Research And Application Of Visual Recommendation Method For Geospatial Data

As one of the effective means of representing geographic information,geographic visualization can directly improve the cognitive efficiency of users when they are perceiving geospatial data.The existing geographic information visualization relies heavily on the background knowledge and visualization skills the data workers own.Therefore,the geographic visualization task is usually very time-consuming and challenging.To lower the threshold of visualization of geographical data,this paper propose a novel chart recommendation system of geographic information visualization called GeoVis.This system extracts the distribution characteristics with adaptive kernel density estimation,and recommends the map type that can best reflect the regularity of data distribution based on latent code.The key idea of how the data-driven recommendation work is to use latent code to express data features and then learn the mapping between data features and visual styles.At the same time,this system recommends design choices(e.g.map styles and color schemes).Users only need to browse the recommendation results to realize explorations and analyses of the dataset,which will greatly improve their work efficiency.This paper conducted a series of evaluation experiments on the proposed system,including case study and user research.The experimental results prove the practicality and effectiveness of the system,which can better recommend the appropriate geographic visualization results.In a word,the contributions of this paper are as follows:· This paper improve the kernel density estimation algorithm and perform spatial feature mining based on the improved algorithm.Through comparing experiments,we find that the method can effectively obtain spatial features.· This paper propose a recommendation model based on latent code to learn the mapping relationship between data features and map type.We find that the recommen-dation model by latent code has high accuracy.At the same time,we use aesthetic measure to recommend design choices.· This paper propose an automatic recommendation method for different charts under the given scattered data,so that users can easily visualize the local geographic information data.As far as we know,this is the first system to automatically recommend charts for geographic information data.We conduct a user survey to verify the consistency between the charts generated by our system and users’ visual perception.Besides,our system provides interactive functions to help users perform data analysis more effectively.