Entity Location Assignment Using Street Segments and Geo-Tagged Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the location of businesses or entities on a map often result in inaccurate locations due to non-linear relationships between street numbers and actual positions, and inaccuracies in latitude and longitude coordinates.
Innovation Solution
A method that divides street maps into segments, assigns entities to these segments based on their addresses or geographic proximity, and uses geo-tagged data points to determine the most accurate locations by maximizing an aggregate confidence score while adhering to physical constraints such as monotonic street numbering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If street numbers are used to determine entity location, then the location can be inferred from address data, but the location accuracy deteriorates due to non-linear relationships between street numbers and actual positions
Solution Approach 1:
The patent segments the street network into blocks and further divides blocks into segments (e.g., northbound/eastbound sides). Entities are assigned to specific segments based on address data, and geo-tagged data points are aggregated within these segments. This segmentation allows the system to handle the non-linear relationship between street numbers and positions by localizing entities to manageable geographic units rather than attempting direct coordinate calculation from address numbers.
2Measurement precision
If latitude and longitude coordinates are used to determine entity location, then pinpoint accuracy appears to be achieved, but the location accuracy deteriorates because reported coordinates may not correspond to the actual entity position
Solution Approach 1:
The patent introduces segments as an intermediary layer between raw coordinate data and entity location determination. Instead of directly using reported coordinates, the system aggregates geo-tagged data points within segments and uses optimization to select representative locations. This intermediary segment-based approach filters out coordinate inaccuracies and provides a more reliable location estimate by considering the spatial distribution of multiple data points.
Solution Approach 2:
The patent collects and aggregates multiple geo-tagged data points within each segment, even though a single coordinate might seem sufficient. By gathering excessive location data (multiple user reports, check-ins, and geo-tagged queries within a segment) and applying optimization, the system overcomes the limitation of individual inaccurate coordinates to determine the true entity location.
3Device complexity
If entities are assigned to segments based on address correspondence, then the location determination process is simplified, but the location accuracy deteriorates when address-based assumptions do not reflect actual positions
Solution Approach 1:
The patent merges two location determination approaches: address-based segment assignment and geo-tagged data point aggregation. Entities are initially assigned to segments using simple address rules (maintaining low complexity), but their final locations are refined by combining and optimizing multiple geo-tagged data points from users within those same segments (improving accuracy). This combination allows the system to benefit from both the simplicity of address-based indexing and the precision of crowd-sourced location data.
Data Source
AI summary
Businesses and other entities may be assigned geographic locations based on various types of data. In one example, entities are associated with segments in a street grid. Additionally, data points (e.g., geotagged blog entries or other online information) are associated with segments in the street grid. For a given segment, data points are compared with entities to identify possible matches between the data points and the entities. Each match is assigned a score, and each match represents a possible physical location for a given entity. The locations of entities on the street are assigned, from among the matches, based on which assignment of entities optimizes the aggregate score for the segment, while satisfying one or more physical constraints.