Public culture knowledge graph platform-based comprehensive recommendation system

Abstract

The invention relates to a public culture knowledge graph platform-based comprehensive recommendation system. The system comprises a labelling unit, a label library, a label mining unit, a recommendation unit and a visualization unit, wherein the labelling unit is used for distributing resource labels for extracted resources and distributing user interest labels for extracted user data; the label library is used for storing the resource labels and the user interest labels; the label mining unit is used for carrying out mining analysis on the labels in the label library; the recommendation unit is used for carrying out comprehensive public culture information recommendation according to a mining analysis result of the label mining unit; and the visualization unit is used for carrying out visualized display on a comprehensive recommendation result of the recommendation unit. According to the system provided by the invention, the cross-field, cross-category, cross-data structure and cross-data source public culture knowledge recommendation is realized.

Description

technical field [0001] The invention belongs to the fields of cultural big data recommendation systems and knowledge retrieval, and specifically relates to a comprehensive recommendation system based on a public cultural knowledge map platform. Background technique [0002] The recommendation system recommends relevant information of interest to users based on their click behavior and interest in online resources when browsing the web. The recommendation system is a complex system engineering, which relies on the organic combination of user data, architecture, algorithm, human-computer interaction and other links, and requires the unified combination of statistical technology, data mining technology, information retrieval technology and other disciplines. Obviously, the recommendation method is the core and most critical part of the entire recommendation system, which determines the performance of the recommendation system. At present, the main recommendation methods includ...

AI Technical Summary

Problems solved by technology

[0005] Problem: Most of the current recommendation systems, such as content-based recommendation, collaborative filtering, hybrid recommendation, etc., focus on a single field and a single type of resource recommendation

The novelty and diversity of the recommendation results are insufficient, especially when there is too little user behavior data, there will be problems of cold start and data sparsity, which seriously affect the quality of recommendation

Images