Webpage Zone Classification via HTML Vector Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Webpage administrators face difficulties in understanding the content and arrangement of webpages due to the varied arrangements of zones or elements, which hinders quick analysis and optimization.
Innovation Solution
An experience analytics system employing machine learning to automatically determine zone types on webpages, using HTML code snippets to generate vectors for training models that can classify nodes without requiring additional effort for new zone types or page categories.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual analysis methods are used to understand webpage zones, then administrators can analyze webpage content, but the process is time-consuming and difficult due to varied zone arrangements
Solution Approach 1:
The patent replaces manual mechanical analysis with an automated machine learning system. The system uses computer vision algorithms to automatically detect and classify webpage zones, substituting human administrators' manual inspection with automated image processing and pattern recognition techniques.
Solution Approach 2:
The webpage analysis system performs self-service by automatically identifying and categorizing zones without requiring manual configuration. The machine learning model autonomously processes webpage images, detects zone boundaries, and classifies zone types based on visual patterns, enabling the system to serve itself rather than requiring continuous human intervention.
2Adaptability or versatility
If traditional classification methods are used for zone types, then existing zones can be categorized, but additional effort is required for each new zone type or page category
Solution Approach 1:
The patent implements a universal machine learning model that can handle multiple zone types and page categories simultaneously. The system uses a unified architecture that processes diverse webpage layouts and zone configurations through the same classification framework, eliminating the need for separate models for different zone types and reducing adaptation effort.
Solution Approach 2:
The system performs preliminary action by pre-training the machine learning model on a comprehensive dataset that includes multiple zone types and page categories. This pre-training establishes a robust foundation that enables the model to quickly adapt to new zone types with minimal additional training, as the core classification capabilities are already in place.
Data Source
AI summary
Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for determining zone types of a webpage. The program and method provide for generating, for at least one node a first webpage, a vector including HTML content corresponding to the at least one node; providing the vector as input to a machine learning model configured to output a predicted node type based on the vector, the machine learning model having been trained with plural vectors including HTML content corresponding to plural nodes of second webpages; and determining, based on the output of the machine learning model, the predicted node type of the vector, to classify the at least one node.