Eye-Tracking Web Page Object Mapping to Reduce Data Volume
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye-tracking technologies face challenges in accurately tracking user gaze points on digital displays due to dynamic web page structures, generating large data volumes that overwhelm processing resources and storage, and struggling to identify and process various types of visual content efficiently.
Innovation Solution
The system transforms gaze points and digital display content into a common coordinate system, identifies relevant objects using the Document Object Model (DOM), and stores only unique data points, optimizing data volume and processing requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If eye-tracking data is collected at high rates (30-120 gaze points per second), then measurement precision is improved, but data volume increases dramatically creating storage and processing burdens
Solution Approach 1:
The patent extracts only the essential information from high-rate eye-tracking data by identifying and recording unique objects of interest and their corresponding gaze points, rather than storing all raw gaze point data. This extraction process filters out redundant information while preserving the core visual attention information.
Solution Approach 2:
The patent changes the parameter of data representation from continuous high-frequency gaze point coordinates to discrete object-identifier mappings. By transforming the data structure to store only unique object references and their gaze points, the system maintains measurement precision while dramatically reducing data volume.
2Reliability
If complete records of gaze points and digital display content are stored, then reliability of visual attention tracking is improved, but processing power and storage requirements become computationally intensive
Solution Approach 1:
The system extracts only the necessary elements for reliable visual attention tracking by identifying unique objects in the browser window and storing their identifiers along with gaze points. This extraction eliminates the need to process and store complete digital display content while maintaining tracking reliability.
Solution Approach 2:
The patent performs preliminary identification and categorization of objects in the browser window before storing gaze data. By pre-processing the display content to create an object inventory with unique identifiers, the system reduces the computational burden during actual gaze data collection and storage operations.
3Loss of information
If all gaze point data and display snapshots are stored at high rates, then completeness of visual attention record is improved, but storage space requirements become prohibitive
Solution Approach 1:
The patent extracts the essential visual attention information by storing only unique object identifiers and their corresponding gaze points, rather than storing complete display snapshots. This extraction maintains the completeness of the visual attention record while dramatically reducing storage space requirements.
Solution Approach 2:
Instead of storing actual display content snapshots, the system creates simplified copies in the form of object identifier references. These symbolic copies preserve the essential information about what was viewed while occupying minimal storage space compared to full image copies.
Data Source
AI summary
Systems and methods for collecting visual attention information are described. The methods comprise the steps of displaying a browser window on a display (210); estimating a user's (220) gaze point within the display (210); transforming the geometry of the estimated gaze point and/or the geometry of the browser window to a common coordinate system; identifying an object (215) in the browser window that corresponds to the estimated gaze point; and storing the estimated gaze point and data corresponding to the identified object (215).