Real-time Entity Metadata Inference via Mobile Sensor Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines provide outdated information about local entities, as user reviews and ratings may be stale, and many local businesses lack recent data on parameters like noise level, occupancy, and music type, which affects the relevance of search results.
Innovation Solution
Crowdsourced data from mobile devices, using sensors like microphones and GPS, is collected and processed to provide real-time or near-real-time metadata about entities, allowing search engines to rank results based on current conditions such as occupancy, noise level, and music type.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If search engines use traditional user reviews and ratings to rank local search results, then the ranking system is simple to implement, but the information becomes stale and not indicative of current conditions at entities
Solution Approach 1:
The system proactively collects sensor data from mobile devices before users need it for search queries. By continuously gathering occupancy, noise level, music type, and other environmental parameters through sensors (microphones, accelerometers, GPS) and checking in at locations, the system prepares real-time entity state information in advance, eliminating the time lag inherent in traditional review-based systems.
Solution Approach 2:
The system implements continuous feedback loops where sensor data from mobile devices is constantly collected, processed, and used to update entity metadata in real-time. This feedback mechanism ensures that search results reflect current conditions at entities by continuously monitoring and updating parameters like occupancy levels, noise levels, and music types based on recent sensor readings from users at those locations.
2Loss of information
If search engines collect real-time sensor data from multiple mobile devices to infer entity metadata, then the information becomes current and accurate, but the system complexity increases significantly
Solution Approach 1:
Mobile devices automatically perform data collection without requiring active user participation. The system leverages existing sensors (microphones, accelerometers, GPS) already present in smartphones to autonomously capture environmental data when users check in at locations. This self-service approach eliminates the need for dedicated data collection hardware or manual data entry, reducing system complexity while maintaining data completeness.
Solution Approach 2:
The system uses multi-functional mobile devices that already serve various purposes (communication, navigation, media playback) to also collect entity metadata. By repurposing existing sensors and checking-in functionality for data collection, the system avoids adding specialized hardware complexity while achieving comprehensive data gathering across multiple parameters simultaneously.
3Reliability
If the system activates sensors immediately when users check in to entities, then real-time data is captured, but energy consumption of mobile devices increases
Solution Approach 1:
Instead of continuous sensor activation, the system uses periodic sampling triggered by user check-in events. Sensors are activated only at specific intervals when a user checks in at an entity, rather than running continuously. This periodic action captures real-time data at meaningful moments while allowing sensors to remain dormant between events, significantly reducing energy consumption.
Solution Approach 2:
The system rapidly activates sensors for brief periods immediately during check-in events to capture essential real-time data, then quickly deactivates them. This rushing through the data collection process in short bursts achieves real-time accuracy for critical moments without the sustained energy drain of continuous operation.
Data Source
AI summary
Various technologies pertaining to crowd sourcing data about an entity, such as a business, are described. Additionally, technologies pertaining to inferring metadata about the entity based upon crowd sourced data are described. A sensor in a mobile computing device is activated responsive to a user of the mobile computing device checking in at an entity. Metadata, such as occupancy at the entity, noise at the entity, and the like is inferred using the data captured by the sensor. A search result for the entity includes the metadata.