Invention Application
- Patent Title: TEXT PROCESSING METHOD, MODEL TRAINING METHOD, AND APPARATUS
-
Application No.: US17526832Application Date: 2021-11-15
-
Publication No.: US20220147715A1Publication Date: 2022-05-12
- Inventor: Yasheng WANG , Xin JIANG , Xiao CHEN , Qun LIU , Zhengyan ZHANG , Fanchao QI , Zhiyuan LIU
- Applicant: Huawei Technologies Co., Ltd. , TSINGHUA UNIVERSITY
- Applicant Address: CN Shenzhen; CN Beijing
- Assignee: Huawei Technologies Co., Ltd.,TSINGHUA UNIVERSITY
- Current Assignee: Huawei Technologies Co., Ltd.,TSINGHUA UNIVERSITY
- Current Assignee Address: CN Shenzhen; CN Beijing
- Priority: CN201910410679.4 20190516
- Main IPC: G06F40/295
- IPC: G06F40/295

Abstract:
This application relates to the field of artificial intelligence, and provides a text processing method, a model training method, and an apparatus. The method includes: obtaining target knowledge data; processing the target knowledge data to obtain a target knowledge vector; processing to-be-processed text to obtain a target text vector; fusing the target text vector and the target knowledge vector based on a target fusion model, to obtain a fused target text vector and a fused target knowledge vector; and processing the fused target text vector and/or the fused target knowledge vector based on a target processing model, to obtain a processing result corresponding to a target task. The foregoing technical solution can improve accuracy of a result of processing a target task by the target processing model.
Public/Granted literature
- US12204859B2 Text processing method, model training method, and apparatus Public/Granted day:2025-01-21
Information query