Intelligent agent autonomous decision-making method and system based on embedded edge computing

By constructing an initial probabilistic decision space and an improved Pusen sampling algorithm, combined with iterative updates and dynamic adjustments of state values, the problem of autonomous decision-making under resource constraints in embedded edge computing devices is solved, achieving high-precision and real-time intelligent agent decision-making and enhancing the application capabilities of embedded edge intelligent agents.

CN122263941APending Publication Date: 2026-06-23QINGDAO TECHCAL UNIV QINDAO COLLEGE
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
QINGDAO TECHCAL UNIV QINDAO COLLEGE
Filing Date
2026-01-22
Publication Date
2026-06-23

AI Technical Summary

Technical Problem

Embedded edge computing devices are resource-constrained, making it difficult to achieve high-precision and real-time autonomous decision-making. Existing methods lack a complete closed-loop feedback chain, resulting in poor task performance of intelligent agents in complex environments.

Method used

An initial probabilistic decision space is constructed, and state values ​​are sampled using an improved Pusen sampling algorithm. By combining iterative updates of state values ​​and dynamic adjustment of sampling intensity, the state transition probabilities are calibrated to generate the optimal action strategy.

Benefits of technology

It improves the accuracy and real-time performance of autonomous decision-making, enhances the reliability and response efficiency of agent decision-making under conditions of limited computing resources, and significantly improves its application capabilities in complex dynamic environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122263941A_ABST
    Figure CN122263941A_ABST
Patent Text Reader

Abstract

The application discloses an agent autonomous decision-making method and system based on embedded edge computing, comprising the following steps: constructing an initial probability decision space according to an observation state, and performing localized simplification processing on state characteristic parameters under the calculation power and storage constraints of an embedded edge device; sampling the initial state value by using an improved Posen sampling algorithm, generating a decision value update sequence, and iteratively obtaining an updated state value; dynamically adjusting the sampling intensity according to the convergence trend of the updated state value to obtain a state value threshold; correcting the decision value update sequence according to the state value threshold and generating a decision path; feeding back the decision path to the initial probability decision space to calibrate the state transition probability; and finally obtaining a real-time optimal action strategy based on the calibrated state transition probability. The application effectively improves the real-time performance and reliability of the autonomous decision-making process in the embedded resource-constrained environment.
Need to check novelty before this filing date? Find Prior Art