IN A GRAPHICAL USER INTERFACE - The present invention provides a computer implemented method and data processing system for effectively presenting popup and related windows on a computer GUI. An example system may include a computer processor coupled to the computer readable memory. The computer processor is configured to receive content of a new window for display in the display screen, perform a text analysis on the content of the new window to determine a relevance of the new window to the user, and determine a display position of the new window on the display screen based on the relevance of the new window to the user and a cursor position in the GUI displaying keyboard input such that the new window is displayed on the display screen at the determined display position. | 11-17-2011 |
20110304446 | SYSTEM FOR PREVENTING HANDHELD DEVICE USE WHILE OPERATING A VEHICLE - Techniques for preventing a driver of a moving vehicle from using a handheld device while driving. An example system of the invention includes a plurality of biometric sensors configured to receive biometric data from the driver and a user of the handheld device. Contemporaneously with operation of the vehicle and the handheld device, the biometric data is analyzed in order to determine a match between the identity of the vehicle driver and the user of the handheld device. A controller is configured to selectively interrupt operation of the vehicle or handheld device upon detecting the match. | 12-15-2011 |
20120016674 | Modification of Speech Quality in Conversations Over Voice Channels - Techniques are disclosed for modifying speech quality in a conversation over a voice channel. For example, a method for modifying a speech quality associated with a spoken utterance transmittable over a voice channel comprises the following steps. The spoken utterance is obtained prior to an intended recipient of the spoken utterance receiving the spoken utterance. An existing speech quality of the spoken utterance is determined. The existing speech quality of the spoken utterance is compared to at least one desired speech quality associated with at least one previously obtained spoken utterance to determine whether the existing speech quality substantially matches the desired speech quality. At least one characteristic of the spoken utterance is modified to change the existing speech quality of the spoken utterance to the desired speech quality when the existing speech quality does not substantially match the desired speech quality. The spoken utterance is presented with the desired speech quality to the intended recipient. | 01-19-2012 |
20120078621 | SPARSE REPRESENTATION FEATURES FOR SPEECH RECOGNITION - Techniques are disclosed for generating and using sparse representation features to improve speech recognition performance. In particular, principles of the invention provide sparse representation exemplar-based recognition techniques. For example, a method comprises the following steps. A test vector and a training data set associated with a speech recognition system are obtained. A subset of the training data set is selected. The test vector is mapped with the selected subset of the training data set as a linear combination that is weighted by a sparseness constraint such that a new test feature set is formed wherein the training data set is moved more closely to the test vector subject to the sparseness constraint. An acoustic model is trained on the new test feature set. | 03-29-2012 |
20120189878 | Optimizing Battery Usage - Techniques for optimizing battery usage are provided. The techniques include sensing energy level of a battery, comparing the sensed energy level of the battery to a predetermined energy threshold for the battery, and controlling energy flow to and from the battery based on the comparison of the sensed energy level and the energy threshold. | 07-26-2012 |
20120210277 | USAGE BASED SCREEN MANAGEMENT - An apparatus and method are provided for a power saving for multi-media output devices that belong to two or more interconnected devices. The method includes receiving a set of predetermined criteria associated with at least one of application type, user behavior, and user characteristics. The method further includes selectively modifying portions of at least one of the multi-media output devices in accordance with the set of predetermined criteria. The one or more portions are less than an entirety of the at least one of the multi-media output devices. | 08-16-2012 |
20120215843 | Virtual Communication Techniques - Techniques for facilitating communication are provided. The techniques include using a machine-to-machine communication to facilitate communication between one or more human users of a communicator device and a compatible communicator device, wherein using the machine-to-machine communication to facilitate communication between one or more human users comprises initiating a machine-to-machine communication with a compatible communicator device if the device is within the geographic proximity, wherein the machine-to-machine communication incorporates one or more related items from a user profile of each device automatically extracted by the device initiating the machine-to-machine communication, and conducting the machine-to-machine communication in a manner in which the communication can be monitored by the one or more human users. | 08-23-2012 |
20120240237 | SYSTEM AND METHOD FOR IN-PRIVATE BROWSING - A method, system, and computer program product for operating a web browser in an open browsing mode and a private browsing mode. The method may include calculating, by a computer processor, a privacy probability that a website contains information sensitive to the user. The privacy probability may be based, at least in part, on historical use of the private browsing mode by the user. The method may also include comparing the privacy probability to a privacy threshold and automatically switching the browser from the open browsing mode to the private browsing mode for the website if the privacy probability is greater than the privacy threshold. | 09-20-2012 |
20120243670 | Automatically Updating Meeting Information - Techniques for automatically providing updated meeting information are provided. The techniques include facilitating receipt of a message pertaining to a meeting, automatically interpreting the message to determine if the message requires that meeting information be changed, automatically updating the meeting information if a change is required from the message, and automatically sending a message to each meeting participant informing each participant of the updated meeting information. | 09-27-2012 |
20120253784 | LANGUAGE TRANSLATION BASED ON NEARBY DEVICES - A device, method, and computer program for performing language translation. An example embodiment may include a communications module configured to receive device data from a nearby device. A constraint module is configured to limit a translation domain of the language translation based on the device data. Language translation is performed within the limited translation domain. | 10-04-2012 |
20120290299 | Translating Between Spoken and Written Language - Techniques for converting spoken speech into written speech are provided. The techniques include transcribing input speech via speech recognition, mapping each spoken utterance from input speech into a corresponding formal utterance, and mapping each formal utterance into a stylistically formatted written utterance. | 11-15-2012 |
20130198761 | Intelligent Dialogue Amongst Competitive User Applications - A method, an apparatus and an article of manufacture for enabling communication between at least two computer applications that is observable to a user. The method includes obtaining a description of functions for each of the at least two computer applications, comparing the description of functions for each of the at least two computer applications, generating a dialog between the at least two applications based on the comparing of the description of functions for each of the at least two computer applications, and making the dialog available to a user. | 08-01-2013 |
20130227701 | Masking Mobile Message Content - A method, an apparatus and an article of manufacture for masking a message on an electronic device. The method includes receiving a message on an electronic device, determining if a message category label is included in the message, mapping the message category to a corresponding masking format if a message category label is included in the message, extracting the content of the message to generate a message category if a message category label is not included in the message, wherein each message category generated corresponds to a masking format, and masking the message on the electronic device by transforming the message into the masking format that corresponds to the message category for the message. | 08-29-2013 |
20130268242 | Sparse Representation for Dynamic Sensor Networks - A method, an apparatus and an article of manufacture for evaluating data from a network of sensors. The method includes analyzing data received from at least one sensor using exemplar-based sparse representation processing to create a sparse representation of the data, determining at least one discrete sparse characteristic of an event in the data received from the at least one sensor based on the sparse representation of the data, and evaluating the at least one discrete sparse characteristic of an event in the data to perform at least one task associated with the representation of the event in the data. | 10-10-2013 |
20140012563 | PROVIDING MULTI-LINGUAL SEARCHING OF MONO-LINGUAL CONTENT - Approaches for translating a transliterated search query are provided. An approach includes: receiving a search query containing a transliterated word; determining a source language corresponding to the transliterated word; converting the transliterated word to a word in the source language; translating the word in the source language to a word in a target language; and performing a search using the word in the target language. | 01-09-2014 |
20140012567 | Text Auto-Correction via N-Grams - An input text string is received that contains characters or words. The input text string can be completed or corrected using contact scores based on n-grams. In addition, a subsequent text string and a preceding text string for the input text string are also identified, again using n-gram scores. A corrected text string is created by inserting the preceding text string before the input text string and appending the subsequent text string after the input text string. | 01-09-2014 |
20140012568 | Text Auto-Correction via N-Grams - An input text string is received that contains characters or words. The input text string can be completed or corrected using contact scores based on n-grams. In addition, a subsequent text string and a preceding text string for the input text string are also identified, again using n-gram scores. A corrected text string is created by inserting the preceding text string before the input text string and appending the subsequent text string after the input text string. | 01-09-2014 |
20140012912 | Controlled Resources Based on Good Behavior - Computing system resources are controlled based on the behavioral attributes associated with users of the computing system. These behavioral attributes are monitored in real time and through a historical log, and behavioral attributes that fall outside pre-determined preferred behavioral parameters are detected. Access by the computing system user to computing system resources contained in a preferred and habitually accessed computing system resource set associated with the computing system user are adjusted in response to the detection of the behavioral attribute outside the pre-determined preferred behavioral parameters. | 01-09-2014 |
20140013445 | Controlled Resources Based on Good Behavior - Computing system resources are controlled based on the behavioral attributes associated with users of the computing system. These behavioral attributes are monitored in real time and through a historical log, and behavioral attributes that fall outside pre-determined preferred behavioral parameters are detected. Access by the computing system user to computing system resources contained in a preferred and habitually accessed computing system resource set associated with the computing system user are adjusted in response to the detection of the behavioral attribute outside the pre-determined preferred behavioral parameters. | 01-09-2014 |
20140019388 | SYSTEM AND METHOD FOR LOW-RANK MATRIX FACTORIZATION FOR DEEP BELIEF NETWORK TRAINING WITH HIGH-DIMENSIONAL OUTPUT TARGETS - Systems and methods for reducing a number of training parameters in a deep belief network (DBN) are provided. A method for reducing a number of training parameters in a deep belief network (DBN) comprises determining a network architecture including a plurality of layers, using matrix factorization to represent a weight matrix of a final layer of the plurality of layers as a plurality of matrices, and training the DBN having the plurality of matrices. | 01-16-2014 |
20140019697 | CLIPBOARD FOR PROCESSING RECEIVED DATA CONTENT - An embodiment of the invention directed to a method is associated with data content, comprising discrete data portions including first data and second data portions separated from each other in the data content. A copy operation is implemented on data portions so that at least some of the data portions are each copied to a buffer, which include the first and second data portions. A paste operation is carried out to present each of the copied data portions as an input for an output data selection task. Prespecified criteria is used in the output data selection task to select a number of the copied data portions to be selected data for a given purpose, the selected number of copied data portions being less than data portions presented by the paste operation, and the selected copied data portions including the first and second data portions. | 01-16-2014 |
20140019857 | CLIPBOARD FOR PROCESSING RECEIVED DATA CONTENT - An embodiment of the invention directed to a method is associated with data content, comprising discrete data portions including first data and second data portions separated from each other in the data content. A copy operation is implemented on data portions so that at least some of the data portions are each copied to a buffer, which include the first and second data portions. A paste operation is carried out to present each of the copied data portions as an input for an output data selection task. Prespecified criteria is used in the output data selection task to select a number of the copied data portions to be selected data for a given purpose, the selected number of copied data portions being less than data portions presented by the paste operation, and the selected copied data portions including the first and second data portions. | 01-16-2014 |
20140032570 | Discriminative Learning Via Hierarchical Transformations - Techniques for discriminative learning via hierarchical transformations. A method includes obtaining a model of a first set of data, two or more data transformations, and a second set of data, evaluating the two or more data transformations to determine which data transformation will most effectively modify the second set of data to match the model, and selecting the data transformation that will most effectively modify the second set of data to match the model based on the evaluation. | 01-30-2014 |
20140032571 | Discriminative Learning Via Hierarchical Transformations - A system and an article of manufacture for discriminative learning via hierarchical transformations, which includes obtaining a model of a first set of data, two or more data transformations, and a second set of data, evaluating the two or more data transformations to determine which data transformation will most effectively modify the second set of data to match the model, and selecting the data transformation that will most effectively modify the second set of data to match the model based on the evaluation. | 01-30-2014 |
20140039691 | Multi-Dimensional Heating and Cooling System - Methods and system for facilitating multi-dimensional personal heating and cooling. User information is used as a mean to configure the temperature in a surrounding environment, thereby facilitating comfort for a user and, in the case wherein multiple users are accessing an area, classifying the area into a number of regions and maintaining each region at a different temperature and guiding the users to desired regions. | 02-06-2014 |
20140074943 | Electronic Communication Warning and Modification - Techniques for electronic communication warning and modification. A method includes automatically detecting an emotional state of a sender of an electronic communication, encoding the detected emotional state of the sender, using input from at least one additional source, as metadata, embedding the metadata in the electronic communication to create an annotated version of the electronic communication, and transmitting the annotated version of the electronic communication to a recipient. | 03-13-2014 |
20140074945 | Electronic Communication Warning and Modification - A system and article of manufacture for electronic communication warning and modification include automatically detecting an emotional state of a sender of an electronic communication, encoding the detected emotional state of the sender, using input from at least one additional source, as metadata, embedding the metadata in the electronic communication to create an annotated version of the electronic communication, and transmitting the annotated version of the electronic communication to a recipient. | 03-13-2014 |
20140112201 | Forming a Convex Polygon of Mobile Sensors - Forming a convex polygon of a plurality of mobile sensors in an area is provided. Sensor output data received from the plurality of mobile sensors in the area is analyzed using an optimization problem. It is determined whether the plurality of mobile sensors forms the convex polygon in the area. In response to determining that the plurality of mobile sensors does form the convex polygon in the area, an objective function and a set of constraints corresponding to the optimization problem are generated. Then, a sparse solution of the optimization problem is calculated using the objective function and the set of constraints to determine vector weight values for each of the plurality of mobile sensors. | 04-24-2014 |
20140114625 | Forming a Convex Polygon of Mobile Sensors - Forming a convex polygon of a plurality of mobile sensors in an area is provided. Sensor output data received from the plurality of mobile sensors in the area is analyzed using an optimization problem. It is determined whether the plurality of mobile sensors forms the convex polygon in the area. In response to determining that the plurality of mobile sensors does form the convex polygon in the area, an objective function and a set of constraints corresponding to the optimization problem are generated. Then, a sparse solution of the optimization problem is calculated using the objective function and the set of constraints to determine vector weight values for each of the plurality of mobile sensors. | 04-24-2014 |
20140119563 | SYSTEM AND METHOD FOR USING BIOMETRICS TO PREDICT AND SELECT MUSIC PREFERENCES - Systems and methods for using biometrics to select music preference are provided. A system for using biometrics to select music preferences for a user in a vehicle, comprises a music selection module electrically coupled to at least one biometric sensor in the vehicle, wherein the at least one biometric sensor senses a characteristic of the user and outputs data for the sensed characteristic to the music selection module, and wherein the music selection module selects a music selection for the user based on the sensed characteristic data, and a controller module electrically coupled to the music selection module to control playing of the music selection, wherein the controller module receives an output including the music selection from the music selection module. | 05-01-2014 |
20140119564 | SYSTEM AND METHOD FOR USING BIOMETRICS TO PREDICT AND SELECT MUSIC PREFERENCES - Systems and methods for using biometrics to select music preference are provided. A system for using biometrics to select music preferences for a user in a vehicle, comprises a music selection module electrically coupled to at least one biometric sensor in the vehicle, wherein the at least one biometric sensor senses a characteristic of the user and outputs data for the sensed characteristic to the music selection module, and wherein the music selection module selects a music selection for the user based on the sensed characteristic data, and a controller module electrically coupled to the music selection module to control playing of the music selection, wherein the controller module receives an output including the music selection from the music selection module. | 05-01-2014 |
20140156176 | MANAGING VEHICLES ON A ROAD NETWORK - A system and method for managing vehicles on a road network can include a processor that performs operations including accessing a matrix of vehicle parameters of a plurality of communicating vehicles on the road network and representing the plurality of communicating vehicles in a graph with a plurality of nodes corresponding to the plurality of communicating vehicles and edges corresponding to the vehicle parameters. The system and method can include partitioning, with a processing device, the graph to reduce disruptions to the road network below a threshold level to support safe and efficient traffic flow and assigning one or more exclusion zones within the road network to each partition of the graph by associating the vehicle parameters for each vehicle. | 06-05-2014 |
20140156177 | MANAGING VEHICLES ON A ROAD NETWORK - A system and method for managing vehicles on a road network can include a processor that performs operations including accessing a matrix of vehicle parameters of a plurality of communicating vehicles on the road network and representing the plurality of communicating vehicles in a graph with a plurality of nodes corresponding to the plurality of communicating vehicles and edges corresponding to the vehicle parameters. The system and method can include partitioning, with a processing device, the graph to reduce disruptions to the road network below a threshold level to support safe and efficient traffic flow and assigning one or more exclusion zones within the road network to each partition of the graph by associating the vehicle parameters for each vehicle. | 06-05-2014 |
20140156575 | Method and Apparatus of Processing Data Using Deep Belief Networks Employing Low-Rank Matrix Factorization - Deep belief networks are usually associated with a large number of parameters and high computational complexity. The large number of parameters results in a long and computationally consuming training phase. According to at least one example embodiment, low-rank matrix factorization is used to approximate at least a first set of parameters, associated with an output layer, with a second and a third set of parameters. The total number of parameters in the second and third sets of parameters is smaller than the number of sets of parameters in the first set. An architecture of a resulting artificial neural network, when employing low-rank matrix factorization, may be characterized with a low-rank layer, not employing activation function(s), and defined by a relatively small number of nodes and the second set of parameters. By using low rank matrix factorization, training is faster, leading to rapid deployment of the respective system. | 06-05-2014 |
20140214403 | SYSTEM AND METHOD FOR IMPROVING VOICE COMMUNICATION OVER A NETWORK - Systems and methods for improving communication over a network are provided. A system for improving communication over a network, comprises a detection module capable of detecting data indicating a problem with a communication between at least two participants communicating via communication devices over the network, a management module capable of analyzing the data to determine whether a participant is dissatisfied with the communication, wherein the management module includes a determining module capable of determining that the participant is dissatisfied, and identifying an event causing the dissatisfaction, and a resolution module capable of providing a solution for eliminating the problem. | 07-31-2014 |
20140214426 | SYSTEM AND METHOD FOR IMPROVING VOICE COMMUNICATION OVER A NETWORK - Systems and methods for improving communication over a network are provided. A system for improving communication over a network, comprises a detection module capable of detecting data indicating a problem with a communication between at least two participants communicating via communication devices over the network, a management module capable of analyzing the data to determine whether a participant is dissatisfied with the communication, wherein the management module includes a determining module capable of determining that the participant is dissatisfied, and identifying an event causing the dissatisfaction, and a resolution module capable of providing a solution for eliminating the problem. | 07-31-2014 |
20140297783 | UNDOING SENT COMMUNICATIONS - Techniques for managing objects sent in a communication system. For example, a method for managing an object in a communication system comprises the following steps. An object previously sent in the communication system is identified. A first target to which the object was sent is determined. A first agent is deployed to the first target. The first agent is configured to undo the previously sent object at the first target, and determine if the previously sent object was sent from the first target to a second target. When the previously sent object was sent from the first target to the second target, the method deploys a second agent to the second target to undo the previously sent object at the second target. | 10-02-2014 |
20140297786 | UNDOING SENT COMMUNICATIONS - Techniques for managing objects sent in a communication system. For example, an apparatus for managing an object in a communication system is configured to identify an object previously sent in the communication system. A first target to which the object was sent is determined. A first agent is deployed to the first target. The first agent is configured to undo the previously sent object at the first target, and determine if the previously sent object was sent from the first target to a second target. When the previously sent object was sent from the first target to the second target, the apparatus deploys a second agent to the second target to undo the previously sent object at the second target. | 10-02-2014 |
20140317069 | INDEXING OF SIGNIFICANT MEDIA GRANULARS - Identifying significant media granulars may comprise partitioning a media document into one or more media granulars. A score may be assigned to each of the one or more media granulars. The one or more media granulars may be monitored to detect one or more user actions on the one or more media granular. The score associated with a respective one of the media granulars may be updated based on a number of user actions detected on the respective one of the media granulars. A media granular may be identified as being significant based on the score meeting a threshold. | 10-23-2014 |
20140317123 | INDEXING OF SIGNIFICANT MEDIA GRANULARS - Identifying significant media granulars may comprise partitioning a media document into one or more media granulars. A score may be assigned to each of the one or more media granulars. The one or more media granulars may be monitored to detect one or more user actions on the one or more media granular. The score associated with a respective one of the media granulars may be updated based on a number of user actions detected on the respective one of the media granulars. A media granular may be identified as being significant based on the score meeting a threshold. | 10-23-2014 |
20140352139 | POWER SOURCE ENCAPSULATION - A method comprising the steps of encapsulating a power source including a set of power terminals in a cover and sealing the power source including the set of power terminals within the cover and inserting a set of conductive contacts through the cover to contact the set of power terminals and provide conductive access to the set of power terminals of the power source from outside the cover without allowing exposure of the power source to an environment outside the cover. | 12-04-2014 |
20140356699 | POWER SOURCE ENCAPSULATION - A system includes a power source having a set of power terminals, a cover encapsulating the power source including the set of power terminals and sealing the power source including the set of power terminals within the cover, and a set of conductive contacts passing through the cover, contacting the set of power terminals, and providing conductive access to the set of power terminals of the power source from outside the cover without allowing exposure of the power source to an environment outside the cover. | 12-04-2014 |
20140372538 | SYSTEM AND METHOD FOR GENERATING INTENTIONAL INTERRUPTIONS DURING GATHERINGS - Systems and methods for generating interruptions are provided. A method for generating interruptions, comprises generating a message for one or more recipients, detecting that a computing device is being used for a presentation, concluding, using a processor, that the one or more recipients are in an audience for the presentation, and after concluding that the one or more recipients are in the audience, interrupting the presentation with the message. | 12-18-2014 |
20140372650 | SYSTEM AND METHOD FOR GENERATING INTENTIONAL INTERRUPTIONS DURING GATHERINGS - Systems and methods for generating interruptions are provided. A method for generating interruptions, comprises generating a message for one or more recipients, detecting that a computing device is being used for a presentation, concluding, using a processor, that the one or more recipients are in an audience for the presentation, and after concluding that the one or more recipients are in the audience, interrupting the presentation with the message. | 12-18-2014 |
20150051826 | SYSTEM AND METHOD FOR PROVIDING GLOBAL POSITIONING SYSTEM (GPS) FEEDBACK TO A USER - Systems and methods for providing global positioning system (GPS) feedback to a user are provided. A method for providing global positioning system (GPS) feedback to a user, comprises evaluating a route of the user to determine potential points of confusion, collecting at least one of behavioral information and physiological information from the user, analyzing the collected information to determine a level of user confusion at a point on the route and whether the level of the user confusion exceeds a threshold, and providing the user with clarifying feedback upon at least one of a determination of a potential point of confusion and the level of the user confusion exceeding the threshold. | 02-19-2015 |
20150058312 | PROVIDING MULTI-LINGUAL SEARCHING OF MONO-LINGUAL CONTENT - Approaches for translating a transliterated search query are provided. An approach includes receiving a search query containing a transliterated word. The approach also includes determining a source language corresponding to the transliterated word. The approach further includes converting the transliterated word to a word in the source language. The approach additionally includes translating the word in the source language to a word in a target language. The approach also includes performing a search using the word in the target language. | 02-26-2015 |
20150058426 | SYSTEM AND METHOD FOR AUTOMATICALLY GENERATING EMAIL SUBJECT LINES - Systems and methods for automatically generating e-mail subject lines are provided. A method for automatic generation of subject lines for electronic mail (email), comprises extracting topics from an email message, computing a sender relevance score for each topic, computing a receiver relevance score for each topic, ranking the topics based on the sender and receiver relevance scores, extracting syntactic units from the email message, ranking the extracted syntactic units from the email message based on the topic ranking, and assigning one or more subject lines to the email message based on the ranking of the syntactic units. | 02-26-2015 |
20150058428 | SYSTEM AND METHOD FOR AUTOMATICALLY GENERATING EMAIL SUBJECT LINES - Systems and methods for automatically generating e-mail subject lines are provided. A method for automatic generation of subject lines for electronic mail (email), comprises extracting topics from an email message, computing a sender relevance score for each topic, computing a receiver relevance score for each topic, ranking the topics based on the sender and receiver relevance scores, extracting syntactic units from the email message, ranking the extracted syntactic units from the email message based on the topic ranking, and assigning one or more subject lines to the email message based on the ranking of the syntactic units. | 02-26-2015 |