A big data-oriented intelligent screening and sorting method for project cooperative enterprises

Abstract

The invention proposes a big data-oriented intelligent screening and sorting method for project cooperation enterprises. When the project demander has project cooperation needs, it always seeks cooperative enterprises through more traditional methods such as intermediaries or circles of friends. The invention utilizes the relevant big data of project cooperation between the project demander and the project undertaking enterprise, and models the cooperative project and the undertaking enterprise as two attribute sets. According to the evaluation of the cooperation satisfaction of the undertaking enterprise by the project demander, and the mutual information between each attribute of the cooperative project and the undertaking enterprise, a Bayesian network is constructed to calculate the probability distribution of the satisfaction of the project cooperation. After the construction of the Bayesian network is completed, according to the project requirements, the attributes of each cooperative project are assigned, and the attribute values ​​of each enterprise in the big data are sequentially substituted to calculate the satisfaction probability of each enterprise and the cooperative project. And screen out the companies with a higher probability of satisfaction, sort them according to the probability of satisfaction, and finally output them to the project demander for their reference.

Description

technical field [0001] The invention relates to a screening and sorting method, in particular to a big data-oriented intelligent screening and sorting method for project cooperative enterprises. Background technique [0002] For the evaluation and screening methods of objective entities, AHP is mainly used at present. AHP is a simple, flexible and practical multi-criteria decision-making method for quantitative analysis of qualitative problems. It is characterized by dividing various factors in complex problems into interrelated and orderly levels to make them organized, and combining expert opinions with analysts' opinions based on the subjective judgment structure (mainly pairwise comparison) of a certain objective reality. The objective judgment results are directly and effectively combined to quantitatively describe the importance of pairwise comparisons of first-level elements. Then, mathematical methods are used to calculate the weights reflecting the relative import...

AI Technical Summary

Problems solved by technology

However, the general model of this type of method is relatively simple, and the variables screened overlap with each other. Although it has some advantages in terms of computational complexity, it cannot flexibly change the evaluation criteria according to actual needs.

Images