Knowledge Graph-based Diversity Analysis of Supplier Holographic Portraits

Abstract

Fully understand the development of suppliers in order to make better supplier selection. This paper is based on the knowledge graph, through the knowledge updating of the knowledge graph combined with the Transformer model for knowledge extraction of supplier entity relationship, forming the ternary semantic information of supplier entity relationship. Then, based on the big data platform for the construction of supplier holographic portrait and knowledge storage, through information integration, analysis and other links to identify the supplier attributes for label definition. Taking cell phone product suppliers as an example, we use Python technology to obtain relevant data and validate the specific role of supplier holographic portrait in terms of the supplier’s comprehensive strength, behavioral prediction, transaction closeness, and comprehensive evaluation. The results show that: the correlation between the comprehensive strength of suppliers and the amount of winning bids is strong, and its R2 test result is 0.5924, and it can realize the behavioral prediction of suppliers in the supply chain. Supplier H offers a range of cell phone products in 2022, which is 17.62%21.17% higher than the benchmark market price. The holographic portrait of suppliers based on a knowledge graph combined with a big data platform can meet the need to carry out an all-around analysis of suppliers and provide more accurate support for diversified decision-making on the demand side.

Keywords

• knowledge graph
• transformer model
• knowledge extraction
• supplier
• holographic portrait
• 00a73