Evaluation information generated by various users is processed using various requirements and data to make recommendations for solving the problems, and it analyzes satisfaction with the results. Despite people normally utilizes the processed information for decision making, not all information, however, brings positive outcomes to users. There are some users who perceived it negatively. In order to minimize the occurrence of such negative effects, the analysis of various user requirements is essential as well as diversifying user inputs for each requirement. Consequently, the results from individual inputs must be predicted. In the past, since the system relies on a single-expert system, it is necessary to accept and process various limitations of recommendation and multiple requirements. Therefore, the results of the recommendation also have various problems. In order to solve this problem, this study applied an analytic hierarchy process to multiadvisor configuration. In the proposed system, one or multiple advisors are defined, and after analyzing the predefined requirements, the system accepts only the requirements that can be processed and calculates the individual recommendation results. A recommendation system was going to be studied by learning all situation.

中文翻译：

---

基于层次结构模糊分析层次过程的多顾问定制智能推荐研究

各种用户产生的评价信息，利用各种需求和数据进行处理，提出解决问题的建议，并对结果进行满意度分析。尽管人们通常将处理后的信息用于决策，但并非所有信息都能为用户带来积极的结果。有一些用户对此持负面看法。为了最大限度地减少这种负面影响的发生，对各种用户需求的分析以及针对每个需求使用户输入多样化是必不可少的。因此，必须预测来自单个输入的结果。过去，由于系统依赖于单一专家系统，因此需要接受和处理推荐的各种限制和多重需求。所以，建议的结果也存在各种问题。为了解决这个问题，本研究将层次分析法应用于多顾问配置。在提议的系统中，定义了一个或多个顾问，在分析了预定义的需求后，系统只接受可以处理的需求并计算单个推荐结果。将通过学习所有情况来研究推荐系统。