Natural Language Patents (Class 704/9)
  • Patent number: 10210866
    Abstract: Ambient assistance is described. An assistant device can detect speech in its environment and determine that the speech includes words or phrases of a local dictionary of the assistant device. The assistant device can then generate an interaction opportunity based on the words or phrases of the speech.
    Type: Grant
    Filed: May 18, 2017
    Date of Patent: February 19, 2019
    Assignee: ESSENTIAL PRODUCTS, INC.
    Inventors: Mara Clair Segal, Manuel Roman, Dwipal Desai, Andrew E. Rubin
  • Patent number: 10210249
    Abstract: Disclosed are system, method and computer program product for synthesis of natural-language text; receiving information objects; selecting among the received information objects information objects and an associated synthesis templates in a template library, each synthesis template including a template semantic-syntactic tree; generating for each selected information object a synthesis semantic-syntactic tree based on the template semantic-syntactic tree; and generating natural language text based on each generated synthesis semantic-syntactic tree.
    Type: Grant
    Filed: May 20, 2015
    Date of Patent: February 19, 2019
    Assignee: ABBYY PRODUCTION LLC
    Inventors: Anatoly Starostin, Dmitrii Kuklin
  • Patent number: 10210158
    Abstract: Exemplary embodiments relate to detecting, removing, and/or replacing objectionable words and phrases in a machine-generated translation. A classifier identifies translations containing target words or phrases. The classifier may be applied to the output translation to remove target words and phrases from the translation, or to prevent target words and phrases from being automatically presented. Further, the classifier may be applied to a translation model to prevent the target words and phrases from appearing in the output translation. Still further, the classifier may be applied to training data so that the translation model is not trained using the target words of phrases. The classifier may remove target words or phrases only when the target words or phrases appear in the output translation but not the source language input data. The classifier may be provided as a standalone service, or may be employed in the context of a machine translation system.
    Type: Grant
    Filed: June 24, 2016
    Date of Patent: February 19, 2019
    Assignee: FACEBOOK, INC.
    Inventors: Matthias Gerhard Eck, Priya Goyal
  • Patent number: 10204100
    Abstract: A computer-implemented method executed on a processor for lexicon extraction from non-parallel data is provided. The computer-implemented method includes representing each word of a plurality of words by a vector of documents in which the word appears, modeling each word as a topic distribution by using the vector of documents, receiving a first word in a source language, and finding a second word in a target language as a translation of the first word based on similarity of topic distributions of the first word and the second word.
    Type: Grant
    Filed: March 28, 2017
    Date of Patent: February 12, 2019
    Assignee: International Business Machines Corporation
    Inventor: Tengfei Ma
  • Patent number: 10204101
    Abstract: A computer-implemented method executed on a processor for lexicon extraction from non-parallel data is provided. The computer-implemented method includes representing each word of a plurality of words by a vector of documents in which the word appears, modeling each word as a topic distribution by using the vector of documents, receiving a first word in a source language, and finding a second word in a target language as a translation of the first word based on similarity of topic distributions of the first word and the second word.
    Type: Grant
    Filed: November 8, 2017
    Date of Patent: February 12, 2019
    Assignee: International Business Machines Corporation
    Inventor: Tengfei Ma
  • Patent number: 10200331
    Abstract: A method of obfuscating at least a portion of content of an email message may include identifying an email message that has been sent to one or more recipients and that pertains to one or more end user processes of a print environment, identifying a content section of the email message, and identifying one or more delimiters associated with the identified content section. The method involves determining whether the identified content section includes the delimiters, and if so, generating an obfuscated content section by obfuscating all content of the identified content section except the one or more identified delimiters. The method includes analyzing the obfuscated content section to ascertain information relevant to the one or more end user processes, and associating the ascertained information with one or more of the one or more end user processes.
    Type: Grant
    Filed: June 28, 2017
    Date of Patent: February 5, 2019
    Assignee: Xerox Corporation
    Inventor: Fritz Francis Ebner
  • Patent number: 10199123
    Abstract: In general, a computer-implemented method is described for receiving one or more requests to generate a medical study, retrieving from one or more data repositories one or more medical study instruments, receiving a selection of a particular medical study instrument to use in the medical study, generating by one or more computers a list of one or more research collaborators invited to review the medical study, and generating by one or more computers a list of one of more participants invited to join the medical study. Additionally, the computer-implemented method generates by one or more computer systems a data filter to format medical data from a first data format to a second data format, wherein the second data format complies with a third data format associated with one or more medical study instruments.
    Type: Grant
    Filed: June 11, 2014
    Date of Patent: February 5, 2019
    Assignee: Universal Research Solutions, LLC
    Inventor: Ali Adel Hussam
  • Patent number: 10198637
    Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.
    Type: Grant
    Filed: December 20, 2017
    Date of Patent: February 5, 2019
    Assignee: Facebook, Inc.
    Inventors: Du Le Hong Tran, Balamanohar Paluri, Lubomir Bourdev, Robert D. Fergus, Sumit Chopra
  • Patent number: 10198501
    Abstract: A computer-implemented method generates a candidate answer triple for use in retrieving information used to answer a question. One or more processors parse a question to identify a lexical answer type for the question, a question action for the question, and a question timestamp for the question to make up a question triple. One or more processors retrieve multiple candidate passages for answering the question, and parse each of the multiple candidate passages to identify a candidate entity, a candidate action, and a candidate timestamp from each of the multiple candidate passages to generate a candidate answer triple. One or more processors compare the question triple to the candidate answer triple and establish a match score for each candidate answer triple, which is used in retrieving information used to answer the question.
    Type: Grant
    Filed: September 28, 2016
    Date of Patent: February 5, 2019
    Assignee: International Business Machines Corporation
    Inventors: Kyle L. Croutwater, Vikrant Verma, Le Zhang, Zhe Zhang
  • Patent number: 10198431
    Abstract: For generating a word space, manual thresholding of word scores is used. Rather than requiring the user to select the threshold arbitrarily or review each word, the user is iteratively requested to indicate the relevance of a given word. Words with greater or lesser scores are labeled in the same way depending upon the response. For determining the relationship between named entities, Latent Dirichlet Allocation (LDA) is performed on text associated with the name entities rather than on an entire document. LDA for relationship mining may include context information and/or supervised learning.
    Type: Grant
    Filed: August 22, 2011
    Date of Patent: February 5, 2019
    Assignee: SIEMENS CORPORATION
    Inventors: Swapna Somasundaran, Dingcheng Li, Amit Chakraborty
  • Patent number: 10198506
    Abstract: A method, computer-readable medium, and a computer system for automatically generating sentiment data are disclosed. One or more portions of at least one document may be determined to be associated with at least one sentiment of one or more other portions of the at least one document. One or more scores associated with the at least one sentiment may be automatically determined based on at least one respective attribute of the one or more portions. The at least one respective attribute may include a positive category, a negative category, a neutral category, a degree associated with a positive sentiment, a degree associated with a negative sentiment, some combination thereof, etc. In this manner, data associated with sentiment of one or more portions of at least one document may be generated.
    Type: Grant
    Filed: April 20, 2012
    Date of Patent: February 5, 2019
    Assignee: Lexxe Pty Ltd.
    Inventor: Hong Liang Qiao
  • Patent number: 10191970
    Abstract: Methods and apparatus, including computer program products, implementing and using techniques for customized data parsing and paraphrasing. A communications module receives content from several resources. An analytics engine parses the content based on a user query for content. An artificial intelligence engine determines a confidence ranking for the parsed content and determines a set of prioritized parsed content from the parsed content, based on the confidence ranking for the parsed content. A natural language engine converts, using a natural language processing technique, the set of prioritized parsed content into a format for user interface. A user interface presents a summarized output including the converted set of prioritized parsed content based on information associated with the user query.
    Type: Grant
    Filed: August 19, 2015
    Date of Patent: January 29, 2019
    Assignee: International Business Machines Corporation
    Inventors: Trudy L. Hewitt, Zachary Satira, Nathan Stewart, Wilson Velez, Heidi D. Williams
  • Patent number: 10191975
    Abstract: Methods for classifying a point of view and diegesis are provided. A method can include providing a processor in operable communication with a computer-readable medium, receiving a narrative text, extracting a set of features from the narrative text, transmitting the features into a feature vector, transmitting a plurality of feature vectors to a support vector machine, predicting a point of view and diegesis for the narrative text associate with a particular feature vector, and annotating the narrative text.
    Type: Grant
    Filed: November 16, 2017
    Date of Patent: January 29, 2019
    Assignee: The Florida International University Board of Trustees
    Inventors: Joshua Daniel Eisenberg, Mark Finlayson
  • Patent number: 10193849
    Abstract: A system identifies unconnected content items of high quality and provides the unconnected content items for display to a user. The method comprises receiving several content items posted on pages of a social networking system. The system then determines a subset of those content items (e.g., high quality content items). A topic is then extracted from each of the subset of content items. The topic is mapped to one or more related pages of the social networking system that represent an expanded set of pages associated with the content item. For each of the related pages, a user is identified who is connected to the related page. Finally, the content item (e.g., a high quality content item) is provided to the user for display in the user's newsfeed.
    Type: Grant
    Filed: June 28, 2017
    Date of Patent: January 29, 2019
    Assignee: Facebook, Inc.
    Inventors: Gregory Joseph Klein, Bradley Ray Green, Jun Li, Jonathan Daniel Sorg
  • Patent number: 10185712
    Abstract: Embodiments relate to a system and a method for identifying, from contractual documents, (i) standard exact clauses matching clause examples and (ii) non-standard clauses semantically related to but not matching the clause examples. A standard feature data set comprising standard exact clauses matching clause examples is obtained. In addition, a mirror feature data set comprising semantically related clauses of the clause examples is obtained using semantic language analysis, where the mirror feature data set encompasses the standard feature data set. Non-standard clauses are obtained by extracting a difference between the mirror feature data set and the standard exact feature data set.
    Type: Grant
    Filed: October 2, 2017
    Date of Patent: January 22, 2019
    Assignee: Seal Software Ltd.
    Inventor: Kevin Gidney
  • Patent number: 10185709
    Abstract: Disclosed are various embodiments for creating and providing narratives associated with a type of subject (e.g., person, movie, place, etc.). Following a detected change in the system, a narrative template is selected based on a variety of factors. The template may provide variations of sentences based on the amount of data provided. Following the selection of the optimal narrative, fields in the selected template are filled with stored data associated with the subject. Some of the stored data may need to be translated prior to adding to the template depending on whether the selected narrative template is in a different language. The new or updated narrative may be stored in a memory. The system may encode a network page with the narrative and send the encoded network page to a client device.
    Type: Grant
    Filed: November 29, 2012
    Date of Patent: January 22, 2019
    Assignee: IMDB.COM, INC.
    Inventors: Rachel Jane MacTaggart, Adam Carlson, Simon Alexander Poole, Richard David Williams
  • Patent number: 10187761
    Abstract: A method and system enables converting Application-to-Person (A2P) messaging to Person-to-Person (P2P) messaging. Customer replies to short code A2P messages are diverted to alternate destinations in an enterprise. Enterprise destinations include call center operations and data enabled devices in various departments in an enterprise. Information collected from the reply messages can be used to determine the appropriate destination and can be used to analyze support and marketing statistics.
    Type: Grant
    Filed: November 29, 2017
    Date of Patent: January 22, 2019
    Assignee: SALESFORCE.COM, INC.
    Inventor: Eugene Lee Lew
  • Patent number: 10180989
    Abstract: Techniques for generating query language statements for a document repository are described herein. An example method includes detecting a search query corresponding to a document repository and generating a modified search query by adding atomic tags to the search query, the atomic tags being based on prior knowledge obtained by static analysis of the document repository and semantic rules. The method also includes generating enriched tags based on combinations of the atomic tags and any previously identified enriched tags and generating a first set of conditions based on combinations of the atomic tags and the generated enriched tags and generating a second set of conditions based on free-text conditions. The method also includes generating the query language statements based on the first set of conditions and the second set of conditions and displaying a plurality of documents from the document repository that satisfy the query language statements.
    Type: Grant
    Filed: July 24, 2015
    Date of Patent: January 15, 2019
    Assignee: International Business Machines Corporation
    Inventors: Yigal S. Dayan, Josemina M. Magdalen, Irit Maharian, Victoria Mazel, Oren Paikowsky, Andrei Shtilman
  • Patent number: 10180929
    Abstract: Systems and methods are disclosed for key phrase clustering of documents. In accordance with one implementation, a method is provided for key phrase clustering 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 identifying a plurality of clusters of segments from the plurality of segments, determining statistical significance of the plurality of clusters based at least on the statistical model and the content, and providing for display a representative cluster from the plurality of tokens, the representative cluster being determined based at least on the statistical significance. The method further includes determining a label for the representative cluster based at least on the plurality of clusters and the statistical significance.
    Type: Grant
    Filed: October 13, 2016
    Date of Patent: January 15, 2019
    Assignee: Palantir Technologies, Inc.
    Inventors: Max Kesin, Hem Wadhar
  • Patent number: 10181098
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating representations of input sequences. One of the methods includes obtaining an input sequence, the input sequence comprising a plurality of inputs arranged according to an input order; processing the input sequence using a first long short term memory (LSTM) neural network to convert the input sequence into an alternative representation for the input sequence; and processing the alternative representation for the input sequence using a second LSTM neural network to generate a target sequence for the input sequence, the target sequence comprising a plurality of outputs arranged according to an output order.
    Type: Grant
    Filed: June 4, 2015
    Date of Patent: January 15, 2019
    Assignee: Google LLC
    Inventors: Oriol Vinyals, Quoc V. Le, Ilya Sutskever
  • Patent number: 10182266
    Abstract: Systems and methods are described for automatically enabling subtitles based on a user profile when a language is spoken with an accent a user has difficulty understanding. For example, a media guidance application may detect a first plurality of user interactions of the user while the given language is being spoken with the accent. Based on the first plurality of interactions, the media guidance application may calculate a first value associated with a user specific level of difficulty indicating how difficult it is for the user to understand the language when spoken with the accent. If the first plurality of user interactions are not being performed again, the media guidance application may update the user specific difficulty with a second value that is lower than the first value. The media guidance application may automatically generate for display subtitles for a media asset based on the user specific level of difficulty.
    Type: Grant
    Filed: November 17, 2017
    Date of Patent: January 15, 2019
    Assignee: Rovi Guides, Inc.
    Inventors: Vishwas Sharadanagar Panchaksharaiah, Vikram Makam Gupta
  • Patent number: 10176889
    Abstract: A computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to receive a document having multiple section headers, segment the document into at least first and second sections based on the section headers, segment items in the first section into fragments and identify a section type for each of the fragments, determine that the identified section type for at least one of the fragments better matches a type of the second section than it matches a type of the first section, and re-locate the at least one of the fragments to the second section.
    Type: Grant
    Filed: February 9, 2017
    Date of Patent: January 8, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Alfredo Alba, Anni R. Coden, Clemens Drews, Daniel F. Gruhl, Neal R. Lewis, Pablo N. Mendes, Cartic Ramakrishnan, Joseph F. Terdiman
  • Patent number: 10176424
    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: February 3, 2017
    Date of Patent: January 8, 2019
    Assignee: DeepMind Technologies Limited
    Inventors: Ivo Danihelka, Danilo Jimenez Rezende, Shakir Mohamed
  • Patent number: 10168870
    Abstract: Annotations can be handled by a computer system that receives a query that specifies parameters for extraction of particular annotations from a set of annotations. Annotations include metadata that describes properties of the associated text fragment. A first entity subset, a second entity subset and a relations subset of annotations are extracted from an annotated text corpus. Contextual information relative to the extracted annotations is also extracted from the corpus. A user interface is generated to display frame elements that include the extracted annotations subsets and the extracted contextual information. In response to selections to the frame elements, the system receives input that specifies modifications to the annotations. Based on the input received, the set of annotations is modified in the annotated text corpus.
    Type: Grant
    Filed: May 19, 2016
    Date of Patent: January 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: Branimir K. Boguraev, Anthony T. Levas
  • Patent number: 10169484
    Abstract: Example methods and apparatus to manage process control search results are disclosed. A disclosed example method includes receiving a search parameter from a user via an application to view search results associated with the search parameter, determining a display context based on the application, searching a search index for control parameters that match the search parameter to form a set of matched control parameters, wherein the search index includes control parameters that correspond to runtime data generated by a controller within a process control system, and rendering the set of matched control parameters for display via the application as the search results based on the determined display context.
    Type: Grant
    Filed: September 23, 2010
    Date of Patent: January 1, 2019
    Assignee: FISHER-ROSEMOUNT SYSTEMS, INC.
    Inventors: Keith Richard Bellville, Bryan Michael Jones, John Mark Caldwell
  • Patent number: 10169453
    Abstract: A summary of a document is generated in near real time. In aspects, an indication to summarize the document is received and the document is processed to generate a summary. For instance, processing includes extracting sentences from the document and generating a plurality of candidate passages from the extracted sentences. Features are extracted from each of the plurality of candidate passages and each candidate passage is ranked based at least in part on the extracted features. High-ranking candidate passages are considered likely to be important and/or representative of the document. A summary of the document is generated including one or more of the high-ranking candidate passages. The summary includes portions of the document that are considered important and/or representative of the document, so a user may review the summary in lieu of reading the entire document.
    Type: Grant
    Filed: March 28, 2016
    Date of Patent: January 1, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Gang Luo, Qi Liu, Krishna Sravanthi Rajanala Sai, Dario Bigongiari, Qifa Ke, Oana Diana Nicolov, Srinivas Vadrevu
  • Patent number: 10169323
    Abstract: Embodiments herein include a natural language computing system that provides a diagnosis for a participant in the conversation which indicates the likelihood that the participant exhibited a symptom of autism. To provide the diagnosis, the computing system includes a diagnosis system that performs a training process to generate a machine learning model which is then used to evaluate a textual representation of the conversation. For example, the diagnosis system may receive one or more examples of baseline conversations that exhibit symptoms of autisms and those that do not. The diagnosis system may annotate and the baseline conversations and identify features that are used to identify the symptoms of autism. The system generates a machine learning model that weights the features according to whether the identified features are, or are not, an indicator of autism.
    Type: Grant
    Filed: September 23, 2015
    Date of Patent: January 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: Adam T. Clark, Brian J. Cragun, Anthony W. Eichenlaub, John E. Petri, John C. Unterholzner
  • Patent number: 10169353
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving at least one electronic document, and identifying one or more words, phrases, or patterns used within the electronic document and that are based on a lexicon. Mapping, using a concept library, the one or more words, phrases, or patterns to a concept intended to be conveyed by the one or more words, phrases, or patterns according to the lexicon. Generating concept data based on the mapping, and storing the concept data in association with data identifying the electronic document.
    Type: Grant
    Filed: October 29, 2015
    Date of Patent: January 1, 2019
    Assignee: United Services Automobile Association (USAA)
    Inventors: Timothy L. Riley, Barrington R. Young
  • Patent number: 10170104
    Abstract: Provided are an electronic device, a method and a training method for natural language processing. The electronic device for natural language processing includes a processor configured to: for each of words obtained by segmenting a sentence in a training data set, obtain an attention parameter representing correlation between the word and each of one or more words of other words in the sentence, where each of the words is represented by a real vector; and train, based on each of the words in the sentence, information on the attention parameter acquired for the word and label information of the sentence in the training data set, a neural network for sentence classification.
    Type: Grant
    Filed: January 5, 2017
    Date of Patent: January 1, 2019
    Assignee: SONY CORPORATION
    Inventors: Zhiwei Zhao, Youzheng Wu
  • Patent number: 10169471
    Abstract: Techniques for generating query language statements for a document repository are described herein. An example method includes detecting a search query corresponding to a document repository and generating a modified search query by adding atomic tags to the search query, the atomic tags being based on prior knowledge obtained by static analysis of the document repository and semantic rules. The method also includes generating enriched tags based on combinations of the atomic tags and any previously identified enriched tags and generating a first set of conditions based on combinations of the atomic tags and the generated enriched tags and generating a second set of conditions based on free-text conditions. The method also includes generating the query language statements based on the first set of conditions and the second set of conditions and displaying a plurality of documents from the document repository that satisfy the query language statements.
    Type: Grant
    Filed: April 28, 2016
    Date of Patent: January 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: Yigal S. Dayan, Josemina M. Magdalen, Irit Maharian, Victoria Mazel, Oren Paikowsky, Andrei Shtilman
  • Patent number: 10169456
    Abstract: A method, a system and a computer program product provide responses to inquiries residing within text processed by an application. An inquiry is identified within text being processed by the application, and a context of the identified inquiry is determined. One or more available data sources is searched to produce a series of responses to the identified inquiry, and the series of responses is evaluated to rank and determine an accuracy level value for each response. The ranked responses along with associated accuracy levels can be displayed.
    Type: Grant
    Filed: August 14, 2012
    Date of Patent: January 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: Al Chakra, John A. Feller, Trudy L. Hewitt, Francesco C. Schembari
  • Patent number: 10169330
    Abstract: A device may receive a set of first samples of textual content. A device may identify a set of clusters of first samples of the set of first samples. A device may identify a pattern of occurrence based on the set of clusters. The pattern of occurrence to identify two or more clusters, of the set of clusters, based on an order in which first samples associated with the two or more clusters were generated or received. A device may receive one or more second samples of textual content. A device may determine that the one or more second samples are semantically similar to one or more corresponding clusters associated with the pattern of occurrence. A device may identify a predicted sample based on the pattern of occurrence and the one or more corresponding clusters. A device may perform an action based on identifying the predicted sample.
    Type: Grant
    Filed: December 6, 2016
    Date of Patent: January 1, 2019
    Assignee: Accenture Global Solutions Limited
    Inventors: Janardan Misra, Divya Rawat, Milind Savagaonkar, Sanjay Podder
  • Patent number: 10169335
    Abstract: Embodiments described herein provide approaches for validating synonyms in ontology driven natural language processing. Specifically, an approach is provided for receiving a user input containing a token, structuring the user input into a semantic model comprising a set of classes each containing a set of related permutations of the token, designating the token as a synonym of one of the set of related permutations, annotating the token with a class from the set of classes corresponding to the one of the set of related permutations, and validating the annotation of the token by determining an accuracy of the designation of the token as a synonym of the one of the set of related permutations. In one embodiment, the accuracy is determined by quantifying a linear distance between the token and a contextual token also within the user input, and comparing the linear distance to a pre-specified linear distance limit.
    Type: Grant
    Filed: April 5, 2016
    Date of Patent: January 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: Stephen J. Edwards, Ahmed M. Nassar, Craig M. Trim, Albert T. Wong
  • Patent number: 10169490
    Abstract: Query disambiguation can include identifying, a first set of word clusters in a first candidate answer generated in response to a first input query for a question-answering system. Each of the first set of word clusters can be classified according to a syntactic element of a first set of syntactic elements. Query disambiguation can include identifying, in the first input query, a second set of word clusters. Each of the second set of word clusters can be classified according to a syntactic element of a second set of syntactic elements. Query disambiguation can include determining that the first word cluster is classified according to a first syntactic element that is not present in the second set of syntactic elements and generating a second input query using the first input query and the first word cluster.
    Type: Grant
    Filed: September 24, 2015
    Date of Patent: January 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: Corville O. Allen, Claire L. Kohler
  • Patent number: 10169733
    Abstract: A method, system and computer program product for improving management and performance of an employee. An indication of a goal sponsored by an owner, such as a manager, is received. After receiving an indication of a user subscribing to the goal sponsored by the owner, communications (e.g., posts) on the social network involving the subscribed user that include a tag designating the goal may be monitored. Upon detecting a completion of the goal by the subscribed user in the monitored communications, a pattern of steps (e.g., “prepare,” “review” and “finish”) to accomplish the goal is determined based on the monitored communications. The pattern may then be used to recommend actions to other users subscribed to the goal concerning accomplishing the goal based on the pattern. Furthermore, the owner may receive indications as to the progress of the user in accomplishing the goal based on the pattern.
    Type: Grant
    Filed: October 28, 2015
    Date of Patent: January 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: Paul R. Bastide, Matthew E. Broomhall, Sean Callanan, Sandra L. Kogan
  • Patent number: 10169452
    Abstract: A computer-implemented method includes receiving a search label and accessing a hierarchical data source comprising a plurality of nodes. One node may be a context node. The method further includes determining a similarity score between the search label and a node label of each node, determining a contextual score between the context node and each node, combining, for each node, the similarity score with the contextual score to yield a combined score, and returning a result. The result may be based on ordering the plurality of nodes according to each node's combined score. A corresponding computer program product and computer system are also disclosed.
    Type: Grant
    Filed: June 30, 2015
    Date of Patent: January 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: James P. Boland, David M. Doran, Niketh J. Kala, Junaid Y. A. Mohammed
  • Patent number: 10162817
    Abstract: Creation data can be received from a computer-readable developer profile, with the creation data including instructions to create a messaging bot. A messaging bot definition can be generated using the instructions, and a messaging bot may be executed using the definition. The instructions may include natural language instructions defining one or more messaging bot characteristics. The natural language instructions can be matched with one or more commands to include one or more characteristics in the messaging bot, and instructions for those characteristic(s) can be included in the messaging bot definition. The instructions can be instructions that are not in a computer programming language, and they can be instructions to create one or more general messaging bot characteristics configured to be implemented with a specific dialog structure that defines one or more specific natural language dialog scripts.
    Type: Grant
    Filed: June 14, 2016
    Date of Patent: December 25, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Benny Schlesinger, Hen Fitoussi, Avichai Cohen, Yuval Pinchas Borsutsky, Eldar Cohen, William Ramsey, Delia Koren
  • Patent number: 10162885
    Abstract: A method for providing information to a user in response to a received user query. A natural language analysis generates substrings relevant to an input user query pertaining to a problem a user experiences with a product or service. An ontology analysis outputs: terms of an ontology matching the relevant generated substrings; and relationships between the terms. Elements of a perfect or complete query are captured and include information pertaining to the user's problem. The input user query is refined based on the outputted terms and relationships between the terms. A search query is performed, based on the refined user query. The results of the search are provided to the user.
    Type: Grant
    Filed: May 29, 2018
    Date of Patent: December 25, 2018
    Assignee: International Business Machines Corporation
    Inventors: Eniko I. Rozsa, Homa Javahery, Paul Alan Yamamoto, Peter C. Boyle
  • Patent number: 10162823
    Abstract: Methods and apparatus for populating a contact entry of a user based on information obtained from one or more sources that are external to the contact entry. Some implementations are directed generally to analyzing text of a document associated with the user to identify contact information in the document. In some versions of those implementations, an affinity measure associated with the document may be determined that is indicative of an amount of interest of the user in the document and a contact entry may be populated with one or more aspects of the contact information based on the affinity measure satisfying a threshold.
    Type: Grant
    Filed: May 17, 2017
    Date of Patent: December 25, 2018
    Assignee: GOOGLE LLC
    Inventors: Bryan Christopher Horling, Okan Kolak, Rosa Wu
  • Patent number: 10163227
    Abstract: A computer-implemented method is provided for retrieving an image from a user in a desired format and for detecting a compression efficiency for the image. When the compression efficiency is above a pre-selected threshold the computer-implemented method includes obtaining a saliency representation of the image, capturing a feature description of a non-salient portion of the image, flattening the non-salient portion in a new image, storing the new image in a selected format in a memory and storing a background descriptor for the image in the memory.
    Type: Grant
    Filed: December 28, 2016
    Date of Patent: December 25, 2018
    Assignee: SHUTTERSTOCK, INC.
    Inventors: Kevin Scott Lester, Nathan Hurst, Michael Ranzinger
  • Patent number: 10162887
    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: April 10, 2017
    Date of Patent: December 25, 2018
    Assignee: PALANTIR TECHNOLOGIES INC.
    Inventors: Max Kesin, Hem Wadhar
  • Patent number: 10162814
    Abstract: The present invention provides a conversation processing method, a conversation management system and a computer device. The method comprises: acquiring task-related user requirement data; updating a user conversation state based on the user requirement data and a pre-configured task-related task parameter; generating at least one piece of candidate action data according to the user conversation state; and generating response text data according to the at least one piece of candidate action data. The expandability of the conversation management system is improved by customizing the conversion service related to the task in the conversation system.
    Type: Grant
    Filed: October 21, 2015
    Date of Patent: December 25, 2018
    Assignee: Baidu Online Network Technology (Beijing) Co., Ltd.
    Inventors: Zengtao Jiao, Guanchun Wang
  • Patent number: 10157615
    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: March 8, 2018
    Date of Patent: December 18, 2018
    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: 10157177
    Abstract: A method for entity extraction within an electronic document including executing by a computer processor a conditional random field algorithm stored on a computer readable medium to generate a conditional random field model; the conditional random field algorithm having an input including one or more training text documents; executing by a computer processor an entity extraction algorithm stored on a computer readable medium to generate an entity extraction model; the entity extraction algorithm having an input including the same one or more training text documents input into the conditional random field algorithm; applying by a computer processor the conditional random field model to at least one electronic document; wherein application of the conditional random field model returns a list of passages in the at least one electronic document having an entity; applying by a computer processor the entity extraction model to the at least one electronic document; wherein application of the entity extraction model
    Type: Grant
    Filed: October 28, 2016
    Date of Patent: December 18, 2018
    Assignee: KIRA INC.
    Inventors: Robert Henry Warren, Alexander Karl Hudek
  • Patent number: 10157174
    Abstract: A method, system or computer usable program product for utilizing a dialectical model for providing an answer to a user query including receiving, by a system, a natural language query from a user; applying, by the system, natural language processing (NLP) to the query to generate a first set of NLP structures; generating, by the system, a contrary set of NLP structures which represent an opposite polarity query to the user query; evaluating, by the system, the first set of NLP structures to identify a first set of evidence for candidate answers; evaluating, by the system, the contrary set of NLP structures to identify a second set of evidence for candidate answers; evaluating, by the system, a first set of hypotheses from the first set of NLP structures based on the first set of evidence for candidate answers, and a contrary set of hypotheses from the contrary set of NLP structures based on the second set of evidence for candidate answers, to determine a set of answers to the user query; converting, by the s
    Type: Grant
    Filed: May 21, 2017
    Date of Patent: December 18, 2018
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Donna K. Byron, Ashok Kumar, Mary D. Swift
  • Patent number: 10158583
    Abstract: A method and apparatus for scaling a VNF on a first PoP associated with at least one wireless device (WD) to a second PoP. A probabilistic estimate of a likelihood that the WD(s) will be handed over to at least one candidate PoP is generated and a VNF state associated with such candidate(s) is scaled and populated with state context information related to a handover of the WD(s) from the first PoP to the candidate(s). The second PoP is identified from the candidate(s) prior to handover using the probabilistic estimate. Thereafter the VNF is scaled from the first PoP to the second PoP, followed by handover of the WD(s) from the first PoP to the second PoP.
    Type: Grant
    Filed: March 17, 2016
    Date of Patent: December 18, 2018
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Jaya Rao, Xu Li
  • Patent number: 10157175
    Abstract: Techniques are described for modeling information from a data source. In one example, a method for modeling information from a data source includes comparing, with one or more computing devices, a data item heading from the data source with concept keywords in a concept library, the concept library comprising a plurality of concepts and one or more of the concept keywords in at least one language associated with each of one or more of the concepts. The method further includes identifying, with one or more computing devices, one or more matches between the data item heading and one or more concept keywords associated with a particular concept from among the concepts comprised in the concept library. The method further includes identifying, with one or more computing devices, the data item heading as being associated with the particular concept.
    Type: Grant
    Filed: March 15, 2013
    Date of Patent: December 18, 2018
    Assignee: International Business Machines Corporation
    Inventors: Robin N. Grosset, Mohsen Rais-Ghasem, Graham A. Watts, Qing Wei
  • Patent number: 10146751
    Abstract: System and methods for creating structured or semi-structured representations of information extracted from unstructured text data sources are described. In some embodiments, without requiring a predefined target data structure, the methods identify the grammatical and semantic attributes and context information in a text content, and create object-properties association data as knowledge and information extracted from the unstructured data, and represent such information in a structured or semi-structured format to facilitate search and trend analysis. In some other embodiments, the methods identify the types of information contained in the unstructured data, and for a pre-defined target information type, the methods identify the context and content of the portion of the text that represents the target information type, and extract the text, attach a tag or label to the extracted text, and store or display the data in a database table format or xml format for further pattern and trend analysis.
    Type: Grant
    Filed: December 7, 2015
    Date of Patent: December 4, 2018
    Inventor: Guangsheng Zhang
  • Patent number: 10146395
    Abstract: Techniques described herein provide quality of experience (QoE) diagnosis and analysis for wireless communications. Implementations include generating, by a user device, a user interaction event. The user device may obtain data associated with one or more QoE metrics, and cause analysis on the data associated with the one or more metrics to identify QoE issues.
    Type: Grant
    Filed: March 26, 2015
    Date of Patent: December 4, 2018
    Assignee: T-Mobile USA, Inc.
    Inventors: Jie Hui, Qi Chen, Haokun Luo, Kevin Lau, Karthik Iyer, Kranthi Sontineni
  • Patent number: 10147050
    Abstract: Methods to provide selective supporting evidence processing by applying a first machine learning (ML) model to a first candidate answer to generate a first confidence score that does not consider supporting evidence for the first candidate answer, determining, from a second ML model, an expected contribution of processing supporting evidence for the first candidate answer, and upon determining that the expected contribution does not exceed a specified threshold, skipping supporting evidence processing for the first candidate answer.
    Type: Grant
    Filed: September 22, 2015
    Date of Patent: December 4, 2018
    Assignee: International Business Machines Corporation
    Inventors: Michael W. Britt, Adam C. Lange-Pearson, Thomas P. Pitzen, Richard J. Stevens