Learning analysis provides a new opportunity for the development of online education, and has received extensive attention from scholars at home and abroad. How to use data and models to predict learners’ academic success or failure and give teaching feedback in a timely manner is a core problem in the field of learning analytics. At present, many scholars use key learning behaviors to improve the prediction effect by exploring the implicit relationship between learning behavior data and grades. At the same time, it is very important to explore the association between categories and prediction effects in learning behavior classification. This paper proposes a self-adaptive feature fusion strategy based on learning behavior classification, aiming to mine the effective E-learning behavior feature space and further improve the performance of the learning performance prediction model. First, a behavior classification model (E-learning Behavior Classification Model, EBC Model) based on interaction objects and learning process is constructed; second, the feature space is preliminarily reduced by entropy weight method and variance filtering method; finally, combined with EBC Model and a self-adaptive feature fusion strategy to build a learning performance predictor. The experiment uses the British Open University Learning Analysis Dataset (OULAD). Through the experimental analysis, an effective feature space is obtained, that is, the basic interactive behavior (BI) and knowledge interaction behavior (KI) of learning behavior category has the strongest correlation with learning performance.And it is proved that the self-adaptive feature fusion strategy proposed in this paper can effectively improve the performance of the learning performance predictor, and the performance index of accuracy(ACC), F1-score(F1) and kappa(K) reach 98.44%, 0.9893, 0.9600. This study constructs E-learning performance predictors and mines the effective feature space from a new perspective, and provides some auxiliary references for online learners and managers.

The rapid development of information technology and Internet technology has a far-reaching impact on vocational education. It is possible to accurately and objectively evaluate the training of learners by recording the process data of learners’ realization. The teaching evaluation of traditional vocational skill training requires time, workforce, and educational resources. Due to the limitations of experimental conditions, it is easy to ignore the procedural characteristics of skill training and difficult to implement the procedural evaluation. Based on the above problems, combined with virtual reality and the parts of vocationally skilled auto repair training specialty, using machine learning methods, engineering design of process evaluation method for skilled auto repair training, and takes the secondary vocational auto repair specialty as an example, constructs an evaluation index model based on KSA theoretical model, and evaluates three dimensions: knowledge acquisition, skill mastery, and ability cultivation (knowledge, skill, ability, KSA). The experimental verification of the process evaluator is carried out in the theoretical training evaluation auto repair system (TTE) based on virtual reality. The experimental results can effectively evaluate the practical training of students. The research results of this paper provide a new perspective and reference for the learning evaluation of skill-based training majors.