Network-Side AI Service Processing with Assistance Information
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless networks in mobile communication systems do not provide AI services to external applications, limiting their ability to support advanced use cases such as autonomous driving and robotics.
Innovation Solution
An AI service processing method where a network-side device receives an AI service request from a target device, including an AI service identifier and assistance information, and provides a service result based on this information, enhancing the quality of AI services.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If wireless networks do not provide AI services to external applications, then the network structure remains simple, but the ability to support advanced use cases such as autonomous driving and robotics is limited
Solution Approach 1:
The patent introduces an AI service processing method where the network side device acts as an intermediary between external applications and the core network. The target device (e.g., autonomous driving system) sends AI service requests to the network side device, which processes these requests and interacts with the core network functions. This intermediary approach enables AI service support without fundamentally restructuring the entire network architecture.
Solution Approach 2:
The network side device is designed to handle multiple types of AI service requests from different external applications (autonomous driving, robotics, etc.) through a unified processing mechanism. The device can process various AI services by receiving requests, obtaining assistance information, and generating appropriate service results, making the network infrastructure universally applicable to diverse AI use cases without requiring separate dedicated systems for each application type.
2Measurement precision
If AI services are provided without assistance information, then the service processing is simple, but the service accuracy and completeness are insufficient
Solution Approach 1:
The patent implements preliminary action by obtaining assistance information from the target device before processing the AI service request. The network side device receives the AI service request, then obtains additional assistance information (such as context data, device capabilities, or environmental information) that is crucial for accurate AI service delivery. This preliminary data collection enables the network to provide more accurate and complete AI services while maintaining a clear processing workflow.
Solution Approach 2:
The service processing method incorporates feedback mechanisms where the network side device uses the assistance information to generate service results and feeds these results back to the target device. The feedback loop allows the system to adjust and optimize future service processing based on the received assistance information, thereby improving service accuracy and completeness while managing processing complexity through iterative refinement.
Data Source
AI summary
This application relates to an artificial intelligence (AI) service processing method and a device in the field of communication technologies. The artificial intelligence AI service processing method of embodiments of this application includes: receiving, by a network-side device, an AI service request from a target device, where the AI service request includes an AI service identifier of a requested first service and AI assistance information, the AI assistance information includes AI service trigger information and/or assistance information related to an AI model; and feeding back, by the network-side device, a service result of the first service to the target device based on the AI service identifier of the first service and the AI assistance information.