Natural Language Patents (Class 704/9)
  • Patent number: 11366966
    Abstract: Methods, and systems for named entity recognition and disambiguation. One of the methods includes: receiving a document; extracting a plurality of mentions within the document; clustering the plurality of mentions to produce at least one cluster; identifying a plurality of candidate entities for the cluster; pairing each candidate entity and the cluster to create a plurality of candidate entity-cluster pairings; generating features for each candidate entity-cluster pairing; and selecting an entity, from the plurality of candidate entities, for the cluster based at least in part on features of a candidate entity pairing.
    Type: Grant
    Filed: July 16, 2019
    Date of Patent: June 21, 2022
    Assignee: Kensho Technologies, LLC
    Inventors: Michael Ramsey, Gabriel Parlato-Altay, Aron Szanto, Anthony Liu, Sireesh Gururaja, Benjamin Hsu, Domenic Puzio
  • Patent number: 11360802
    Abstract: Techniques for processing “destructive” database statements are provided. Destructive database statements, when processed, cause metadata of a database object to be changed. Examples of such database statements include ones that delete an index, that set a column as unused, and that drop a constraint on a column. When such a statement is received, a change is made to metadata of a database object. Such a metadata change may involve setting an index as unusable, disabling a constraint, or invalidating a cursor. After the metadata change, a first time is determined. Then, it is determined when one or more database transactions that were pending at the first time have committed. After those database transaction(s) have committed, one or more operations are performed, such as dropping an index or dropping a constraint.
    Type: Grant
    Filed: May 29, 2020
    Date of Patent: June 14, 2022
    Assignee: Oracle International Corporation
    Inventors: Ramesh Kumar, Ananth Raghavan, George Eadon
  • Patent number: 11361158
    Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for determining a language of a text string are presented. A language detection model may be maintained. The language detection model may comprise identities and weights for initial and final consonants, identities and weights for prefixes and suffixes, and identities and weights for vowel sequences, where each identity is derived from a training corpus. The weights may correspond to a frequency of a text unit in the corpus. A text string may be received and a match score between the text string and the language of the language detection model may be determined. The match score may be based on initial and final consonant scores, prefix and suffix scores, and/or vowel sequence scores for each word in the text string. If the match score meets a threshold value a follow-up action associated with the language may be performed.
    Type: Grant
    Filed: September 17, 2020
    Date of Patent: June 14, 2022
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Andrew Stuart Glass, Margaret Hope Magnus, Roland Radtke
  • Patent number: 11361167
    Abstract: Embodiments are directed to organizing conversations. Words may be provided from a conversation stream. Each word may be mapped to a graph model based on characteristics of each word. The graph model may be partitioned based on one or more attributes of a nodes and edges included in the graph model such that nodes associated with relationship strength that exceeds a threshold value may be grouped together. Sentence models may be generated based on sentences included in the conversation stream. Combined models may be generated based on the sentence models and the graph such that each sentence model may be associated with one or more partitions of the graph model. A conversation digest may be generated based on the combined model such that the conversation digest identifies one or more dominant portions of the conversation that include key subject matter.
    Type: Grant
    Filed: July 29, 2021
    Date of Patent: June 14, 2022
    Assignee: Rammer Technologies, Inc.
    Inventors: Toshish Arun Jawale, Ansup Babu, Anthony Claudia
  • Patent number: 11362981
    Abstract: The system and method delivers a digital therapeutic, specific to an emotional or mental state (EMS) parsed from an electronic message, comprising: an electronic computing device communicatively coupled to a processor. The processor further comprising; an EMS store; a message prescriber; a sentiment vector generator comprising: a parsing module; a coordinate-based sentiment value spectrum comprising one positive to negative-scaled axis and one perpendicular active to passive scaled axis forming a two-dimensional plot of a sentiment value along a positive to negative line (positivity correlate) and an active to passive line (activity correlate).
    Type: Grant
    Filed: February 21, 2019
    Date of Patent: June 14, 2022
    Assignee: AEBEZE LABS
    Inventor: Michael Phillips Moskowitz
  • Patent number: 11360969
    Abstract: An analysis system connects to a set of data sources and perform natural language questions based on the data sources. The analysis system connects with the data sources and retrieves metadata describing data assets stored in each data source. The analysis system generates an execution plan for the natural language question. The analysis system finds data assets that match the received question based on the metadata. The analysis system ranks the data assets and presents the ranked data assets to users for allowing users to modify the execution plan. The analysis system may use execution plans of previously stored questions for executing new questions. The analysis system supports selective preprocessing of data to increase the data quality.
    Type: Grant
    Filed: March 19, 2020
    Date of Patent: June 14, 2022
    Assignee: Promethium, Inc.
    Inventor: Kaycee Lai
  • Patent number: 11361151
    Abstract: A system for intelligent editing of legal documents. The system includes a computing device. The computing device is configured to access a plurality of legal source texts from a plurality of legal sources, generate a score for each of the plurality of legal source texts, train a natural language processing model as a function of the scored legal source texts and a first machine-learning process, receive user inputted legal text from a user device being operated by a human user to create a user legal document, analyze the user inputted legal text using the natural language processing model, suggest, as a function of the analyzing, a modification to a target text of the user inputted legal text, and generate a score for a modified user legal document. A method for intelligent editing of legal documents is also provided.
    Type: Grant
    Filed: October 18, 2021
    Date of Patent: June 14, 2022
    Assignee: BriefCatch LLC
    Inventors: Ross Guberman, Thai Doan
  • Patent number: 11361257
    Abstract: Methods and systems are described for managing diagnostic imaging order requests. A system is configured to receive diagnostic image order request from ordering physicians. The received diagnostic imaging order requests comprise imaging order information including ordering provider information, patient information, diagnostic imaging order information, and/or clinical decision support information. Upon determining that a guideline-based clinical decision support system process was required but not followed, a notification to the ordering physician is generated and sent.
    Type: Grant
    Filed: May 11, 2018
    Date of Patent: June 14, 2022
    Assignee: RAMSOFT Inc.
    Inventor: Vijay Ramanathan
  • Patent number: 11354368
    Abstract: A server system detects presentation of a media content item being played at a first device in proximity to a second device associated with a first user. It also receives from the second device content information derived from sound output from the presentation of the media content item at the first device captured at the second device. Based on the received content information, it identifies the media content item being played at the first device and a plurality of first quotations associated with the media content item. The server system sends to the second device the first quotations and a plurality of quotation operation affordances. It receives selection by the first user of a first affordance of the quotation operation affordances for a first one of the first quotations. In accordance with the selection, it performs an operation with respect to the first one of the first quotations.
    Type: Grant
    Filed: July 21, 2020
    Date of Patent: June 7, 2022
    Assignee: Google LLC
    Inventors: Ant Oztaskent, Yaroslav Volovich, Ingrid Mcaulay Trollope
  • Patent number: 11354341
    Abstract: A method of translating software queries into natural language may comprise receiving a user instruction to identify a data set through a database query defined by a received user-selected query object and user-selected query value in setting a portion of a currently modeled integration process, and to perform a user-selected action on the data set, and translating a suggested database query associated in memory with the user-selected query object to a natural language translation. The method may also comprise displaying the natural language translation of the suggested database query, receiving a user instruction to include the suggested database query in the currently modeled integration process, and automatically generating and transmitting to a remote location for later execution, code instructions for performing the user-selected action on data sets stored at the remote database meeting the selected, suggested database query.
    Type: Grant
    Filed: January 31, 2020
    Date of Patent: June 7, 2022
    Assignee: Boomi, LP
    Inventors: Daniel Schwartz, Michael J. Morton
  • Patent number: 11354499
    Abstract: Disclosed is a meta-knowledge fine tuning method and platform for a multi-task language model. The method is to obtain highly transferable shared knowledge, that is, meta-knowledge, on different data sets of tasks of the same category, perform interrelation and mutual reinforcement on the learning processes of the tasks of the same category that correspond to different data sets and are in different domains, so as to improve the fine tuning effect of downstream tasks of the same category on data sets of different domains in the application of the language model, and improve the parameter initialization ability and the generalization ability of a general language model for the tasks of the same category.
    Type: Grant
    Filed: November 22, 2021
    Date of Patent: June 7, 2022
    Assignee: ZHEJIANG LAB
    Inventors: Hongsheng Wang, Haijun Shan, Shengjian Hu
  • Patent number: 11354513
    Abstract: A technique for intelligently identifying concept labels for a text fragment where the identified concept labels are representative of and semantically relevant to the information contained by the text fragment is provided. The technique includes determining, using a knowledge base storing information for a reference set of concept labels, a first subset of concept labels that are relevant to the information contained by the text fragment. The technique includes ordering the first subset of concept labels according to their relevance scores and performing dependency analysis on the ordered list of concept labels. Based on the dependency analysis, the technique includes identifying concept labels for a text fragment that are more independent (e.g., more distinct and non-overlapping) of each other, representative of and semantically relevant to the information represented by the text fragment.
    Type: Grant
    Filed: February 6, 2020
    Date of Patent: June 7, 2022
    Assignee: Adobe Inc.
    Inventors: Natwar Modani, Srinivas Saurab Sirpurkar, Paridhi Maheshwari, Harsh Deshpande, Diviya Singh
  • Patent number: 11354504
    Abstract: Embodiments relate to an intelligent computer platform to identify and process communications across multiple languages. An originating communication is identified, including identification of language, action tokens, and linguistic features. A first map of the identified action tokens and linguistic features from the originating language to a second format is created and populated into identifying machine learning model (MLM). A second communication is identified, including the originating language, action tokens, and linguistic features, and a second map is created of the identified action tokens and linguistic features of the second communication. The second map and the MLM are leveraged to identify and return a predicted action token class of the identified action tokens in the second communication.
    Type: Grant
    Filed: July 10, 2019
    Date of Patent: June 7, 2022
    Assignee: International Business Machines Corporation
    Inventors: Hamid Reza Motahari Nezhad, Pravar Dilip Mahajan
  • Patent number: 11354521
    Abstract: Techniques described herein relate to facilitating end-to-end multilingual communications with automated assistants. In various implementations, speech recognition output may be generated based on voice input in a first language. A first language intent may be identified based on the speech recognition output and fulfilled in order to generate a first natural language output candidate in the first language. At least part of the speech recognition output may be translated to a second language to generate an at least partial translation, which may then be used to identify a second language intent that is fulfilled to generate a second natural language output candidate in the second language. Scores may be determined for the first and second natural language output candidates, and based on the scores, a natural language output may be selected for presentation.
    Type: Grant
    Filed: February 17, 2020
    Date of Patent: June 7, 2022
    Assignee: GOOGLE LLC
    Inventors: James Kuczmarski, Vibhor Jain, Amarnag Subramanya, Nimesh Ranjan, Melvin Jose Johnson Premkumar, Vladimir Vuskovic, Luna Dai, Daisuke Ikeda, Nihal Sandeep Balani, Jinna Lei, Mengmeng Niu, Hongjie Chai, Wangqing Yuan
  • Patent number: 11354684
    Abstract: Data analytics techniques can improve international software product quality and user experience. The system uses data mining to identify and assess region-specific issues in a software product. The system uses predetermined keywords, patterns and neural networks to mine customer feedback from heterogeneous data sources in order to accurately and efficiently identify and assess technical problems in a software product. The system, upon mining the data sources to determine the usage patterns and expectations that led to the identified technical problems, can facilitate the development of a software update or patch for the software product that can solve or mitigate the identified technical problem, resulting in the software product having improved globalization maturity and international user experience.
    Type: Grant
    Filed: February 6, 2018
    Date of Patent: June 7, 2022
    Assignee: Citrix Systems, Inc.
    Inventor: Karthikeyan Ravichandran
  • Patent number: 11348693
    Abstract: This disclosure relates generally to method and system for graph convolution based gene prioritization on heterogeneous networks. The method includes obtaining a set of entities for human rare diseases from one or more sources containing rare diseases, genes, phenotypes for rare diseases and biological pathways and constructing an initial heterogeneous network using each of an entity from the set of entities. the initial heterogeneous network applying Graph Convolution-based Association Scoring (GCAS) to the initial heterogeneous network to derive inferred associations and creating a Heterogeneous Association Network for Rare Diseases (HANRD) by adding the inferred associations to the initial heterogeneous network and generating a prioritized set of genes for an input query being received in the HANRD.
    Type: Grant
    Filed: April 8, 2019
    Date of Patent: May 31, 2022
    Assignee: Tata Consultancy Services Limited
    Inventors: Thomas Joseph, Aditya Rao, Naveen Sivadasan, Saipradeep Govindakrishnan Vangala, Sujatha Kotte, Rajgopal Srinivasan
  • Patent number: 11348582
    Abstract: An electronic device may capture a voice command from a user. The electronic device may store contextual information about the state of the electronic device when the voice command is received. The electronic device may transmit the voice command and the contextual information to computing equipment such as a desktop computer or a remote server. The computing equipment may perform a speech recognition operation on the voice command and may process the contextual information. The computing equipment may respond to the voice command. The computing equipment may also transmit information to the electronic device that allows the electronic device to respond to the voice command.
    Type: Grant
    Filed: March 31, 2020
    Date of Patent: May 31, 2022
    Assignee: Apple Inc.
    Inventor: Aram M. Lindahl
  • Patent number: 11347942
    Abstract: An information processing apparatus according to the present invention includes: an acceptance unit that accepts a process request to an operation system; a specifying unit that, based on the process request, specifies an operation task to be executed in the operation system; an extraction unit that performs text analysis on the process request and extracts an answer item corresponding to an input item required at execution of the operation task from the process request; and an execution unit that executes the operation task based on the answer item.
    Type: Grant
    Filed: November 2, 2018
    Date of Patent: May 31, 2022
    Assignee: NEC CORPORATION
    Inventors: Masako Imanishi, Yousuke Motohashi, Koichi Todo, Sawako Umezu
  • Patent number: 11347807
    Abstract: A system may include a processor, a user input, and memory comprising a graph and executable instructions. The executable instructions may cause the processor to effectuate operations. The operations include receiving, via the user input, a query comprising a class generalization and pathway variables. The operations include identifying a query class based on at least the class generalization and determining an anchor set based on at least one of the pathway variables. The operations also include translating the pathway variables into a pathway algebraic expression based on the anchor set and the query class and executing the pathway algebraic expression on the graph to return a pathway set.
    Type: Grant
    Filed: March 9, 2020
    Date of Patent: May 31, 2022
    Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.
    Inventors: Theodore Johnson, Vladislav Shkapenyuk
  • Patent number: 11347381
    Abstract: A set of images and a corresponding set of textual information are received, such that a first textual information is to be presented with a first image. The first textual information is translated into a set of translated textual information, each textual information in the set of translated textual information corresponding to a language in a set of languages. A set of layout parameters is determined for at least one translated textual information. The translated textual information is transformed according to the set of layout parameters and overlaid on the first image. The overlaying causes a pixel of the transformed translated textual information to be superimposed on a pixel of the first image.
    Type: Grant
    Filed: June 13, 2019
    Date of Patent: May 31, 2022
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Su Liu, Yang Liang, Debbie Anglin, Cheng Xu
  • Patent number: 11341203
    Abstract: This disclosure relates to methods and systems to generate information about news source items from a corpus of news sources, where identified news source items describe or are associated with a news event or topic of interest. The generated information can be presented as collections of news source items describing a news event or topic in, e.g., a newsfeed format, a report, a dashboard configuration, or for use in machine learning processes. News sources can be associated with a rating. The news source items, news sources, and collections can be analyzed to generate information including differences in coverage of generated or selected news events or topics according to various considerations, such as news source characteristics (e.g., bias/skew/viewpoint rating, age, location of news source or event, etc.), time, and presence, absence, or frequency of news sources ratings in a collection of news source items describing the news event or topic.
    Type: Grant
    Filed: August 25, 2020
    Date of Patent: May 24, 2022
    Assignee: SNAPWISE INC.
    Inventors: Sukhsagar Singh Jolly, Payman Pouladdej, Jan Kulinski, Guy Streetley, Harleen Kaur Jolly
  • Patent number: 11341178
    Abstract: Systems and methods are disclosed for key phrase characterization of documents. In accordance with one implementation, a method is provided for key phrase characterization of documents. The method includes obtaining a first plurality of documents based at least on a user input, obtaining a statistical model based at least on the user input, and obtaining, from content of the first plurality of documents, a plurality of segments. The method also includes determining statistical significance of the plurality of segments based at least on the statistical model and the content, and providing for display a representative segment from the plurality of segments, the representative segment being determined based at least on the statistical significance.
    Type: Grant
    Filed: December 4, 2018
    Date of Patent: May 24, 2022
    Assignee: Palantir Technologies Inc.
    Inventors: Max Kesin, Hem Wadhar
  • Patent number: 11341327
    Abstract: An information processing device includes an input device, an output device, a processing device, a storage device, and a generating unit. The generating unit includes a first function of inputting text data; a second function of inputting a synonym dictionary including synonyms; a third function of extracting a first piece of text data from the multiple pieces of text data; a fourth function of extracting from the synonym dictionary synonyms in which a certain word in the first piece of text data is included; a fifth function of extracting from the text data second multiple pieces of text data including a synonym belonging to the extracted synonyms; and a sixth function of generating a score to evaluate a relationship between the first piece of text data and the extracted synonyms from a relationship between the first piece of text data and the second multiple pieces of text data.
    Type: Grant
    Filed: March 13, 2020
    Date of Patent: May 24, 2022
    Assignee: HITACHI, LTD.
    Inventors: Yu Asano, Makoto Iwayama
  • Patent number: 11341127
    Abstract: This invention provides an information processing apparatus for learning parameters to convert a question in a natural language into a query expression in a formal language, including an acceptor accepting an input of a set of a question in the natural language and a correct answer to the question, a condition generator generating condition(s) to be satisfied by the formal language input on searching a database for the correct answer, a query expression generator generating a query expression in the formal language corresponding to the question using parameters of the converter to satisfy any of the at least one condition, an answer acquirer acquiring an answer to the question based on a search of the database using the generated query expression, and a updater updating the parameters such that the question is converted with priority into the generated query expression when the answer and the correct answer match.
    Type: Grant
    Filed: March 31, 2017
    Date of Patent: May 24, 2022
    Assignee: NEC CORPORATION
    Inventors: Yuzuru Okajima, Kunihiko Sadamasa
  • Patent number: 11341339
    Abstract: Techniques for creating and calibrating natural-language understanding (NLU) machine learning models are described. In certain embodiments, a training service tunes parameters of a function, taking the output from an NLU machine learning model as an input of the function, to calibrate the NLU machine learning model's output to optimize the interpretability of the resulting output, e.g., confidence score(s). Embodiments herein include generating, by the NLU machine learning model, an output based at least in part on an input (e.g., utterance) from a user, and applying a tuned, output modifying function to the output from the NLU machine learning model to generate a modified output. An inference may be generated based at least in part on the modified output.
    Type: Grant
    Filed: May 14, 2020
    Date of Patent: May 24, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Shang-Wen Daniel Li, Meghana Puvvadi, Trevor Andrew Morse, Roger Scott Jenke, Yi Zhang, Rama Krishna Sandeep Pokkunuri
  • Patent number: 11334721
    Abstract: A corpus pattern paraphrasing method, system, and non-transitory computer readable medium, include aligning slots of patterns for verbal phrases based on syntactical and lexical features along with calculated synonyms to predict paraphrases that are not previously stored in a corpus of sentences in a database.
    Type: Grant
    Filed: July 31, 2019
    Date of Patent: May 17, 2022
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Octavian Popescu, Vadim Sheinin
  • Patent number: 11334720
    Abstract: A method, system, and computer program product for using a natural language processor includes importing a training text including a plurality of training nodes and having a first marked span that includes some of the plurality of training nodes and a first training trigger, wherein each training node includes a first attribute and a second attribute. Also included are generating a first plurality of training tree tables for each training node with respect to a first training traversal from the first training trigger, each training tree table including the first and second attributes of each training node in the first training traversal, and generating a first plurality of training comparison tables from the first plurality of training tree tables. Each training comparison table is also analyzed to determine if a target node belongs in the first marked span, and labeling each training comparison table accordingly.
    Type: Grant
    Filed: April 17, 2019
    Date of Patent: May 17, 2022
    Assignee: International Business Machines Corporation
    Inventors: Joshua Cason, Kandhan Sekar, Thomas Hay Rogers
  • Patent number: 11334800
    Abstract: In one general embodiment, a computer program product for altering input search terms comprises a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, and where the program instructions are executable by a processor to cause the processor to perform a method comprising identifying an input search term, utilizing the processor, determining, utilizing the processor, an additional term associated with the input search term, where the additional term targets a predetermined entity, altering, utilizing the processor, the input search term utilizing the determined additional term, and performing, utilizing the processor, a search, utilizing the altered input search term.
    Type: Grant
    Filed: May 12, 2016
    Date of Patent: May 17, 2022
    Assignee: International Business Machines Corporation
    Inventors: Corville O. Allen, Malous M. Kossarian
  • Patent number: 11334333
    Abstract: The present invention may include an embodiment that receives a deployment declaration in a natural language. The embodiment may detect one or more sequencing entities and one or more parameter entities using trained natural language processing. The embodiment may sequence a configuration file based on the one or more sequencing entities. The embodiment may determine a plurality of configuration parameters in the sequenced configuration file. The embodiment may substitute a configuration parameter from the plurality of configuration parameters of the sequenced configuration file with the one or more parameter entities. The embodiment may align the plurality of configuration parameters of the sequenced configuration file based on organization compliance data and deploys a tuned cloud service using the sequenced configuration file.
    Type: Grant
    Filed: November 10, 2020
    Date of Patent: May 17, 2022
    Assignee: International Business Machines Corporation
    Inventors: Abhishek Malvankar, Shikhar Kwatra, Charles E. Beller, Carlos A. Fonseca
  • Patent number: 11334816
    Abstract: A mechanism is provided in a data processing system having a processor and a memory. The memory comprises instructions which are executed by the processor to cause the processor to implement a training system for finding an optimal surface for hierarchical classification task on an ontology. The training system receives a training data set and a hierarchical ontology data structure. A surface finding component executing within the training system selects a surface that passes through each path from a root to a leaf node in the hierarchical ontology data structure. The surface finding component determines a plurality of adjacent surfaces that differ from the selected component by one node. The surface finding component selects an optimal surface, based on the selected surface and the plurality of adjacent surfaces, that maximizes accuracy and coverage. The training system trains a classifier model for a cognitive system using the optimal surface and the training data set.
    Type: Grant
    Filed: November 14, 2018
    Date of Patent: May 17, 2022
    Assignee: International Business Machines Corporation
    Inventors: Eitan D. Farchi, Pathirage Perera, Orna Raz
  • Patent number: 11334712
    Abstract: Described are techniques for minimizing the performance of sets of actions in undesired situations. For example, a set of actions may be triggered based on a sensor detecting the presence of an individual, but the sensor may be faulty and trigger the set of actions to be performed based on false detections of an individual. A system may maintain a record of past executions of sets of actions. The system may analyze the past executions to determine a frequency with which a set of actions was executed, whether the past executions resulted in failed processing, etc. If the system determines, based on these determinations, that a set of actions should not be performed in the present instance, the system prevents the set of actions from being performed. The system may notify a user of such and provide the user with the ability to override the system's determination.
    Type: Grant
    Filed: June 24, 2019
    Date of Patent: May 17, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Vinaya Nadig, Bo Li
  • Patent number: 11334726
    Abstract: Disclosed herein is computer technology that applies natural language processing (NLP) techniques to training data to generate information used to train a natural language generation (NLG) system to produce output that stylistically resembles the training data. In this fashion, the NLG system can be readily trained with training data supplied by a user so that the NLG system is adapted to produce output that stylistically resembles such training data. In an example, an NLP system detects a plurality of linguistic features in the training data. These detected linguistic features are then aggregated into a specification data structure that is arranged for training the NLG system to produce natural language output that stylistically resembles the training data. Parameters in the specification data structure can be linked to objects in an ontology used by the NLG system to facilitate the training of the NLG system based on the detected linguistic features.
    Type: Grant
    Filed: June 18, 2019
    Date of Patent: May 17, 2022
    Assignee: NARRATIVE SCIENCE INC.
    Inventors: Daniel Joseph Platt, Nathan D. Nichols, Michael Justin Smathers, Jared Lorince
  • Patent number: 11334819
    Abstract: The present teaching relates to estimating one or more parameters on a system including a plurality of nodes. In one example, the system comprises: one or more learner nodes, each of which is configured for generating information related to a group of words for estimating the one or more parameters associated with a machine learning model; and a plurality of server nodes, each of which is configured for obtaining a plurality of sub-vectors each of which is a portion of a vector that represents a word in the group of words, updating the sub-vectors based at least partially on the information to generate a plurality of updated sub-vectors, and estimating at least one of the one or more parameters associated with the machine learning model based on the plurality of updated sub-vectors.
    Type: Grant
    Filed: August 28, 2020
    Date of Patent: May 17, 2022
    Assignee: Verizon Patent and Licensing Inc.
    Inventors: Andrew Feng, Erik Ordentlich, Lee Yang, Peter Cnudde
  • Patent number: 11334609
    Abstract: A non-transitory computer-readable recording medium stores a semantic structure search program. The semantic structure search program causes a computer to execute the following process. The computer generates a plurality of search semantic symbols from a search request. Next, the computer specifies a position of a specific word that corresponds to the search request in a search target document, by the plurality of search semantic symbols and document semantic structure position information. The document semantic structure position information includes a relationship information between a plurality of semantic symbols and a plurality of positions of a plurality of words in the search target document. The plurality of semantic symbols represent a semantic structure corresponding to the plurality of words. Thereafter, the computer outputs a search result including the specific word and the position of the specific word in the search target document.
    Type: Grant
    Filed: February 10, 2020
    Date of Patent: May 17, 2022
    Assignee: FUJITSU LIMITED
    Inventors: Seiji Okura, Masahiro Kataoka, Masao Ideuchi
  • Patent number: 11336539
    Abstract: A support ticket summarizer, similarity classifier, and resolution forecaster are described. A system trains a machine learning model to identify topic sequences for support ticket communications, identify topic sequences that are classified as similar, and predict subsequent topics for multiple support ticket communications, in response to receiving the support ticket communications. The machine learning model receives a communication for a support ticket, and then identifies a sequence of topics for the communication for the support ticket. The machine-learning model identifies historical sequences of topics, for historical support tickets, which are classified as similar to the sequence of topics. The machine-learning model uses the historical sequences of topics to predict at least one subsequent topic for the sequence of topics. The system outputs the at least one subsequent topic.
    Type: Grant
    Filed: March 22, 2021
    Date of Patent: May 17, 2022
    Assignee: SupportLogic, Inc.
    Inventor: Poonam Rath
  • Patent number: 11328131
    Abstract: A method for translating messages between users is presented. The method includes receiving, at a first computing device, a message from a first user associated with a first language, in which content of the message is in the first language. The method also includes transmitting the message to a second computing device associated with a second language of a second user. The method further includes receiving the message and an indication of the second language from the second computing device as well as transmitting the message to a translation server to be translated to the second language. Furthermore, the method includes receiving a translated message from the translation server and transmitting the translated message to the second computing device of the second user.
    Type: Grant
    Filed: March 12, 2019
    Date of Patent: May 10, 2022
    Inventors: Jordan Abbott Orlick, Matthew Jason Weisman, Collin Javon Alford, Jr.
  • Patent number: 11328018
    Abstract: A system for state dependency-based task execution and natural language response generation is disclosed. The system includes an input request acquisition subsystem to obtain a plurality of natural language input requests from one or more sources through at least one information capturing medium; a state definition subsystem to determine a plurality of states for a plurality of obtained natural language input requests; a state dependency definition subsystem to create a list of a plurality of determined states required to generate a dependency order, to analyse a generated dependency order of the plurality of determined states, to generate a dynamic working procedure to generate a temporary natural language response; a state based response generation subsystem to generate a structured natural language response dynamically upon successful execution of the dynamic working procedure.
    Type: Grant
    Filed: November 26, 2019
    Date of Patent: May 10, 2022
    Inventor: Shibabrata Mondal
  • Patent number: 11328715
    Abstract: Systems and method for automatically assigning cooperative platform tasks to appropriate participants are disclosed. In embodiments, a method includes receiving new task data for a new task posted to a remote server; transforming the new task data by natural language processing to produce transformed new task data; representing the new task as a vector in a vector space based on the transformed new task data, wherein the vector space includes representations of completed tasks, and the completed tasks are associated with respective participants; calculating distances between the new task and the respective completed tasks represented in the vector space; ranking the respective participants based on the distances between the new task and the completed tasks associated with respective participants; determining a select participant of the respective participants to be assigned to the new task based on the ranking; and initiating automatic assignment of the new task to the select participant.
    Type: Grant
    Filed: September 24, 2019
    Date of Patent: May 10, 2022
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Alexandre Quemy, Umit Bektas, Adam Nowotarski
  • Patent number: 11328175
    Abstract: A method and apparatus for facilitating training of agents is disclosed. Raw transcripts representing textual form of interactions between the agents and customers of the enterprise are transformed to generate transformed transcripts. An interaction summary is generated in relation to each transformed transcript. A plurality of intent-based interaction clusters are derived using the interaction summary generated in relation to each transformed transcript. The plurality of interactions are classified based on the plurality of intent-based interaction clusters and an interaction flow map is generated for each intent-based interaction cluster based on the interactions classified into the respective intent-based interaction cluster. The generated interaction flow map is capable of facilitating training of agents for interacting with the customers of the enterprise.
    Type: Grant
    Filed: September 11, 2019
    Date of Patent: May 10, 2022
    Assignee: [24]7.ai, Inc.
    Inventors: Abhi Ram Reddy Salammagari, Abhishek Ghose, Anand Madhavan, Suneet Grover
  • Patent number: 11321613
    Abstract: The disclosed system incorporates a new learning module, the Learning Kernel Activation Module (LKAM), at least serving the purpose of enforcing the utilization of less convolutional kernels by learning kernel activation rules and by actually controlling the engagement of various computing elements: The exemplary module activates/deactivates a sub-set of filtering kernels, groups of kernels, or groups of full connected neurons, during the inference phase, on-the-fly for every input image depending on the input image content and the learned activation rules.
    Type: Grant
    Filed: November 16, 2017
    Date of Patent: May 3, 2022
    Assignee: IRIDA LABS S.A.
    Inventors: Ilias Theodorakopoulos, Vassileios Pothos, Dimitris Kastaniotis, Nikos Fragoulis
  • Patent number: 11322143
    Abstract: Techniques are described herein for chatbots to achieve greater social grace by tracking users' states and providing corresponding dialog. In various implementations, input may be received from a user at a client device operating a chatbot, e.g., during a first session between the user and the chatbot. The input may be semantically processed to determine a state expressed by the user to the chatbot. An indication of the state expressed by the user may be stored in memory for future use by the chatbot. It may then be determined, e.g., by the chatbot based on various signals, that a second session between the user and the chatbot is underway. In various implementations, as part of the second session, the chatbot may output a statement formed from a plurality of candidate words, phrases, and/or statements based on the stored indication of the state expressed by the user.
    Type: Grant
    Filed: December 12, 2019
    Date of Patent: May 3, 2022
    Assignee: GOOGLE LLC
    Inventors: Bryan Horling, David Kogan, Maryam Garrett, Daniel Kunkle, Wan Fen Nicole Quah, Ruijie He, Wangqing Yuan, Wei Chen, Michael Itz
  • Patent number: 11321621
    Abstract: An automatic system and method for the performance of scientific inferencing including the determination of a null hypothesis significance testing on an interactive computer system, the method including the steps of: (a) providing for the input of an input description of a proposed hypothesis test, the input description including a number of relevant input parameters; (b) utilising the computational system for processing the input description into a null hypothesis significance test; (c) executing the null hypothesis significance test on the computational system; and (d) visually displaying the results of the execution.
    Type: Grant
    Filed: October 20, 2016
    Date of Patent: May 3, 2022
    Inventor: Ronald Christopher Monson
  • Patent number: 11321373
    Abstract: This disclosure covers methods, non-transitory computer readable media, and systems that use an intelligent analytics interface to process natural-language and other inputs to configure an analytics task for the system. The disclosed methods, non-transitory computer readable media, and systems provide the intelligent analytics interface to facilitate an exchange between the systems and a user to determine values for the analytics task. The methods, non-transitory computer readable media, and systems then use these values to execute an analytics task.
    Type: Grant
    Filed: November 27, 2019
    Date of Patent: May 3, 2022
    Assignee: Adobe Inc.
    Inventors: Prakhar Gupta, Iftikhar Ahamath Burhanuddin, Harvineet Singh, Atanu Ranjan Sinha
  • Patent number: 11321539
    Abstract: A system comprising a computer-readable storage medium storing at least one program and a computer-implemented method for creating advertisement messages using generative grammar models is presented. A generative grammar model defining a message structure of requested message is accessed. The message structure includes a plurality of lexical slots. The generative grammar model includes a corpus of source data to populate each lexical slot in the plurality of lexical slots to generate an advertisement message for a product listing. An advertisement message is generated in accordance with the generative grammar model and the message is published. The advertisement message for the product listing is then transmitted to a client device.
    Type: Grant
    Filed: April 10, 2020
    Date of Patent: May 3, 2022
    Assignee: eBay Inc.
    Inventors: Elizabeth Churchill, Atish Das Sarma, Corinne Sherman Stewart, Gyanit Singh
  • Patent number: 11316882
    Abstract: The disclosed embodiments relate to a system that generates an alert based on information extracted from search results generated by a query. During operation, the system executes the query to generate the search results. The system also obtains configuration information for the alert, wherein the configuration information identifies information associated with the search results, and also specifies a trigger condition for the alert. Next, when the trigger condition for the alert is met, the system uses the configuration information to generate a payload containing the identified information associated with the search results. The system then invokes alert-generating functionality and provides the payload as input to the alert-generating functionality. This enables the alert-generating functionality to use the information from the search results while performing one or more alert actions association with the alert.
    Type: Grant
    Filed: July 30, 2020
    Date of Patent: April 26, 2022
    Assignee: Splunk Inc.
    Inventors: Nicholas J. Filippi, Siegfried Puchbauer-Schnabel, Carl S. Yestrau, Vivian Shen, J. Mathew Elting
  • Patent number: 11308128
    Abstract: A method, system and computer program product for classifying a data collection of data of a predefined domain. A hierarchical representation scheme describing terms of the domain and one or more relationships between the terms is provided. At least one classifier may be applied on the data collection, resulting in a set of term assignments. Each term assignment of the term assignments associates a term candidate with a respective confidence value to the collection or to one or more data items of the collection. At least one of the term assignments may be refined based on the representation scheme and the set of term assignments.
    Type: Grant
    Filed: December 11, 2017
    Date of Patent: April 19, 2022
    Assignee: International Business Machines Corporation
    Inventors: Peter Gerstl, Robert Kern, Albert Maier, Thomas Schwarz, Oliver Suhre
  • Patent number: 11308274
    Abstract: A computer-implemented method is provided. The method includes acquiring a seed word; calculating a similarity score of each of a plurality of words relative to the seed word for each of a plurality of models to calculate a weighted sum of similarity scores for each of the plurality of words; outputting a plurality of candidate words among the plurality of words; acquiring annotations indicating at least one of preferred words and non-preferred words among the plurality of the candidate words; updating weights of the plurality of models in a manner to cause weighted sums of similarity scores for the preferred words to be relatively larger than the weighted sums of the similarity scores for the non-preferred words, based on the annotations; and grouping the plurality of candidate words output based on the weighted sum of similarity scores calculated with updated weights of the plurality of models.
    Type: Grant
    Filed: May 17, 2019
    Date of Patent: April 19, 2022
    Assignee: International Business Machines Corporation
    Inventors: Ryosuke Kohita, Issei Yoshida, Tetsuya Nasukawa, Hiroshi Kanayama
  • Patent number: 11308419
    Abstract: A method including: generating, from a text corpus, a lexicon of unigrams and bigrams comprising an embedding for each of said unigrams and bigrams; training a machine learning classifier on a training set comprising a subset of said lexicon, wherein each of said unigrams and bigrams in said subset has a sentiment label; applying said machine learning classifier to said lexicon, to (i) predict a sentiment of each of said unigrams and bigrams, and (ii) update said lexicon with the predicted sentiments; and performing statistical analysis on said updated lexicon, to extract one or more sentiment composition lexicons, wherein each of said one or more sentiment composition lexicons is associated with a sentiment composition class.
    Type: Grant
    Filed: November 15, 2018
    Date of Patent: April 19, 2022
    Assignee: International Business Machines Corporation
    Inventors: Ranit Aharonov, Roy Bar-Haim, Alon Halfon, Charles Arthur Jochim, Amir Menczel, Noam Slonim, Orith Toledo-Ronen
  • Patent number: 11308397
    Abstract: A modified model of the Rosenblatt perceptron and learning method leading to a significant increase in the intelligence and learning speed of the Rosenblatt perceptron itself, as well as arbitrary neural network topologies based on it, based on the modified error correction method and the modified “Back propagation” algorithm. To increase the manageability of the perceptron topology, as well as the processes of recognition and learning, the cost of connection is added at the synapses in addition to the weighting factor.
    Type: Grant
    Filed: February 13, 2019
    Date of Patent: April 19, 2022
    Inventor: Ilya Sorokin
  • Patent number: 11308405
    Abstract: An apparatus is pre-equipped with a plurality of dialogue robots, and each dialogue robot is configured to conduct a human-computer dialogue based on at least one topic. The method includes: obtaining a text entered by a user; determining at least one topic related to the text, and determining a target dialogue robot from the plurality of dialogue robots based on the at least one topic related to the text and a predefined mapping relationship between a dialogue robot and a topic, where a target topic corresponding to the target dialogue robot is some or all of the at least one topic related to the text; and allocating the text to the target dialogue robot and obtaining a reply for the text from the target dialogue robot, where the reply is generated by the target dialogue robot based on at least one semantic understanding of the text.
    Type: Grant
    Filed: July 17, 2019
    Date of Patent: April 19, 2022
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Lifeng Shang, Zhengdong Lu, Hang Li