Commodity classification method and device

Abstract

The invention discloses a commodity classification method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining commodity classification training data; training to obtain a commodity classification model for commodity classification based on a neural network by using the commodity classification training data; according tothe commodity description information of the to-be-classified commodities, using the commodity classification model to predict the probability that the to-be-classified commodities belong to the commodity categories in the commodity classification table and the probability that words in the commodity description information of the to-be-classified commodities serve as the commodity categories; and determining the commodity category to which the to-be-classified commodity belongs according to the sequence of the predicted probabilities from high to low. According to the specific implementationmode, the effectiveness and reliability of commodity classification training data are guaranteed, automatic classification of commodities is achieved, and meanwhile possible new vocabularies can be mined to serve as commodity classifications.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a commodity classification method and device. Background technique [0002] With the increasing variety of commodities, in order to facilitate the management of commodities and facilitate users to quickly find the commodities they are interested in or intend to purchase from a large number of commodities, it is necessary to classify the commodities. [0003] At present, the commonly used product classification method is to use a manually set hierarchical classification structure to classify products through manual classification. For example, a flat-screen TV is classified as "household appliances, major appliances, and flat-screen TVs." , where "Household Appliances" is the highest-level classification, "Major Appliances" is the second-level classification, and "Flat Panel TV" is the last-level classification. [0004] In the process of realizing the present invention...

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the inventor found that there are at least the following problems in the prior art: due to the large variety of commodities, manual classification requires a large amount of labor, which makes the efficiency of commodity classification low; the same commodity may belong to multiple categories, and It is difficult to find the most suitable product category by manual classification; the artificially set hierarchical classification structure has its own limitations, is not easy to adjust, and cannot well adapt to new product categories

Images