Storage device, hazardous chemical accident case retrieval method, device and equipment
By setting the accident cause section as standard target text in the hazardous chemical accident case library, and combining the TextRank model and multiple influencing factors, the characteristic keywords of hazardous chemical accident cases are extracted, and the problems of low extraction efficiency and insufficient accuracy in the existing technology are solved, and more efficient and accurate feature keyword extraction is achieved.
Patent Information
- Application Number
- CN202011278061.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-11-16
- Publication Date
- 2025-03-25
- Estimated Expiration
- 2040-11-16
AI Technical Summary
In the prior art, the extraction efficiency of the characteristic keywords of hazardous chemical accident cases is low and the accuracy is too low, so it cannot effectively meet the requirements of hazardous chemical accident cases.
When building a hazardous chemical accident case library, the content of the accident cause section is set as the standard target text, and through unsupervised learning, especially based on the TextRank model, the weight of candidate keywords is calculated and characteristic keywords are extracted through unsupervised learning, especially based on the TextRank model.
It improves the extraction efficiency and accuracy of keywords for hazardous chemical accident cases, reduces the introduction of irrelevant candidate keywords, enhances the expression of accident characteristics, and meets the needs of hazardous chemical accident cases.