微型电脑应用

为了提高企业在线培训系统的个性化推荐质量和交互效率，提出一种基于蚁群优化的词频—逆文档频率(ACO-TF)算法。通过融合蚁群算法(ACO)与词频—逆文档频率(TF-IDF)算法对关键词进行提取，实现动态课程推荐策略的优化。实验结果表明，ACO-TF算法的工作绩效增长率达到15.63%,任务完成速度提升至1.23倍，课程完成率为93.47%,平均课时时长降至45.28 min,平均响应时间缩短至1.87 h,测试成绩提升率达到20.45%,知识点覆盖率为86.42%,均优于其他2种比较算法。ACO-TF算法对于解决冷启动和数据稀疏问题，提升员工培训参与度和效果具有显著贡献，对企业在线培训具有重要的理论和实践意义。

In order to improve the personalized recommendation quality and interaction efficiency in the enterprise online training systems, an algorithm based on ant colony optimization-term frequency-inverse document frequency(ACO-TF) is proposed. The optimization of the dynamic course recommendation strategy is achieved by integrating the ant colony optimization(ACO) algorithm and the term frequency-inverse document frequency(TF-IDF) algorithm to extract keywords. The experimental results show that the ACO-TF algorithm achieves a job performance growth rate of 15.63%, the task completion speed increases to 1.23 times, and the course completion rate is 93.47%. The average class time is reduced to 45.28 min, the average response time is reduced to 1.87 h, the test score improvement rate reaches 20.45%, and the knowledge point coverage rate is 86.42%, which are all superior to the other two algorithms. The ACO-TF algorithm has significant contributions to solving cold start and data sparsity problems, improving employee training participation and effectiveness, and has important theoretical and practical significance for enterprise online training.