Intelligent network connection automobile data training method based on privacy data protection, electronic equipment and computer readable storage medium

Abstract

The invention discloses an intelligent network connection automobile data training method based on privacy data protection, and the method comprises the steps: carrying out the marking of historically collected road test data, carrying out the model training, obtaining a first edition model, and deploying a low-layer feature extraction layer of the first edition model to an automobile end; on a vehicle end, for original data collected by the vehicle end, on one hand, feature extraction is performed through a deployed low-level feature extraction layer to obtain a low-level feature data set and upload the low-level feature data set to a cloud end; on the other hand, performing anonymization processing on the original data and uploading the original data to the cloud for data annotation; at the cloud, training and updating other feature extraction layers except the low-layer feature extraction layer by using the uploaded data set and the historical data set; and the updated model is pushed to the vehicle end for synchronous updating. According to the method, while data privacy transmission is ensured, the problem of algorithm performance reduction caused by anonymization data is solved, an algorithm closed loop is constructed on the basis, and the problem of model iteration updating is solved.

Description

technical field [0001] The invention relates to the improvement of data processing technology of intelligent networked vehicles, in particular to a data training method of intelligent networked vehicles based on privacy data protection, and belongs to the technical field of data processing and training. Background technique [0002] With the vigorous development of autonomous driving technology in China, major host manufacturers and technology suppliers are striving to improve their competitiveness, and have proposed various methods of data collection and algorithm training. For example: (1) CN202210057268 data collection method, device, equipment and storage medium of Zhejiang Geely Holding Group Co., Ltd. proposes the following technology: in the process of vehicle driving, the vehicle-end data collected by the vehicle-end sensors and the data collected by the road-end sensors are obtained. Road-side data, perform space-time synchronization on vehicle-side data and road-si...

AI Technical Summary

Problems solved by technology

[0006] In view of the above-mentioned deficiencies existing in the prior art, the purpose of the present invention is to provide a data training method for intelligent networked cars based on privacy data protection. problem, and on this basis, an algorithm closed loop is constructed to solve the problem of iterative update of the model

Images