Data automatic matching method, electronic equipment and computer readable storage medium

Abstract

The invention discloses a data automatic matching method. The data automatic matching method comprises the steps of acquiring classification features obtained by a feature extraction operation; performing normalization processing on the classification features obtained by the feature extraction operation according to a preset dynamic list to obtain normalized classification features; extracting aspecial field containing detachable characters from the normalized classification features, splitting the special field into a plurality of field fragments according to positions of the detachable characters in the special field, and matching the split field fragments with target classification; and matching the unsuccessfully matched field with the target classification through a preset field logic inclusion relation. The invention further provides electronic equipment and a computer readable storage medium. The matching success rate and accuracy rate of the classification features and the target classification can be improved by using the data automatic matching method disclosed by the invention.

Description

technical field [0001] The invention relates to the field of computer information technology, in particular to a data automatic matching method, electronic equipment and a computer-readable storage medium. Background technique [0002] Feature extraction is an important step in various data mining prediction models, and normalizing classification features according to existing target classifications plays a very important role in the data preprocessing stage. However, the direct and complete matching of uncleaned classification features and target classifications has problems such as extremely low data matching success rate and accuracy, which cannot meet the model requirements. Moreover, due to the continuous influx of massive data, the magnitude of the data has far exceeded the control range of manual matching. Therefore, the design of the data matching algorithm in the prior art is not reasonable enough and urgently needs to be improved. Contents of the invention [0...

AI Technical Summary

Problems solved by technology

However, the direct and complete matching of uncleaned classification features and target classifications has problems such as extremely low data matching success rate and accuracy, which cannot meet the model requirements.

Moreover, due to the continuous migration of massive data, the magnitude of data has far exceeded the control range of manual matching

Therefore, the design of the data matching algorithm in the prior art is not reasonable enough and urgently needs to be improved.

Images