地理信息志愿者信誉度评估的版本相似度模型——以面目标为例

Version Similarity-based Model for Volunteers' Reputation of Volunteered Geographic Information:A Case Study of Polygon

针对自发地理信息中存在大量恶意、虚假、低质量数据,提出了一种基于版本相似度的VGI志愿者信誉度计算模型。该模型将每个志愿者对某个地理空间目标的一次编辑结果定义为一个版本,当其他用户编辑该目标版本时,通过计算版本相似度来获得其他用户对该志愿者这个目标版本的支持度;然后通过计算其他贡献者对某志愿者所贡献的每个目标的支持度,对所有目标的支持度进行加权平均获得该志愿者的综合信誉度。其中版本相似度综合目标空间和属性相似性的主要因素进行加权计算。然后以面目标为例阐述了本文志愿者信誉度计算过程。为了验证本文信誉度计算模型的合理性,笔者采用德国柏林OpenStreetMap数据进行试验,试验表明通过本文模型计算获得的用户信誉度与其贡献的要素质量总体上正相关。

At present,it is difficult to evaluate the qual ity of volunteered geographic information(VGI), which have mal icious,false,and poor qual ity data.Therefore,a version simi larity-based reputation model for volunteers of VGI system is proposed.In the model,each editing to a geographic spatial object of each volunteer is defined as a version.When the object version is modified by other users,support degree of the version is computed through version simi larity.Then,support degree of every object contributed by a volunteer is calculated according by others’modifications.The volunteer’s reputation is obtained through weighted average of al l his support degrees.The version simi larity composites major factors of spatial simi larity and attributes simi larity between versions of a same object.Polygon objects are employed as an example to describe the computation process of volunteer reputation of our model.For verifying and analyzing the rational ity of our reputation model,Berl in’s historical data from OpenStreetMap are used for experiments.It shows that users’reputation calculated by our model has a positive correlation with qual ity of objects contributed by them as a whole.