Rail transit rule system automatic revision method and system based on knowledge base and LLM

By constructing a knowledge base and using Large Language Model (LLM) to automatically identify and process regulatory document slices, the problems of low revision efficiency and poor accuracy in existing technologies have been solved, enabling efficient and accurate automatic revision of rail transit regulations.

CN121766418BActive Publication Date: 2026-05-05CHENGDU YUNDA TECH CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202610262344.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-03-05
Publication Date
2026-05-05
Estimated Expiration
2046-03-05

AI Technical Summary

Technical Problem

The revision of existing rail transit regulations is inefficient, with manual comparison being time-consuming, prone to omissions and erroneous changes, making it difficult to ensure the consistency and accuracy of revisions. Furthermore, the lack of knowledge association means that the revised content cannot be automatically located to the specific clauses in the original regulations knowledge base.

Method used

By constructing a knowledge base of rules and regulations, using Large Language Model (LLM) to identify and process document segments, and combining knowledge base retrieval technology, the system automatically identifies newly added, modified, and deleted content, and introduces an exception retry mechanism and output format verification to generate structured revision results.

Benefits of technology

It has automated and intelligentized the revision of rules and regulations, significantly reduced labor costs, improved the accuracy and efficiency of revisions, and ensured that the revised content accurately corresponds to the specific clauses of the original document.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This invention discloses an automatic revision method and system for rail transit regulations based on a knowledge base and LLM (Local Language Model), relating to the field of rail transit regulation revision technology. The method includes: first, constructing a regulations knowledge base; parsing the original document as plain text, slicing and vectorizing it, and storing it, associating and recording relevant IDs; receiving the revision object uploaded by the user and the selected original document information; parsing the revision object and slicing it to generate a first array; identifying the paragraphs to be revised in the array using a first large language model, aggregating them to form a set to be revised; searching for similar candidate sets within the locked knowledge base, cleaning and standardizing them, and combining them with the revision content to input into a second large language model to generate a standardized revision result and aggregating it; finally, automatically revising according to preset rules and storing the revised result in the database. This application solves the problem that traditional character comparison cannot understand "wording adjustments without semantic change" or "large-scale logical restructuring" through large model recognition, thus automating the regulations revision process.
Need to check novelty before this filing date? Find Prior Art