Predictive Search Using Multi-Device Location Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines cannot account for a user's travel plans, behavior patterns, or schedule, leading to irrelevant search results when users search for future-oriented terms like 'tonight' or 'tomorrow', and they lack the capability to determine location on all devices, reducing search effectiveness.
Innovation Solution
The system combines search terms with current state information, historical data, and expected location hints to predict the user's future location and behavior, using data from multiple devices to modify search results accordingly, incorporating temporal terms and user-related information to provide relevant results at the right time and place.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If current search engines use only user-entered search terms and current location information, then the search system remains simple and fast, but the search results become irrelevant when users search for future-oriented terms or when location capability is unavailable
Solution Approach 1:
The system performs preliminary actions by predicting user's future location and behavior patterns before the actual search is executed. It analyzes historical data, calendar events, and travel plans in advance to determine where the user will be and what they will need, then uses these predictions to modify search terms and provide relevant results for future time periods
Solution Approach 2:
The search system dynamically adapts by incorporating temporal context and predicted user state. Instead of static search based on current location only, the system adjusts search parameters dynamically based on predicted future location, time of day, day of week, and user behavior patterns, making the search results adaptable to future conditions
2Reliability
If search engines incorporate user's travel plans, behavior patterns, and calendar information, then search results become more relevant to future activities, but the system requires access to multiple data sources and devices
Solution Approach 1:
The system achieves universality by implementing a multi-device architecture where location and behavior data from any user device (mobile phone, tablet, computer) can be utilized. The search system on one device can access and process location information, calendar events, and behavior patterns from another device, making the predictive search capability universally applicable across different device types and platforms
Solution Approach 2:
The system uses an intermediary approach by having one device act as a mediator that provides location and behavior data to another device for search processing. The first device can request predictive information from a second device, which then uses the second device's location capability and stored user data to generate predictive search modifiers that are sent back to the first device
3Ease of operation
If search engines return results based on current location only, then the system remains simple to operate, but it cannot provide relevant results for users awaiting travel or on non-mobile devices
Solution Approach 1:
The system performs preliminary analysis of user's travel plans and calendar events to predict future location and needs before the user actually arrives at the destination or before the search becomes time-sensitive. This allows the system to prepare relevant search results in advance, reducing the time delay between user need and relevant result delivery
Solution Approach 2:
The system dynamically adjusts search relevance based on temporal factors such as time of day, day of week, and predicted arrival time. It modifies search results dynamically to account for the user's immediate future state, making the search operationally relevant at the right time without requiring complex user input
Data Source
AI summary
Systems, methods, and devices use search terms, current state information, historical data, and expected location hints to predict where a user may be when a search may be relevant. In an embodiment, search terms entered on a first user computing device may be combined with location information resident on a second user computing device to determine where a user is likely to be and what results are likely to be relevant to a user in the future. In a further embodiment, relevant search terms indicative of time, such as “tomorrow” or “tonight,” and/or user-related information may also be used to return predictive search results. In a further embodiment, user-related information from other users may also be used to return predictive search results.