High-risk enterprise illegal production identification method based on electric power big data

The invention discloses a high-risk enterprise illegal production identification method based on electric power big data, and the method is characterized in that the method comprises the following steps: 1, obtaining a list of a high-risk enterprise and a non-high-risk enterprise, matching power consumption data and user basic information, and carrying out the preprocessing of the data; 2, constructing an enterprise characteristic feature library, and extracting and screening enterprise characteristic features; 3, establishing and training a high-risk enterprise identification model by using the screened enterprise characteristics, and identifying high-risk enterprises; 4, for the identified high-risk enterprises, constructing a power utilization production characteristic feature library, and extracting and screening power utilization characteristic features; and 5, establishing and training an illegal production identification model by using the screened power utilization production characteristics, and iden