Unmanned training data classification method and device and electronic equipment

Abstract

The invention provides an unmanned training data classification method and device and electronic equipment. The method comprises the steps of acquiring N data sets, wherein the N data sets comprise data in collected data samples, each data sample comprises data of N types of attribute information, the attribute information of the data belonging to the same data set is the same, and N is an integerlarger than 1; clustering the N data sets one by one, obtaining M data categories of the finally clustered data set in the N data sets, wherein data samples corresponding to the data in different data categories are used for training different prediction models, the clustering of the (K + 1) th data set is carried out based on the clustering result of the Kth data set, K is a positive integer smaller than N, and M is an integer larger than 1. Thus, the efficiency of training the prediction model can be improved, and the accuracy of the prediction model obtained through training can be improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method, device and electronic equipment for classifying unmanned driving training data. Background technique [0002] With the rapid development of technologies such as computers, image processing, and wireless communications, the automotive industry is currently developing in the direction of intelligence, and autonomous driving is the direction of the development of automobile intelligence. Existing self-driving cars usually use deep learning technology to output vehicle control instructions according to the needs of specific driving scenarios through pre-training of predictive models, so as to realize the automatic driving of vehicles. [0003] Wherein, in the training process of the existing prediction model, in order to ensure the accuracy of the obtained prediction model, it is usually necessary to train the prediction model through training data c...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a method, device and electronic equipment for unmanned driving training data classification, so as to solve the problem of low efficiency of training prediction models in the current training process of prediction models

Images