Data detection method, device, electronic equipment and storage medium

By combining multiple initial detection results of small models and secondary processing of the intermediate detection results of large models, the problem of high computing resources consumption when large models work together is solved, and more efficient computing resources utilization is achieved.

CN119313981BActive Publication Date: 2025-04-01HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202411853966.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-12-16
Publication Date
2025-04-01
Estimated Expiration
2044-12-16

AI Technical Summary

Technical Problem

When large models work together with small models, the computing resources consumed are large, resulting in inefficiency.

Method used

By combining multiple initial detection results belonging to the same task type, using a large model to detect the combined data, intermediate detection results are obtained, and secondary detection results of each data to be detected based on the intermediate detection results and data mapping relationship, and finally the final detection results of the data to be detected are obtained.

Benefits of technology

A large model only needs to perform one detection to obtain the final detection results for multiple data to be detected in the small model, reducing the number of times the large model detects data and reducing the computing resources consumed by the large model working together with the small model.

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

Abstract

The embodiment of the present application provides a data detection method, device, electronic device and storage medium, which relates to the field of artificial intelligence technology. The method includes: obtaining each initial detection result obtained by a small model for detecting multiple data to be detected; combining the initial detection results belonging to the same task type to obtain the combined data and data mapping relationship of the task type; using the large model to be used for the task type to detect the combined data to obtain the intermediate detection result of the task type; for each initial detection result of the task type, determining the part corresponding to the initial detection result from the intermediate detection result based on the data mapping relationship, and obtaining the secondary detection result of the data to be detected corresponding to the initial detection result; determining the final detection result of the data to be detected based on the secondary detection result of each data to be detected. This solution reduces the computing resource consumption of the large model and the small model for collaborative work.
Need to check novelty before this filing date? Find Prior Art