Natural Language Patents (Class 704/9)
  • Patent number: 10691584
    Abstract: According to some embodiments, systems and methods are provided, comprising receiving a first test script in a file as text; receiving the file at a Behavior Driven Development (BDD) test integration module; transforming one or more elements in the test script into one or more corresponding tokens; mapping each of the tokens to a respective code in a code repository; generating a second test script from the code; transforming the generated second test script into natural language; and executing the generated second test script. Numerous other aspects are provided.
    Type: Grant
    Filed: September 28, 2018
    Date of Patent: June 23, 2020
    Assignee: SAP SE
    Inventors: Bandita Talukdar, Smrithi Jayarajan
  • Patent number: 10691685
    Abstract: The subject technology provides for converting natural language input to structured queries. The subject technology receives a user input query in a natural language format. The subject technology determines scores for candidate entities derived from the user input query. The subject technology selects an entity with a highest score among the candidate entities, and converts, using a context-free grammar, the user input query to a structured query based at least in part on the selected entity. The subject technology classifies the structured query to an expected answer type, the expected answer type corresponding to a type of an expected answer of the structured query. The subject technology queries a database based on the expected answer type and the structured query, the database including information corresponding to a knowledge graph. The subject technology provides, for display, an answer to the user input query based on a result of querying the database.
    Type: Grant
    Filed: September 29, 2017
    Date of Patent: June 23, 2020
    Assignee: Apple Inc.
    Inventors: Vishal Verma, Gang Xiang, Vishnu Konda, Chetan V. Kale
  • Patent number: 10691891
    Abstract: Systems and methods for extracting facts from natural language texts. An example method of information extraction comprises extracting, from a natural language text, a first plurality of information objects; extracting, from the natural language text, a second plurality of information objects; identifying a set of conflicting information objects, such that a first information object of the set of conflicting information objects belongs to the first plurality of information objects and a second information object of the set of conflicting information objects belongs to the second plurality of information objects; and producing a final list of information objects extracted from the natural language text, by applying, to the set of conflicting information objects, a conflict arbitration function which performs at least one of: modifying the first information object, deleting the first information object, or merging two or more information objects of the set of conflicting information objects.
    Type: Grant
    Filed: August 20, 2019
    Date of Patent: June 23, 2020
    Assignee: ABBYY Production LLC
    Inventors: Stepan Evgenyevich Matskevich, Ilya Aleksandrovich Bulgakov
  • Patent number: 10691766
    Abstract: A method and apparatus are provided for automatically generating and processing first and second concept vector sets extracted, respectively, from a first set of concept sequences and from a second, temporally separated, concept sequences by performing a natural language processing (NLP) analysis of the first concept vector set and second concept vector set to detect changes in the corpus over time by identifying changes for one or more concepts included in the first and/or second set of concept sequences.
    Type: Grant
    Filed: September 27, 2018
    Date of Patent: June 23, 2020
    Assignee: International Business Machines Corporation
    Inventors: Tin Kam Ho, Luis A. Lastras-Montano, Oded Shmueli
  • Patent number: 10691507
    Abstract: A generic application program interface (API) may learn heterogeneous APIs based on their API documentations that understands functionalities, parameters, operations, accessibility and outputs of APIs. The generic API collects API documentation from different sources based on a target human language by crawling a network such as the Internet. The generic API reads the documents of an API to recognize features of an API including type of services, concepts, protocols, accessibility methods, security methods, functionalities, outputs and base operations. Each given instruction for different APIs is mapped to generic API features. A programmer or end-user have access to multiple and heterogeneous APIs based on the generic API. The generic API provides a unified interface that allows a programmer or end-user to interact with different target APIs through the generic API. By raising a request to generic API a native API code is generated, executed and returns to the programmer or end-user.
    Type: Grant
    Filed: December 9, 2016
    Date of Patent: June 23, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Mehdi Bahrami, Wei-Peng Chen, Takuki Kamiya
  • Patent number: 10691900
    Abstract: A text analytics platform includes instructions embodied in one or more non-transitory machine accessible storage media configured to cause a computing device to retrieve text from at least one text source and implement one or more algorithms to determine a quantitative linguistics assessment for the retrieved text and provide as output a numeric value corresponding to the quantitative linguistics assessment. The quantitative linguistics assessment is based at least in part on a trained model.
    Type: Grant
    Filed: April 5, 2019
    Date of Patent: June 23, 2020
    Assignee: SRI International
    Inventors: John J. Niekrasz, Edmond D. Chow
  • Patent number: 10685189
    Abstract: A method includes performing, with at least one processing device, natural language generation using both (i) a semantic word and clause representation generated from syntactically-labeled context and (ii) a syntax generated from common semantic relations between sequential words and clauses. Performing the natural language generation includes pushing words onto a stack based on the semantic word and clause representation and based on words and clauses already on the stack and popping the words and clauses off the stack to be replaced by clauses based on the syntax. Pushing the words onto the stack could be based only on components of the semantic word and clause representation coming from future context.
    Type: Grant
    Filed: November 15, 2017
    Date of Patent: June 16, 2020
    Assignee: Goldman Sachs & Co. LLC
    Inventor: Paul Burchard
  • Patent number: 10685301
    Abstract: A method and system are described that provide responses to natural language queries regarding the performance of a business. The method and system processes data from multiple data sources including information generated by the business and analyzes the data to provide actionable suggestions as to how to determine how to improve the performance of the business. The use of natural language queries allows for a merchant without a business intelligence background obtain these insights easily.
    Type: Grant
    Filed: June 30, 2017
    Date of Patent: June 16, 2020
    Assignee: MASTERCARD INTERNATIONAL INCORPORATED
    Inventors: Andrew J. Smith, Siddique Hameed, Michael K. Forbis, Stewart Boling, Adam Kenneth Hosp, Ted P. Sanders, Jr.
  • Patent number: 10685188
    Abstract: Systems, methods, and non-transitory computer readable media can generate a plurality of language clusters based on one or more of: language similarity between languages or social behavior similarity between languages. A representative language for a language cluster of the plurality of language clusters can be determined. For the language cluster of the plurality of language clusters, a machine learning model can be trained based on the representative language for the language cluster to classify content items in languages included in the language cluster.
    Type: Grant
    Filed: July 6, 2018
    Date of Patent: June 16, 2020
    Assignee: Facebook, Inc.
    Inventors: Ying Zhang, Arun Babu, James Li
  • Patent number: 10679607
    Abstract: A device causes a communication session to be established between the device and a user device to allow the device and the user device to communicate speech, and receives user speech from the user device. The device processes the user speech using a natural language processing technique to determine a plurality of characteristics of the user speech, and updates a speech generation setting of a plurality of speech generation settings based on the plurality of characteristics of the user speech. The device generates, after updating the speech generation setting, device speech using a text-to-speech technique based on the speech generation setting, and sends the device speech to the user device.
    Type: Grant
    Filed: September 20, 2019
    Date of Patent: June 9, 2020
    Assignee: Capital One Services, LLC
    Inventors: Joshua Edwards, Michael Mossoba, Abdelkadar M'Hamed Benkreira, Alexandra Colevas
  • Patent number: 10678820
    Abstract: A semantic indexing system, the semantic indexing system comprising a processing resource configured to: provide a corpus comprising a plurality of textual documents, wherein (a) each of the textual documents being composed of one or more sentences; (b) each of the sentences being composed of one or more statements; and generate an index, the index mapping each of the statements to one or more frames; wherein each frame defines a structure that carries a semantic meaning, thereby enabling searching the corpus by the semantic meaning of a search statement.
    Type: Grant
    Filed: April 11, 2019
    Date of Patent: June 9, 2020
    Inventor: Abel Browarnik
  • Patent number: 10679006
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing sequential data. In one aspect, a computer-implemented method includes receiving a request to generate a system output for an input data sequence, the input data sequence including a plurality of tokens. One or more tokens may be designated as tokens to be skipped. When a token has not been designated as a token to be skipped, the token is processed using a recurrent neural network to update a current internal state of the recurrent neural network. The system output is generated from the final internal state of the recurrent neural network.
    Type: Grant
    Filed: July 10, 2019
    Date of Patent: June 9, 2020
    Assignee: Google LLC
    Inventors: Quoc V. Le, Hongrae Lee, Wei Yu
  • Patent number: 10678870
    Abstract: A search system as disclosed analyzes a file name to identify any potential tokens or words that might be relevant, and creates supplementary information for the file name. The supplementary information is indexed and searchable, thereby significantly improving the ability of a search engine to discover and return successful search hits.
    Type: Grant
    Filed: November 21, 2013
    Date of Patent: June 9, 2020
    Assignee: Open Text SA ULC
    Inventor: Patrick Thomas Sidney Pidduck
  • Patent number: 10678866
    Abstract: A novel computer-based method and associated network database architecture is described to solve the problem of the management, tracking, tracing, auditing, and life cycle management of information artifacts within a content network. In the context of the content network, information artifacts represent models and relationships associated with documents, components, collections, structures, metadata, tasks, milestones, objectives. All information artifacts that define the content network are represented as individual nodes within the network database, which can be a graph database, or a graph-enabled relational or multi-model database. Relationships that exist between the node and its parent node, between nodes representing individual information artifacts or a set of artifacts, as well as reference links to external sources where the information artifact may have originated (such as an external database or system) are represented as a set of edges.
    Type: Grant
    Filed: August 9, 2017
    Date of Patent: June 9, 2020
    Inventors: Vasumathi Ranganathan, Gerald Kukko
  • Patent number: 10679631
    Abstract: Automatic generation of a chat bot from an API specification to carry out a dialogue with a user and invoke an API call described in the API specification. Based on input API specification, a conversational bot specification representing a dialog flow is constructed. A natural language expression is received and transformed into instructions based on the conversational bot specification. Based on the instructions, a natural language prompt to the user and executable computer code for invoking the API call may be generated.
    Type: Grant
    Filed: June 6, 2019
    Date of Patent: June 9, 2020
    Assignee: International Business Machines Corporation
    Inventors: Martin Hirzel, Louis Mandel, Avraham E. Shinnar, Jerome Simeon, Mandana Vaziri, Charles Wiecha
  • Patent number: 10671683
    Abstract: A method and apparatus are provided for automatically generating and processing first and second concept vector sets extracted, respectively, from a first set of concept sequences and from a second, temporally separated, concept sequences by performing a natural language processing (NLP) analysis of the first concept vector set and second concept vector set to detect changes in the corpus over time by identifying changes for one or more concepts included in the first and/or second set of concept sequences.
    Type: Grant
    Filed: August 31, 2018
    Date of Patent: June 2, 2020
    Assignee: International Business Machines Corporation
    Inventors: Tin Kam Ho, Luis A. Lastras-Montano, Oded Shmueli
  • Patent number: 10671812
    Abstract: Certain aspects produce a scoring model that can automatically classify future text samples. In some examples, a processing device perform operations for producing a scoring model using active learning. The operations includes receiving existing text samples and searching a stored, pre-trained corpus defining embedding vectors for selected words, phrases, or documents to produce nearest neighbor vectors for each embedding vector. Nearest neighbor selections are identified based on distance between each nearest neighbor vector and the embedding vector for each selection to produce a text cloud. Text samples are selected from the text cloud to produce seed data that is used to train a text classifier. A scoring model can be produced based on the text classifier. The scoring model can receive a plurality of new text samples and provide a score indicative of a likelihood of being a member of a selected class.
    Type: Grant
    Filed: March 22, 2018
    Date of Patent: June 2, 2020
    Assignee: EQUIFAX INC.
    Inventors: Rajkumar Bondugula, Allan Joshua, Hongchao Li, Hannah Wang
  • Patent number: 10671807
    Abstract: A system, method and computer-readable storage devices for providing unsupervised normalization of noisy text using distributed representation of words. The system receives, from a social media forum, a word having a non-canonical spelling in a first language. The system determines a context of the word in the social media forum, identifies the word in a vector space model, and selects an “n-best” vector paths in the vector space model, where the n-best vector paths are neighbors to the vector space path based on the context and the non-canonical spelling. The system can then select, based on a similarity cost, a best path from the n-best vector paths and identify a word associated with the best path as the canonical version.
    Type: Grant
    Filed: September 24, 2018
    Date of Patent: June 2, 2020
    Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.
    Inventor: Vivek Kumar Rangarajan Sridhar
  • Patent number: 10671806
    Abstract: The embodiments disclose a method including providing a website interface within the customizable application builder with no code visualization tools for an application creation user, providing a form builder for creating at least one form, with at least one form element for receiving form input from an end user, with a conditional rule builder, an auto pdf mapping tool, a manual pdf mapping tool and at least two dynamic pdf mapping tools, wherein each of the pdf mapping tools has no code visualization tools and allows the user to drag and drop form elements onto a pdf format, wherein the auto pdf mapping tool automatically generates a pdf of the entire form, wherein the manual pdf mapping tool automatically generates a customizable pdf of the form, and wherein the dynamic pdf mapping tool user may edit the blank html template and dynamically generates a customizable pdf of the form.
    Type: Grant
    Filed: August 24, 2019
    Date of Patent: June 2, 2020
    Inventor: Binyamin Tsabba
  • Patent number: 10671929
    Abstract: Mechanisms are provided in a question answering (QA) system comprising a QA system pipeline that analyzes an input question and generates an answer to the input question, for pre-processing the input question. The mechanisms receive an input question and input the input question to a pre-processor flow path having one or more pre-processors. The one or more pre-processors transform the input question into a transformed question by correcting errors in a formulation of the input question that are determined to be detrimental to efficient and accurate processing of the input question by a QA system pipeline of the QA system. The transformed question is then input to the QA system pipeline of the QA system which processes the transformed question to generate and output an answer to the input question.
    Type: Grant
    Filed: August 29, 2014
    Date of Patent: June 2, 2020
    Assignee: International Business Machines Corporation
    Inventors: Branimir K. Boguraev, John P. Bufe, III, Matthew T. Hatem, Jared M. D. Smythe
  • Patent number: 10673910
    Abstract: Implementations described and claimed herein provide systems and methods for differentiating a portion of network traffic having an Internet Protocol-based attribute with reasonable certainty. In one implementation, data corresponding to a delivery of network traffic across a communications network is received. A first filter is applied to obtain a first subset of the data based on one or more characteristics of originating access traffic. The first subset includes network traffic known to originate with the Internet Protocol-based attribute. A second filter is applied to data excluded from the first subset based on one or more characteristics of terminating access traffic to obtain a second subset of the data. The second subset includes network traffic known to terminate with the Internet Protocol-based attribute. The first subset is correlated with the second subset to identify the portion of network traffic having the Internet Protocol-based attribute.
    Type: Grant
    Filed: May 16, 2013
    Date of Patent: June 2, 2020
    Assignee: Level 3 Communications, LLC
    Inventor: Mack Denzil Greene
  • Patent number: 10664472
    Abstract: Described systems and methods allow an automatic translation from a natural language (e.g., English) into an artificial language such as a structured query language (SQL). In some embodiments, a translator module includes an encoder component and a decoder component, both components comprising recurrent neural networks. Training the translator module comprises two stages. A first stage trains the translator module to produce artificial language (AL) output when presented with an AL input. For instance, the translator is first trained to reproduce an AL input. A second stage of training comprises training the translator to produce AL output when presented with a natural language (NL) input.
    Type: Grant
    Filed: June 27, 2018
    Date of Patent: May 26, 2020
    Assignee: Bitdefender IPR Management Ltd.
    Inventors: Elena Burceanu, Florin Brad, Traian Rebedea
  • Patent number: 10664505
    Abstract: An approach is provided for identifying entity relationships based on word classifications extracted from business documents stored in a plurality of corpora. In the approach, performed by an information handling system, a plurality of cluster classifications are identified for the business documents so that entity information from the business documents can be classified or assigned to the cluster classifications, such as by performing natural language processing (NLP) analysis of the business documents. The approach applies semantic analysis to identify and score entity relationships between the entity information classified in the cluster classifications, and based on the scored entity relationships, cluster relationships between the cluster classifications are identified.
    Type: Grant
    Filed: May 17, 2017
    Date of Patent: May 26, 2020
    Assignee: International Business Machines Corporation
    Inventors: Donna K. Byron, Swaminathan Chandrasekaran, Lakshminarayanan Krishnamurthy
  • Patent number: 10665030
    Abstract: A natural language scene description is converted into a scene that is rendered in three dimensions by an augmented reality (AR) display device. Text-to-AR scene conversion allows a user to create an AR scene visualization through natural language text inputs that are easily created and well-understood by the user. The user can, for instance, select a pre-defined natural language description of a scene or manually enter a custom natural language description. The user can also select a physical real-world surface on which the AR scene is to be rendered. The AR scene is then rendered using the augmented reality display device according to its natural language description using 3D models of objects and humanoid characters with associated animations of those characters, as well as from extensive language-to-visual datasets. Using the display device, the user can move around the real-world environment and experience the AR scene from different angles.
    Type: Grant
    Filed: January 14, 2019
    Date of Patent: May 26, 2020
    Assignee: Adobe Inc.
    Inventors: Sumit Shekhar, Paridhi Maheshwari, Monisha J, Kundan Krishna, Amrit Singhal, Kush Kumar Singh
  • Patent number: 10664659
    Abstract: Embodiments of the present disclosure disclose a method for modifying a segmentation model based on artificial intelligence, a device and a storage medium. The method may include: acquiring a model parameter of the segmentation model, and performing a training on a feature vector corresponding to a preset generalized feature of a first training corpus via a neural network so as to acquire a model parameter of the preset generalized feature; performing a word segmentation on the first training corpus according to the model parameter of the segmentation model and the model parameter of the preset generalized feature, so as to acquire a segmentation result; and comparing the segmentation result with the first training corpus according to a preset rule, and modifying the model parameter of the segmentation model and a parameter of the neural network according to a comparison result.
    Type: Grant
    Filed: March 23, 2018
    Date of Patent: May 26, 2020
    Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
    Inventors: Liqun Zheng, Jinbo Zhan, Qiugen Xiao, Zhihong Fu, Jingzhou He, Guyue Zhou
  • Patent number: 10664340
    Abstract: A non-transitory computer-readable storage medium storing therein a failure analysis program that causes a computer to execute a process includes: extracting, for respective incidents, first material names that satisfy a first condition from character strings included in each incident; extracting, for the respective incidents, second material names, which are the same material names as the first material names, from the character strings included in each incident; calculating a combination of feature values corresponding respectively to the one or more features from character strings correlated with the extracted second material names, for the respective incidents and for the respective second material names; and specifying a specific combination that satisfies a second condition from the combinations of feature values corresponding to the respective material names, for the respective second material names.
    Type: Grant
    Filed: February 8, 2018
    Date of Patent: May 26, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Hiroshi Otsuka, Yukihiro Watanabe, Masahiro Asaoka, Reiko Kondo, Ken Yokoyama
  • Patent number: 10657445
    Abstract: Disclosed are systems and methods for training and executing a neural network for collaborative monitoring of resource usage metrics. For example, a method may include receiving user data sets, grouping the user data sets into one or more clusters of user data sets, grouping each of the one or more clusters into a plurality of subclusters, for each of the plurality of subclusters, training the neural network to associate the subcluster with one or more sequential patterns found within the subcluster, grouping the plurality of user data sets into a plurality of teams, receiving a first series of transactions of a first user, inputting the first series of transactions into the trained neural network, classifying, using the trained neural network, the first user into a subcluster among the plurality of subclusters, generating a metric associated with the first series of transactions, generating a recommendation to the first user.
    Type: Grant
    Filed: May 16, 2019
    Date of Patent: May 19, 2020
    Assignee: Capital One Services, LLC
    Inventors: Reza Farivar, Jeremy Goodsitt, Fardin Abdi Taghi Abad, Austin Walters, Mark Watson, Anh Truong, Vincent Pham
  • Patent number: 10654380
    Abstract: The present application describes a system and method for converting a natural language query to a standard query using a sequence-to-sequence neural network. As described herein, when a natural language query is receive, the natural language query is converted to a standard query using a sequence-to-sequence model. In some cases, the sequence-to-sequence model is associated with an attention layer. A search using the standard query is performed and various documents may be returned. The documents that result from the search are scored based, at least in part, on a determined conditional entropy of the document. The conditional entropy is determined using the natural language query and the document.
    Type: Grant
    Filed: June 2, 2017
    Date of Patent: May 19, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Keng-hao Chang, Ruofei Zhang, Zi Yin
  • Patent number: 10657206
    Abstract: The present invention is a system and method for generating narrative text utilizing data input from one or more data sources to drive the creation of a narrative text output. Narrative text is generated in accordance with sets of data that provide the scope of text to be generated. A narrative text editor permits automatic generation of narrative text automatically using pre-defined scope for the generated text, or under the guidance of scope input by a user. Generated text retains links to the origin structure and scope used in creation of the narrative text permitting quick troubleshooting of issues in the narrative text generation and rapid review and updating under the guidance of established rule sets or system users.
    Type: Grant
    Filed: March 11, 2015
    Date of Patent: May 19, 2020
    Assignee: STATS LLC
    Inventors: Adam Long, Robert Allen, Ren Bauer, Robert C. Rogers, Anne Johnson, Joe Procopio
  • Patent number: 10657436
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network system. In one aspect, a neural network system includes a recurrent neural network that is configured to, for each time step of a predetermined number of time steps, receive a set of latent variables for the time step and process the latent variables to update a hidden state of the recurrent neural network; and a generative subsystem that is configured to, for each time step, generate the set of latent variables for the time step and provide the set of latent variables as input to the recurrent neural network; update a hidden canvas using the updated hidden state of the recurrent neural network; and, for a last time step, generate an output image using the updated hidden canvas for the last time step.
    Type: Grant
    Filed: January 7, 2019
    Date of Patent: May 19, 2020
    Assignee: DeepMind Technologies Limited
    Inventors: Ivo Danihelka, Danilo Jimenez Rezende, Shakir Mohamed
  • Patent number: 10657572
    Abstract: Disclosed subject matter relates to virtual assistance that includes a method and system for automatically generating response to a user query without language constraints. A response generating system receives the user query from a computing device associated with an end user and determines whether the user query belongs to at least one domain to determine goal data and a problem category of the user query. Further, a problem node associated with the user query is detected from problem nodes by parsing a predefined knowledge graph based on the goal data and the problem category. Furthermore, questions are provided based on problem sub-nodes of the problem node to the computing device to receive a feedback. The response to the user query extracted from the one of the problem sub-nodes is displayed to the end user based on the feedback. The present disclosure is highly scalable, reusable and requires minimal human supervision.
    Type: Grant
    Filed: March 20, 2017
    Date of Patent: May 19, 2020
    Assignee: Wipro Limited
    Inventors: Channarayapatna Sathyanarayana Kiran Kumar, Sawani Bade
  • Patent number: 10650104
    Abstract: A system comprising a computer-readable storage medium storing at least one program and a computer-implemented method for creating 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, and a grammatical constraint for each lexical slot in the plurality of lexical slots. A message is generated in accordance with the generative grammar model and the message is published.
    Type: Grant
    Filed: July 20, 2018
    Date of Patent: May 12, 2020
    Assignee: eBay Inc.
    Inventors: Elizabeth Churchill, Atish Das Sarma, Corinne Elizabeth Sherman-Stewart, Gyanit Singh
  • Patent number: 10650812
    Abstract: A system for extracting verifiable entities from a user-utterance received on an automated calling service is provided. The system may include a receiver configured to receive a user-utterance, a processor and a non-transitory computer-readable media comprising computer-executable instructions. The processor may be configured to execute the instructions which, canonicalize the user-utterance into a plurality of tokens, determine the number of tokens of the user-utterance, and generate, using a sliding-window protocol, a comprehensive number of n-gram sequences from the user-utterance. The processor may be configured to process a plurality of threads of execution that may include a series of actions executed on the n-gram sequences to identify and extract verified entities from the user-utterance.
    Type: Grant
    Filed: August 13, 2018
    Date of Patent: May 12, 2020
    Assignee: Bank of America Corporation
    Inventors: Viju Kothuvatiparambil, Maruthi Z. Shanmugam, Donatus Asumu
  • Patent number: 10650819
    Abstract: A method and system of providing a portable voice-based control user interface for multiple types of appliances are disclosed. The method includes activating a built-in voice communication interface of a voice control apparatus; selecting a first target appliance to receive voice-based commands; receiving a first voice input; in accordance with a determination that the first target appliance is a first appliance of a first appliance type, processing the first voice input using a first NLP model corresponding to the first appliance type to obtain a first machine command, and sending the first machine command to the first appliance; and in accordance with a determination that the first target appliance is a second appliance of a second appliance type, processing the first voice input using a second NLP model corresponding to the second appliance type to obtain a second machine command, and sending the second machine command to the second appliance.
    Type: Grant
    Filed: October 15, 2018
    Date of Patent: May 12, 2020
    Assignee: MIDEA GROUP CO., LTD.
    Inventors: Haibin Huang, Chen Zhang, Xin Liu
  • Patent number: 10643035
    Abstract: A computer-implemented technique is described for facilitating the creation of a language understanding (LU) component for use with an application. The technique allows a developer to select a subset of parameters from a larger set of parameters. The subset of parameters pertains to a LU scenario to be handled by the application. The larger set of parameters pertains to a plurality of LU scenarios handled by an already-existing generic LU model. The technique creates a constrained LU component that is based on the subset of parameters in conjunction with the generic LU model. At runtime, the constrained LU component interprets input language items using the generic LU model in a manner that is constrained by the subset of parameters that have been selected, to provide an output result. The technique also allows the developer to create new rules and/or supplemental models.
    Type: Grant
    Filed: June 25, 2019
    Date of Patent: May 5, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Young-Bum Kim, Ruhi Sarikaya, Alexandre Rochette
  • Patent number: 10645044
    Abstract: A method and system for processing a text message to be sent by electronic mail to a receiving address. A text message addressed to the receiving address is generated. The text message is analyzed and a content score value is assigned to categories. Context data values relating to the text message and to context categories is collected. A context score value for each context category is determined by comparing the context data values of the text message with context data threshold values and by comparing the content score value of the text message for each content category against content threshold values. A difference factor value is calculated by comparing the context score values with the content score values. Based on whether the difference factor value is ascertained to be greater than a specified difference factor threshold value, the electronic mail is or is not sent to the receiving address.
    Type: Grant
    Filed: March 24, 2017
    Date of Patent: May 5, 2020
    Assignee: International Business Machines Corporation
    Inventors: Giulia Carnevale, Marco Gianfico, Ciro Ragusa, Roberto Ragusa
  • Patent number: 10642938
    Abstract: The present disclosure discloses an artificial intelligence based method and apparatus for constructing a comment graph. A specific embodiment of the method comprises: determining a comment text based on comment data on a network page; identifying a comment subject and a comment opinion in the comment text, based on a characteristic in the comment text; generating a subject opinion pair including the comment subject, the comment opinion and an emotional tendency based on the comment subject and the comment opinion; generating a comment label associated with the subject opinion pair based on news information; and generating a comment graph, based on the comment label and the subject opinion pair. This embodiment improves the pertinence and the accuracy of the comment and the control to the comment emotion, when providing comments externally.
    Type: Grant
    Filed: March 30, 2018
    Date of Patent: May 5, 2020
    Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
    Inventors: Yingchao Shi, Jianqing Cui, Wei He
  • Patent number: 10643291
    Abstract: Described herein are various techniques for managing media related to a construction project, which may relate to one or more buildings to be built and/or renovated as part of the construction project. In accordance with techniques described herein, the media may be managed according to information regarding the construction project that is stored by one or more other systems separate from a media management system. The other systems may be construction information management systems that each store information regarding a construction project, including information relating to planning and/or execution of the construction project. For example, the media management system may generate tags based on the information regarding the construction project, may be trained to recognize features in the media that relate to the tags, and add the appropriate tags to the media based on the recognized features.
    Type: Grant
    Filed: September 28, 2016
    Date of Patent: May 5, 2020
    Assignee: Smartvid.io, Inc.
    Inventors: Joshua Kanner, Andrew J. Hiser, Sean D. True
  • Patent number: 10642975
    Abstract: Systems and methods for detecting deceptive opinion spam. Certain embodiments include a classifier with improved accuracy for detecting deceptive opinion entries. A feature analysis of learned models reveals a relationship between deceptive opinions and imaginative writing. By modeling deception in a generative framework, the prevalence of deception in two popular online review communities may be determined. Deceptive opinion spam is a rapidly growing and widespread problem, especially in review communities with minimal posting requirements.
    Type: Grant
    Filed: October 18, 2012
    Date of Patent: May 5, 2020
    Assignee: Cornell University
    Inventors: Myle Ott, Yejin Choi, Claire Cardie, Jeffrey Hancock
  • Patent number: 10635750
    Abstract: A computer-implemented method can include identifying a first set of text samples that include a particular potentially offensive term. Labels can be obtained for the first set of text samples that indicate whether the particular potentially offensive term is used in an offensive manner. A classifier can be trained based at least on the first set of text samples and the labels, the classifier being configured to use one or more signals associated with a text sample to generate a label that indicates whether a potentially offensive term in the text sample is used in an offensive manner in the text sample. The method can further include providing, to the classifier, a first text sample that includes the particular potentially offensive term, and in response, obtaining, from the classifier, a label that indicates whether the particular potentially offensive term is used in an offensive manner in the first text sample.
    Type: Grant
    Filed: April 17, 2018
    Date of Patent: April 28, 2020
    Assignee: Google LLC
    Inventors: Mark Edward Epstein, Pedro J. Moreno Mengibar
  • Patent number: 10635977
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing multi-task learning. In one method a system obtains a respective set of training data for each of multiple machine learning tasks. For each of the machine learning tasks, the system configures a respective teacher machine learning model to perform the machine learning task by training the teacher machine learning model on the training data. The system trains a single student machine learning model to perform the multiple machine learning tasks using (i) the configured teacher machine learning models, and (ii) the obtained training data.
    Type: Grant
    Filed: July 1, 2019
    Date of Patent: April 28, 2020
    Assignee: Google LLC
    Inventors: Junyoung Chung, Melvin Jose Johnson Premkumar, Michael Schuster, Wolfgang Macherey
  • Patent number: 10635861
    Abstract: This application addresses techniques for personalizing natural language generation by conversational agents. These solutions allow for human-like, large scale opinion expression using a consistent style or personality. Training sentences may be retrieved and a vocabulary may be built based on an analysis of the training sentences. The sentences may be analyzed to determine: (1) whether they express an opinion; (2) whether the opinion is positive or negative; (3) whether the sentence fits in the context of the currently communication; and (4) whether the sentence came from a person with first-hand experience of the topic. Further classifications may be made based on characteristics such as the age or gender of the person expressing the opinion. These opinions may be entered into a repository and used for opinion expression, for example by using the statements directly in a conversation or by training a language generation model with the opinions.
    Type: Grant
    Filed: December 29, 2017
    Date of Patent: April 28, 2020
    Assignee: FACEBOOK, INC.
    Inventors: Antoine Raux, Martin Plouy
  • Patent number: 10635860
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for resolving ambiguity in received voice queries. An original voice query is received following one or more earlier voice queries, wherein the original voice query includes a pronoun or phrase. In one implementation, a plurality of acoustic parameters is identified for one or more words in the original voice query. A concept represented by the pronoun is identified based on the plurality of acoustic parameters, wherein the concept is associated with a particular query of the one or more earlier queries. The concept is associated with the pronoun. Alternatively, a concept may be associated with a phrase by using grammatical analysis of the query to relate the phrase to a concept derived from a prior query.
    Type: Grant
    Filed: June 15, 2018
    Date of Patent: April 28, 2020
    Assignee: Google LLC
    Inventors: Gabriel Taubman, John J. Lee
  • Patent number: 10636038
    Abstract: Generating a solution keyword tag cloud is provided. Keywords are identified in a question asking how to resolve an issue experienced by a user with a product. The keywords identified in the question are matched with keyword tags included in a set of condition-solution trees corresponding to the product. The solution keyword tag cloud for the product is generated based on the matching of the keywords identified in the question with the keyword tags included in the set of condition-solution trees corresponding to the product. The solution keyword tag cloud is presented in a graphical user interface display on a client device corresponding to the user.
    Type: Grant
    Filed: October 31, 2016
    Date of Patent: April 28, 2020
    Assignee: International Business Machines Corporation
    Inventors: Ching-Wei Cheng, Tzuching Kuo, June-Ray Lin, Yi Chun Tsai
  • Patent number: 10628528
    Abstract: A method for automated aspect-based sentiment analysis includes parsing reviews from a first domain to generate rhetorical structure trees and extracting rhetorical rules from the rhetorical structure trees, each rhetorical rule including a path extracted from at least one span in at least one of the rhetorical structure trees associated with a probability that the path corresponds to a positive or negative sentiment based on annotation data. The method further includes parsing reviews from a second domain to generate a second plurality of rhetorical structure trees, generating training data that associates at least one aspect in the review from the second domain with a sentiment associated with a rhetorical rule in the plurality of rhetorical rules, and training a classifier to identify sentiments in reviews from the second domain using the second plurality of reviews and the training data.
    Type: Grant
    Filed: June 22, 2018
    Date of Patent: April 21, 2020
    Assignee: Robert Bosch GmbH
    Inventors: Yifan He, Lin Zhao, Kui Xu, Zhe Feng
  • Patent number: 10629189
    Abstract: Arrangements relate to automatically taking notes in a virtual meeting. The virtual meeting has meeting content that includes a plurality of meeting content streams. One or more of the meeting content streams is in a non-text format. The one or more meeting content streams in a non-text format can be converted into text. As a result, the plurality of meeting content streams is in text format. The text of the plurality of meeting content streams can be analyzed to identify a key element within the text. Consolidated system notes that include the key element can be generated.
    Type: Grant
    Filed: March 17, 2014
    Date of Patent: April 21, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Edwin W. Peters, Sherry L. Platek, Nitty T. Pulikan, Balaji Ranganathan, Liviu Rodean, Balasubramanian Sivasubramanian, Eric Woods
  • Patent number: 10629188
    Abstract: Arrangements relate to automatically taking notes in a virtual meeting. The virtual meeting has meeting content that includes a plurality of meeting content streams. One or more of the meeting content streams is in a non-text format. The one or more meeting content streams in a non-text format can be converted into text. As a result, the plurality of meeting content streams is in text format. The text of the plurality of meeting content streams can be analyzed to identify a key element within the text. Consolidated system notes that include the key element can be generated.
    Type: Grant
    Filed: March 15, 2013
    Date of Patent: April 21, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Edwin W. Peters, Sherry L. Platek, Nitty T. Pulikan, Balaji Ranganathan, Liviu Rodean, Balasubramanian Sivasubramanian, Eric Woods
  • Patent number: 10628152
    Abstract: A device may receive information that identifies code associated with an application. The device may generate a technical description of the code based on the information that identifies the code associated with the application. The device may generate a set of rules based on the technical description of the code. The set of rules being associated with a semantics of business vocabulary and business rules (SBVR) format. The device may generate a set of microservices based on the set of rules. The device may provide information that identifies the set of microservices to cause an action to be performed.
    Type: Grant
    Filed: June 19, 2017
    Date of Patent: April 21, 2020
    Assignee: Accenture Global Solutions Limited
    Inventors: M. Chandramouli, Vidyasagar Honnappa, Nitin Madhukar Sawant, Pramod Bijani, Ravichandran Subramaniam, Satya Bharat
  • Patent number: 10628522
    Abstract: In an approach to rule and dictionary creation based on an improvement cycle, a computing device receives a corpus, wherein the corpus comprises textual data. The computing device stores, in a rule database, a rule based on a user input. The computing device stores, in a dictionary, one or more words based on the corpus. The computing device updates one or more of the rule database and the dictionary based on an improvement cycle comprising user selections from system-generated recommendations.
    Type: Grant
    Filed: June 27, 2016
    Date of Patent: April 21, 2020
    Assignee: International Business Machines Corporation
    Inventors: Satoshi Hosokawa, Shunsuke Ishikawa, Chikako Oyanagi, Yuichi Suzuki
  • Patent number: 10628529
    Abstract: Methods for determining whether two sets of words are similar are provided. In one aspect, a method includes receiving a first set of words and a second set of words, whichare subsets of a vocabulary, and each of the first and second sets of words include word embeddings corresponding to each word. The method also includes determining a word membership function for each word in the vocabulary. Determining the word membership includes determining a set of similarity values, each representing the similarity between the word and a respective word in the vocabulary. The method also includes determining a membership function for the first and second sets of words based on the determined word membership functions, and determining a set-based coefficient for the similarity between the first and second sets of words based on the membership function. Systems and devices are also provided.
    Type: Grant
    Filed: February 22, 2019
    Date of Patent: April 21, 2020
    Assignee: Babylon Partners Limited
    Inventors: Vitalii Zhelezniak, Alexsandar Savkov, Francesco Moramarco, Jack Flann, Nils Hammerla