Knowledge reasoning system and method based on social network knowledge mapping

Abstract

The invention discloses a knowledge reasoning system and method based on the social network knowledge mapping. The system comprises a data source module, a multigraph network engine module, a knowledge mapping discovery module, a distributed graph database module, and a core sub-algorithm module; the data source module, the knowledge mapping discovery module, the distributed graph database module, and the core sub-algorithm module are all connected with the multigraph network engine module, and the distributed graph database module is connected with the core sub-algorithm module. According to the knowledge reasoning system and method based on the social network knowledge mapping, more social relationships can be discovered through the knowledge mapping of the social networks, hidden relationships in the knowledge maps of the social networks can be found as needed, according to the algorithm model, the graph models are periodically and incrementally updated, and more innovative and more accurate relationship models are obtained.

Description

technical field [0001] The present invention relates to a knowledge reasoning system and method, in particular to a knowledge reasoning system and method based on a social network knowledge map. Background technique [0002] The current analysis methods based on social network knowledge graphs are usually based on the three basic data sources of entity database, attribute database, and relationship database to analyze multiple graph networks, and then discover the knowledge information through the knowledge graph. Since the entity database, attribute database and relational database are basic databases, although the data volume is huge and the types are rich. Due to the large volume and variety, it is impossible to find specific and useful graphic data on demand, and it is difficult to produce efficient and useful graphic models, and the analysis accuracy of the corresponding relationship method is low. Entity databases, attribute databases, and relational databases are rel...

AI Technical Summary

Problems solved by technology

Due to the large volume and many categories, it is impossible to find specific and useful graphic data on demand, it is difficult to produce efficient and useful graphic models, and the analysis accuracy of the corresponding relationship method is low

Entity database, attribute database, and relational database are relatively explicit graphic data, and some common graphic data can be directly queried, lacking many innovative graphic modes

Images