Product perceptual image vocabulary extraction method and system

Abstract

The invention discloses a product perceptual image vocabulary extraction method and system, and the method comprises the following steps: collecting comment text data of a target product, carrying outthe word segmentation of the comment text data, and obtaining evaluation vocabularies; extracting high-frequency vocabularies for evaluating the appearance in the evaluation vocabularies as central vocabularies, and extracting adjectives in the evaluation vocabularies to obtain adjective vocabularies; converting the evaluation vocabulary into a word vector, calculating the similarity between eachadjective vocabulary and the central vocabulary based on the word vector, and extracting the corresponding adjective vocabulary as an initial perceptual image vocabulary according to the similarity;and clustering the initial perceptual image vocabularies, and extracting the corresponding initial perceptual image vocabularies as perceptual image vocabularies according to a clustering result. Theperceptual image vocabularies of the target product can be objectively and accurately extracted based on the comment text data, meanwhile, the labor cost can be reduced, and the extraction efficiencyis improved.

Description

technical field [0001] The invention relates to the field of computer-aided design, in particular to a method and system for extracting product perceptual image vocabulary. Background technique [0002] In view of the increasingly strong emotional needs of consumers for products nowadays, designers need to accurately obtain user needs in the process of product appearance design in order to design products that meet user emotional needs. [0003] Facing a product, users usually use their own perceptual image models to match and evaluate. At this time, certain perceptual image vocabulary will be used, such as "beautiful", "luxury" and so on. The traditional method of extracting perceptual image vocabulary is usually to invite several experts with semantic learning background and product field background, and then use the card sorting method to preliminarily screen the collected relevant perceptual image vocabulary before classifying and extracting. This method has high labor c...

AI Technical Summary

Problems solved by technology

The traditional method of extracting perceptual image vocabulary is usually to invite several experts with semantic learning background and product field background, and then use the card sorting method to preliminarily screen the collected relevant perceptual image vocabulary before classifying and extracting. This method has high labor costs. , rely too much on experts, have a large subjective component, too many interference factors, and are not conducive to the processing of a large number of words, and cannot extract image words for a large number of users' perceptual intention samples, which is out of touch with the technology in the era of big data

Images