PREDICTION PROGRAM, INFORMATION PROCESSING DEVICE, AND PREDICTION METHOD

    公开(公告)号:EP4365778A1

    公开(公告)日:2024-05-08

    申请号:EP23192145.3

    申请日:2023-08-18

    申请人: Fujitsu Limited

    发明人: UKAI, Takanori

    IPC分类号: G06N5/025 G06N5/046

    摘要: A prediction program including instructions which, when executed by a computer, cause the computer to perform processing that uses knowledge graph embedding, the processing including: determining whether or not graph data to be predicted is data that includes a node link that indicates a relationship between nodes not included in training data used for training of the knowledge graph embedding; specifying, in a case where it is determined that the graph data to be predicted is the data that includes the node link not included in the training data, graph data similar to the graph data to be predicted from the training data based on a result of embedding prediction for a label of a node included in the graph data to be predicted; and determining a prediction result for the graph data to be predicted based on the specified similar graph data.

    NETWORK DEVICE IDENTIFICATION
    4.
    发明公开

    公开(公告)号:EP4243362A1

    公开(公告)日:2023-09-13

    申请号:EP23150657.7

    申请日:2023-01-09

    申请人: Cujo LLC

    摘要: Network device identification is disclosed. A set of user devices in a computer network is selected (200) based on one or more selection criteria. A set of data attributes relating to at least two different data types is extracted (201) from network traffic data associated with each user device of a set of user devices. A cluster data set of one or more known device clusters is expanded (202) with the set of data attributes for generating an expanded cluster data set. One or more new device clusters is identified (203) from the expanded cluster data set of the one or more known device clusters by using similarity-based metrics and a weighting factor selected based on the data types of the set of data attributes, and one or more device identification rules is generated (205) based on the one or more new device clusters.

    METHOD, APPARATUS AND ELECTRONIC DEVICE FOR DETECTING DATA ANOMALIES, AND READABLE STORAGE MEDIUM

    公开(公告)号:EP4339845A1

    公开(公告)日:2024-03-20

    申请号:EP23197462.7

    申请日:2023-09-14

    发明人: FENG, Cheng QU, Ying

    摘要: Embodiments of the present invention disclose a method, an apparatus, an electronic device, and a readable storage medium for detecting data anomalies. The method comprises receiving data to be tested; matching the data to be tested with a data rule determined on the basis of historical data, the historical data having the same data type as the data to be tested, the data rule containing an antecedent predicate set and a consequent predicate set, wherein the intersection of the antecedent predicate set and the consequent predicate set is an empty set, the antecedent predicate set contains at least one antecedent predicate, and the consequent predicate set contains at least one consequent predicate; and, when the data to be tested satisfies all the antecedent predicates in the antecedent predicate set and fails to satisfy at least one consequent predicate in the consequent predicate set, determining that the data to be tested is anomalous due to failure to satisfy the data rule. With embodiments of the present invention, data anomalies are accurately detected, and reasons for the occurrence of anomalies are also interpretable.

    METHOD AND APPARATUS FOR KNOWLEDGE ANSWERING, METHOD AND APPARATUS FOR GENERATING KNOWLEDGE ANSWERING SYSTEM

    公开(公告)号:EP4160490A3

    公开(公告)日:2023-05-03

    申请号:EP22216308.1

    申请日:2022-12-23

    摘要: A method and an apparatus for knowledge answering, a method and an apparatus for generating a knowledge answering system relate to the fields of intelligent search, knowledge graph, and natural language processing. The method includes: receiving a user question entered by a client, and obtaining a target insurance rule matching the user question from a plurality of insurance rules; searching for an answer in an insurance knowledge graph based on the target insurance rule, in which the insurance knowledge graph is generated based on the plurality of insurance rules; and returning the answer to the client. Therefore, the insurance rule matching the user question is obtained from the plurality of insurance rules, and a more accurate answer is obtained by querying the insurance knowledge graph generated according to the insurance rules based on the matched insurance rule, and the more accurate answer is returned to the client.