工程项目会议问题预录入方法、装置、设备及存储介质
By performing semantic vectorization and entity recognition on engineering project meeting issues, and combining this with an engineering domain knowledge base, a semantic graph of the issues is constructed. This solves the problems of low efficiency and poor accuracy in organizing meeting issues in existing technologies, and achieves efficient and accurate generation of pre-meeting topics.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HUATENG JIANXIN TECH CO LTD
- Filing Date
- 2025-10-30
- Publication Date
- 2026-07-17
AI Technical Summary
Existing project meeting management solutions suffer from low efficiency and accuracy in organizing meeting issues, making it difficult to identify semantically equivalent issues and capture project entities and their relationships. This results in a lack of logical hierarchy in the organization of topics and a low rate of eliminating duplicate issues.
By acquiring the text of engineering project meeting questions submitted by multiple users, performing semantic vectorization processing, using an engineering project domain knowledge base for entity recognition and relation extraction, constructing a semantic graph of the questions, calculating comprehensive semantic similarity, and generating a hierarchical list of pre-meeting topics.
It enables efficient and accurate organization of meeting issues in engineering projects, generating a logical and hierarchical list of pre-meeting topics, thus improving the efficiency and accuracy of organizing meeting issues.
Smart Images
Figure CN121301585B_ABST