知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

246 条记录 (耗时 0.032 秒)

    INFORMATION SEARCHING SYSTEM AND INFORMATION SEARCHING METHOD
    1.
    发明申请
    INFORMATION SEARCHING SYSTEM AND INFORMATION SEARCHING METHOD 审中-公开

    公开(公告)号：US20190251201A1

    公开(公告)日：2019-08-15

    申请号：US16140683

    申请日：2018-09-25

    申请人： Hitachi, Ltd.

    发明人： Kentaro CHIGUSA ,  Masashi TSUCHIDA

    IPC分类号： G06F17/30

    CPC分类号： G06F16/338 ,  G06F16/3334 ,  G06F16/353 ,  G06F16/93

    摘要： An information searching system 1 includes a conversation-history storage unit T11 configured to store conversation histories for inquiries, a conversation-history acquisition unit P132 configured to acquire, from the conversation-history storage unit T11, a predetermined conversation history corresponding to a search query based on input information, a search-query amendment unit P114 configured to amend the search query on the basis of the predetermined conversation history, and a searching unit P115 configured to search, on the basis of the amended search query, the conversation histories stored in the conversation-history storage unit T11 and output a search result.

    DISAMBIGUATING CONCEPTS IN NATURAL LANGUAGE
    3.
    发明申请
    DISAMBIGUATING CONCEPTS IN NATURAL LANGUAGE 审中-公开

    公开(公告)号：US20180329885A1

    公开(公告)日：2018-11-15

    申请号：US15594829

    申请日：2017-05-15

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： BRENDAN BULL ,  PAUL LEWIS FELT

    IPC分类号： G06F17/27 ,  G06F17/30

    CPC分类号： G06F17/2785 ,  G06F16/00 ,  G06F16/3334 ,  G06F16/3347 ,  G10L15/18 ,  G10L15/1815

    摘要： A computer receives a plurality of text and determines a concept is present in the plurality of text. The computer determines a set of hypotheses for the determined concept, wherein the set of hypotheses is a plurality of natural language representations of the determined concept. The computer substitutes the determined concept in the plurality of text with a hypothesis from the determined set of hypotheses. The computer determines the hypothesis is valid based on analyzing the plurality of text with a neural network, wherein the neural network is trained for hypothesis validation. Based on determining that the hypothesis is valid, the computer storing the plurality of text with the determined hypothesis in place of the substituted concept and displays the stored plurality of text.

    SYSTEMS AND METHODS FOR PARAGRAPH-BASED DOCUMENT SEARCHING
    4.
    发明申请
    SYSTEMS AND METHODS FOR PARAGRAPH-BASED DOCUMENT SEARCHING 审中-公开

    公开(公告)号：US20180268067A1

    公开(公告)日：2018-09-20

    申请号：US15984714

    申请日：2018-05-21

    申请人： LexisNexis, a division of Reed Elsevier Inc.

    发明人： Paul Zhang ,  David Steiner

    IPC分类号： G06F17/30

    CPC分类号： G06F16/9535 ,  G06F16/24578 ,  G06F16/3334 ,  G06F16/334

    摘要： Computer programs for searching a collection of electronic documents are disclosed. A computer program for searching a collection of electronic documents, includes instructions that cause the computer to carry out steps of: replacing a set of synonymous terms appearing in a paragraph with a set of standardized paragraph terms, where each standardized paragraph term has an associated term weight and generating standardized search terms in response to a search query, generating paragraph scores for paragraphs of a document based at least in part on the associated weights of standardized paragraph terms that match one or more of the standardized search terms. The computer program further includes determining overall document scores for the electronic documents based at least in part on a combination of the paragraph scores, and determining a set of matching documents, wherein the set of matching documents is ordered using the overall document scores.

    EXPERT STANCE CLASSIFICATION USING COMPUTERIZED TEXT ANALYTICS
    5.
    发明申请
    EXPERT STANCE CLASSIFICATION USING COMPUTERIZED TEXT ANALYTICS 审中-公开

    公开(公告)号：US20180260476A1

    公开(公告)日：2018-09-13

    申请号：US15453918

    申请日：2017-03-09

    申请人： International Business Machines Corporation

    发明人： Roy Bar-Haim ,  Noam Slonim ,  Orith Toledo-Ronen

    IPC分类号： G06F17/30

    CPC分类号： G06F16/353 ,  G06F16/31 ,  G06F16/3334 ,  G06F16/334 ,  G06F16/93 ,  G06F16/9566 ,  G06F17/27

    摘要： A computerized text analysis method that comprises: searching a resource of information with a search query comprising at least one of: (a) the specific debatable topic, and (b) a personal derivation of the specific debatable topic, to obtain a list of indices whose index subject contains the personal derivation and/or the specific debatable topic; determining, by applying a rule-based classifier, whether the index subject of each of the indices is (i) in favor of the debatable topic or (ii) against the debatable topic; detecting, in each of the indices, hyperlinks to encyclopedic entries whose entry subjects are person names; and determining that: if the index subject of each of the one or more indices is in favor of the specific debatable topic, then the persons are in favor of the specific debatable topic, and vice versa.

    Method and apparatus for searching using an active ontology
    6.
    发明授权
    Method and apparatus for searching using an active ontology 有权

    公开(公告)号：US10002189B2

    公开(公告)日：2018-06-19

    申请号：US12341743

    申请日：2008-12-22

    申请人： Adam Cheyer

    发明人： Adam Cheyer

    IPC分类号： G06F17/30

    CPC分类号： G06F16/367 ,  G06F16/3334 ,  G06F16/334

    摘要： Embodiments of the present invention provide a method and apparatus for searching using an active ontology. One embodiment of a method for searching a database includes receiving a search string, where the search string comprises one or more words, generating a semantic representation of the search string in accordance with an ontology, searching the database using the semantic representation, and outputting a result of the searching.

    SEARCH METHOD AND APPARATUS
    8.
    发明申请
    SEARCH METHOD AND APPARATUS 审中-公开

    公开(公告)号：US20180137195A1

    公开(公告)日：2018-05-17

    申请号：US15534373

    申请日：2015-11-30

    申请人： Baidu Online Network Technology (Beijing) Co. Ltd.

    发明人： Hongjian Zou ,  Gaolin Fang ,  Jun Cheng

    IPC分类号： G06F17/30

    CPC分类号： G06F16/3349 ,  G06F16/3334 ,  G06F16/3338

    摘要： A search method and apparatus. A specific embodiment of the search method includes: finding a set of first time-effective search queries from a search log; selecting search queries meeting one of the following selection requirements as candidate time-effective search queries: included in the search log and semantically associated with the first time-effective search queries in the set of first time-effective search queries; included in the search log and containing a combination of preset keywords; processing the candidate time-effective search queries to obtain second time-effective search queries; performing search with a second time-effective search query, when a search query entered by the user matches the second time-effective search query. The present disclosure achieves obtaining the second time-effective search queries from the search queries of the search log based on the identified first time-effective search queries, thus raising the identification recall rate and further improving the identification effect of the time-effective search queries, on the condition that the identification accuracy is ensured in the identification process of the time-effective search queries.

    ARTIFICIAL INTELLIGENCE METHOD AND APPARATUS
    9.
    发明申请
    ARTIFICIAL INTELLIGENCE METHOD AND APPARATUS 审中-公开

    公开(公告)号：US20180107940A1

    公开(公告)日：2018-04-19

    申请号：US14195826

    申请日：2014-03-03

    申请人： Jeremy Lieberman

    发明人： Jeremy Lieberman

    IPC分类号： G06N99/00 ,  G06F17/30 ,  G06F7/24

    CPC分类号： G06N20/00 ,  G06F7/24 ,  G06F16/3334 ,  G06F16/338 ,  G06F16/35 ,  G06F16/367 ,  G06F16/93 ,  G06F16/951 ,  G06N5/022

    摘要： The invention entails a method of Etiological prioritization based on an original symbolic model of the causative construction of singular logical relations which are built from an initiation of sensed masses in patterns, the naming of sensed patterns into words, the description of the relations of masses using specific English language primitives, the relations between masses and words, and the relations between primitive words. This process is built upon a theory and model of discretized human capabilities and learned experiential meanings. Human capabilities and learned experiential meanings are identified as singular primitives and amount to words identified and matched to singular parts that make up human capabilities and the inventive model of the experiences of the sensing and understanding of the spatiotemporal physical world. Continued etiological development of the inventive model entails new primitive meanings being built via the combination of the inventive model of the primitives of human capabilities with the inventive model of the primitives not representing human capabilities. The method of etiological prioritization is used to create the inventive model of the definitions of many hundreds of English language words and is applied to the explication of specialized domains of knowledge. In accordance with the invention, the method may comprise identifying a plurality of primitive words in a first group, where the primitive words in the first group have a singular meaning. The plurality of primitive words in the first group having a singular meaning are stored at a first set of storage locations in a computing device. A plurality of primitive words in a second group are identified. The plurality of primitive words in the second group have associated meanings which may be defined by the primitive words in the first group and/or other primitive words in the second group. The plurality of primitive words in the second group are stored at a second set of storage locations in a computing device. For each of the primitive words in the second group, its respective associated meanings are stored as definitional linking information, linking a respective primitive word to respective defining primitive words in the first group and/or other primitive words in the second group, whereby upon the identification of any word, a definition comprising linked primitive words may be retrieved. For each of a plurality of definable words, wherein the definable words are selected from the first and second groups, one selects words from the first and second groups as relative words having substantially the same meaning as its respective definable word, and/or associates words in the first and second groups into respective relative phrases having substantially the same meaning as its respective definable word, each of the definable words, together with its respective relative words and relative phrases forming a relative set. For each of the definable words, relative set linking information linking each of the definable words to its respective relative words and relative phrases is stored, whereby upon the identification of any word, the other members of a relative set may be retrieved.