Intelligent agent task scheduling planning method

By constructing a subtask dependency graph and a resource state tensor, and combining dynamic capability matching and predictive load balancing, the problems of insufficient dependency verification and static resource allocation in existing agent task scheduling are solved, thereby achieving efficient and stable agent task scheduling and improved resource utilization.

CN122019098APending Publication Date: 2026-05-12BEIJING DECK SMART TECH CO LTD
0 Cites 8 Cited by

Patent Information

Application Number
CN202610149388.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-02-03
Publication Date
2026-05-12

AI Technical Summary

Technical Problem

Existing intelligent agent task scheduling schemes fail to effectively verify the closed-loop nature and completeness of dependencies, leading to task deadlock and resource contention. Static resource allocation cannot predict peak demand, and the scheduling scheme lacks dynamic adjustment, affecting task completion efficiency and system stability.

Method used

Atomic tasks are generated by parsing task instructions, a subtask dependency graph is constructed, resource-task association and priority ranking are performed by combining the agent's resource state tensor, dynamic capability matching and predictive load balancing are adopted, and time-series scheduling and conflict resolution are performed to generate a collaborative execution scheme.

Benefits of technology

It improves the efficiency and robustness of task scheduling, reduces execution chaos and resource contention, increases resource utilization and task completion efficiency, and ensures system stability and consistency.

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

Abstract

The invention discloses an agent task scheduling planning method, and relates to the technical field of agent scheduling. The method comprises the steps of analyzing a task instruction to generate atomic tasks capable of being independently executed, constructing a subtask dependency graph, and defining association constraints between the tasks; determining the real-time resource occupancy state of the intelligent agent to obtain a resource state tensor, completing resource-task association anchoring and dependency priority ranking in combination with the sub-task dependency graph, and generating a task priority sequence with resource constraint; performing dynamic capability matching and predictive load balancing calculation on the sequence through a task-agent adaptation model, and determining a target execution agent of each atomic task; and based on the target execution agent and the subtask dependency graph, performing time sequence scheduling arrangement and conflict resolution, and generating a collaborative execution scheme. The method improves the reasonability and efficiency of agent task scheduling, reduces resource conflicts and execution timeout risks, and is suitable for agent cluster collaborative scheduling in a complex scene.
Need to check novelty before this filing date? Find Prior Art