Title: A risk identification method for abnormal key data in the whole process of production project

Authors: Ya Zhou; Yaopeng Zhao; Wei Li; Jianhui Liang; Qiwu Zou

Addresses: Qingyuan Power Supply Bureau of Guangdong Power Grid Co., Ltd., Qingyuan, Guangdong, China ' Qingyuan Power Supply Bureau of Guangdong Power Grid Co., Ltd., Qingyuan, Guangdong, China ' Qingyuan Power Supply Bureau of Guangdong Power Grid Co., Ltd., Qingyuan, Guangdong, China ' Qingyuan Power Supply Bureau of Guangdong Power Grid Co., Ltd., Qingyuan, Guangdong, China ' Qingyuan Power Supply Bureau of Guangdong Power Grid Co., Ltd., Qingyuan, Guangdong, China

Abstract: In order to improve the identification accuracy of risk categories in each stage of production projects, a method for identifying abnormal risks of key data in the whole process of production projects is proposed. Extract the risk factors of the whole process data of the production project, and use the improved fuzzy comprehensive evaluation method to judge whether the risk factor risk item is empty; screen the data with high correlation with the risk factor as abnormal key data; identify the risk according to the corresponding risk item of the abnormal data category. Taking the artificial intelligence production project as an example, the screening risk data is used as the test data to set up a comparative experiment. The results show that the proposed method has a higher recognition accuracy rate of risk categories, and the recognition results are more accurate and reliable.

Keywords: fuzzy comprehensive evaluation; production item; risk factor; risk item; abnormal data; risk identification.

DOI: 10.1504/IJDMB.2022.130345

International Journal of Data Mining and Bioinformatics, 2022 Vol.27 No.1/2/3, pp.1 - 12

Received: 15 Aug 2022
Accepted: 15 Dec 2022
Published online: 17 Apr 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article