Page processing method and device and storage medium

By performing sentence-partitioning and word-partitioning on the automotive information page and using the recognition model for semantic understanding, the problem of not being able to fully identify and bind product nouns in automotive information in the existing technology is solved, and a more comprehensive information display is achieved.

CN119759242APending Publication Date: 2025-04-04BEIJING CHENGSHI WANGLIN INFORMATION TECH CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202411824901.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-11
Publication Date
2025-04-04

AI Technical Summary

Technical Problem

When the prior art automatically displays car information details, due to the technician's understanding of the products, it is impossible to fully find and bind product terms on the page, resulting in insufficient comprehensive information.

Method used

By obtaining the text content of the target page, performing sentence classification and word segmentation processing, using the recognition model for semantic understanding, analyzing the candidate word segmentation set according to the preset product attribute dimension, determining the product noun, and binding it to detailed information.

Benefits of technology

It realizes more comprehensive identification and binding of product nouns in the page text content, and improves the comprehensiveness and accuracy of automatic display information.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The embodiment of the invention provides a page processing method and device and a storage medium. In the embodiment of the application, the text content in the target page is subjected to sentence segmentation and word segmentation processing to obtain at least one sentence and a candidate word segmentation set corresponding to the at least one sentence, and the recognition model can be utilized to perform semantic understanding on the sentence according to the preset commodity attribute dimension to output commodity attribute description information for each candidate word segmentation. And if a target word matched with the commodity attribute description information is found in a preset commodity word bank, determining the candidate segmented word as a commodity noun, and binding detail information to the found commodity noun. In this way, semantic understanding is conducted on the clauses and the candidate word segmentation sets corresponding to the clauses through the recognition model, and the semantics expressed by each vocabulary in the text content can be understood more accurately; in combination with the preset commodity word bank, the commodity nouns in the text content can be identified more comprehensively and accurately, so that more comprehensive detail information is bound to the text content in the page.
Need to check novelty before this filing date? Find Prior Art