User Behavior Model for Contextual Mobile Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users of mobile devices face difficulties in obtaining relevant search results for businesses like restaurants and hotels due to the need for detailed search parameters, especially in mobile environments where inputting information can be challenging, leading to unsatisfactory initial search outputs and iterative searching.
Innovation Solution
A user behavior model that refines user input with contextual information such as time and location, ranking entity types like restaurants and hotels based on relevance from a large-scale database, providing a streamlined user interface that displays a ranked list of entity types with the highest-ranked entity within each type, and replacing the interface with a hierarchy upon selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If detailed search parameters are required to obtain useful search results, then search result quality is improved, but user operation difficulty increases
Solution Approach 1:
The system performs preliminary actions by automatically collecting user context information (location, time, device state) and pre-processing search queries based on user profiles and historical behavior before the user even initiates a search. This eliminates the need for users to manually input detailed parameters while maintaining high search result quality.
Solution Approach 2:
The search system serves itself by automatically generating optimized search queries using collected context data and user profiles. The system autonomously determines search parameters, selects relevant entities, and constructs queries without requiring manual user input, thus resolving the contradiction between detailed parameter requirements and ease of operation.
2Reliability
If iterative searching is performed to obtain satisfactory results, then search result satisfaction is improved, but time consumption increases
Solution Approach 1:
The system performs preliminary ranking and filtering of search results based on user profiles and context information before presenting results to the user. By pre-processing and prioritizing relevant entities, the system ensures satisfactory results are delivered in a single search operation, eliminating the need for iterative searching and reducing time consumption.
Solution Approach 2:
The system implements feedback mechanisms by analyzing user interactions with search results (selections, views, skips) and continuously refining user profiles and ranking algorithms. This feedback loop improves search result satisfaction over time while maintaining efficient single-shot search performance, preventing the need for repeated iterative searches.
3Ease of operation
If simplified user interface is used in mobile environment, then ease of operation is improved, but information completeness decreases
Solution Approach 1:
The system extracts and utilizes rich context information (location, time, device state, user profile) from external sources and system sensors, removing the burden from users to manually input this data. The simplified interface presents only essential interaction elements while the system independently gathers and processes comprehensive information needed for personalized recommendations.
Solution Approach 2:
The search system performs multiple functions through a unified simplified interface: automatic query generation, context analysis, personalized ranking, and result presentation. This multi-functional approach maintains ease of operation while ensuring information completeness by integrating various data sources and processing stages within the same streamlined interface.
Data Source
AI summary
A user behavior model provides personalized recommendations based in part on time and location, particularly to users of mobile devices. Entity types are ranked according to relevance to the user. Example entity types are restaurant, hotel, etc. The relevance may be based on reference to a large-scale database containing queries from other users. Additionally, entities within each entity type may be ranked based on relevance to the user and the time and location context. A user interface may display a ranked list of entity types, such as restaurant, hotel, etc., wherein each entity type is represented by a highest-ranked entity with the entity type. Thus, the user interface may display a highest-ranked restaurant, a highest-ranked hotel, etc. Upon user selection of one such entity type the user interface is replaced with a second user interface, for example showing a ranked hierarchy of restaurants, headed by the highest-ranked restaurant.