污染源信息推荐的用户喜好模型研究

Study on User Preference Model about Recommendation of Pollution Source Information

由于污染给社会生活带来的诸多困扰和污染源的固有特性,作为污染源信息需求者的环境保护机构和个人,如何从大量污染源信息中找到自己关注的信息;同时,对于污染源信息提供者,怎样使自己的信息为广大用户所关注,是环保领域比较突出的矛盾和问题。本文通过建立基于年龄和职业的用户喜好模型,利用UFTB算法从用户看过的污染源信息及其信息类型入手,对用户看过的污染源信息类型与评分数据进行分析。在建立分析污染源信息推荐模型中,采用协同过滤算法计算修正后的余弦相似度,对缺省值进行预测以优化算法。为防止过度优化,采取剔除用户非喜好类型污染源信息,得到优化缺省值预测矩阵,将相似度数据带入推荐公式得出数值并使用排序,根据搜索出的与目标用户相似度最高的N位用户的喜好对目标用户进行污染源信息推荐。

Because of the many problems brought by pollution to social life and the inherent characteristics of pollution sources, as the environmental protection institutions and individuals who demand infor-mation from pollution sources, how to find their own information from a large number of pollution source information, and how to make their own information for the vast number of users concerned about, are the more prominent contradictions and problems in the field of environmental protec-tion. By establishing an age-based and occupation-based user preference model, UFTB algorithm is used to analyze the type of pollution source information and scoring data that users have seen. In establishing the recommendation model for analyzing pollution source information, the modified cosine similarity is calculated by using the co-filter algorithm, and the default value is predicted to optimize the algorithm. In order to prevent over-optimization, we should take the information of eliminating the user’s non-preferred type of pollution source, get the optimization default predic-tion matrix, bring the similarity data into the recommended formula to get the value and use the sort, and recommend the pollution source information to the target user according to the prefer-ences of the n-bit users with the highest similarity to the target user.