基于卷积神经网络的高校创新创业资源推荐方法  

Recommendation Method of Innovation and Entrepreneurship Resources in Colleges and Universities Based on Convolutional Neural Network

作　　者：罗永莲[1] LUO Yonglian(Network Information Center of Jinzhong University,Jinzhong Shanxi 030619,China)

机构地区：[1]晋中学院网络信息中心,山西晋中030619

出　　处：《信息与电脑》2022年第21期121-123,共3页Information & Computer

基　　金：山西省教育科学“十三五”规划课题“基于创新创业教育理念的大数据相关专业教学模式研究”(项目编号:GH-18091)。

摘　　要：为提高推荐资源与用户需求资源的适配度,引进卷积神经网络,设计一种针对高校创新创业资源的推荐方法。首先引进协同过滤算法,确定资源推荐的目标群体,计算用户偏好度;其次引进卷积神经网络,训练数据信息,得到资源的特征参数,进行创新创业资源的定向抽取;最后引进加权模糊计算方法,结合资源在空间中的表达方式,确定资源的推荐层级,从而实现对资源的主动推荐。实验结果证明,设计方法可以降低推荐资源与用户需求之间的差异度,保证推荐资源与用户需求资源之间具有较高的适配度。in order to improve the adaptability between recommended resources and user demand resources, a convolution neural network is introduced to design a recommendation method for innovation and entrepreneurship resources in Colleges and universities. The collaborative filtering algorithm is introduced to determine the target group of Resource Recommendation and calculate the user preference;The convolution neural network is introduced to train data information, obtain the characteristic parameters of resources, and conduct directional extraction of innovation and entrepreneurship resources;The weighted fuzzy calculation method is introduced to determine the recommendation level of resources and realize the active recommendation of resources based on the expression of resources in space. The experimental results show that the design method can reduce the difference between recommended resources and user needs, and ensure a high degree of adaptation between recommended resources and user needs.

关 键 词：卷积神经网络 模糊加权 协同过滤算法 创新创业资源 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]