Rapid and automatic material classification method and device based on single-channel algorithm

Abstract

The invention relates to a rapid and automatic material classification method and device based on a single-channel algorithm, belongs to the field of material management and artificial intelligence, and solves the problems of low recognition accuracy and slow speed in the prior art. The method comprises the following steps: collecting new material data; calculating the similarity between the new material data and clusters corresponding to each material in a preset material classification database, taking the cluster with the maximum similarity as a target cluster, and performing the following judgment according to the maximum similarity: when the maximum similarity is greater than the first threshold and less than a second threshold, determining that the new material data is the target cluster; distributing the new material data to a classification label corresponding to the target cluster, and writing the new material data as cluster feature data into a cluster data set corresponding to the target cluster; wherein the cluster feature data is used for describing the features of the clusters in the material classification database and is stored in the cluster data sets corresponding to the clusters. According to the technical scheme provided by the invention, the accuracy of data classification can be improved.

Description

technical field [0001] The invention belongs to the fields of material management and artificial intelligence, and in particular relates to a method and device for rapid automatic classification of materials based on a single-channel algorithm. Background technique [0002] The construction of material automation management system is an important strategic goal to promote the modernization of enterprises. With the development of industry and the improvement of generation technology, the types and quantities of materials involved in enterprise material management have increased rapidly. It is time-consuming and laborious to rely on manpower to manage huge material data, which can no longer meet the needs of current material management. [0003] Nowadays, artificial intelligence technologies such as natural language processing and machine learning can identify material classification through material data, realize automatic material classification and improve material classifi...

Images