Mobile User Profiling via Location History Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
User profiles are difficult to obtain as users have little incentive to generate them, and their recollection of behavior over time can be unreliable, making existing methods tedious and inaccurate.
Innovation Solution
A process that generates user profiles based on location history from mobile devices, using location-attribute scores to determine user-attribute scores, which are then stored in a user-profile datastore, allowing for privacy-friendly and accurate characterization of users without manual effort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If users manually generate their own profiles, then the profile data can be directly obtained, but the process is tedious and users have little incentive to participate
Solution Approach 1:
The system automatically generates user profiles by collecting location data from mobile devices and processing it through location-attribute scoring, eliminating the need for users to manually create or update their profiles. The profiling process serves itself by using passive location information that is already being collected by the mobile device.
Solution Approach 2:
The patent introduces an intermediary profiling system that acts as a mediator between raw location data and user profile applications. This intermediary automatically processes location histories, calculates location-attribute scores, and generates user-attribute scores, thereby resolving the contradiction between data availability and user effort.
2Measurement precision
If users manually recall and report their behavior, then profile data can be obtained, but the recollection is unreliable and inaccurate
Solution Approach 1:
The patent replaces the mechanical process of human recollection and reporting with an automated electronic system that passively collects location data from mobile device sensors. This substitution eliminates human memory limitations and provides more accurate, objective behavior data.
Solution Approach 2:
The system continuously collects location data and updates user profiles in real-time or near-real-time, creating a feedback loop where the profile automatically reflects current user behavior patterns without requiring active user participation or recollection.
3Adaptability or versatility
If comprehensive user profiles are created, then advertising targeting can be improved, but user privacy concerns increase
Solution Approach 1:
The patent applies local quality by computing location-attribute scores for specific geographic locations and then aggregating these local scores into overall user-attribute scores. This approach allows for detailed local analysis while maintaining privacy at the user level, as the system processes location data in discrete, manageable units rather than continuously tracking complete user trajectories.
Data Source
AI summary
Provided is a process of profiling a user of a mobile computing device, the process including: obtaining a location history of a user, the location history being based on signals from a mobile computing device of the user; obtaining a location-attribute score of a location identified in, or inferred from, the location history; determining, with a computer, a user-attribute score based on the location-attribute score; and storing the user-attribute score in a user-profile datastore.