Method and device for classifying repair shops

Abstract

The embodiment of the present application discloses a repair shop classification method and a related device. According to the feature information of n repair shops, respectively construct n feature information sets corresponding to the n repair shops; determine the C-type tags corresponding to the L target feature information sets from the n feature information sets; and each The target feature information set corresponds to a label; according to the L target feature information sets and the C-type labels corresponding to the L target feature information sets, determine (n-L) unlabeled feature information sets by the label propagation algorithm LPA A tag corresponding to any feature information set in the C-type tags. The repair shop classification method provided in the embodiment of the present application predicts and determines the repair shop category corresponding to a large amount of unlabeled data through a small amount of marked repair shop data, reduces the difficulty of data mining, and makes the classification more objective and reasonable.

Description

technical field [0001] The present application relates to the technical field of data mining, in particular to a maintenance shop classification method and device. Background technique [0002] Repair shops directly provide various services to consumers, and their professional level and service quality affect the experience of consumers. According to the large amount of data of each repair shop, it is of great practical significance to distinguish repair shops with different professional levels and service quality. [0003] At present, the classification method based on the linear regression supervised learning model and the expert system, the classification rules are not uniform, resulting in large deviations in the results, and the linear correlation between the classification results and the data features is weak. The supervised learning algorithm trains a machine learning model and establishes a classification method for a large amount of objectively marked repair shop ...

AI Technical Summary

Problems solved by technology

[0003] At present, the classification method based on the linear regression supervised learning model and the expert system, the classification rules are not uniform, resulting in large deviations in the results, and the linear correlation between the classification results and the data features is weak

The supervised learning algorithm trains the machine learning model and establishes the classification method for a large amount of objectively marked repair shop data; in practice, it is very difficult to obtain a large amount of objectively marked data, which requires a lot of manpower, material resources, and financial resources.

Another classification method based on the K-means clustering unsupervised learning algorithm has high requirements for the input data, and the actual significance of the classification results is uncertain

In addition, unsupervised learning algorithms directly model and classify unlabeled original repair shop data, the results may not be objective, and the practicability is questionable

Images