Finite-state agent behavior decision-making method, device and equipment, medium and product

By constructing a system action graph and a set of logical mappings, and combining task description information, the initial decisions of the agent are generated, which solves the problems of insufficient interpretability, reliability and scalability of existing agent behavior decision-making methods, and realizes automated processing from natural language to task execution.

CN121541944APending Publication Date: 2026-02-17TRANSWARP TECHNOLOGY (SHANGHAI) CO LTD
0 Cites 1 Cited by

Patent Information

Application Number
CN202511668657.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-14
Publication Date
2026-02-17

AI Technical Summary

Technical Problem

Existing methods for agent behavior decision-making have shortcomings in terms of interpretability, reliability, automation, and scalability. In particular, deep reinforcement learning based on end-to-end training is costly and has low sample utilization efficiency, planning based on large language models has poor reliability, and planning based on traditional symbolic methods is costly and not easily scalable.

Method used

A method for making decisions about the behavior of intelligent agents in finite states is proposed. By acquiring relevant system information, an Action Graph is constructed, which includes nodes and edges. Nodes contain functions, operations, and tasks, while edges contain dependencies. By combining a set of logical mappings and task description information, the initial decision is determined, including task identification, operation sequence, data dependency constraints, and cost evaluation metrics.

Benefits of technology

It achieves fully automated processing from natural language task description to task execution, and the generated decisions are theoretically correct and practically executable, improving operational efficiency and resource utilization while reducing knowledge construction costs.

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

Abstract

The invention discloses a finite-state agent behavior decision-making method, device and equipment, a medium and a product. The method comprises the following steps: acquiring system related information; according to the system related information, a system action graph Action-Graph is constructed, and the Action-Graph comprises nodes and edges; according to the Action-Graph, a logic mapping set is constructed, and the logic mapping set comprises an initial function set, an operation set and a dependency relationship between functions and operations; according to the logic mapping set, the Action-Graph and the task description information, an initial decision is determined, the initial decision comprises at least one of a task identifier, an operation sequence, a data dependence constraint and a cost evaluation index, through the technical scheme of the invention, an end-to-end automatic process suitable for the intelligent agent can be constructed, and the efficiency of the end-to-end automatic process is improved. And full-process automatic processing from task description of a natural language to task execution is realized.
Need to check novelty before this filing date? Find Prior Art