Semantic Place Name Determination Using Aggregated Point Clouds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in accurately determining semantic place names from raw location data due to imprecise location reports and sparse or unavailable building geometry data, leading to difficulties in inferring the true position and semantic place name of a user's location, especially in environments with limited GPS signals.
Innovation Solution
The method involves generating point clouds from high-quality visits aggregated from multiple devices, which are then used to identify and match location reports to determine semantic place names by analyzing patterns and probability values associated with candidate semantic locations, incorporating signals like distance, search history, and social signals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If raw location data is used to determine semantic place names, then the system operates with simple data input, but the accuracy of place name determination deteriorates due to imprecise location reports and sparse building geometry data
Solution Approach 1:
The patent combines multiple data sources including location reports from multiple devices, building geometry data when available, and point cloud data representing physical structures. By merging these diverse data sources, the system compensates for the sparsity of individual data types and achieves more accurate semantic place name determination even when building geometry data is unavailable.
Solution Approach 2:
The system performs preliminary actions by generating point clouds from aggregated location reports of multiple devices before attempting to determine semantic place names. These pre-computed point clouds represent physical structures and are stored for future matching, enabling accurate place identification without requiring complete building geometry data at the time of query.
2Reliability
If traditional location determination methods are used, then the system works with available GPS signals, but reliability deteriorates in environments with limited GPS signals
Solution Approach 1:
The patent introduces point clouds as an intermediary representation of physical structures between the device and the final place name determination. Instead of relying directly on GPS signals, the system uses point clouds derived from aggregated location data to mediate the matching process, enabling reliable location determination even when GPS signals are limited or unavailable.
Solution Approach 2:
The system creates copies of physical structure information in the form of point clouds from aggregated location reports. These point cloud representations serve as substitutes for direct GPS-based location determination, allowing the system to match device locations against known structures without requiring strong GPS signals.
3Measurement precision
If point clouds from multiple devices are aggregated, then the accuracy of location matching improves, but the complexity of data processing increases
Solution Approach 1:
The patent segments the complex task of place name determination into distinct components: generating point clouds from aggregated location reports, storing these point clouds as reference data, and matching new location reports against the pre-computed point clouds. This segmentation reduces processing complexity by pre-computing and storing intermediate results rather than performing all calculations in real-time.
Data Source
AI summary
Systems and methods for determining semantic place names from one or more location reports received from a user device are provided. High quality visits for a candidate semantic place location from a plurality of previously obtained location reports can be aggregated and used to generate a point cloud for the semantic place location. A high quality visit can correspond to a visit by a device that is determined to be associated with a candidate semantic place location with greater likelihood relative to a plurality of other candidate semantic place locations. Data associated with one or more point clouds can be accessed and used to support determinations of semantic place name for one or more location reports. In example embodiments, the semantic place name can be stored as part of a location history and/or provided for display in a user interface presented on a display device.