Place Location Determination via Weighted Check-in Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing social-networking systems face challenges in accurately determining the location and perimeter of a place based on check-in location data, which is essential for providing relevant location-based services but is often inconsistent due to varying accuracy and reliability of user-provided GPS coordinates.
Innovation Solution
A server-side process that calculates a weighted mean of check-in locations using exponential decay, accuracy, and trustworthiness, projects these coordinates into a three-dimensional sphere, and determines a central location and perimeter by selecting a subset of check-in locations within a certain distance, constructing a cumulative distribution function to define a circular or non-circular area representative of the place.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If user-provided GPS coordinates are used to determine place location and perimeter, then location-based services can be provided, but the accuracy and reliability of the determined location and perimeter deteriorate due to varying accuracy of user-provided data
Solution Approach 1:
The patent applies parameter changes by transforming the weighting methodology from uniform to variable based on multiple parameters including recency, accuracy, and trustworthiness. The exponential decay function changes the temporal parameter weighting, while accuracy metrics (such as GPS precision levels) and trustworthiness scores dynamically adjust the influence of each check-in location on the final place location and perimeter determination.
Solution Approach 2:
The system implements feedback mechanisms by using accuracy information and trustworthiness metrics from check-in data to continuously refine place location and perimeter determinations. The accumulated place information is fed back into the calculation process, allowing the system to learn from past check-ins and improve future location estimates. Users can also provide feedback through place corrections, which are incorporated into the place information.
2Measurement precision
If all check-in locations are considered equally, then the calculation process is simple, but the determined place area becomes inaccurate due to inconsistent data quality
Solution Approach 1:
The patent introduces multiple parameters (recency weights via exponential decay, accuracy metrics, trustworthiness scores) to differentiate the quality of check-in locations. This transforms the calculation from a simple average to a weighted aggregation that accounts for data quality variations, thereby improving precision at the cost of increased computational complexity.
Solution Approach 2:
The check-in dataset is segmented into distinct quality categories based on accuracy levels and trustworthiness scores. By dividing the data into segments with different reliability characteristics, the system can apply appropriate weighting to each segment, improving overall determination accuracy while managing computational complexity through structured processing.
3Reliability
If recent check-in data is given higher weight, then the place location reflects current state better, but the influence of historical check-in data is reduced
Solution Approach 1:
The patent implements a dynamic weighting system where the importance of check-in data varies over time according to an exponential decay function. Recent check-ins receive higher weights that gradually decrease for older check-ins, creating a time-dependent weighting scheme. This dynamic approach allows the system to adapt to changes in place location while still incorporating historical information, balancing current representativeness with historical continuity.
Data Source
AI summary
In one embodiment, a computing device accesses a social graph comprising nodes and edges connecting the nodes. Each of the edges between two of the nodes represents a single degree of separation between them. The nodes include user nodes corresponding to users of an online social network, and concept nodes corresponding to places. A particular place corresponds to a particular concept node, and corresponds to an associated location and a perimeter. A number of check-ins are received, each check-in being associated with the particular place and having a geographic location. Each check-in corresponds to an edge of the social graph between a user node and the particular concept node. Based on the received check-ins the computing device determines whether to update the associated location and the perimeter.