Data processing method and device, computer readable medium and electronic equipment

CN116956012BActive Publication Date: 2026-07-07TENCENT TECHNOLOGY (SHENZHEN) CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TENCENT TECHNOLOGY (SHENZHEN) CO LTD
Filing Date
2023-03-08
Publication Date
2026-07-07

AI Technical Summary

Technical Problem

In existing technologies, when using a single machine learning model for industrial anomaly detection, the prediction results are unreliable and greatly affected by the machine learning model algorithm, resulting in inconsistent prediction results from different models for the same data to be processed.

Method used

At least two machine learning models are used, and the prediction results of each model are standardized by co-standardizing parameters to eliminate the differences between models and determine the uncertainty of the prediction results of the data to be processed.

Benefits of technology

This improves the reliability of prediction results, reduces the probability of misjudgment, and ensures the accuracy of prediction results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116956012B_ABST
    Figure CN116956012B_ABST
Patent Text Reader

Abstract

Embodiments of the present application provide a data processing method, device, computer readable medium and electronic equipment. The data processing method comprises: inputting to-be-processed data into at least two machine learning models to obtain target probability values for a prediction result output by each machine learning model; performing standardization processing on the target probability values output by each machine learning model based on a corresponding collaborative standardization parameter of the at least two machine learning models to obtain a standardization processing result corresponding to each machine learning model; and determining a prediction result uncertainty corresponding to the to-be-processed data according to the standardization processing result corresponding to each machine learning model. The scheme of the embodiments of the present application performs standardization processing on the output results of each machine learning model based on a collaborative standardization parameter, reduces the influence of differences between the output results of different machine learning models, and thus makes the prediction result corresponding to the to-be-processed data more reliable.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Data processing method, device and equipment

    CN114298153A

  • Unsupervised anomaly detection method based on traffic log feature extraction

    CN114528909A