Video interview multi-dimensional scoring method and system, computer equipment and storage medium

Abstract

The invention discloses a video interview multi-dimensional scoring method and system, computer equipment and a storage medium. The scoring method comprises the following steps of performing data preprocessing on video interview data of an applicant; based on the preprocessed data, performing multi-dimensional scoring on the applicants through a multi-dimensional scoring module, and generating a video interview multi-dimensional analysis report; when the applicant interview result data is accumulated to a preset number, starting a comprehensive recommendation index algorithm module, and fitting a comprehensive recommendation index model of a target position in combination with a multi-dimensional scoring module; and outputting a corresponding recommendation index from the new applicant data through the comprehensive recommendation index model of the target position, and pushing the recommendation index to a video interview multi-dimensional analysis report. According to the method, multi-dimensional scores such as statement quality and competency can be output on the basis of video interview, a fitting algorithm can be automatically learned by automatically combining multiple dimensions on the basis of an evaluation result of an interviewer, a comprehensive recommendation index model is generated, and an enterprise is helped to complete a high-quality screening target.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to a video interview multi-dimensional scoring method, system, computer equipment and storage medium. Background technique [0002] As the competition for talents continues to intensify, some surveys have shown that the most pressing core challenge for companies in recruitment in recent years is that the proportion of valuable resumes is too low and the screening workload is heavy. Further analysis of the working hours allocation of HR (the human resources workers of the enterprise, referred to as HR) in charge of recruitment, it is found that for large and medium-sized enterprises with good employer brand building, HR and interviewers spend a lot of time (up to about 40%) Time) In the process of talent selection and initial communication, the efficiency and cost pressure of talent selection is still huge. How to efficiently select valuable resumes from a large num...

AI Technical Summary

Problems solved by technology

[0004] However, there are generally two problems in the interview reports provided by the intelligent video interview systems on the market or in the evaluation methods for candidates: first, there are relatively few evaluation dimensions for candidates, and the information that interviewers can obtain from the reports is limited. Generally, you still have to browse the original recorded video to form your own judgment; the second is to serve the screening, the interview report generally provides an overall evaluation index for the applicant, which can serve the screening, such as the employment level, AI recommendation index, etc.

However, starting from the competency scoring vocabulary model, it may not be accurate enough to evaluate the applicant's competency by calculating the frequency of related words, and the scheme still uses the method of prefabricated weights to weight the scores of each competency dimension to form Overall scoring, giving suggestions on the applicant's employment level, lacking other evaluation dimensions related to the applicant, such as appearance and temperament, statement quality, personal intention, etc. to comprehensively evaluate the overall situation of the applicant

The screening accuracy achieved by this method still needs to be further improved.

Images