Multi-mode space-time memory retrieval system for AI intelligent agent

The AI ​​intelligent agent memory system, which integrates unified storage and multi-mode retrieval, solves the problems of low efficiency in processing spatiotemporal related information and insufficient accuracy in multi-mode information retrieval. It achieves efficient and accurate memory storage and natural forgetting, thereby enhancing the decision-making ability of the AI ​​intelligent agent.

CN121502045APending Publication Date: 2026-02-10TONGJI UNIV
0 Cites 1 Cited by

Patent Information

Application Number
CN202511487659.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-10-17
Publication Date
2026-02-10

AI Technical Summary

Technical Problem

Existing AI intelligent agent memory systems cannot effectively process spatiotemporal related information, resulting in low retrieval efficiency, insufficient accuracy in multimodal information retrieval, and a lack of forgetting mechanisms that conform to human cognitive patterns, leading to a waste of storage resources.

Method used

The ConceptNode structure is used to uniformly store heterogeneous memory content. It combines a multimodal retrieval module, a timeliness calculation module, and a forgetting calculation and management module. Through a comprehensive scoring function of keyword matching degree, semantic matching degree, and spatiotemporal matching degree, it realizes multimodal retrieval. It also dynamically manages memory duration through a nonlinear life cycle function and configures differentiated parameters to simulate the laws of human memory.

Benefits of technology

It significantly improves the efficiency of spatiotemporal information processing, enhances retrieval accuracy, optimizes storage space utilization, strengthens system adaptability, and makes the behavior more natural and reliable.

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

Abstract

The invention discloses a multi-mode space-time memory retrieval system for an AI agent, and the system comprises a memory storage module which employs a ConceptNode structure to uniformly store heterogeneous memory content; the multi-modal retrieval module is used for realizing memory retrieval sorting through a comprehensive scoring function; the three retrieval modes specifically comprise a keyword matching degree retrieval mode, a semantic matching degree retrieval mode and a time-space matching degree retrieval mode; the timeliness calculation module adopts an exponential decay function; the importance evaluation module is used for automatically generating importance scores by combining a large language model with domain knowledge; and the forgetting calculation management module is used for dynamically distributing memory duration based on a nonlinear life cycle function, configuring differentiated parameters for different memory types and supporting life cycle extension of access triggering. According to the method, the adaptive learning ability and decision authenticity of the AI intelligent agent in a dynamic environment are remarkably improved, and the method is suitable for intelligent decision scenes such as urban traffic simulation and robot navigation.
Need to check novelty before this filing date? Find Prior Art