Crowdsourced Spatial Model Generation Using Mobile Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for creating spatial models, such as aerial photography and satellite imagery, are expensive, require specialized equipment, and are not scalable for generating accurate spatial models for large numbers of locations, especially indoor structures like office buildings and stadiums.
Innovation Solution
The use of crowdsourcing to generate contextual spatial models by collecting location and contextual information from a plurality of devices, which are then processed using rules-based or machine learning models to create dynamic and accurate spatial maps that can manage resource allocation efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If aerial photography and satellite imagery are used to create spatial models, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent uses mobile devices (smartphones, tablets) as portable copying tools to capture spatial data through camera imaging and GPS positioning. Instead of requiring specialized aerial photography equipment, the system copies spatial information using widely available consumer devices, thereby reducing device complexity while maintaining measurement precision through multiple data collection points
Solution Approach 2:
The patent replaces traditional mechanical surveying equipment with software-based processing of data from mobile devices. The spatial model generation uses computational algorithms to process images and location data, substituting complex mechanical measurement systems with software-driven solutions that leverage existing mobile device capabilities
2Manufacturing precision
If manual efforts are used to create spatial models, then manufacturing precision is improved, but productivity decreases
Solution Approach 1:
The system enables self-service spatial model creation by allowing multiple users to independently contribute data using their own mobile devices. Each user's device automatically captures location and imaging data, and the system aggregates these contributions without requiring centralized manual intervention, thereby maintaining precision through multiple validation points while dramatically improving productivity and scalability
Solution Approach 2:
The patent merges data from multiple independent sources (multiple mobile devices, multiple users, different locations) into a single comprehensive spatial model. This combination of distributed data sources maintains reliability through cross-validation while enabling parallel data collection that significantly increases productivity and scalability compared to single-operator manual methods
3Measurement precision
If conventional spatial modeling techniques are used, then measurement precision is maintained, but loss of time increases
Solution Approach 1:
The system performs preliminary data collection continuously as mobile devices move through the area of interest, capturing spatial information in advance rather than through coordinated manual surveys. This preliminary action allows the spatial model to be generated more quickly when needed, as the raw data is already collected and ready for processing, maintaining precision through pre-captured multi-angle observations
Data Source
AI summary
Contextual spatial models for indoor and outdoor structures are created from a plurality of devices using crowdsourcing. A method for creating a contextual spatial model for a premises includes receiving location information and contextual information from a plurality of devices. For each of the plurality of devices, the method receives location information of the device's location, and contextual information related to at least one of the device and a user associated with the device when the device is at the location. The method then determines a designation for each subject location within the premises by applying the received contextual information associated with the subject location to a location model (e.g., rules-based model or a machine learning model).