Personalized Media Search via User Playback Vector Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulty in navigating and discovering new digital media due to the overwhelming number of options, as existing search engines do not consider personal tastes when providing search results, limiting access to both previously consumed and new content.
Innovation Solution
A system generates a query with search criteria and a vector representation of a user's playback history to identify media items from a content library, providing personalized recommendations by matching relevant content items that have been previously consumed, and using these to suggest both familiar and new content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If search results are generated solely from user's playback history, then personalization is improved, but content diversity and access to new content deteriorates
Solution Approach 1:
The patent merges two different content sources: (1) content from the user's playback history that matches search criteria, and (2) additional content from the overall content library that matches search criteria. This combination is achieved by generating a modified query that incorporates both the user's historical preferences and the broader content available, thereby personalizing results while maintaining content diversity and enabling discovery of new content.
2Device complexity
If generic search results are provided without considering user preferences, then content diversity is improved, but personalization and user experience deteriorates
Solution Approach 1:
The patent applies local quality by differentiating the treatment of content based on its relationship to the user. Content from the user's playback history receives special weighting and prioritization in the search results, while other content from the library is presented with standard relevance ranking. This allows the system to maintain overall content diversity while injecting personalized elements at the local level where it matters most - in the prioritization and weighting of results relevant to the specific user.
3Adaptability or versatility
If the system provides only previously consumed content, then personalization is improved, but the ability to recommend new content deteriorates
Solution Approach 1:
The patent uses the user's playback history as a preliminary foundation for generating search results. By first identifying content that matches both the search criteria and the user's historical preferences, the system establishes a personalized baseline. Then, it expands beyond this baseline by incorporating additional content from the overall library, effectively using the preliminary personalized results as a springboard for recommending new content that the user might enjoy.
Data Source
AI summary
An electronic device stores, for a user of a media-providing service, a playback history that includes information about media items that have previously been consumed by the user. The electronic device receives a request to search for media content including search criteria. In response to the request, and without additional user intervention, the electronic device generates a vector representation of the user using media items from the playback history of the user that are relevant to the search criteria. The electronic device identifies one or more media content items from a media content library that match the vector representation of the user and the search criteria and provides, to the user, the one or more media content items.