POI Visit Estimation Using Probabilistic Location Uncertainty
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing user device tracking systems inaccurately determine point of interest (POI) visit counts due to bias towards larger geographic footprints, leading to inefficient use of network, processing, and memory resources.
Innovation Solution
A probabilistic approach is employed to estimate POI visit counts by determining probability values and durations for each POI location based on user device location uncertainty, using triangulation data to mitigate bias and improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional user device tracking systems determine POI visit counts based on location data, then POI visit counts can be obtained, but the results are biased towards larger geographic footprints and lack accuracy
Solution Approach 1:
The patent transforms the visit count estimation from a deterministic binary approach (visited/not visited) to a probabilistic approach by introducing probability values and duration metrics. This parameter change allows the system to account for location uncertainty by weighting visits based on probability, thereby improving measurement precision while maintaining reliability through statistical aggregation across multiple user devices
Solution Approach 2:
The patent introduces probability values as an intermediary between location data and visit count determination. Instead of directly mapping location data to visit counts, the system uses probability values derived from location uncertainty to mediate the estimation process, which resolves the contradiction by providing both accuracy (through probabilistic weighting) and reliability (through aggregated statistical data)
2Measurement precision
If systems use deterministic visit count determination, then processing is simple, but accuracy is reduced due to bias towards larger footprints
Solution Approach 1:
The system changes the determination parameter from binary (visited/not visited) to continuous probability values between 0 and 1. This allows for nuanced accuracy in visit count estimation while managing complexity through efficient probabilistic calculations and aggregation methods that leverage mathematical properties of probability distributions
Solution Approach 2:
The patent applies partial action by estimating visit counts probabilistically rather than requiring complete certainty for each individual visit. By accepting probabilistic evidence from multiple user devices and aggregating results, the system achieves high overall accuracy without the excessive complexity of determining each visit with absolute certainty
3Measurement precision
If probabilistic estimation with duration is implemented, then accuracy improves, but computational resources increase
Solution Approach 1:
The system changes from counting discrete visit events to estimating continuous duration metrics weighted by probability. This parameter change improves accuracy by capturing the temporal dimension of visits while managing computational resources through efficient integration of probability distributions over time intervals rather than processing each moment separately
4Measurement precision
If location uncertainty is accounted for, then estimation accuracy improves, but data processing complexity increases
Solution Approach 1:
The patent uses probability values as an intermediary that encapsulates location uncertainty without requiring direct processing of complex uncertainty representations. This mediator simplifies data processing by transforming uncertain location data into manageable probability weights that can be efficiently aggregated and used in visit count estimations
Solution Approach 2:
The system transforms complex location uncertainty data into simplified probability parameters that range from 0 to 1. This parameter transformation reduces data processing complexity while maintaining accuracy by preserving the essential information about location confidence in a computationally efficient format
Data Source
AI summary
In some implementations, a device may obtain location data associated with one or more user devices, wherein the location data indicates, for the one or more user devices, respective geographic locations and respective durations. The device may determine, based on the location data, one or more point of interest (POI) locations associated with respective user devices from the one or more user devices. The device may determine, for each user device from the one or more user devices, probability values for respective POI locations from the one or more POI locations, wherein the probability values indicate likelihoods of user visits at the respective POI locations. The device may determine one or more probability metrics for the respective POI locations, from the one or more POI locations, associated with user visits to the respective POI locations. The device may store the one or more probability metrics.