Multi-agent cooperation method, system and device based on shared memory data and medium

By employing a multi-agent collaborative method that shares memory data and utilizes a semantic signature similarity calculation mechanism, the problem of repetitive reasoning and cache not being shared across nodes in traditional systems is solved, achieving efficient resource utilization and response optimization.

CN121882153APending Publication Date: 2026-04-17SHANDONG INSPUR SCI RES INST CO LTD
0 Cites 2 Cited by

Patent Information

Application Number
CN202511778672.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-28
Publication Date
2026-04-17

AI Technical Summary

Technical Problem

Traditional inference systems cannot recognize semantic similarities between different agents, leading to redundant inference calculations and wasted resources. Furthermore, cached results cannot be shared across nodes, and the problem is even more severe when deployed in a multi-node environment.

Method used

By introducing a multi-agent collaboration method with shared memory data, and utilizing a semantic signature similarity calculation mechanism to identify the correlation between requests, a unique semantic signature is generated, and the caching strategy is dynamically adjusted to achieve cross-node cache sharing and resource optimization.

Benefits of technology

It accurately identifies the semantic relationships between requests from intelligent agents, avoids redundant reasoning calculations, reduces computing resource consumption, improves system response efficiency, and enables intelligent matching of cached resources to improve overall utilization.

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

Abstract

The invention discloses a multi-agent cooperation method, system and device based on shared memory data, and a medium, mainly relates to the technical field of multi-agents, and aims to solve the problem that a traditional reasoning system cannot recognize semantic similarity between requests and cannot sense a context relationship of agent tasks, so that the efficiency is improved. The intelligent agent system is often deployed at multiple nodes, and the cache result cannot be shared across the nodes. Comprising the steps of obtaining an output result and an intermediate result generated by each path node; caching the semantic signature and the output result to a preset result cache layer; caching an intermediate result generated by each path node as context information to a preset context cache layer; and according to a preset time window, detecting inference frequencies of different semantic signatures generated by all the agents, and according to the inference frequencies, adjusting storage time of output results corresponding to the semantic signatures in a preset result cache layer.
Need to check novelty before this filing date? Find Prior Art