Classification Or Recognition Patents (Class 706/20)
  • Patent number: 10290148
    Abstract: Sustainable building lighting and energy modelling and control, and the associated computer graphics, including real-time dynamic lighting simulation, are concerned with: an optimized method for radiance modelling, including its application to predictive daylight harvesting; and the real-time simulation of physically-based electric lighting and daylighting for architectural, horticultural, and theatrical lighting systems visualization. In order to display and analyze in real time a photometrically accurate representation of an environment, thousands of lighting channels may have their intensity settings continually varied such that a user may interactively view the three-dimensional environment without the need for ongoing global illumination calculations. This can be accomplished utilizing texture maps as a multiplicity of canonical radiosity solutions, each representing a lighting channel for dynamic lighting simulation, and storing the solutions in the texture memory of a graphics processing unit.
    Type: Grant
    Filed: August 2, 2017
    Date of Patent: May 14, 2019
    Inventors: Ian Ashdown, Wallace Jay Scott
  • Patent number: 10282677
    Abstract: A method and system are provided. The method includes deriving a set of user attributes from an aggregate analysis of images and videos of a user. The deriving step includes recognizing, by a set of visual classifiers, semantic concepts in the images and videos of the user to generate visual classifier scores. The deriving step further includes deriving, by a statistical aggregator, the set of user attributes. The set of user attributes are derived by mapping the visual classifier scores to a taxonomy of semantic categories to be recognized in visual content. The deriving step also includes displaying, by an interactive user interface having a display, attribute profiles for the attributes and comparisons of the attribute profiles.
    Type: Grant
    Filed: November 5, 2015
    Date of Patent: May 7, 2019
    Assignee: International Business Machines Corporation
    Inventors: Michele Merler, Jae-Eun Park, John R. Smith, Rosario Uceda-Sosa
  • Patent number: 10284585
    Abstract: Methods and apparatus for optimizing computer detection of malware using pattern recognition by refreshing random classification forests are described. In one embodiment, one or more selected trees of a random forest on a computing system may be replaced by one or more new trees. As new categorized data becomes available, one or more new trees may be generated using the new categorized data. Once the one or more new trees are available, the performance of the one or more new trees may be compared to the performance of the trees in the current random forest. Based on this comparison, one or more trees of the random forest may be selected to be replaced by one or more of the new trees.
    Type: Grant
    Filed: September 28, 2016
    Date of Patent: May 7, 2019
    Assignee: Symantec Corporation
    Inventors: Mark Kennedy, Andrew B. Gardner
  • Patent number: 10262274
    Abstract: The present invention relates to a method for incremental learning of a classification model, where pre-defined weak incremental learners are distributed over the distinct regions in a set of partitionings of the input domain. The partitionings and regions are organized via a binary tree and they are allowed to vary in a data-driven way, i.e., in a way to minimize the classification error rate. Moreover, to test a given data point, a mixture of decisions is obtained through the models learned in the regions that this point falls in. Hence, naturally, in the cold start phase of the data stream, the simpler models belonging to the larger regions are favored and as more data get available, the invention automatically puts more weights on the more complex models.
    Type: Grant
    Filed: July 22, 2013
    Date of Patent: April 16, 2019
    Assignee: ASELSAN ELEKTRONIK SANAYI VE TICARET ANONIM SIRKETI
    Inventor: Hüseyin Ozkan
  • Patent number: 10264096
    Abstract: A system, method, and apparatus are provided for depicting attributes of a user's or member's connections within a professional or social network, in a manner that enables insight into the nature of the connections. When insight into a first member's connections is to be depicted, one or more attributes of first-degree connections (i.e., direct connections) and/or other connections are retrieved (e.g., employer or associated organization, function or role, seniority, skill(s)), over all time or some threshold period of time into the past. The values for the attributes are aggregated over the examined connections, and some or all values are displayed with one or more visual characteristics (e.g., size, color) that indicate a frequency or commonness of the values among the connections. The system or apparatus may include a user interface through which the depiction is presented in place of or in addition to a display of the connections.
    Type: Grant
    Filed: March 19, 2015
    Date of Patent: April 16, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Guan Wang, Huan V. Hoang
  • Patent number: 10255124
    Abstract: Embodiments are disclosed for determining whether a computing node is in a normal or an abnormal condition based on its characteristics relative to those of other computing nodes. In embodiments, log files for the computing node are used to develop a state model of the computing node, and where the state model differs between two similar computing nodes, an abnormality is identified. In other embodiments, characteristics about computing nodes (e.g., CPU resources used) are used to cluster those computing nodes, and those computing nodes that lie outside of a cluster are identified as abnormal.
    Type: Grant
    Filed: June 21, 2013
    Date of Patent: April 9, 2019
    Assignee: Amazon Technologies, Inc.
    Inventors: Carl Bellingan, Atle Jorgensen
  • Patent number: 10243988
    Abstract: According to an example, configurable network security may include receiving data flows directed to end node modules of a server, and selecting data flows from the received data flows based on an analysis of attributes of the received data flows. The selected data flows may be less than the received data flows. A number of IPS data plane modules of the server that are available for inspection of the selected data flows may be determined. The selected data flows may be distributed between the IPS data plane modules based on the determined number of the IPS data plane modules. The distributed data flows may be inspected using the IPS data plane modules to identify malicious and benign data flows, and to determine whether to drop the malicious data flows, direct the malicious data flows to a predetermined destination, or forward the benign data flows to the end node modules.
    Type: Grant
    Filed: October 13, 2016
    Date of Patent: March 26, 2019
    Assignee: Trend Micro Incorporated
    Inventors: Stephen G. Low, James Rolette, Matthew Laswell
  • Patent number: 10243976
    Abstract: A system for verifying resource propagations in real-time typically includes a classical computer apparatus and a quantum optimizer in communication with the classical computer apparatus. The quantum optimizer is configured to analyze resource propagation information related to previous resource propagations and confirmed attacks to generate a model for verifying resource propagations or mitigating potential attacks. When the classical computer apparatus receives indication of a present resource propagation, the classical computer apparatus transfers attributes of the present resource propagation to the quantum optimizer, which analyzes the resource propagation using the model to determine whether the resource propagation involves a potential attack. Based on the indication from the quantum optimizer, the classical computer apparatus attempts to mitigate the potential attack or allows the resource propagation to proceed.
    Type: Grant
    Filed: February 24, 2017
    Date of Patent: March 26, 2019
    Assignee: Bank of America Corporation
    Inventor: Jason Todd Greeter
  • Patent number: 10235437
    Abstract: A computer system and computer implemented method for extracting data set from data clusters that comprises of rows and columns of heterogeneous data values. A plurality of random data groups comprising of at least one of a plurality of contiguous row or columns of data values are selected. Each data value has a data type. A table template type is identified based on detection of a pattern between the data cells of the contiguous rows or columns. A table template header is identified that comprises of a starting position, and ending position and a width. A reference row or reference column indicating a start of a table body is determined. The data cells of the subsequent rows or columns in the table body are compared to the data cells of the reference rows to identify noise rows or columns that are removed from the table body.
    Type: Grant
    Filed: March 31, 2015
    Date of Patent: March 19, 2019
    Assignee: Informatica LLC
    Inventors: Saurabh Diwan, Shivananda P. J.
  • Patent number: 10234957
    Abstract: An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points; an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation.
    Type: Grant
    Filed: March 16, 2018
    Date of Patent: March 19, 2019
    Assignee: SONY CORPORATION
    Inventors: Keisuke Yamaoka, Jun Yokono
  • Patent number: 10230764
    Abstract: Various embodiments of the present technology include methods of assessing risk of a cyber security failure in a computer network of an entity. Some embodiments involve using continual or periodic data collecting to improve inferential analysis, as well as obtaining circumstantial or inferential information from social networks. Machine learning may be used to improve predicitive capabilities. Some embodiments allow for identification of an entity from circumstantial or inferential information based on the machine learning and comparative analyses.
    Type: Grant
    Filed: December 6, 2016
    Date of Patent: March 12, 2019
    Assignee: Guidewire Software, Inc.
    Inventors: George Y. Ng, Brian Wu, Ming Yang, Paul Yang, Fernando Tancioco, Jr.
  • Patent number: 10228818
    Abstract: Content that is significant to a user may be determined. An indication that a user finds content within a document significant may be received. In response to the received indication, the document may be analyzed to identify a set of topics associated with the content of the document. From the set of topics, a subset of topics responsible for the user finding the document significant may be identified. A user profile associated with the user may be updated based on the subset of topics.
    Type: Grant
    Filed: September 13, 2012
    Date of Patent: March 12, 2019
    Assignee: FACEBOOK, INC.
    Inventors: Hermannus Vandermolen, Charles Fish, Karen Howe, Paul Vidich, Scott J. Levine
  • Patent number: 10224931
    Abstract: A current-mode PUF circuit based on a reference current source comprises an input register, the reference current source, a deviation current comparator and a timing controller. The input register is used for ensuring synchronization of the input challenges to avoid influences of asynchronous challenges on output responses. The reference current source generates a reference current for temperature and voltage compensation. A deviation current source array generates two paths of deviation currents under the control of the input challenges. The deviation current comparator generates and outputs a judgement according to the magnitude of the current provided by the deviation current source array. The timing controller is used for generating timing information for operation of the PUF circuit. The invention has the following advantages: the deviation current source array outputs deviation currents with high robustness and high reliability.
    Type: Grant
    Filed: July 19, 2018
    Date of Patent: March 5, 2019
    Assignee: Ningbo University
    Inventors: Pengjun Wang, Gang Li, Huihong Zhang
  • Patent number: 10223330
    Abstract: Group aware command based arrangement is provided. An alignment command can be received, an undirected graph comprising a group of graph nodes connected by graph edges can be constructed, wherein the group of graph nodes represent a group of selected display elements, and the undirected graph can be partitioned as a function of identifying a severable graph edge of the graph edges that connects a pair of graph nodes included in the group of graph nodes to form a first collection of graph nodes and a second collection of graph nodes.
    Type: Grant
    Filed: August 26, 2015
    Date of Patent: March 5, 2019
    Assignees: CITY UNIVERSITY OF HONG KONG, THE HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY
    Inventors: Hongbo Fu, Pengfei Xu, Chiew-Lan Tai
  • Patent number: 10217147
    Abstract: Techniques for mapping item listings from a first taxonomy to a second taxonomy are described. In an example embodiment, item listings from a first database storing a first taxonomy and item listings from a second database storing a second taxonomy are obtained. Then, for each of the obtained item listings, a plurality of features is extracted, including at least one feature related to an image associated with the item listing and at least one feature related to text associated with the item listing. Then a mapping between item listings in the first taxonomy and item listings in the second taxonomy is created based on the plurality of features extracted by the feature extraction component, wherein the mapping identifies which item listings in the first taxonomy correlate to a same product as which item listings in the second taxonomy.
    Type: Grant
    Filed: October 17, 2014
    Date of Patent: February 26, 2019
    Assignee: eBay Inc.
    Inventors: Gurudatta Horantur Shivaswamy, Hancheng Ge, Lili Yuan
  • Patent number: 10216938
    Abstract: Dynamically developing and maintaining threat models, threat landscapes and threat matrices are described. Specifically described are techniques on how to relate: (1) attack surfaces, (2) attack histories, (3) threats and (4) historical responses, by loading these four types of data, as well as other data, into a data store. One example data store disclosed includes some variations of a graph data structure. Upon loading the data, the populated data store may be used to develop Threat Models that will represent a Threat Landscape and a Threat Matrix. These may then be queried for recommended reactive and proactive responses with respect to an installation, in order to improve security.
    Type: Grant
    Filed: December 3, 2015
    Date of Patent: February 26, 2019
    Assignee: T-Mobile USA, Inc.
    Inventors: Gregory Robert Reith, Brett Christopher Peppe
  • Patent number: 10216933
    Abstract: The disclosed computer-implemented method for determining whether malicious files are targeted may include (i) applying, to a malware detection structure, a plurality of sample data points, each sample data point corresponding to at least one of a malicious file known to be targeted and a malicious file known to be non-targeted, (ii) identifying one or more boundaries of the sample data points within the malware detection structure, (iii) determining, after identifying the sample boundaries, that a new data point falls outside of the boundaries, and (iv) classifying a malicious file associated with the new data point as non-targeted in response to determining that the new data point falls outside of the sample boundaries. Various other methods, systems, and computer-readable media are also disclosed.
    Type: Grant
    Filed: September 16, 2016
    Date of Patent: February 26, 2019
    Assignee: Symantec Corporation
    Inventor: Ryan Ross Curtin
  • Patent number: 10213605
    Abstract: Optimizing temporal pulse patterns for stimulation delivery to a subject includes: generating a first generation pulse pattern; delivering stimulation according to the first generation pattern to a subject; measuring efficacy, efficiency and side-effect parameters affected by the delivered stimulation; determining a fitness of the first generation pattern using the measured parameters; generating a second generation pattern using the first generation pattern according to the determined fitness of the first generation temporal pattern; and delivering stimulation according to the second generation pattern. Iterative further optimization may include crossing any particular generation temporal pulse pattern with at least one other temporal pulse pattern to generate offspring patterns for further use and optimization. Immigrant random patterns may be added, and offspring patterns may receive point mutations.
    Type: Grant
    Filed: March 9, 2017
    Date of Patent: February 26, 2019
    Assignee: DUKE UNIVERSITY
    Inventors: Warren M. Grill, Tianhe Zhang
  • Patent number: 10210331
    Abstract: Embodiments include identifying, at a logical path node, a first logical path and a second logical path; executing, by a processor implemented at least partially in hardware, a first set of instructions to follow the first logical path; storing, in a memory, a first set of information obtained from following the first logical path; evaluating, by a malware handler module implemented at least partially in hardware, the first set of information for malware; restoring, from the memory, environmental data for the first logical path node; executing, by the processor, a second set of instructions to follow the second logical path; storing, in a memory, a second set of information obtained from following the second logical path; and evaluating, by the malware handler module, the second set of information for malware.
    Type: Grant
    Filed: December 24, 2015
    Date of Patent: February 19, 2019
    Assignee: McAfee, LLC
    Inventors: Ravi Sahita, Xiaoning Li, Lixin Lu, Lu Deng, Alexander Shepsen, Xiang Xu, Liangjun Huang, Hua Liu, Kai Huang
  • Patent number: 10204183
    Abstract: A configuration engine traverses sequential levels of a decision tree in order to iteratively refine a configuration for a solar power system. At each level of the decision tree, the configuration engine determines the outcome of a design decision based on computing the result of a value function. The configuration engine explores configurations that optimize the value function result compared to other configurations, and may also discard less optimal configurations. When a current configuration is considered less optimal than a previous configuration generated at a previous level, the configuration engine discards the current configuration and re-traverses the decision tree starting with the previous configuration.
    Type: Grant
    Filed: September 15, 2015
    Date of Patent: February 12, 2019
    Assignee: Sunrun, Inc.
    Inventors: Billy Hinners, Gary Wayne
  • Patent number: 10198954
    Abstract: A method and apparatus are provided for positioning an unmanned robotic vehicle (URV). The URV captures a set of one or more of image and non-image information of an object while positioned at a first position, provides the set of image/non-image information to a server entity, in response to providing the set of image/non-image information, receives a three-dimensional (3D) model associated with the object, autonomously determines a second position based on the 3D model, and autonomously navigates to the second position. At the second position, the URV may capture further image and/or non-image information and, based on the further captured image/non-image information, autonomously determine, and navigate to, a third position. The steps of capturing further image and/or non-image information and, based on the captured image and/or non-image information, autonomously determining and navigating to further positions may be repeated indefinitely, or until otherwise instructed.
    Type: Grant
    Filed: December 30, 2015
    Date of Patent: February 5, 2019
    Assignee: MOTOROLA SOLUTIONS, INC.
    Inventors: Guy Holtzman, Baruh Hason, Salomon Serfaty
  • Patent number: 10198825
    Abstract: A method for analyzing three-dimensional image data of a target region of a subject, the method comprising identifying a region of interest within the target region containing imaging information predictive of a disease state of the target region, calculating at least two radiomic features associated with the region of interest, and classifying the region of interest based on the calculated radiomic features.
    Type: Grant
    Filed: October 28, 2014
    Date of Patent: February 5, 2019
    Assignees: LONDON HEALTH SCIENCES CENTRE RESEARCH INC.
    Inventors: Aaron Ward, David Palma, Sarah Mattonen, Suresh Senan
  • Patent number: 10188308
    Abstract: A method of identifying a spatial distribution of areas includes: a first step of determining a rough spatial distribution of at least one area in a sensory area of cerebral cortex in each of a left hemisphere and right hemisphere of the brain that is a target area of the identification; a second step of applying a sensory stimulus to the identification target area; a third step of obtaining brain activity information; and a fourth step of using the brain activity information to calculate one of a coefficient of cross-correlation, and coherence, between brain activity information of areas, assessing synchrony between the left and right hemispheres, and changing the spatial distribution determined in the first step.
    Type: Grant
    Filed: June 3, 2014
    Date of Patent: January 29, 2019
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Atsushi Komoto, Yoshikatsu Ichimura, Yasuhiro Kawashima, Jungo Miyazaki
  • Patent number: 10187405
    Abstract: A governance apparatus and a communication method for communicating within the governance apparatus. The governance apparatus includes a Government. The Government includes Councils such that a macro grid including an artificial intelligence and the Government is configured to respond to an alert pertaining to an event through use of the artificial intelligence and the Government. The governance apparatus also includes an enhanced Transmission Control Protocol/Internet Protocol (TCP/IP) communication stack of layers including a Governance Layer and an Intelligence Layer. The Intelligence Layer includes intelligence software configured to process data pertaining to the event, data pertaining to the alert, and data pertaining to the Government.
    Type: Grant
    Filed: June 13, 2016
    Date of Patent: January 22, 2019
    Assignee: International Business Machines Corporation
    Inventor: Ian E. Oakenfull
  • Patent number: 10187328
    Abstract: Historical telemetry data can be used to generate predictions for various classes of data at various aggregates of a system that implements an online service. An anomaly detection process can then be utilized to detect anomalies for a class of data at a selected aggregate. An example anomaly detection process includes receiving telemetry data originating from a plurality of client devices, selecting a class of data from the telemetry data, converting the class of data to a set of metrics, aggregating the set of metrics according to a component of interest to obtain values of aggregated metrics over time for the component of interest, determining a prediction error by comparing the values of the aggregated metrics to a prediction, detecting an anomaly based at least in part on the prediction error, and transmitting an alert message of the anomaly to a receiving entity.
    Type: Grant
    Filed: April 20, 2018
    Date of Patent: January 22, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Nagaraj Patil, Kiran Nallabothula, Christopher Barnes, Nagaraju Palla
  • Patent number: 10185751
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for query analysis. Queries are identified in query data, and an entity-descriptive portion and a suffix are determined in each query. Query counts are determined for a number of times that the respective queries occur in the query data. Based on the query counts, an entity-level count is estimated, which represents a number of query submissions that include the particular suffix and are considered to refer to a first entity. The entity is determined to be a particular type of entity. A type-level count is determined, which represents a number of query submissions that include the first suffix and are estimated to refer to entities of the particular type of entity. A score is assigned to the particular suffix based on the entity-level count and the type-level count.
    Type: Grant
    Filed: May 6, 2015
    Date of Patent: January 22, 2019
    Assignee: Google LLC
    Inventors: Benjamin J. Mann, Randolph G. Brown, John R. Provine, Vinicius J. Fortuna, Andrew W. Hogue
  • Patent number: 10176400
    Abstract: A method and apparatus for locating dot text in an image are described. A set of dots is extracted. A determination of whether a first region of interest (ROI) including the set of dots satisfies selection criteria is performed, where the first region of interest is oriented based on results from a principal component analysis of the set of dots. Responsive to determining that the first ROI does not satisfy the selection criteria, performing the following: removing an outlier dot from the first set of dots to obtain a second set of dots; when the second ROI satisfies the selection criteria, outputting the second ROI as a location of the dot text in the image, and when the second region of interest does not satisfy the selection criteria, repeating the operations until a resulting ROI is determined to satisfy the selection criteria.
    Type: Grant
    Filed: September 27, 2016
    Date of Patent: January 8, 2019
    Assignee: MATROX ELECTRONIC SYSTEMS LTD.
    Inventor: Dominique Rivard
  • Patent number: 10171415
    Abstract: Embodiments relate to systems, devices, and computer-implemented methods for characterizing domain names by determining a name server switching footprint for domain names using a data set corresponding to name server operations for the domain names. The domain names can be clustered into groups based on the name server switching footprints, and intended uses of domain names in a group can be extrapolated to other domain names in the group. Name server switching footprints can also be predicted for new domains names using a prediction model trained using the determined name server switching footprints for the domain names in the data set.
    Type: Grant
    Filed: October 9, 2014
    Date of Patent: January 1, 2019
    Assignee: VERISIGN, INC.
    Inventors: Md Mansurul Alam Bhuiyan, Yannis Labrou, Abedelaziz Mohaisen
  • Patent number: 10163061
    Abstract: A quality-directed adaptive analytic retraining is provided. Training example data with which to retrain a machine learning model that has been previously trained is received. The training example data is stored in a memory. The machine learning model is evaluated at least by running the machine learning model with the training example data. A normalized quality measure may be determined based on the evaluating. Whether to retrain the machine learning model is determined at least based on the normalized quality measure. Responsive to determining that the machine learning model is to be retrained, the machine learning model is retrained.
    Type: Grant
    Filed: June 18, 2015
    Date of Patent: December 25, 2018
    Assignee: International Business Machines Corporation
    Inventors: David P. Grove, Martin J. Hirzel, Wei Zhang
  • Patent number: 10154419
    Abstract: A method and a device are disclosed for controlling at least one data connection and/or one data transmission through the at least one data connection for a mobile radio device. Control information that was previously collected by one or more agents coupled to the mobile radio device is taken into account in the control of the data connection and/or the data transmission. The control information contains route- and/or user-specific information. The collecting of data is carried out by an agent, which is preferably designed to be self-learning.
    Type: Grant
    Filed: July 2, 2015
    Date of Patent: December 11, 2018
    Assignee: Bayerische Motoren Werke Aktiengesellschaft
    Inventors: Levent-Yusuf Ekiz, Christian Lottermann, Oliver Klemp
  • Patent number: 10154042
    Abstract: In one embodiment, a method includes receiving usage data regarding usage of a subscription-based media service account, generating a plurality of sharing scores based on the usage data, each of the plurality of sharing scores being indicative of a confidence that the usage of the subscription-based media service account is subject to a respective type of sharing, comparing each of the plurality of sharing scores to a respective threshold, and, in response to one of the plurality of sharing scores exceeding its respective threshold, presenting a challenge associated with the respective type of sharing.
    Type: Grant
    Filed: April 29, 2016
    Date of Patent: December 11, 2018
    Assignee: CISCO TECHNOLOGY, INC.
    Inventors: Steven Jason Epstein, Hillel Michael Solow, Ariel Imber, Roee Friedman, Harel Menachem Cain, Melvyn Adam Mildiner
  • Patent number: 10147020
    Abstract: A system and method for inferring an organizational structure of a record based on position role transitions from a parsed plurality of record profiles using machine learning techniques described herein. A piece-wise graph of transitions between positions across a normalized user employment landscape are computed to recover properties of user hierarchical structures across a plurality of position information by analysis of transition trajectories.
    Type: Grant
    Filed: September 5, 2017
    Date of Patent: December 4, 2018
    Assignee: Cognism Limited
    Inventors: James Hodson, Johannes Erett, Sinan James Isilay
  • Patent number: 10146944
    Abstract: Dynamically developing and maintaining threat models, threat landscapes and threat matrices are described. Specifically described are techniques on how to relate: (1) attack surfaces, (2) attack histories, (3) threats and (4) historical responses, by loading these four types of data, as well as other data, into a data store. One example data store disclosed includes some variations of a graph data structure. Upon loading the data, the populated data store may be used to develop Threat Models that will represent a Threat Landscape and a Threat Matrix. These may then be queried for recommended reactive and proactive responses with respect to an installation, in order to improve security.
    Type: Grant
    Filed: December 3, 2015
    Date of Patent: December 4, 2018
    Assignee: T-Mobile USA, Inc.
    Inventors: Gregory Robert Reith, Brett Christopher Peppe
  • Patent number: 10148525
    Abstract: Methods and systems are presented for monitoring data entry from one or more client devices, obtaining a predicted value for a particular field using one or more data handling rules, logging significant user input from at least one of the client devices superseding the predicted value, and automatically responding by generating a message that presents an option to deactivate one or more of the data handling rules.
    Type: Grant
    Filed: April 13, 2018
    Date of Patent: December 4, 2018
    Assignee: WINSHUTTLE, LLC
    Inventors: Vikram Chalana, Deep Dhillon
  • Patent number: 10133987
    Abstract: Systems and methods are provided for categorizing signals sensed from receivers into one of a plurality of categories using a machine learning component that obfuscates other characteristics of the signals beyond the categorization of the signal. A set of training signals is generated that includes signals representative of each of a plurality of categories of signals. A machine learning component is trained using the set of training signals so that the machine learning technique can categorize new signals into one of the plurality of categories. The machine learning component is transmitted to one or more receivers so that each receiver can categorize sensed signals into one of the plurality of categories using the machine learning component while obfuscating other characteristics of the sensed signals.
    Type: Grant
    Filed: July 14, 2014
    Date of Patent: November 20, 2018
    Assignee: FEDERATED WIRELESS, INC.
    Inventor: Joseph Mitola, III
  • Patent number: 10130323
    Abstract: The invention provides a method and apparatus for classifying a region of interest in imaging data, the method comprising: calculating a feature vector for at least one region of interest in the imaging data, said feature vector including features of a first modality; projecting the feature vector for the at least one region of interest in the imaging data using a decision function to generate a classification, wherein the decision function is based on classified feature vectors including features of a first modality and features of a second modality; estimating the confidence of the classification if the feature vector is enhanced with features of the second modality.
    Type: Grant
    Filed: July 13, 2015
    Date of Patent: November 20, 2018
    Assignee: Delineo Diagnostics, Inc
    Inventors: Scott Anderson Middlebrooks, Henricus Wilhelm van der Heijden
  • Patent number: 10127321
    Abstract: A system and method for proactively making knowledge offers. A processor is configured to gather information on interactions by a user with resources provided by an enterprise having a customer contact center. The processor anticipates need of the user based on the gathered information, and generates a query based on the anticipated need. Prior to the user expressly requesting knowledge relating to a particular topic, the processor proactively identifies and suggests the knowledge to the user based on the generated query. The processor receives feedback relating to the suggested knowledge and outputs based on the feedback, a relevance score for the suggested knowledge.
    Type: Grant
    Filed: February 23, 2015
    Date of Patent: November 13, 2018
    Inventors: Bharath Aravamudhan, Conor McGann, Anand Pai Krishnanand Nitin, Bohdan Klepar, Andriy V. Ryabchun, Gordon Bell, Francisco Gutierrez, Josef Eric Eisner, Nikolay I. Korolev, Herbert Willi Artur Ristock, Stanislav Lypachanskyy
  • Patent number: 10109211
    Abstract: An emotional wellness management system and methods of managing emotional wellness, to help people interactively and iteratively manage and improve their daily processes of emotional wellness are disclosed. The system comprises storage coupled to a controller able to capture, store, retrieve, process, update and display information related to a user's psychological condition comprising user affects, user influencers, and actions. A user interface device is coupled to the controller and configured to have executable buttons to capture user inputs of states of user affects and user influencers, and to provide a plurality of action links for accessing resources in the user interface device, also providing visual feedback. The system is configured to interface with external devices and may be configured for use in commonly available computing devices. This system can be used as a standalone system without network, or a networked system to serve multiple users simultaneously over multiple communication channels.
    Type: Grant
    Filed: February 3, 2016
    Date of Patent: October 23, 2018
    Inventor: Satoru Isaka
  • Patent number: 10101490
    Abstract: Methods and systems for obtaining an electrical impedivity and/or resistivity image of a subterranean formation are provided. The electrical impedivity and/or resistivity image can be obtained by determining first formation impedivity data and second formation impedivity data. The first formation impedivity data can be based on a component of the measured impedance data orthogonal a downhole fluid impedance. The second formation impedivity data can be based on an amplitude of the measured impedance data. A combined formation impedivity data can be obtained by combining a portion of the first formation impedivity data based on a first formation impedivity determination process with a portion of the second formation impedivity data based on a second formation impedivity determination process. The electrical impedivity and/or resistivity image of the subterranean formation can then be obtained by using the combined formation impedivity data.
    Type: Grant
    Filed: November 8, 2016
    Date of Patent: October 16, 2018
    Assignee: SCHLUMBERGER TECHNOLOGY CORPORATION
    Inventors: Philip S. Cheung, Tianhua Zhang
  • Patent number: 10098569
    Abstract: A method of operating a computational device to process patient sounds, the method comprises the steps of: extracting features from segments of said patient sounds; and classifying the segments as cough or non-cough sounds based upon the extracted features and predetermined criteria; and presenting a diagnosis of a disease related state on a display under control of the computational device based on segments of the patient sounds classified as cough sounds.
    Type: Grant
    Filed: March 28, 2013
    Date of Patent: October 16, 2018
    Assignee: The University of Queensland
    Inventors: Udantha R. Abeyratne, Vinayak Swarnkar, Yusuf A. Amrulloh
  • Patent number: 10099369
    Abstract: A method of generating a configuration of a robotic hand for automatically grasping a first object, the robotic hand comprising a plurality of parts, is provided. The method comprises: receiving data representing the first object; receiving a plurality of first models generated based upon an example grasp of a second object, the example grasp being based upon a configuration of the robotic hand for grasping the second object in which a plurality of parts of said hand contact said second object, each of said plurality of first models representing a relationship between a respective part of the robotic hand and a property of the second object associated with said part of the robotic hand; and processing the data representing the first object based upon the plurality of first models to determine said configuration of the robotic hand for automatically grasping the first object.
    Type: Grant
    Filed: May 21, 2014
    Date of Patent: October 16, 2018
    Assignee: The University of Birmingham
    Inventor: Marek Kopicki
  • Patent number: 10089580
    Abstract: Functionality is described herein for generating a model on the basis of user-behavioral data and knowledge data. In one case, the user-behavioral data identifies queries submitted by users, together with selections made by the users in response to the queries. The knowledge data represents relationships among linguistic items, as expressed by one or more structured knowledge resources. The functionality leverages the knowledge data to supply information regarding semantic relationships which may not be adequately captured by the user-behavioral data, to thereby produce a more robust and accurate model (compared to a model produced on the basis of only user-behavioral data). Functionality is also described herein for applying the model, once trained. In one case, the model may correspond to a deep learning model.
    Type: Grant
    Filed: August 11, 2014
    Date of Patent: October 2, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Ying Shan, Jianchang Mao
  • Patent number: 10074050
    Abstract: A neural network is implemented as a memristive neuromorphic circuit that includes a neuron circuit and a memristive device connected to the neuron circuit. A conductance balanced voltage pair is provided for the memristive device, where the conductance balanced voltage pair includes a set voltage for increasing the conductance of the memristive device and a reset voltage for decreasing the conductance of the memristive device. Either the set voltage and reset voltage, when applied to the memristive device, effects a substantially same magnitude conductance change in the memristive device over a predetermined range of conductance of the memristive device. The provided voltage pair is stored as a conductance balanced map. A training voltage based on the conductance balanced map is applied to the memristive device to train the neural network.
    Type: Grant
    Filed: July 13, 2015
    Date of Patent: September 11, 2018
    Assignees: DENSO CORPORATION, The Regents of the University of California
    Inventors: Irina Kataeva, Dmitri B. Strukov, Farnood Merrikh-Bayat
  • Patent number: 10075458
    Abstract: From a record of a packet in a Domain Name System (DNS) communication between a DNS client and a DNS server, an input feature is constructed. Using the packet, a metadata item supporting the input feature is computed. Using a processor and a memory to execute a trained cognitive classification model, and by supplying the input feature and the supporting metadata item as inputs to the cognitive classification model, a transmission of the packet is classified as malicious use of DNS tunneling between the DNS client and the DNS server. From the cognitive classification model, a classification of the packet as malicious, and a confidence value in the malicious classification are output. By generating a notification, the DNS client is caused to cease the malicious use of the DNS tunneling.
    Type: Grant
    Filed: April 29, 2016
    Date of Patent: September 11, 2018
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Aaron K. Baughman, Mauro Marzorati, Gregory A. Porpora
  • Patent number: 10063924
    Abstract: A system and method for operating a user receiving device includes a first user device that receives first user settings and stores the first user settings therein. The first user device communicates first user settings to a second user receiving device. The second user receiving device operates with the first user settings.
    Type: Grant
    Filed: March 12, 2014
    Date of Patent: August 28, 2018
    Assignee: The DIRECTV Group, Inc.
    Inventors: Kuriacose Joseph, Scott D. Casavant, Sean S. Lee, Phillip T. Wang, Christopher Yang, Woei-Shyang Yee, Wesley W. Huie, Gerard V. Talatinian
  • Patent number: 10043106
    Abstract: A corresponding point searching method searches corresponding points in plural images, acquired by in-vehicle cameras, for each pixel in a reference image by using a predetermined first method, for example, the Viterbi algorithm. The method searches corresponding points in the plural images for each pixel in the reference image by using a predetermined second method, for example, an optical flow method. The method detects whether or not a search accuracy of the corresponding points in each region divided in the reference image obtained by the predetermined first method is not less than a reference value. When not less than the reference value, the method selects the corresponding points obtained by the predetermined first method. When less than the reference value, the searching method selects the corresponding points obtained by the predetermined second method. The searching method provides the corresponding points between the plural images with a high accuracy.
    Type: Grant
    Filed: June 2, 2016
    Date of Patent: August 7, 2018
    Assignees: DENSO CORPORATION, TOYOTA SCHOOL FOUNDATION
    Inventors: Kazuhisa Ishimaru, Noriaki Shirai, Hossein Tehrani Niknejad, Seiichi Mita, Qiwei Xie, Qian Long
  • Patent number: 10042837
    Abstract: A method, system and computer-usable medium are disclosed for identifying unchecked criteria within a form. Natural Language Processing (NLP) is applied to unstructured data within a target form to identify elements of a form structure. Analytic analysis is then applied to the resulting form structure elements to identify a hierarchical structure and associated element placement. Implicit selections within the form are then identified by applying rules based upon other selections and their orientation to anchor terms to determine the completeness of the form, based upon aggregation of form elements. The form structure elements and the hierarchy metadata are then processed logically reassemble the form's hierarchy in flattened forms for multi-layer, sub-element anaphora resolution.
    Type: Grant
    Filed: December 2, 2014
    Date of Patent: August 7, 2018
    Assignee: International Business Machines Corporation
    Inventors: Scott R. Carrier, Lee M. Surprenant, Amy E. Veatch
  • Patent number: 10037437
    Abstract: In an example, for each value of a plurality of values of a first attribute of members of a social networking service who have submitted confidential data, an allowed range for normalized confidential data values submitted by members having the value for the first attribute, across all values of a second attribute, is calculated, and then shifted based on an inferred median confidential data value relative to a median of confidential data values. Then, anomalous confidential data values can be detected using this information.
    Type: Grant
    Filed: June 9, 2017
    Date of Patent: July 31, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Krishnaram Kenthapadi, Stuart MacDonald Ambler
  • Patent number: 10037378
    Abstract: Techniques for classifying and labeling data are disclosed. In one embodiment, the techniques may be realized as a system for classifying and labeling data comprising one or more processors. The one or more processors may be configured to distribute training data across a plurality of hosts. Each of the hosts may be assigned a random subset of the training data, and configured to cluster its own subset independently. The one or more processors may be further configured to label each cluster of the training data. The one or more processors may be further configured to receive new data, associate the new data with a plurality of the clusters of the training data, and assign the new data a label. The label may be chosen from labels of the plurality of the clusters. And the label may have a maximum associative factor of the new data.
    Type: Grant
    Filed: December 11, 2015
    Date of Patent: July 31, 2018
    Assignee: SYMANTEC CORPORATION
    Inventors: Anudeep Kumar, Yashodhan Pawar, Himanshu Dubey, Ajitesh Roychowdhury
  • Patent number: 10032089
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using an image processing neural network system that includes a spatial transformer module. One of the methods includes receiving an input feature map derived from the one or more input images, and applying a spatial transformation to the input feature map to generate a transformed feature map, comprising: processing the input feature map to generate spatial transformation parameters for the spatial transformation, and sampling from the input feature map in accordance with the spatial transformation parameters to generate the transformed feature map.
    Type: Grant
    Filed: June 6, 2016
    Date of Patent: July 24, 2018
    Assignee: DeepMind Technologies Limited
    Inventors: Maxwell Elliot Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu