Knowledge Processing System Patents (Class 706/45)
  • Patent number: 10705513
    Abstract: The disclosure herein relates to a quality control method and system in aeronautical manufacturing. The system comprises a tablet connected to a concession management server, the server being itself linked to an aircraft configuration database, a three-dimensional digital model of the aircraft and a fault database. The element to be inspected is identified using the digital model and the fault is characterized by browsing a predetermined decision tree associated with the element.
    Type: Grant
    Filed: June 17, 2015
    Date of Patent: July 7, 2020
    Assignee: Airbus Operations (S.A.S.)
    Inventor: Olivier Harasse
  • Patent number: 10708363
    Abstract: Systems and methods are provided for recognition of an application in communication traffic flow in a network using an artificial intelligence (AI) based hierarchical service awareness engine. A decode equivalent class (DEC) can be used to provide information on the application. A DEC corresponds to a class of traffic that is mapped to an artificial intelligence (AI) model associated with parameters related to the class of traffic. DEC information can be fed to an AI model set and an inference model can be derived from a AI model of the AI model set corresponding to a DEC. The inference model can be provided to a gateway of the network to recognize a specific application of a service in communication flows. In various embodiments, in training the AI models, the gateway can provide DEC information for the AI model set from classifying flows of data traffic received from the network into DECs.
    Type: Grant
    Filed: August 10, 2018
    Date of Patent: July 7, 2020
    Assignee: Futurewei Technologies, Inc.
    Inventors: Hang Shi, Yinghua Ye
  • Patent number: 10699217
    Abstract: The present disclosure relates to system(s) and method(s) for reflective learning in a cognitive decision-making process. In one embodiment, the method comprises receiving input data and computing a first deviation in user behavior based on input data. The method further comprises classifying the business opportunities and the strategies as one of an accurate business opportunities or an inaccurate business opportunities and an accurate strategies or an inaccurate strategies based on comparison of the first deviation with a predefined threshold and identifying one or more algorithm and metadata associated with the inaccurate business opportunities and the inaccurate strategies. The method furthermore comprises executing one of a retraining of the one or more algorithm, a modifying the metadata associated with the inaccurate business opportunities and the inaccurate strategies or generating a new algorithm thereby enabling reflective learning in a cognitive decision-making process.
    Type: Grant
    Filed: October 19, 2017
    Date of Patent: June 30, 2020
    Assignee: DIWO, LLC
    Inventors: Satyendra Pal Rana, Chandra Puttanna Keerthy, Krishna Prakash Kallakuri
  • Patent number: 10699321
    Abstract: A digital medium environment is described to facilitate recommendations based on vectors generated using feature word embeddings. A recommendation system receives data that describes at least one attribute for a user profile, at least one item, and an interaction between the user profile and the at least one item. The recommendation system associates each user profile attribute, each item, and each interaction between a user profile and an item as a word, using natural language processing, and combines the words into sentences. The sentences are input to a word embedding model to determine feature vector representations describing relationships between the user profile attributes, items, and explicit and implicit interactions. From the feature vector representations, the recommendation system ascertains a similarity between different features.
    Type: Grant
    Filed: October 17, 2017
    Date of Patent: June 30, 2020
    Assignee: Adobe Inc.
    Inventors: Balaji Krishnamurthy, Nikaash Puri
  • Patent number: 10692127
    Abstract: Systems and methods are provided for determining or predicting user demographic information using user behaviors through a Bayesian inference. A computing system may determine demographic information (such as age or gender) of a user based on a Bayesian update and a purchase or other user action by the user. In some embodiments, the computing system may determine the household composition of a user account based on multiple purchases by the user account. The computing system may generate recommendations for the user or the user account based on the demographic information of the user or the household composition of the user account.
    Type: Grant
    Filed: October 12, 2016
    Date of Patent: June 23, 2020
    Assignee: Amazon Technologies, Inc.
    Inventors: Pooja Ashok Kumar, Roopesh Ranjan, Neela Kamlakar Sawant
  • Patent number: 10685310
    Abstract: A device receives historical risk management data associated with products and processes the historical risk management data to generate processed historical risk management data. The device trains a machine learning model with the processed historical risk management data to generate a trained machine learning model and receives, from a user device, product data associated with a potential product. The device applies weights to different portions of the product data, based on risks associated with the different portions of the product data, to generate weighted product data and processes the weighted product data, with the trained machine learning model, to generate one or more of complexity levels, risk data, or recommendations associated with the potential product. The device performs one or more actions based on the one or more of the complexity levels, the risk data, or the recommendations associated with the potential product.
    Type: Grant
    Filed: May 2, 2019
    Date of Patent: June 16, 2020
    Assignee: Capital One Services, LLC
    Inventors: Daryl McCuiston, Gregory Powell, Zaheer Ladak, Jennifer Little
  • Patent number: 10683088
    Abstract: An unmanned aerial vehicle for providing ameliorative action. The unmanned aerial vehicle includes a processor-based monitoring device to monitor a plurality of individuals to determine crowd data associated with the plurality of individuals, a crowd estimator configured to receive the crowd data to estimate a crowd pressure estimation value indicative of a likelihood of a crowd event, the crowd pressure estimation value being based on the crowd data, and an ameliorative action generator to automatically perform a function when the crowd pressure estimation value exceeds a predetermined threshold value, wherein the function includes activating one or more feedback outputs configured to provide an ameliorative action.
    Type: Grant
    Filed: May 27, 2016
    Date of Patent: June 16, 2020
    Assignee: International Business Machines Corporation
    Inventors: Thomas D. Erickson, Clifford A. Pickover, Maja Vukovic
  • Patent number: 10684821
    Abstract: A context aware service provision method and apparatus for recognizing the user context and executing an action corresponding to the user context according to a rule defined by the user and feeding back the execution result to the user interactively are provided. The method for providing a context-aware service includes receiving a user input, the user input being at least one of a text input and a speech input, identifying a rule including a condition and an action corresponding to the condition based on the received user input, activating the rule to detect a context which corresponds to the condition of the rule, and executing, when the context is detected, the action corresponding to the condition.
    Type: Grant
    Filed: August 3, 2018
    Date of Patent: June 16, 2020
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Jooyoon Bae, Minjeong Ko, Sungsoo Kim, Jinsung Kim, Hwakyung Kim, Jinha Jun
  • Patent number: 10681161
    Abstract: A system and method for trend detection in a messaging platform. A trend detection model is selected and a time series having a plurality of instances of social data is received, wherein the instances of social data share a countable parameter. A count is made of occurrences of countable parameters in each instance of social data assigned to that bin and a trend detected based at least in part on the trend detection model and on the count for each bin.
    Type: Grant
    Filed: April 19, 2019
    Date of Patent: June 9, 2020
    Assignee: Twitter, Inc.
    Inventors: Scott Hendrickson, Jeffrey Aaron Kolb, Joshua Montague, Brian Lehman
  • Patent number: 10679009
    Abstract: A chat bot is a system designed to engage in a conversation with users on various tasks, like resolving a complaint, especially over internet. The present disclosure computes a set of hidden intent of a user from by using a set of words and a domain ontology associated with the set of words. Initially, the input sentence is analyzed to identify a category associated with it. Further, the set of words are extracted from the categorized input sentence using sentence parsers. Further, the set of hidden intent of the user is utilized for computing a set of epistemic rules. Further, the set of epistemic rules are utilized to compute a set of hop states and a next sentence is generated based on the set of hop states.
    Type: Grant
    Filed: April 20, 2018
    Date of Patent: June 9, 2020
    Assignee: Tata Consultancy Services Limited
    Inventors: Chandrasekhar Anantaram, Amit Sangroya
  • Patent number: 10678625
    Abstract: Systems and methods for automatically generating failure signatures in a computer system for performing computer system fault diagnosis are provided. The method includes receiving log data, converting each log in the log data into a collection of log pattern sequences including one or more log pattern sequences corresponding to one or more respective failure categories associated with the computer system, generating a collection of seed patterns by computing a global set of patterns from the collection of log pattern sequences, and extracting the collection of seed patterns from the global set of patterns, generating a log pattern grammar representation for each of the one or more log pattern sequences, generating a failure signature for each of the one or more failure categories based on the log pattern grammar representation and the collection of seed patterns, and employing the failure signatures to perform computer system fault diagnosis on new log data.
    Type: Grant
    Filed: July 12, 2018
    Date of Patent: June 9, 2020
    Assignee: NEC Corporation
    Inventors: Pranay Anchuri, Jianwu Xu, Hui Zhang
  • Patent number: 10672077
    Abstract: Pursuant to some embodiments, systems, methods, apparatus and computer program code for proactive underwriting are provided. Pursuant to some embodiments, a computer implemented processing method is provided which includes identifying, by an insurance processing platform, an action by an entity that matches at least a first trigger rule. A proactive underwriting template is selected based on the at least first trigger rule, where the proactive underwriting template defines a number of data items required to complete the proactive underwriting template. The insurance processing platform is operated to automatically collect data associated with the plurality of required data items, and to perform a proactive underwriting analysis using the collected data. An underwriting determination is then rendered based on the proactive underwriting analysis.
    Type: Grant
    Filed: June 14, 2013
    Date of Patent: June 2, 2020
    Assignee: Hartford Fire Insurance Company
    Inventors: Ryan Owen Denning, Mushter Munib Moin, Deborah L. Perschy
  • Patent number: 10672153
    Abstract: Image reconstruction can include using a statistical or machine learning, MAP estimator, or other reconstruction technique to produce a reconstructed image from acquired imaging data. A Conditional Generative Adversarial Network (CGAN) technique can be used to train a Generator, using a Discriminator, to generate posterior distribution sampled images that can be displayed or further processed such as to help provide uncertainty information about a mean reconstruction image. Such uncertainty information can be useful to help understand or even visually modify the mean reconstruction image. Similar techniques can be used in a segmentation use-case, instead of a reconstruction use case. The uncertainty information can also be useful for other post-processing techniques.
    Type: Grant
    Filed: November 13, 2018
    Date of Patent: June 2, 2020
    Assignee: Elekta AB (publ)
    Inventors: Jonas Anders Adler, Ozan Öktem
  • Patent number: 10666525
    Abstract: A performance management engine may be implemented to continuously detecting entity performance issues. The performance management engine may calculate one or more key performance indicators (KPIs) that measure performance of an entity. The performance management engine may further receive one or more additional sources of data regarding the entity via a data management platform that interfaces with multiple data sources. The performance management engine may aggregate the KPIs and the one or more additional sources of data into datasets according to one or more grouping parameters. The data in one or more datasets may be analyzed by the performance management engine to generate one or more comprehensive performance indicators. The comprehensive performance indicators are then provided for display on a user device. Each KPI or comprehensive performance indicator measures performance of a device, a component, a node, or a service of the entity.
    Type: Grant
    Filed: January 11, 2019
    Date of Patent: May 26, 2020
    Assignee: Tupl Inc.
    Inventors: Pablo Tapia, Rafael Guerrero
  • Patent number: 10666735
    Abstract: The invention concerns computer systems that are specially adapted to propagate content over a dynamic network, substantially in real time, by virtue of the locational proximity of interconnected network-joined Client Computers, at least one of which communicates with an interconnected Client Computer via infrared signal, laser pulse, or radio frequency. Preferably, the content will also be weighted (for example, proximity-weighted, rank-weighted, topic-weighted, query-weighted, time-weighted, location-weighted, locality-weighted, vote-weighted, segment-weighted, geophysically-weighted, etc.). The invention particularly concerns such computer systems that employ more than one such weighting. The invention particularly concerns such computer systems that operate using, or through, mobile devices, particularly for distributed computing applications, including social media applications and communications applications conducted over Restricted Computer Networks.
    Type: Grant
    Filed: April 16, 2019
    Date of Patent: May 26, 2020
    Inventor: Michael Harrison Tretter Auerbach
  • Patent number: 10656909
    Abstract: A method and system are provided. The method includes receiving, by a microphone and camera, user utterances indicative of user commands and associated user gestures for the user utterances. The method further includes parsing, by a hardware-based recognizer, sample utterances and the user utterances into verb parts and noun parts. The method also includes recognizing, by a hardware-based recognizer, the user utterances and the associated user gestures based on the sample utterances and descriptions of associated supporting gestures for the sample utterances. The recognizing step includes comparing the verb parts and the noun parts from the user utterances individually and as pairs to the verb parts and the noun parts of the sample utterances. The method additionally includes selectively performing a given one of the user commands responsive to a recognition result.
    Type: Grant
    Filed: July 24, 2018
    Date of Patent: May 19, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Jonathan Lenchner, Vinay Venkataraman
  • Patent number: 10656860
    Abstract: A method and system for improving tape drive memory storage is provided. The method includes receiving, by a storage tape drive hardware device, a data stream. Duplicate data chunks of the data stream are identified and deleted such that a group of data chunks remain in a non-volatile memory device (NVS2) of the storage tape drive. The group of data chunks is written to a data storage tape cartridge. Pointers are generated and stored within the data storage tape cartridge. The pointers are associated with a location within an NVS1 for storing de-duplication hashes identifying each data chunk of the group of data chunks stored within data storage tape cartridge. The de-duplication hashes are written from the NVS1 to a manager non-volatile memory device (MNVS) of a storage tape drive hardware library system. The MNVS is updated.
    Type: Grant
    Filed: February 8, 2019
    Date of Patent: May 19, 2020
    Assignee: International Business Machines Corporation
    Inventors: Ole Asmussen, Robert Beiderbeck, Erik Rueger, Markus Schäfer
  • Patent number: 10659521
    Abstract: The present invention proposes a method for providing a broadcast content in an apparatus, the method comprising: requesting a filter code to an application running on the apparatus by using a first Application Programming Interface (API); receiving a JavaScript Object Notation (JSON) object from the application in response to the first API; storing the filter code; receiving an Extended File Delivery Table (EFDT) having a first filter code associated with a first file; and selectively downloading the first file by comparing the stored filter code with the first filter code in the EFDT.
    Type: Grant
    Filed: November 22, 2017
    Date of Patent: May 19, 2020
    Assignee: LG ELECTRONICS INC.
    Inventors: Somi Park, Minsung Kwak
  • Patent number: 10656910
    Abstract: A method and system are provided. The method includes receiving, by a microphone and camera, user utterances indicative of user commands and associated user gestures for the user utterances. The method further includes parsing, by a hardware-based recognizer, sample utterances and the user utterances into verb parts and noun parts. The method also includes recognizing, by a hardware-based recognizer, the user utterances and the associated user gestures based on the sample utterances and descriptions of associated supporting gestures for the sample utterances. The recognizing step includes comparing the verb parts and the noun parts from the user utterances individually and as pairs to the verb parts and the noun parts of the sample utterances. The method additionally includes selectively performing a given one of the user commands responsive to a recognition result.
    Type: Grant
    Filed: July 24, 2018
    Date of Patent: May 19, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Jonathan Lenchner, Vinay Venkataraman
  • Patent number: 10656923
    Abstract: A system for determining regulatory compliance of smart contracts is disclosed. The system may receive positive smart contracts that comply with regulations, convert positive section(s) of the positive smart contracts into a first set of intermediate representation of code, and train a neural network to classify smart contract sections. The system may then receive a first smart contract including first sections, convert the first sections into a second set of intermediate representation of code, classify the second set of intermediate representation of code as a first classification corresponding to the first set of intermediate representation of code or as a second classification not corresponding to the first set of intermediate representation of code, and generate for display a negative or positive indication based on the classification.
    Type: Grant
    Filed: July 31, 2019
    Date of Patent: May 19, 2020
    Assignee: CAPITAL ONE SERVICES, LLC
    Inventors: Reza Farivar, Austin Walters, Anh Truong, Vincent Pham, Fardin Abdi Taghi Abad, Mark Watson, Jeremy Edward Goodsitt, Kenneth Taylor
  • Patent number: 10657727
    Abstract: An augmented reality (AR) output device or virtual reality (VR) output device is worn by a user and includes one or more sensors positioned to detect actions performed by a user of the immersive output device. A processor provides a data signal configured for the AR or VR output device, causing the immersive output device to provide AR output or VR output via a stereographic display device. The data signal encodes audio-video data. The processor controls a pace of scripted events defined by a narrative in the one of the AR output or the VR output, based on output from the one or more sensors indicating actions performed by a user of the AR or VR output device. The audio-video data may be packaged in a non-transitory computer-readable medium with additional content that is coordinated with the defined narrative and is configured for providing an alternative output, such as 2D video output or the stereoscopic 3D output.
    Type: Grant
    Filed: February 15, 2019
    Date of Patent: May 19, 2020
    Assignee: WARNER BROS. ENTERTAINMENT INC.
    Inventors: Christopher DeFaria, Piotr Mintus, Gary Lake-Schaal, Lewis Ostrover
  • Patent number: 10657117
    Abstract: In an approach for dynamically ranking SMEs, based on the SMEs' activities during a critical situation, a processor identifies SMEs to work in a collaboration channel. A processor monitors an activity of the SME within the collaboration channel. A processor receives information from the monitored activity. A processor analyzes the information from the monitored activity. A processor updates a database that contains details about a plurality of SMEs.
    Type: Grant
    Filed: April 6, 2016
    Date of Patent: May 19, 2020
    Assignee: International Business Machines Corporation
    Inventors: Pritpal S. Arora, Bijo S. Kappen, Gopal S. Pingali
  • Patent number: 10657162
    Abstract: Method and system for visualizing documents. N-dimensional compact representations are obtained for a set of documents. A plurality of documents are then retrieved with the corresponding N-dimensional compact representations. Each of the retrieved documents is associated with at least one concept. Each of the retrieved documents is projected to a point on a K-dimensional map based on its N-dimensional compact representation so that projected document points in the K-dimensional map maintain the relative distances among the retrieved documents in the N-dimensional space. Regions in the K-dimensional map associated with a concept are identified. A label is generated for each concept in each identified region. Then generated labels are rendered on the K-dimensional map in a corresponding region identified.
    Type: Grant
    Filed: June 8, 2016
    Date of Patent: May 19, 2020
    Assignee: TEXTWISE COMPANY, LLC
    Inventors: Robert Solmer, Wen Ruan
  • Patent number: 10649882
    Abstract: A computer-implemented method of training, using a computer log file, an application error prediction engine to identify one or more application errors includes parsing the computer log file into a plurality of data sets. Each data set is associated with a unique computing session having a session identifier and ending in an application or. The method also includes extracting, from each data set, values for a specified set of parameters in each data set. The method also includes encoding the extracted values for each data set into a corresponding data structure. The method also includes generating, for each data structure, a corresponding vector, the corresponding vectors collectively forming a matrix. The method also includes calculating, based on the matrix, a set of clusters, each cluster corresponding to a known error type, the set of clusters used to create a model used to identify new error types.
    Type: Grant
    Filed: August 29, 2017
    Date of Patent: May 12, 2020
    Assignee: FMR LLC
    Inventors: Pu Li, Maohua Sun, Hua Hao, Junmei Liu, Yuanjun Liu, Yucai Yang
  • Patent number: 10642580
    Abstract: Techniques for simplifying and reusing visual programming graphs are described herein. In some examples, visual programming graphs may be simplified by decoupling execution signals from data resolution. Execution of a particular node may be triggered through a representation of a signal sent from a signal output slot of another node to a signal input slot on the node being triggered. Additionally, evaluation of data values may be represented by a connection between a data output slot on the node providing the data value to a data input slot on the node receiving the data value. Another technique for simplifying visual programming graphs may include combining and/or collapsing of multiple selected visual programming nodes into a single reusable visual programming node. In some examples, reusable combined visual programming nodes may be exposed using unlocked versions and/or locked versions.
    Type: Grant
    Filed: September 20, 2016
    Date of Patent: May 5, 2020
    Assignee: Amazon Technologies, Inc.
    Inventors: Luis René Sempé Sosa, Justin Boswell, Michael Eric Deem
  • Patent number: 10644979
    Abstract: A method for evaluating and predicting telecommunications network traffic includes receiving site data for multiple geographic areas via a processor. The processor also receives weather data, event data, and population demographic data for the geographic areas. The processor also generates predicted occupancy data for each of the geographic areas and for multiple time intervals. The processor also determines a predicted telecommunications network metric for each of the geographic areas and for each of the time intervals, based on the predicted occupancy data.
    Type: Grant
    Filed: June 6, 2019
    Date of Patent: May 5, 2020
    Assignee: The Joan and Irwin Jacobs Technion-Cornell Institute
    Inventor: Payman Samadi
  • Patent number: 10642677
    Abstract: Techniques for log-based diagnosis for declarative-deployed applications can comprise: based on a labeled deployment declaration, classifying, by a device operatively coupled to a processor, a runtime log associated with an application, resulting in a classified runtime log. Techniques can also comprise: based on the classified runtime log, training, by the device, an aggregation model to represent a defined state of the application.
    Type: Grant
    Filed: November 2, 2017
    Date of Patent: May 5, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Peng Fei Chen, Fan Jing Meng, Jing Min Xu, Lin Yang
  • Patent number: 10636039
    Abstract: Disclosed herein is a method and system for generating an ontology based on plurality of tickets in an enterprise system 100. The method includes processing, by the enterprise system 100, input data associated with the plurality of tickets to obtain a structured data 228 associated with each of the plurality of tickets. Also, the method comprises performing multi-level clustering on the structured data 228 to obtain a plurality of clusters and corresponding error indicators, based on one or more parameters associated with the plurality of tickets. Further, the method comprises mapping each of the plurality of dusters with each of the error indicators, to obtain a mapped data at each cluster of the plurality of clusters and generating the ontology using the mapped data at each duster of the plurality of clusters, corresponding to the plurality of tickets.
    Type: Grant
    Filed: March 31, 2017
    Date of Patent: April 28, 2020
    Assignee: Wipro Limited
    Inventor: Selvakuberan Karuppasamy
  • Patent number: 10635721
    Abstract: Embodiments of the present disclosure provide a method and apparatus for document recommendation by obtaining a plurality of first data for a source recommendation task from activities related to a source user using a plurality of first documents; obtaining a plurality of second data for a target recommendation task from activities related to a target user using a plurality of second documents; performing the target recommendation task based on the plurality of first data, the plurality of second data, and knowledge transferred from the source recommendation task to obtain a target recommendation model; and conducting document recommendation to the target user using the target recommendation model.
    Type: Grant
    Filed: June 20, 2014
    Date of Patent: April 28, 2020
    Assignee: EMC IP Holding Company LLC
    Inventors: Tao Chen, Baoyao Zhou, Yu Cao, Xiaoyan Guo, Qianjie Zhong
  • Patent number: 10635982
    Abstract: According to one embodiment, a method for solving a plurality of spatiotemporal planning problems. The method may include creating a domain model. The method may also include assigning a solution bound associated with the created domain model to infinity. The method may further include calculating a solution to the created domain model based on the assigned solution bound using at least one of a best-first search algorithm. The method may also include updating the assigned solution bound based on the calculated solution. The method may further include presenting the calculated solution to a user based on the updated solution bound not equaling infinity.
    Type: Grant
    Filed: September 10, 2015
    Date of Patent: April 28, 2020
    Assignee: International Business Machines Corporation
    Inventors: Jonathan Bnayahu, Michael Katz, Dany Moshkovich
  • Patent number: 10631257
    Abstract: A first request to establish a communication session with a contact center is received from a user communication device. For example, a request to establish a voice communication session is received at the contact center. A machine learning model uses prior communication sessions with the contact center to identify a first set of one or more sensors that are external to the user communication device. External sensor information is received (e.g., during the request to establish the communication session) by the contact center. The external sensor information is from the first set of one or more sensors that are external to the user communication device. The communication session in the contact center is routed based on the received external sensor information. For example, instead of the communication session being routed to an Interactive Voice Response (IVR) system, the communication session is routed to a high priority contact center queue.
    Type: Grant
    Filed: November 27, 2018
    Date of Patent: April 21, 2020
    Assignee: Avaya Inc.
    Inventors: Eyal Serero, Gal Netanel, Ronen Bar-Yoav, Roman Nekrashevich, Tamar Barzuza
  • Patent number: 10621284
    Abstract: Training data including a first and second group of questions each associated with an answer is read into memory by a computer. A class of answers including the answer to a question for each question is determined, where each class of answers has a class label that is associated with each of the questions, and each of the questions are classified into a respective class of answers, accordingly. First and second training data is generated including the first and second groups of questions and corresponding classes of answers for use in first and second classifiers, respectively. Each question of the first and second group of questions is classified by the second and first classifiers, respectively, where the classifying generates corresponding classification results. The first or second training data is updated based on the classification results to generate corresponding updated first or second training data, respectively.
    Type: Grant
    Filed: June 28, 2019
    Date of Patent: April 14, 2020
    Assignee: International Business Machines Corporation
    Inventors: Hiroaki Komine, Kaori Maruyama, Takumi Yanagawa
  • Patent number: 10621596
    Abstract: There is provided a system and method for a video optimizer for determining relationships between events. The method comprises receiving a total number of events for a plurality of contents over a period of time, receiving a first number of events of a first content of the plurality of contents over the period of time, receiving a second number of events of the plurality of contents over the period of time, and determining a relationship between the first content and the second content based on the first number of events, the second number of events, and the total number of events. A second relationship may be determined by utilizing a first time of event by a user of the first content, a second time of event by the user of the second content, and a weighed correspondence.
    Type: Grant
    Filed: March 15, 2013
    Date of Patent: April 14, 2020
    Assignee: Disney Enterprises, Inc.
    Inventors: Peter Fernando, Michael Clements
  • Patent number: 10623343
    Abstract: Message processing includes activating an out-of-office function for a messaging account, wherein the out-of-office function has a scheduled end time. A determination is made, using a processor, that a current time is after the scheduled end time and that a deactivation condition for the out-of-office function has not occurred. Responsive to the determination, an out-of-office action is performed using the processor.
    Type: Grant
    Filed: June 25, 2018
    Date of Patent: April 14, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Luca Alfarano, Srinivas Allampally, Gaurav Bhagat, Conor T. Boland
  • Patent number: 10623344
    Abstract: Message processing includes activating an out-of-office function for a messaging account, wherein the out-of-office function has a scheduled end time. A determination is made, using a processor, that a current time is after the scheduled end time and that a deactivation condition for the out-of-office function has not occurred. Responsive to the determination, an out-of-office action is performed using the processor.
    Type: Grant
    Filed: June 27, 2018
    Date of Patent: April 14, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Luca Alfarano, Srinivas Allampally, Gaurav Bhagat, Conor T. Boland
  • Patent number: 10614091
    Abstract: Approaches for integrating an operational reporting system with a warehouse based reporting system. The operational reporting system and the warehouse based reporting system may be offered and supported by different vendors, and so may be deployed in different clouds or as separate product installations in case of on-premise software, or these systems may be offered and supported by a single vendor, and so may be deployed in the same cloud or as part of a common product installation in case of on-premise software. The integrated system uses a common or consistent dimensional model to link related measures of the operational reporting system and the warehouse based reporting system, which allows for analysis of real time content with historical and cross subject perspective provided alongside in the same interface. The integration also facilitates trend analysis and predictive analytics in real time.
    Type: Grant
    Filed: September 29, 2016
    Date of Patent: April 7, 2020
    Assignee: Numerify, Inc.
    Inventors: Rahul Kapoor, Gaurav Rewari, Aravind Sridharan, Sadanand Sahasrabudhe, Florian Schouten
  • Patent number: 10616248
    Abstract: A security monitoring system operated by a downstream client continually collects event information indicating events that have occurred within the computing environment of the downstream client. The monitoring system, using software provided by a threat analytics system, aggregates the event information into a secure and space efficient data structure. The monitoring system transmits the data structures storing event information to the threat analytics system for further processing. The threat analytics system also receives threat indicators from intelligence feed data sources. The threat analytics system compares the event information received from each security monitoring system against the threat indicators collected from the intelligence feed data sources to identify red flag events. The threat analytics system processes the event information to synthesize all information related to the red flag event and reports the red flag event to the downstream client.
    Type: Grant
    Filed: January 23, 2019
    Date of Patent: April 7, 2020
    Assignee: Anomali Incorporated
    Inventors: Wei Huang, Yizheng Zhou, Hugh Njemanze
  • Patent number: 10610144
    Abstract: A method and system for generating a personalized health management recommendation for a user. During operation, the system obtains first physiological data generated by a wearable device worn by the user that indicates a physiological condition of the user. The system then generates a prediction model for the user based on the first physiological data. Next, the system obtains real-time physiological data generated by the wearable device. The system may generate a prediction by analyzing the real-time physiological data to determine whether the user's physiological condition exceeds a threshold parameter according to the prediction model. Upon determining that the threshold parameter has been exceeded, the system may select a recommendation and send the recommendation message to the user's mobile device.
    Type: Grant
    Filed: August 19, 2015
    Date of Patent: April 7, 2020
    Assignee: Palo Alto Research Center Incorporated
    Inventors: Hoda M. A. Eldardiry, Jonathan Rubin, Rui Abreu, Shane P. Ahern, Daniel G. Bobrow, David Garcia, Honglu Du, Ashish Pattekar
  • Patent number: 10614269
    Abstract: Training data including a first and second group of questions each associated with an answer is read into memory by a computer. A class of answers including the answer to a question for each question is determined, where each class of answers has a class label that is associated with each of the questions, and each of the questions are classified into a respective class of answers, accordingly. First and second training data is generated including the first and second groups of questions and corresponding classes of answers for use in first and second classifiers, respectively. Each question of the first and second group of questions is classified by the second and first classifiers, respectively, where the classifying generates corresponding classification results. The first or second training data is updated based on the classification results to generate corresponding updated first or second training data, respectively.
    Type: Grant
    Filed: June 28, 2019
    Date of Patent: April 7, 2020
    Assignee: International Business Machines Corporation
    Inventors: Hiroaki Komine, Kaori Maruyama, Takumi Yanagawa
  • Patent number: 10606915
    Abstract: The present disclosure provides an answer searching method and device based on deep question and answer. The method includes: receiving a query statement; obtaining webpages containing candidate answers by searching according to the query statement; obtaining a first candidate answer, a second candidate answer and a third candidate answer based on a webpage analysis method, a deep learning method and a template matching method respectively; determining a final answer according to the first candidate answer, the second candidate answer and the third candidate answer; and displaying the final answer.
    Type: Grant
    Filed: July 6, 2017
    Date of Patent: March 31, 2020
    Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
    Inventor: Xiong Liu
  • Patent number: 10599992
    Abstract: An apparatus comprises a processing platform configured to implement a machine learning system for automated generation of predicted reliability measures and associated early warning indicators for product and part combinations. The machine learning system comprises a data aggregation module configured to extract product and part data from a big data repository, and a reliability predictor configured to generate predicted reliability measures for respective ones of the product and part combinations utilizing a shared model that is determined based at least in part on the extracted product and part data. The machine learning system processes the predicted reliability measures to generate early warning indicators relating to particular ones of the product and part combinations having predicted reliability measures that fail to meet one or more specified criteria.
    Type: Grant
    Filed: September 10, 2015
    Date of Patent: March 24, 2020
    Assignee: EMC IP Holding Company LLC
    Inventors: Raphael Cohen, David M. Dionisio
  • Patent number: 10601743
    Abstract: A message receiving, intercepting and processing method and corresponding application and device may provide receiving a message at a message processing server, pre-processing the message to determine a particular contextual classification associated with a word included in the message and assigning the message to a predefined message bucket that has a number of automated responses. The method may also include identifying an automated response to the message that includes contextual information that is based on the parsed word from the message and processing the message to determine whether to generate the automated response and transmit the automated response to an end user device based on a confidence score.
    Type: Grant
    Filed: September 4, 2018
    Date of Patent: March 24, 2020
    Assignee: West Corporation
    Inventors: Adam Caldwell, Jeffrey William Cordell, James K. Boutcher
  • Patent number: 10599732
    Abstract: Data records are linked across a plurality of datasets. Each dataset contains at least one data record, and each data record is associated with an entity and includes one or more attributes of that entity and a value for each attribute. Values associated with attributes are compared across datasets, and matching attributes having values that satisfy a predetermined similarity threshold are identified. In addition, linkage points between pairs of datasets are identified. Each linkage point links one or more pairs of data records. Each data record in the pair of data records is contained in one of a given pair of datasets, and each pair of data records is associated with a common entity having matching attributes in the given pair of datasets. Data records associated with the common entities are linked across datasets using the identified linkage points.
    Type: Grant
    Filed: February 23, 2017
    Date of Patent: March 24, 2020
    Assignee: International Business Machines Corporation
    Inventors: Oktie Hassanzadeh, Mauricio A Hernandez, Ching-Tien Ho, Lucian Popa
  • Patent number: 10594811
    Abstract: Methods and a system are provided. A method includes optimizing, by a natural language processing based response optimizer having a processor, responses in an online question and answer session using natural language processing. The optimizing step includes deriving a candidate answer to a question posed in natural language and gathering support for the candidate answer by accessing a social network. The support is weighted by at least one of degree centrality, betweenness centrality, closeness centrality, Eigenvalue, hub, and authority of nodes in the social network that are associated with the support.
    Type: Grant
    Filed: June 19, 2015
    Date of Patent: March 17, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: James R. Kozloski, Clifford A. Pickover, Valentina Salapura, Maja Vukovic
  • Patent number: 10593325
    Abstract: Certain example embodiments relate to techniques for creating computerized models usable with enterprise modeling platforms implementing formalized modeling languages. Audio input of an orally-described model having semantic concepts associable with the formalized language but following a natural language pattern rather than an input pattern expected by the formalized language is received. At least some of the semantic concepts are recognizable from a domain-specific grammar that includes possible semantic concepts that are arranged hierarchically and associated with a domain to which the computerized model being created belongs. At least some others are recognizable from a general grammar that includes other possible semantic concepts that are relevant to the computerized model and that are arranged hierarchically but that are domain-independent.
    Type: Grant
    Filed: April 13, 2018
    Date of Patent: March 17, 2020
    Assignee: SOFTWARE AG
    Inventors: Rinku Hazarika, Jivtesh Singh Ahuja, Lakhya Jyoti Nath, Rameshchandra Veeturi
  • Patent number: 10593431
    Abstract: A system for causative chaining of prognostic label classifications includes a classification device configured to receive training data including a plurality of first data entries, each including at least a first element of physiological state data and at least a correlated first prognostic label and a plurality of second data entries, each including at least a second prognostic label and at least a correlated third prognostic label, and to record at least a first biological extraction. The system includes a prognostic label learner configured to generate at least a first prognostic output as a function of the first training set and the at least a physiological test sample, and a causal link learner configured to generate at least a second prognostic output causally linked to the first prognostic output as a function of the second training set and the at least a first prognostic output.
    Type: Grant
    Filed: June 3, 2019
    Date of Patent: March 17, 2020
    Assignee: KPN Innovations, LLC
    Inventor: Kenneth Neumann
  • Patent number: 10594810
    Abstract: Methods and a system are provided. A method includes optimizing, by a natural language processing based response optimizer having a processor, responses in an online question and answer session using natural language processing. The optimizing step includes deriving a candidate answer to a question posed in natural language and gathering support for the candidate answer by accessing a social network. The support is weighted by at least one of degree centrality, betweenness centrality, closeness centrality, Eigenvalue, hub, and authority of nodes in the social network that are associated with the support.
    Type: Grant
    Filed: April 6, 2015
    Date of Patent: March 17, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: James R. Kozloski, Clifford A. Pickover, Valentina Salapura, Maja Vukovic
  • Patent number: 10585938
    Abstract: There is provided a visual localization method comprising: (a) transmitting data representative of one or more detected visual features from a mobile device to a server; (b) estimating the location of the mobile device at the server based on the visual features received from the mobile device; (c) transmitting reference data associated with the estimated location from the server to the mobile device; and (d) the mobile device determining its location based on the reference data received from the server.
    Type: Grant
    Filed: January 28, 2019
    Date of Patent: March 10, 2020
    Assignee: NavVis GmbH
    Inventors: Mohammad Abu-Alqumsan, Anas Al-Nuaimi, Robert Huitl, Georg Schroth, Florian Schweiger, Eckehard Steinbach
  • Patent number: 10579661
    Abstract: The present invention relates in general to the field of parallel data processing, and more particularly to machine learning and classification of extremely large volumes of unstructured gene sequence data using Collaborative Analytics Gene Sequence Classification Learning Systems and Methods.
    Type: Grant
    Filed: May 20, 2014
    Date of Patent: March 3, 2020
    Assignee: Southern Methodist University
    Inventors: Jake Drew, Michael Hahsler, Tyler Moore
  • Patent number: 10582011
    Abstract: A server includes a network communication device, a storage device, and a processing device. The processing device executes computer-readable instructions that, when executed by the processing device, cause the processing device to: receive contextual data from a client computing device via the network communication device, the contextual data indicates a first application view displayed on the client computing device; identify a first application function ID that identifies a first application function corresponding with the first application view; determine a first user intent ID that corresponds with the first application function ID; determine a second user intent ID that transitions from the first user intent ID; identify a second application function ID that corresponds with the second user intent ID; retrieve a card object corresponding with the second application function ID from the storage device; and transmit the card object to the client computing device via the network communication device.
    Type: Grant
    Filed: August 6, 2015
    Date of Patent: March 3, 2020
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Brahm Kiran Singh, Kalyan Desineni, Rajesh Konda, Yeongmi Jeon