Personalized Search via Encoded Device Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines fail to effectively personalize search results based on the device features of user devices, leading to irrelevant or less relevant search outcomes.
Innovation Solution
A method that utilizes an encoded device profile, including Bloom filters, to identify device features such as installed, executed, and deleted applications, and adjusts search results based on these features to provide personalized search outcomes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search engines provide generic search results without personalization, then the system complexity remains low, but the relevance of search results to individual users deteriorates
Solution Approach 1:
The patent segments the search result generation process into multiple stages: initial consideration set generation, device feature extraction, personalized adjustment phase, and final ranking. This segmentation allows the system to add personalization complexity only where needed rather than transforming the entire search engine architecture.
Solution Approach 2:
The patent performs preliminary extraction and analysis of device features (installed applications, usage patterns, device characteristics) before generating search results. This preliminary action enables the system to have personalization data ready in advance, making the actual personalization process more efficient and less complex during query execution.
2Measurement precision
If search engines analyze detailed device features to personalize results, then the relevance improves, but the processing time and computational resources increase
Solution Approach 1:
The patent extracts only the most relevant device features (installed applications, recent usage patterns, device type) rather than analyzing all possible device attributes. This selective extraction reduces computational overhead while maintaining personalization accuracy by focusing on features that most significantly impact search relevance.
Solution Approach 2:
The patent applies partial personalization by adjusting only the consideration set and ranking of search results based on device features, rather than completely regenerating all search results. This partial action achieves personalization benefits while avoiding the excessive computational cost of full reprocessing.
3Ease of operation
If search engines adjust consideration sets based on device features, then the user experience improves, but the complexity of result generation increases
Solution Approach 1:
The patent applies local quality by making personalized adjustments only to specific portions of search results (the consideration set and top-ranked items) rather than uniformly processing all results. This localized approach improves user experience for the most visible results while keeping the overall system complexity manageable.
Data Source
AI summary
The disclosure relates to personalizing search results based on the device features of a user device. An example method for personalizing search results includes receiving an encoded device profile indicating the device features of the device. The device features indicate one or more native applications installed on the device. The device features may further indicate native applications recently executed by the device, native applications that have been deleted from the user device, and/or web applications recently accessed by the user device. The method further includes identifying the device features of the device based on the encoded device profile, receiving a search query from the device, and performing an application search based on the search query to identify a consideration set of records. The method further includes adjusting the consideration set based on the device features and generating search results based on the adjusted consideration set.