A Multi-Agent Collaborative Knowledge Reasoning System Based on a Large Language Model

By using a multi-agent collaborative knowledge reasoning system based on a large language model, the problem of insufficient knowledge fusion in multi-agent systems in cross-domain and time-sensitive scenarios is solved. It realizes continuous incremental updates and global consistency verification of cross-domain knowledge, and outputs root cause diagnosis conclusions with traceability, which is convenient for quality control review.

CN121615675BActive Publication Date: 2026-05-26BEIJING CHINASOFT LINKAGE TECHNOLOGY CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING CHINASOFT LINKAGE TECHNOLOGY CO LTD
Filing Date
2025-11-25
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing multi-agent systems struggle to achieve timely integration of dynamic knowledge in cross-domain, time-sensitive production line scenarios. They lack a unified explicit knowledge representation and composable reasoning mechanism, resulting in high communication overhead, high uncertainty in model generation, impacting consensus efficiency, and a lack of consistency verification and traceability mechanisms for intermediate conclusions.

Method used

A multi-agent collaborative knowledge reasoning system based on a large language model is adopted, including modules for data access and preprocessing, knowledge acquisition and compilation, knowledge base, blackboard and agenda management, reasoning engine, conflict resolution and consistency verification, collaborative coordination and interpretation and tracing. Through explicit knowledge representation and collaborative reasoning mechanism, continuous incremental updates of cross-domain knowledge and global consistency verification are achieved.

Benefits of technology

It enables continuous incremental updates of cross-domain knowledge, avoids the delays and uncertainties caused by long-chain natural language dialogues, reduces the risk of single-source bias and illusion amplification, and outputs cross-domain root cause diagnostic conclusions with traceability, which facilitates quality control review and parameter recalibration.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121615675B_ABST
    Figure CN121615675B_ABST
Patent Text Reader

Abstract

This invention discloses a multi-agent collaborative knowledge reasoning system based on a large language model, relating to the fields of intelligent manufacturing and artificial intelligence. The invention constructs a multi-agent diagnostic system centered on explicit knowledge representation and collaborative reasoning. Through knowledge acquisition and compilation, the natural language output of the large language model is transformed into rules, facts, and ontology fragments that can be directly consumed by the inference engine. Combined with metadata containing source and timestamps, continuous incremental updates of cross-domain knowledge are achieved, overcoming the limitations of traditional static knowledge bases in covering dynamic faults. Secondly, using a blackboard and agenda mechanism as a collaborative carrier, intermediate assertions of agents such as vibration, circuits, and logs are structured for publication and subscription. A conflict resolution and consistency verification module makes unified decisions based on specificity, time freshness, and source credibility, thereby avoiding the accumulation of delays and uncertainties caused by long-chain natural language dialogues in highly real-time scenarios.
Need to check novelty before this filing date? Find Prior Art