A service processing method, apparatus, device, storage medium, and program product
By constructing a three-layer collaborative architecture and optimizing business processes using natural language understanding and resource scheduling models, the problem of low automation in collaboration between intelligent agents and business systems was solved, achieving efficient business processing and process adjustment, and improving the system's flexibility and resource utilization efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 中国移动通信集团江西有限公司
- Filing Date
- 2026-02-13
- Publication Date
- 2026-05-29
AI Technical Summary
In existing technologies, the degree of automation in collaboration between intelligent agents and business systems is low, and business processes or process nodes cannot be adjusted, resulting in insufficient system flexibility, inability to cope with rapid changes in user needs, isolated resource scheduling, and low efficiency.
A three-layer collaborative architecture is constructed, consisting of an intelligent agent application layer, a business orchestration layer, and a basic capability layer. The natural language understanding model is used to parse user intent, generate a sequence of business nodes, and call services of intelligent agents and business systems. Combined with a resource scheduling model and dependency weights, the business process is optimized to achieve efficient collaboration between intelligent agents and business systems.
It improves the level of automation in collaboration between intelligent agents and business systems, enables dynamic adjustment of business processes and process nodes, enhances system flexibility and resource scheduling efficiency, and significantly shortens business processing cycles.
Smart Images

Figure CN122114850A_ABST