一种页面分析方法及装置

By acquiring control attribute information and fusing control features using a global feature extraction function, the problem of difficulty in datafication of page structure tree representation is solved, and datafication of structural feature extraction for page analysis is realized.

CN115729800BActive Publication Date: 2026-07-17DOUYIN VISION CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
DOUYIN VISION CO LTD
Filing Date
2021-08-30
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

In existing technologies, page structures represented by page structure trees are difficult to quantify and cannot be applied to page analysis.

Method used

By obtaining the attribute information of each control on the target page, the control features are fused using a global feature extraction function to obtain structural features, and analysis is performed based on these structural features.

Benefits of technology

It enables the extraction of data structure features from pages with any number of controls, avoids the influence of the input order of control features on the results, and supports page analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115729800B_ABST
    Figure CN115729800B_ABST
Patent Text Reader

Abstract

本发明实施例提供了一种页面分析方法及装置,涉及数据处理技术领域。该方法包括:获取目标页面中各个控件的属性信息;根据各个控件的属性信息获取各个控件的控件特征;通过全局特征提取函数,对所述各个控件的控件特征进行融合,得到所述目标页面的结构特征;其中,所述全局特征提取函数支持对任意数量的控件进行控件特征融合,且,在所述全局特征提取函数中所述任意数量控件的控件特征采用不同的输入位置的情况下,所述全局特征提取函数输出的页面结构特征均相同;基于所述目标页面的结构特征对所述目标页面进行分析。本发明实施例用于解决基于页面结构树表示的页面结构难以数据化,无法应用于页面分析的问题。
Need to check novelty before this filing date? Find Prior Art