知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

91 records (took 0.113 seconds)

    Identifying a stale data source to improve NLP accuracy
    71.
    发明授权
    Identifying a stale data source to improve NLP accuracy 有权

    公开(公告)号：US10394863B2

    公开(公告)日：2019-08-27

    申请号：US13796616

    申请日：2013-03-12

    Applicant: International Business Machines Corporation

    Inventor： Adam T. Clark ,  Joel C. Dubbels ,  Jeffrey K. Huebert ,  John E. Petri

    IPC: G06F16/33 ,  G06F17/27

    Abstract: In some NLP systems, queries are compared to different data sources stored in a corpus to provide an answer to the query. However, the best data sources for answering the query may not currently be contained within the corpus or the data sources in the corpus may contain stale data that provides an inaccurate answer. When receiving a query, the NLP system may evaluate the query to identify a data source that is likely to contain an answer to the query. If the data source is not currently contained within the corpus, the NLP system may ingest the data source. If the data source is already within the corpus, however, the NLP may determine a time-sensitivity value associated with at least some portion of the query. This value may then be used to determine whether the data source should be re-ingested—e.g., the information contained in the corpus is stale.

    Identifying a stale data source to improve NLP accuracy
    72.
    发明授权
    Identifying a stale data source to improve NLP accuracy 有权

    公开(公告)号：US10387468B2

    公开(公告)日：2019-08-20

    申请号：US13804734

    申请日：2013-03-14

    Applicant: International Business Machines Corporation

    Inventor： Adam T. Clark ,  Joel C. Dubbels ,  Jeffrey K. Huebert ,  John E. Petri

    IPC: G06F16/33 ,  G06F17/27

    Abstract: In some NLP systems, queries are compared to different data sources stored in a corpus to provide an answer to the query. However, the best data sources for answering the query may not currently be contained within the corpus or the data sources in the corpus may contain stale data that provides an inaccurate answer. When receiving a query, the NLP system may evaluate the query to identify a data source that is likely to contain an answer to the query. If the data source is not currently contained within the corpus, the NLP system may ingest the data source. If the data source is already within the corpus, however, the NLP may determine a time-sensitivity value associated with at least some portion of the query. This value may then be used to determine whether the data source should be re-ingested—e.g., the information contained in the corpus is stale.

    Managing answer feasibility
    73.
    发明授权
    Managing answer feasibility 有权

    公开(公告)号：US10347147B2

    公开(公告)日：2019-07-09

    申请号：US14739022

    申请日：2015-06-15

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Adam T. Clark ,  Jeffrey K. Huebert ,  Aspen L. Payton ,  John E. Petri

    IPC: G09B7/02 ,  G06F17/27 ,  G09B7/00 ,  G06F16/332

    Abstract: A system, a method, and a computer program product for managing answer feasibility in a Question and Answering (QA) system. A set of candidate situations is established. The set of candidate situations corresponds to a first set of answers. A QA system establishes the set of candidate situations by analyzing a corpus. The first set of answers will answer a question. The QA system identifies a subset of the set of candidate situations. The subset of candidate situations corresponds to a portion of contextual data. The portion of contextual data is from a set of contextual data. The set of contextual data relates to the question. The question-answering system determines a set of answer feasibility factors. The set of answer feasibility factors is determined using the subset of candidate situations. The set of answer feasibility factors indicates the feasibility of the answers in the first set of answers.

    Conversational list management
    74.
    发明授权
    Conversational list management 有权

    公开(公告)号：US10282417B2

    公开(公告)日：2019-05-07

    申请号：US15048057

    申请日：2016-02-19

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Adam T. Clark ,  Jeffrey K. Huebert ,  Aspen L. Payton ,  John E. Petri

    IPC: G06F17/20 ,  G06F17/27 ,  G10L15/00 ,  G10L21/00 ,  G10L25/00 ,  G06F17/30

    Abstract: Software that generates list items from user conversations by performing the following operations: (i) capturing natural language statement(s) spoken by a first user; (ii) converting the natural language statement(s) to text; (iii) performing a natural language processing (NLP) analysis of the text to identify a first list item, wherein the first list item includes one or more words in the text that are likely to be included in a list associated with the first user; and/or performing a first list action utilizing the first list item based, at least in part, on the performed NLP analysis, wherein the first list action includes modifying a first list associated with the first user.

    Structuring narrative blocks in a logical sequence
    75.
    发明授权
    Structuring narrative blocks in a logical sequence 有权

    公开(公告)号：US10248738B2

    公开(公告)日：2019-04-02

    申请号：US14957647

    申请日：2015-12-03

    Applicant: International Business Machines Corporation

    Inventor： Adam T. Clark ,  Jeffrey K. Huebert ,  Aspen L. Payton ,  John E. Petri

    IPC: G06F17/30 ,  G06F17/27

    Abstract: A computer system may obtain a first knowledge graph that was generated based on a work of authorship having a plurality of narrative blocks. The computer system may identify target narrative blocks, which are narrative blocks that include a target concept. The computer system may also identify related background narrative blocks. The computer system may receive a narrative path for the target concept. The narrative path may include the target narrative blocks and the related background narrative blocks ordered in a sequence that is consistent with their order in the work of authorship. The computer system may output the narrative path to an output device coupled with the computer system.

    Dynamically forming and executing application programming interface pipelines
    78.
    发明授权
    Dynamically forming and executing application programming interface pipelines 有权

    公开(公告)号：US09823950B1

    公开(公告)日：2017-11-21

    申请号：US15237756

    申请日：2016-08-16

    Applicant: International Business Machines Corporation

    Inventor： Scott R. Carrier ,  Robert E. Goff ,  Jeffrey K. Huebert ,  Jennifer L. La Rocca

    IPC: G06F9/54 ,  G06F9/445

    CPC classification number: G06F9/543 ,  G06F9/44505 ,  G06F9/541

    Abstract: An embodiment of the present executes a sequence of a plurality of application programming interfaces. Request objects are generated for the application programming interfaces of the sequence. Each request object is generated in accordance with a common object model. Execution of each application programming interface is enabled in an order of the sequence to process a corresponding request object and generate a corresponding response object containing results. Each response object is generated in accordance with the common object model and includes information from the corresponding request object aggregated with the results. Further, each request object for a succeeding application programming interface in the sequence includes the aggregated information from a response object of a prior executed application programming interface in the sequence.

Patent Agency Ranking