Evaluation method of enterprise operating conditions based on electric power big data

Abstract

The invention discloses a method for evaluating the business status of an enterprise based on electric power big data. First, the characteristics of the original power data of the enterprise are extracted to obtain the second-level dimension features, and then the second-level dimension features are extracted to obtain the first-level dimension features, and the isolated forest anomaly detection is further performed The algorithm is combined with the K-means clustering algorithm to evaluate the business status of the enterprise. The present invention can better express the operating status of the enterprise from all aspects through the hierarchical extraction of the original data; and the present invention can dig out the operating status information of the enterprise in the electric power big data under the influence of as few subjective factors and empirical factors as possible, In order to ensure the accuracy of the assessment of business conditions.

Description

technical field [0001] The invention belongs to the technical field of electric power big data application, and relates to a technology for evaluating enterprise operating conditions based on electric power big data. Background technique [0002] Big data technology will promote the upgrading and transformation of information technology platforms, supplement the ability to analyze and utilize unstructured data, and enhance the ability to mine the value of massive data resources. Electric power big data is a new asset of electric power companies, which can promote the development of business management of electric power companies in a more refined and efficient direction. Power big data contains a wealth of information related to electricity companies. The analysis of electric power big data can dig out the operating conditions of enterprises hidden in electric power big data. [0003] With the recent rapid development of data availability, computing power and new algorithm...

AI Technical Summary

Problems solved by technology

The main problems in the above power user credit evaluation method and system are: (1) Since the power data more reflect the production and operation status of the enterprise, and the credit of the enterprise reflected in the public credit data is limited, it is necessary to use these data to evaluate the credit of the enterprise. The credibility is not high; (2) Since the number of cluster centers needs to be divided artificially, it will not only be affected by subjective and empirical factors, but also do not know the credit degree of the enterprise in advance, so the credit rating is not reliable; (3) ) credit rating is a discrete variable, so the credit rating reflected by the rating cannot reflect the credit difference between enterprises of the same rating

[0005] It can be seen that the current use of big data based on electric power is mostly in the analysis of electric power enterprises themselves and the credit evaluation methods of electric power enterprises, which is difficult to objectively and effectively reflect the production and operation of enterprises, and thus it is difficult to provide effective data support for enterprise development.

Images