Legal document generation method and system based on online mediation information data
By calculating the physical screening index and constructing the ternary entity right confirmation index in the legal document generation system, the problem of insufficient accuracy of triplets in the existing technology is solved, and the accuracy of the legal document summary text is significantly improved.
CN119203946BActive Publication Date: 2025-03-25HUNAN GUANWEN TECH SERVICE CO LTD
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202411718268.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-28
- Publication Date
- 2025-03-25
- Estimated Expiration
- 2044-11-28
AI Technical Summary
Technical Problem
In the prior art, triplets constructed only by splitting mediation information have low accuracy, resulting in low accuracy in generated legal document abstract text.
Method used
By obtaining the online mediation record of the case, all initial entity vocabulary and statements in the communication text, calculate the entity screening index of each initial entity vocabulary and filter out the entity vocabulary of the parties; then, a more accurate triple is constructed based on the three-part entity rights confirmation index between the entity vocabulary groups.
Benefits of technology
Improves the accuracy of the triplet, thereby improving the accuracy of the generated legal instrument summary text.
✦ Generated by Eureka AI based on patent content.
Abstract
The present invention relates to the technical field of natural language processing, and in particular to a method and system for generating legal documents based on online mediation information data. Based on the fact that entity words representing parties in mediation record communication texts have a high frequency of occurrence, the party entity screening index of each initial entity word is evaluated according to the local frequency of occurrence of each initial entity word in each sentence and the overall frequency of occurrence in all sentences, so as to screen out the required party entity words; then, based on the fact that the connection between different party entities in the mediation process requires more words to describe, the ternary entity confirmation index between entity word groups is evaluated according to the number of all initial entity words between each entity word group and each other entity word group and the overall size of the party entity screening index, and on this basis, a more accurate ternary construction is performed, so that the accuracy of the generated legal document summary text is higher.
Need to check novelty before this filing date? Find Prior Art