Design And Implementaion Of After-class Support Services Platform On Blending Teaching Environment

In recent years,with the gradual promotion of engineering education concepts and the country’s continuous promotion of education informatization,online education platforms have developed rapidly,and blending teaching models have become popular in more and more colleges and universities.The goal of this topic is to design and implement an online learning support service platform that can provide students with learning support services in the after-school review stage for the problems that students are likely to encounter in the self-learning stage of the after-school review under the blending teaching mode.The main research contents are as follows:Firstly,based on the concept of learning support services,this paper designs an "online"+"offline" mode of providing learning support services.The model is as follows:On the one hand,the platform directly provides learning support services to student users by providing core functional modules.On the other hand,the core functional modules of the platform also provide data support to teachers.Teachers use the data support provided by the platform to help students conduct after-school review guidance offline.This model takes full advantage of the blending teaching environment.Secondly,based on the above-mentioned model and the actual scene-oriented problems,this paper analyzes the user needs of teachers and students,clarifies the business needs of the system,and extracts the functional requirements.And completed the design and development of the after-school review support service platform according to the functional requirements.The core functional modules include:data processing module,used to solve the "data confounding problem" from multiple data sources,and through the establishment of different quantitative models to convert the original data in the multi-channel data sources into first-level data indicators.At the same time,based on the Analytic Hierarchy Process(AHP),a quantitative model of secondary thematic indicators is constructed,and the implicit characteristics of users are deeply excavated.The first-level and second-level data indicators produced by this module provide data support for the realization of the entire platform and the implementation of the subsequent personalized intelligent recommendation algorithm;the academic report module is used to help users with different identities quickly understand the stages that are most relevant to them Analyze information on sexual learning situations;manual analysis module helps users to flexibly query specific data indicators and in-depth analysis of the correlation between specific indicators.Thirdly,this article studies learner portraits and mainstream intelligent recommendation algorithms,designs and implements a personalized intelligent recommendation algorithm based on learner portraits,and designs and implements another core module of the platform,personalized intelligence based on this algorithm.Recommended module.The design and implementation of the algorithm in this paper fully consider the inaccurate calculation of user similarity caused by a single score in the traditional user-based collaborative filtering algorithm.The calculation of user similarity is improved by combining learner portraits.At the same time,the clustering algorithm in the learner’s portrait is researched,and a K-means algorithm that optimizes the selection of the initial centroid is designed and implemented,which improves the accuracy of the portrait and improves the effect of the group portrait.The final recommended learning resources provide personalized guidance to student users during the self-learning stage of after-school review,and also provide them with expanded learning resources.At the end of this article,we use real data from freshmen of our freshman introductory telecommunications course combined with actual application scenarios to test and verify the core functions of the platform.The results prove the stability and feasibility of the system,and design comparative experiments to verify the optimization.The performance improvement of the effectiveness of the designed personalized intelligent recommendation algorithm based on learner profile.