Method, storage device and terminal for automatically determining the industry category of an organization

Abstract

The invention discloses a method, a storage device and a terminal for automatically determining the industry category of an organization. The method includes: acquiring the description content of the organization, performing word segmentation processing on the description content of the organization, and constructing a lexicon; extracting features from the lexicon Words, and the position characteristics of the characteristic words in the organization's description content are used as additional features for determining the industry category of the organization; the entropy value of the characteristic words and the reverse document frequency IDF value are calculated respectively, and the characteristic words are screened twice; according to The preset classifier group calculates the conditional probability that the remaining characteristic words belong to each industry category after two screenings. At the same time, combined with the comprehensive analysis of additional features, the industry category of the organization is determined, and the classification process is completed and the result is output. The invention improves the accuracy of judging the industry category of the organization, improves the industry category classification efficiency of the organization, and effectively reduces the risk of the organization being classified into the wrong industry category.

Description

technical field [0001] The invention relates to the technical field of Internet data processing, in particular to a storage device and a terminal for a method for automatically determining the industry category of an organization. Background technique [0002] The industry of an institution (including enterprises, government agencies, public institutions, etc.) has a high reference value in judging the type, operating status, and future development trend of an institution, especially in the loan qualification inspection and approval process. In order to unify the classification standards, the state promulgated the national standard of "National Economic Industry Classification GB / T 4754-2011". , middle class, small class, and the smallest level (small class) has a total of 1094 categories. Specific to an actual institution, how to accurately determine which industry category it belongs to is an important topic of current industry research. [0003] At present, the common i...

AI Technical Summary

Problems solved by technology

Due to the strong subjectivity of manual classification, and the fact that the applicants have different understandings of the national industry standards themselves, many institutions have been classified into the wrong industry categories, and the efficiency of manual classification is low, requiring a lot of manpower , material and financial resources, which bring huge interference to practical applications

Images