MLCC capacitance parameter matching method

Abstract

The invention belongs to the technical field of artificial intelligence and electric devices, and provides an MLCC capacitance parameter matching method. The method comprises the following steps: S1,collecting material description content input by a user, and judging whether the material description has a brand and an original factory model or not; S2, carrying out the segmented extraction on thesubstrings corresponding to the original factory model, obtaining parameters of the MLCC capacitor, and obtaining a corresponding product and a replaceable product through matching; S3, performing parameter extraction on the pure material description, and matching a corresponding product and an alternative product; S4, calculating the scores of the matched corresponding products and the alternative products thereof; S5, taking each score of each product as the input of the product, calculating the probability that the user may purchase the product by using a naive Bayesian algorithm, sortingthe products with the attributes being purchased according to the probability, and generating a recommendation sequence. According to the invention, the MLCC capacitance matching efficiency and precision are greatly improved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and electrical devices, and in particular relates to a method for matching MLCC capacitance parameters. Background technique [0002] Due to the related characteristics of MLCC capacitors, and the universal availability of MLCC capacitors. There are many ways to describe MLCC capacitors in the industry. At the same time, the requirements for the use of MLCC capacitors in enterprises, in most cases, pay more attention to whether the key parameters match, and whether they can meet the conditions for development and manufacturing; Corresponding requirements, but no requirements for specific products under the brand. Due to the above related reasons, the internal procurement personnel of the enterprise have more variable descriptions of MLCC. At the same time, in some enterprises, with the purchasing personnel's industry experience and habits of MLCC capacitors and the downward transm...

AI Technical Summary

Problems solved by technology

[0004] Decompose these contents manually. In the traditional procurement industry, the average manual speed is 1min / article, which is low in efficiency and is also affected by factors such as manual experience and working time.

Images