Intelligent plan recommendation method based on knowledge graph

Abstract

The invention provides an intelligent plan recommendation method based on a knowledge graph, and the method comprises the steps: building the knowledge graph in a mode from bottom to top, completing the preliminary construction of the knowledge graph through three steps: information extraction, knowledge fusion and knowledge processing, and carrying out the iteration, optimization and updating ofthe knowledge graph through repeating the three steps. According to the recommendation method, entities, relationships and attributes in massive structured data, semi-structured data and non-structured data can be extracted by processing the massive structured data, semi-structured data and non-structured data, and a comprehensive and practical knowledge graph is constructed; and based on the knowledge graph, a plan recommendation technology is researched, a plurality of schemes matched with the scene is optimized from a plan library, and the schemes are recommended to commanders and fighters.

Description

technical field [0001] The invention belongs to the technical field of building knowledge graphs, in particular to an intelligent recommendation method for a plan based on knowledge graphs. Background technique [0002] Specifically, the knowledge map combines the theories and methods of applied mathematics, graphics, information visualization technology, information science and other disciplines with metrology citation analysis, co-occurrence analysis, etc. The core structure, development history, frontier fields, and overall knowledge structure achieve the modern theory of multidisciplinary integration. It displays complex knowledge fields through data mining, information processing, knowledge measurement and graphic drawing, reveals the dynamic development law of knowledge fields, and provides practical and valuable references for subject research. [0003] In the usual process of building knowledge graphs, recommendation technologies based on pragmatic level matching su...

AI Technical Summary

Problems solved by technology

However, there are still some problems, such as (1) it is difficult to meet the needs of fast and accurate matching, there are many deficiencies in the face of precise matching, it is difficult to solve the ambiguity of specific scene descriptions, and the quantitative evaluation of pre-plan optimization; (2) the need for A large number of data samples are used for deep learning and training, but in specific scenarios, the sample data is often too small and difficult to obtain, which has great constraints on the deep learning of artificial intelligence, and cannot meet the needs of deep neural networks for massive samples

Images