The Design And Implementation Of Problem Construction And Analysis System For Expression Ability Evaluation

With the development of social economy,all walks of life have gradually aban-doned the talent recruitment method which takes the academic record and the score as the only index,and chose the talent evaluation system which is based on the comprehen-sive quality evaluation.The ability of expression includes the ability of communication,the ability of generalization,the ability of leadership,the ability of communication and so on.As the basic ability of talents,it plays a very important role in the talent eval-uation system.However,the current evaluation of the expression ability still remains at the primary level based on the interviewer's decision,which requires a large amount of labor and time costs.This kind of evaluation method cannot be quantified and can only be divided into levels by experience.Aiming at this problem,the expression abil-ity evaluation project puts forward a new program of expression ability evaluation.By participating in the evaluation,users can quantify their own level of expression ability.The problem construction and analysis system is the part of the expression ability evaluation project.It focuses on the entire process of the core element of the "problem kit" in the evaluation,from generation and initialization to use and analysis and opti-mization.First,in order to ensure the number and diversity of problems,the system needs to regularly crawl network resources and initialize it as a backup question.Sec-ond,during the user participation in the evaluation process,the system will use audio analysis and text analysis methods to analyze the user's expression level and provide brief comments.Third,the system also needs to use the answer data submitted by the user and use statistical learning method to optimize the parameters of the problem kit and improve the stability of the model.In addition,the system will also provide the necessary support so that professionals can intervene in the problem life cycle,generate new problems from the alternate corpus,or modify the problem parameters artificially.This system adopts the technology of separating the front and back ends.In order to give consideration to the development efficiency and development stability,the front and back ends adopt the mainstream framework.On the aspect of front end,WeChat mini-program client uses applet official MVVC framework while website client uses Vue framework.The backend uses Python as a programming language,Flask as devel-opment framework,and Celery as a distributed task queue framework.In terms of data storage,the system cache data is stored in Redis,structured data is stored in MongoDB,and unstructured file data is stored in baidu object storage BOS.In this paper,the system is functionally tested,and Jmeter is used to stress test the system server.The system has been online and has experienced two experimental operations.The experimental results show that the number of samples within 5 points between the system's scoring results and the expert's score exceeds 75%,indicating that the system can quantify the evaluator's expressive ability to some extent.