Fractional prediction system and prediction method

Abstract

The present invention relates to the field of automation technology, in particular to a fractional prediction system and a prediction method. The system comprises: a student practice terminal, the student practice terminal is used for dividing the score prediction nodes of the test questions in the test question bank according to the rule of the student 's problem making or the rule of the test paper' s problem setting, then forming the test questions between two score prediction nodes into sub-node sets, and counting the number of the corresponding sub-node sets to generate the number of testquestions, and then calculating the proportion between them according to the sub-node sets and the number of the students' test questions, and generating the coverage rate of answering, then dividingthe weight of the test questions from different sources according to the source of the test questions, and calculating the scores of the node items according to the correct rate of the test exercisesfrom different sources, and calculating the predicted scores of the child node sets of the students according to the answer coverage, the node item scores and the smoothing function as the basis of the prediction scores.

Description

technical field [0001] The invention relates to the technical field of automation, in particular to a score prediction system and a prediction method. Background technique [0002] Examination is a process that everyone has experienced in modern life. Candidates often conduct mock tests on their abilities before the exam, and an online mock test system has become a very important development direction. [0003] At present, the main score prediction method is to obtain the key factors affecting students' academic performance through real middle school student data and machine mining algorithms. For example, the family background and school behavior of the students at school. Generate offline models and academic index evaluation reports through logistic regression algorithms, predict students' final grades, and apply the trained offline models to business scenarios. The main disadvantage of this solution is that the deep mining algorithm needs to generate a model by learning...

AI Technical Summary

Problems solved by technology

The main disadvantage of this solution is that the deep mining algorithm needs to generate a model by learning the association between known student feature information and real scores, but the actual situation is that the above information (or predictive factors) of students is difficult for E-end products Obtained, so that the prediction factor is not obtained in time, which affects the accuracy of the prediction score; in addition, the machine mining algorithm is generally more complicated, and the calculation efficiency is easy to form a bottleneck for the calculation of the system with a large amount of concurrency

Images