BOM identification method and device based on machine learning, computer equipment and medium

Abstract

The embodiment of the invention discloses a BOM identification method based on machine learning. The method comprises the following steps: constructing a target identification model by using a machine learning packet scikit-learn of a Python platform; obtaining a to-be-identified BOM, and performing feature extraction on the to-be-identified BOM to obtain a plurality of to-be-identified feature items and corresponding to-be-identified feature data; using the to-be-identified feature data as the input of the target identification model for identification, and determining the feature type of the to-be-identified feature items. Therefore, automatic identification of a BOM is achieved, and user participation is not needed; meanwhile, due to the fact that a BOM is identified through a machine learning algorithm, the BOM identification method can be applied to BOMs of different application scenes and has wide applicability. In addition, the invention further provides a BOM identification device based on machine learning, computer equipment and a medium.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a machine learning-based BOM identification method, device, computer equipment and media. Background technique [0002] BOM (Bill of Material) is a file that describes the product structure in a data format. In actual production, BOM is not only a simple collection of parts and materials, but also contains all valuable attribute information of parts, for example, about electronics In the BOM of components, the drawing number, assembly requirements, quality standards, supplier data, tolerance specifications, pricing data, order quantity, etc. of electronic components. As a tool for storing material information, it is necessary to quickly find the required information from the bill of materials. Therefore, it is necessary to provide a BOM identification method. Since the product structure and manufacturing methods of different industries are very different, and after the...

AI Technical Summary

Problems solved by technology

Since the product structure and manufacturing methods of different industries are very different, and after the user lists the components they want, the writing behavior and typesetting format of different users are different. In the process of processing the BOM table uploaded by the user, it is necessary to Through manual intervention, it is difficult to quickly and accurately identify the BOM

[0003] The database matching and string matching methods currently used by the industry to identify the BOM form, although more accurate results can be obtained under the standard template BOM, but it will be helpless when dealing with some BOM forms that are not standardized enough, and for When the parameter model data of similar components is tens of millions or even billions of data, it is not only impossible to use database matching to exhaust all parameter models, but also the large amount of data will lead to time-consuming recognition and affect the recognition efficiency of the BOM table.

Images