Task planning method and device, electronic equipment, medium and product

By acquiring user interaction statements and generating structured intent objects, and combining business domain task graphs and multi-agent collaboration mechanisms, the problem of not being able to dynamically adjust execution paths in existing technologies has been solved, and adaptive task planning and automatic generation of stable business processes have been achieved.

CN122047972BActive Publication Date: 2026-08-04CHENGDU MINGTU TECH CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202610517746.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-04-20
Publication Date
2026-08-04
Estimated Expiration
2046-04-20

AI Technical Summary

Technical Problem

Existing technologies cannot dynamically adjust execution paths according to real-time needs in complex business process automation scenarios, resulting in process interruptions and a lack of flexible task planning capabilities.

Method used

By acquiring user interaction statements, we perform intent recognition and generate structured intent objects. We then combine these with a task graph of the business domain to perform task planning. We utilize a multi-agent collaborative mechanism to achieve adaptive task execution, including planning, execution, verification, and self-healing replanning in abnormal scenarios.

Benefits of technology

It enables the automatic generation of task execution sequences that fit current needs without relying on static preset processes, improving the dynamic adaptability and execution rationality of task planning, and enhancing the stability and reliability of business processes.

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

Abstract

The application discloses a task planning method and device, electronic equipment, medium and product. The method comprises the following steps: obtaining an interactive sentence input by a target user; performing intent recognition on the interactive sentence to obtain an intent candidate list; generating a structured intent object according to the intent candidate list and multi-round dialogue data of the target user; loading a corresponding business domain task graph according to the structured intent object; and performing task planning according to the business domain task graph to obtain a task execution sequence. The method can combine real-time interactive intent of a user with multi-round dialogue history to form a structured intent expression, and complete adaptive task planning based on a matched business domain task graph, thereby automatically generating a task execution sequence that meets current requirements without relying on a static preset process, and effectively improving dynamic adaptation capability and execution rationality of task planning.
Need to check novelty before this filing date? Find Prior Art