公开(公告)号：GB2605723B

公开(公告)日：2024-12-11

申请号：GB202208933

申请日：2020-10-20

Applicant: IBM

Inventor： WAN WAN MIAO ,  KUN YAN YIN ,  JIAN GONG WANG ,  YAN HU ,  LIAN NA WANG

IPC: G06V20/40 ,  G06F16/75 ,  G06F16/783 ,  G06V10/40

Abstract: A system, method, and computer program product for segmenting videos. The system includes at least one processing component, at least one memory component, a video, an extraction component, and a graphing component. The extraction component is configured to extract image and text data from the video, identify entities in the image data, assign at least one entity relation to the entities in the image data, identifying entities in the text data, and assign at least one entity relation to the entities in the text data. The graphing component is configured to generate an image knowledge graph for the entity relations assigned to the entities in the image data, generate a text knowledge graph for the entity relations assigned to the at least two entities in the text data, and generate a weighted knowledge graph based on the image and text knowledge graphs.

公开(公告)号：GB2583679A

公开(公告)日：2020-11-04

申请号：GB202011326

申请日：2018-11-20

Applicant: IBM

Inventor： XIN TANG ,  KUN YAN YIN ,  HE LI ,  XUELIANG ZHAO ,  XIN XU

IPC: G06F16/95

Abstract: An approach is provided for searching multilingual documents. Structure components are extracted from multilingual documents. Based on the extracted components, the documents are grouped into classifications including respective sets of documents expressed in different respective natural languages. A natural language in a query is detected. One of the documents is selected based on the document having content indicated by the query and the natural language of the document matching the detected natural language. Structure components of the selected document are extracted. Based on the extracted structure components of the selected document, one of the classifications is identified as including the selected document. Other document(s) in the classification are identified and presented as having content that matches the content of the selected document. The natural language(s) of the other document(s) are each different from the natural language of the selected document.

公开(公告)号：GB2597166A

公开(公告)日：2022-01-19

申请号：GB202115690

申请日：2020-04-02

Applicant: IBM

Inventor： ZHONG FANG YUAN ,  KUN YAN YIN ,  YUAN LIN YANG ,  TONG LIU ,  HE LI

IPC: G06F16/00

Abstract: A set of candidate intent vectors is generated from an input intent vector. A validation of the set of candidate intent vectors is performed that selects as valid intent vectors any of the set of candidate intent vectors that are semantically similar to the input intent vector.

公开(公告)号：GB2605723A

公开(公告)日：2022-10-12

申请号：GB202208933

申请日：2020-10-20

Applicant: IBM

Inventor： WAN WAN MIAO ,  KUN YAN YIN ,  JIAN GONG WANG ,  YAN HU ,  LIAN NA WANG

IPC: G06F16/783

Abstract: A system, method, and computer program product for segmenting videos. The system includes at least one processing component, at least one memory component, a video (110), an extraction component (140), and a graphing component (150). The extraction component (140) is configured to extract image and text data (330, 310) from the video (110), identify entities in the image data(330), assign at least one entity relation to the entities in the image data (330), identifying entities in the text data(310), and assign at least one entity relation to the entities in the text data (310). The graphing component (150) is configured to generate an image knowledge graph (360) for the entity relations assigned to the entities in the image data (330), generate a text knowledge graph (350) for the entity relations assigned to the at least two entities in the text data (310), and generate a weighted knowledge graph (370) based on the image and text knowledge graphs (360, 350).