Information processing method, electronic device, and storage medium
By entering node sequence information into the big model, determining the target node and controlling the agent to execute action instructions, the efficiency and accuracy of the large model driving agent in complex tasks is solved, flexible task process planning and controllable execution are realized, and user experience is improved.
WO2025148703A1 Publication Date: 2025-07-17ALIBABA (CHINA) CO LTD
5 Cites 7 Cited by
Patent Information
- Application Number
- PCT/CN2024/142781
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-01-12
- Filing Date
- 2024-12-26
- Publication Date
- 2025-07-17
AI Technical Summary
Technical Problem
Existing large-model-driven agents are difficult to support complex tasks, have low task processing efficiency and accuracy, and are difficult to meet customized needs in different scenarios, and have poor user experience.
Method used
By constructing node sequence information based on flowcharts, using a large model to determine the target node and control the agent to execute action instructions, the controllable planning and execution of the task process is realized.
Benefits of technology
It improves the processing efficiency and accuracy of the agent in complex processes, supports task customization in different scenarios, and improves the user experience.
✦ Generated by Eureka AI based on patent content.
Abstract
Provided in the present disclosure are an information processing method, an electronic device, and a storage medium, which are applied to the technical field of artificial intelligence. The method comprises: determining information to be processed corresponding to an intelligent agent; and inputting the information to be processed and node sequence information into a large model, wherein the node sequence information is used for indicating a plurality of nodes included in a task flow and edges between the nodes, each node represents an action instruction for the intelligent agent, and each edge represents a transition between the nodes, such that the large model determines, on the basis of the information to be processed, a target node to be executed and controls the intelligent agent to execute the action instruction corresponding to the target node. The present disclosure enables the planning of a complex flow and controllability of an execution process, allowing the intelligent agent to complete tasks more efficiently and accurately. Furthermore, the present disclosure can support the customization of different task flows for different scenarios, thereby meeting usage requirements in the different scenarios and improving user experience.
Need to check novelty before this filing date? Find Prior Art