利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

50 条记录 (耗时 0.03 秒)

    HYPOTHESIS SCORING METHOD BASED ON CAUSAL RELATIONSHIP
    21.
    发明公开
    HYPOTHESIS SCORING METHOD BASED ON CAUSAL RELATIONSHIP 审中-公开

    公开(公告)号：US20230229934A1

    公开(公告)日：2023-07-20

    申请号：US17579095

    申请日：2022-01-19

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Futoshi Iwama ,  Sachiko Yoshihama ,  Issei Yoshida ,  Naoto Sato

    IPC分类号： G06N5/02

    CPC分类号： G06N5/02

    摘要： A computer implemented method of hypothesis scoring based on causal relationships is provided. The computer implemented method includes creating a causal relationship model utilizing a plurality of hypotheses and a causal relationship between each of two or more pairs of hypotheses, and obtaining pro and con sentiment scores for each hypothesis utilizing a scoring function. The computer implemented method further includes assigning the obtained pro and con sentiment scores to each hypothesis in the causal relationship model, and propagating the pro and con sentiment scores from leaf hypotheses to a root hypothesis utilizing axioms to test the propagating scores for reasonableness. The computer implemented method further includes determining a final pro and con score for the root hypothesis, and presenting the final pro and con scores representing a prediction of the hypotheses to a user.

    OPTIMIZED DOCUMENT SCORE SYSTEM USING SENTENCE STRUCTURE ANALYSIS FUNCTION
    26.
    发明申请
    OPTIMIZED DOCUMENT SCORE SYSTEM USING SENTENCE STRUCTURE ANALYSIS FUNCTION 有权

    公开(公告)号：US20210271821A1

    公开(公告)日：2021-09-02

    申请号：US16806340

    申请日：2020-03-02

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Kohichi Kamijoh ,  Miki Ishikawa ,  Sachiko Yoshihama ,  Issei Yoshida ,  Yohei Ikawa

    IPC分类号： G06F40/30 ,  G06F40/253 ,  G06F40/166 ,  G06N20/00 ,  G06N5/04

    摘要： A method is provided for determining support of a hypothesis by opinion sentences. The method converts sentence structures in the opinion sentences using various sentence structure conversion methods to obtain converted opinion sentences. For each converted opinion sentence, the method calculates a difference between a proximity label value indicating proximity to the hypothesis and an intermediate score before and after a conversion, adopts the conversion responsive to a condition being met relative to the difference, and adopts the opinion sentence instead responsive to the condition being unmet. The method creates sub-opinions using the various methods applied to adopted conversions and opinion sentences, and obtains an intermediate score for each sub-opinion. The method represents an amount of support for the hypothesis by obtaining and displaying a final score for each adopted conversions and opinion sentences based on the intermediate scores for the sub-opinions and for adopted conversions and opinion sentences.

    EXTRACTING IMPORTANT SENTENCES FROM DOCUMENTS TO ANSWER HYPOTHESIS THAT INCLUDE CAUSES AND CONSEQUENCES
    27.
    发明申请
    EXTRACTING IMPORTANT SENTENCES FROM DOCUMENTS TO ANSWER HYPOTHESIS THAT INCLUDE CAUSES AND CONSEQUENCES 有权

    公开(公告)号：US20210209493A1

    公开(公告)日：2021-07-08

    申请号：US16737489

    申请日：2020-01-08

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Miki Ishikawa ,  Sachiko Yoshihama ,  Issei Yoshida ,  Kohichi Kamijoh

    IPC分类号： G06N5/04 ,  G06F40/49 ,  G06F40/44

    摘要： A method is provided for validating a hypothesis sentence. The method extracts, from a document database D using a hypothesis sentence that includes a causal part and a consequence part, a set D1 of documents related to the causal part. The method extracts, from set D1, a set S of sentences that include expressions of opinion. The method obtains a word list W of words that have a high co-occurrence in the set D1. The method selects, from the set S, a set S1 of sentences that are positionally close to any of the words in the word list W. The method selects, from the set S, a set S2 of sentences that are related to the words in the consequence part of the hypothesis. The method extracts and displays sentences included in both the set S1 and the set S2 as opinion sentences in relation to the hypothesis sentence.

    Method, computer program, and computer for classifying users of social media
    29.
    发明授权
    Method, computer program, and computer for classifying users of social media 有权

    公开(公告)号：US09996611B2

    公开(公告)日：2018-06-12

    申请号：US14775626

    申请日：2014-03-05

    申请人： International Business Machines Corporation

    发明人： Risa Kawanaka ,  Issei Yoshida

    IPC分类号： G06F17/30

    CPC分类号： G06F17/30705 ,  G06F17/30702

    摘要： A computer system and method to classify a plurality of users in a plurality of clusters in social media associating a text profile and text content with each user. The method comprises: generating a content feature vector for each of a portion of users on the basis of content associated with the portion of users; generating mapping the plurality of clusters, and the plurality of clusters and the portion of users, on the basis of the content feature vectors; generating a first profile feature vector for each of the plurality of clusters on the basis of the profiles associated with the portion of users mapped to each cluster; and classifying each of the other users excluding the portion of users in a plurality of clusters on the basis of the profiles associated with the other users and the first profile feature vectors.

    Database Access Using Partitioned Data Areas
    30.
    发明申请
    Database Access Using Partitioned Data Areas 审中-公开
    数据库访问使用分区数据区域

    公开(公告)号：US20150095344A1

    公开(公告)日：2015-04-02

    申请号：US14508579

    申请日：2014-10-07

    申请人： International Business Machines Corporation

    发明人： Kaoru Shinkawa ,  Issei Yoshida

    IPC分类号： G06F17/30 ,  G06F17/27

    CPC分类号： G06F16/22 ,  G06F16/278 ,  G06F16/83 ,  G06F17/2705

    摘要： Provided are techniques that ensure efficient database accesses by partitioning. The techniques includes a partition generating unit which generates a value partition in which a unit subtree including target data to be partitioned is separated and registered according to the target data, and a base partition which includes an index for uniquely identifying the unit subtree, an XML parser which identifies positions of a start to and an end tag defining an attribute value of the structured document and generates a cutting position list Corresponding to the hierarchical structure of the attribute value for registration in a storage area, an XML cutting unit which identifies the start tag position and the end tag position of the unit subtree to be cut, and separates the unit subtree and its index from the structured document, and a cut-XML registration unit which registers the unit subtree and the index in the separate partitions.

    摘要翻译： 提供了通过分区确保有效的数据库访问的技术。 该技术包括：分区生成单元，其生成根据目标数据分离包含要分割的目标数据的单位子树的单位子树的值分区，以及包含用于唯一地识别单位子树的索引的基本分区，XML 分析器，其识别定义结构化文档的属性值的开始和结束标签的位置，并生成切割位置列表对应于用于在存储区域中注册的属性值的分层结构的XML切割单元，其识别开始 标签位置和要切割的单位子树的结束标签位置，并将单位子树及其索引与结构化文档分离;以及切割XML注册单元，其将单位子树和索引登记在单独的分区中。