Machine-Learning Web Element Recognition from Browsing Activity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying and verifying web elements in new web pages or applications is time-consuming, cumbersome, and often inaccurate, especially when migrating from one design to another, and existing methods lack the ability to automatically recognize these elements based on user activity.
Innovation Solution
Utilizing machine learning to train a classifier that maps user browsing activity to web elements, enabling the automatic identification and generation of custom tests tailored to the identified elements, thereby streamlining the web testing process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual identification of web elements is used, then accuracy can be maintained, but time consumption and resource expenditure increase significantly
Solution Approach 1:
The system enables automatic self-identification of web elements by training a classifier on user browsing activity patterns. The classifier learns to recognize web elements based on how users interact with them, eliminating the need for manual identification while maintaining accuracy through data-driven classification.
Solution Approach 2:
The patent replaces manual mechanical identification processes with an automated machine learning-based classification system. The classifier uses computational algorithms to analyze browsing activity and automatically identify web elements, substituting human expertise with an automated intelligent system.
2Extent of automation
If existing web testing techniques are used, then basic testing can be performed, but the ability to automatically recognize web elements based on user activity is lacking
Solution Approach 1:
The system incorporates feedback loops where user browsing activity is continuously monitored and used to train and refine the classifier. The classifier learns from actual user interactions with web elements, adjusting its identification accuracy over time based on observed browsing patterns and user behavior.
Solution Approach 2:
The patent implements automated machine learning classification to replace manual testing procedures. The classifier automatically analyzes browsing activity data and identifies web elements without human intervention, enabling fully automated testing while maintaining high reliability through data-driven classification algorithms.
3Productivity
If manual testing procedures are used, then detailed verification can be performed, but resource consumption and complexity increase
Solution Approach 1:
The system performs self-service by automatically generating test cases and identifying web elements without requiring manual testing procedures. The classifier autonomously analyzes browsing activity, identifies web elements, and generates appropriate test cases, significantly improving productivity while reducing the complexity of testing process management.
Data Source
AI summary
A computer-implemented method includes tracking, by a computing device, user browsing activity of a first page having known elements; mapping, by the computing device, the user browsing activity to the known elements; storing, by the computing device, mapping information that maps the user browsing activity to the known elements; tracking, by the computing device, user browsing activity of a second page having unknown elements; identifying, by the computing device, the unknown elements based on the mapping information and the user browsing activity of the second page; and executing, by the computing device, one or more computer-based instructions based on the determining the unknown elements that were identified.