Device record processing method, device, computer device and storage medium

Abstract

The present invention proposes an equipment record processing method, device, computer equipment, and storage medium, wherein the method includes: generating a first feature vector in the first vector space according to sensor measurement values ​​in each equipment record, and generating a first feature vector in the first vector space according to each equipment record According to the maintenance description in the second vector space, the second eigenvector in the second vector space is generated; according to the mapping relationship between the first vector space and the second vector space, the first mapping vector and the second mapping vector are determined; the second mapping vector is selected Add to the first vector set containing the first feature vector, select the first mapping vector to add to the second vector set containing the second feature vector; cluster the vectors in the first vector set and the second vector set Obtaining the first and second target clusters; combining similar clusters in the first target cluster and the second target cluster, and determining the category to which the device record belongs. Through this method, the amount of information can be increased, and the disadvantage of insufficient available features in the equipment record can be made up for.

Description

technical field [0001] The present invention relates to the technical field of information processing, in particular to a device record processing method, device, computer device and storage medium. Background technique [0002] The same type of equipment produced by the same manufacturer may be used in different places. Taking fire-fighting equipment or air-conditioning equipment as an example, almost every building will be equipped with fire-fighting equipment and air-conditioning equipment. There are many devices of the same model. These devices need to be maintained regularly or irregularly during use, and they need to be repaired when there is a fault. After the maintenance and repair, the maintenance description used to briefly explain the repair or maintenance is manually filled out. However, since these maintenance descriptions are filled in manually, different words may be used for similar repairs or maintenance. How to classify these massive maintenance descriptio...

AI Technical Summary

Problems solved by technology

In addition, word segmentation will also bring more errors, and the maintenance description is mainly entered manually, the information is messy, and there are few available features

When using text mining to directly classify maintenance descriptions and describe the same type of maintenance descriptions in a unified way, there is a technical problem that the classification of maintenance descriptions is inaccurate, resulting in the inability to use a unified way of expression

Images