In the background of big data, the relationship presented in data is not intuitive, so the visualization of the relationship is of great practical value for extracting implicit knowledge. Considering the edge-node relationship of the visualization of character relations and the visualization requirements of displaying the relevant information, the D3.js was improved to optimize the links between edges and nodes, which is convenient for data processing, especially for dynamic data. The shortest path algorithm was improved to solve all the minimum rings containing the specified nodes of undirected graphs, and applied to seeking groups in the relationship map. The data-driven features of D3.js visualization library were taken advantage of to display the character relationship map with data exchange function.