System evaluation method based on knowledge graph and network analysis method

Abstract

The invention discloses a system evaluation method based on a knowledge graph and a network analysis method. The system evaluation method comprises the following steps: establishing the knowledge graph according to text data related to an evaluation target; a control layer of the network analysis method is determined, then a network layer is constructed by utilizing knowledge graph query and specific indexes controlled by keyword word vectors and retrieval criteria according to control layer criteria, and the network layer is modified or supplemented by experts; providing relative importance scales among the indexes for the expert group, correcting the scales according to the similarity between the indexes and the criteria, constructing a judgment matrix, calculating a limit relative sorting vector of the network analysis method, and determining the weight of each index. The efficiency of the evaluation process is improved; meanwhile, the relative importance scale between the indexes is corrected based on the similarity, and the objectivity of the evaluation decision process is improved.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a system evaluation method based on knowledge graph and network analysis method. Background technique [0002] The concept of knowledge graph was first proposed by Google in 2012, and it was initially applied to improve the quality of its search engine. A knowledge graph is essentially a large-scale semantic network with rich nodes and relationships. The nodes that constitute the knowledge graph represent entities or concepts, and the edges represent various relationships between entities or concepts. The technical process of the knowledge map is generally as follows: first determine the knowledge representation model, then select asynchronous knowledge acquisition means to import knowledge according to the data source, and then comprehensively use knowledge reasoning, knowledge fusion, knowledge mining and other technologies to improve the quality of the con...

AI Technical Summary

Problems solved by technology

[0004] At present, most of the research on system evaluation methods tends to be combined with specific applications. The theoretical basis is often the improvement of a single system evaluation method and the synthesis of multiple existing system evaluation methods. Research and development have encountered bottlenecks.

Traditional systematic evaluation methods often rely too much on experts' opinions, which will lead to incomplete index system and difficulty in reflecting the potential relationship between indicators; the distribution of the weight of each factor is highly subjective; the entire system evaluation process has a long period and low efficiency; Existing data cannot be quickly and fully utilized

Images