Motion String Matching for Multi-Device User Identification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing audience measurement technologies face challenges in accurately identifying users and detecting multiple devices carried by individuals, leading to inaccurate media measurement results, especially with the increasing use of portable computing devices equipped with accelerometers.

Innovation Solution

The system processes accelerometer data to create unique user profiles for identifying and authenticating users based on physical activity, and compares data from multiple devices to determine if they are being carried by the same person, thereby associating media exposure data with user identification and activity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If accelerometer data is processed to create unique user profiles for identification, then user identification accuracy is improved, but device complexity increases

Engineering Contradiction:

Improveuser identification accuracyVSAvoiddata processing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by collecting accelerometer data during a training period to create user profiles before actual media measurement. This pre-processing establishes baseline motion patterns for each user, enabling accurate identification during subsequent measurements without requiring complex real-time analysis.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates simplified copies of user motion patterns through accelerometer profiles that capture essential movement characteristics. These profiles serve as representative models that can be quickly compared against new data, reducing the computational complexity of ongoing user identification while maintaining accuracy.

Inventive Principle:

Principle #26Copying

2Reliability

If multiple devices are monitored to detect duplicate carrying, then measurement reliability is improved, but data processing time increases

Engineering Contradiction:

Improvemedia measurement reliabilityVSAvoiddata processing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system segments the analysis by comparing accelerometer data across multiple devices in a systematic manner. By dividing the comparison process into discrete steps—collecting data from each device, normalizing the data, then comparing patterns—it efficiently handles multiple devices without overwhelming processing requirements.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes parameters by transforming raw accelerometer data into standardized motion patterns and comparing key characteristics rather than analyzing complete raw datasets. This parameter transformation reduces processing time while maintaining the ability to detect duplicate device carrying.

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If motion-based user identification is implemented, then intrusiveness is reduced, but measurement precision requirements increase

Engineering Contradiction:

Improveuser identification intrusivenessVSAvoidmotion pattern recognition precision

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system implements self-service by using the user's own natural motion patterns for identification without requiring active participation or conscious input. Users simply go about their normal activities while the accelerometer passively captures motion data, making the identification process completely non-intrusive while leveraging the uniqueness of individual movement styles.

Inventive Principle:

Principle #25Self-service

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach provides a non-intrusive means of user identification and activity recognition, ensuring accurate media measurement by distinguishing between registered and unregistered users and detecting instances of multiple devices being carried, thus enhancing the reliability of media exposure data.

Implementation Method 1

an accelerometer is a sensor that measures acceleration of a device, where the acceleration is attributed either to motion or gravity

Methodology Applied

Scientific EffectAccelerometer sensing: Accelerometer

Implementation Method 2

Acceleration can be generated using static forces such as a constant force of gravity

Methodology Applied

Scientific EffectGravitation: Gravitation

Implementation Method 3

The piezoelectric or MEMS (Micro-Electromechanical System) sensors in accelerometers are actually sensing movement accelerations and the magnitude of gravitational field

Methodology Applied

Scientific EffectPiezoelectric sensing: Piezoelectric Effect

Data Source

PatentUS11828769B2Multiple meter detection and processing using motion data

Publication Date: 2023.11.28 THE NIELSEN CO (US) LLC

AI summary

Apparatuses are disclosed for identifying portable devices carried by the same person. An example apparatus includes at least one memory, instructions on the apparatus, and a processor to execute the instructions to access media exposure data from at least one of a plurality of portable computing devices, access motion strings from each of the plurality of portable computing devices, each of said strings comprising a successive binary representation of motion over a first period of time, compare the motion strings in a processor to determine if at least two motion strings match within a predetermined threshold, and identify the devices that produced matching motion strings.