Passive User Identification via Biometric Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Active people metering in audience measurement systems faces challenges such as user fatigue and inaccuracies due to the need for frequent self-identification, especially in multi-user environments like households with shared devices like tablets, where incorrect media exposure data can be allocated to the wrong user.
Innovation Solution
Implementing passive user identification using sensors on touchscreen devices to capture body characteristic and usage pattern data during normal device interaction, allowing for automatic user identification without the need for active self-identification, by associating unique identifiers with physiological and behavioral data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If active self-identification methods are used for user identification, then user participation can be obtained, but user fatigue increases and data accuracy decreases due to frequent prompting
Solution Approach 1:
The system performs user identification automatically without requiring user action. Sensors continuously capture body characteristic data and usage patterns, and the processor automatically compares this data against stored profiles to identify the current user, eliminating the need for manual self-identification and reducing user fatigue while maintaining high data accuracy
Solution Approach 2:
The patent replaces the mechanical/manual self-identification process with an automated sensor-based system. Instead of users actively selecting their identity, the system uses sensors to capture physiological data (heart rate, body temperature, galvanic skin response) and behavioral data (typing speed, swipe patterns) and automatically processes this information to identify the user
2Ease of operation
If passive sensor-based identification is implemented, then user fatigue is reduced and participation increases, but device complexity increases due to additional sensors and processing requirements
Solution Approach 1:
The system uses existing multi-functional smartphone sensors (accelerometers, gyroscopes, heart rate monitors, temperature sensors) that serve both traditional device functions and user identification purposes. For example, the accelerometer and gyroscope used for screen orientation and motion detection are also utilized to capture device handling patterns for identification, eliminating the need for dedicated identification hardware
Solution Approach 2:
The patent combines multiple data sources (body characteristic data from sensors, usage pattern data from device interactions, and contextual information) into a unified identification system. The processor integrates these diverse data streams and compares them against stored user profiles to perform identification, reducing overall system complexity through data fusion
3Measurement precision
If multiple body characteristics are monitored for identification, then identification accuracy improves, but energy consumption increases due to continuous sensor operation
Solution Approach 1:
The system implements periodic sampling of body characteristic data rather than continuous monitoring. Sensors capture data at intervals during device usage, and the processor compares these periodic samples against stored user profiles. This approach maintains identification accuracy by capturing sufficient data points while significantly reducing energy consumption compared to continuous sensor operation
Solution Approach 2:
The system captures a comprehensive set of body characteristic data (heart rate, body temperature, galvanic skin response, respiratory rate) that exceeds the minimum required for identification. This excessive data collection ensures high identification accuracy and reliability, particularly in multi-user environments, while the periodic sampling strategy mitigates the associated energy consumption
Data Source
AI summary
Systems and methods for identifying a user of an electronic device are disclosed. An example method includes capturing body characteristic data associated with a user via a sensor on a computing device. The body characteristic data is captured as the user interacts with the computing device for a purpose different from user identification. The example method includes determining an identifier associated with the user based on the captured body characteristic data.