Relationship-Based Search for Streaming Media
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search result generation in streaming media services is unsatisfactory for non-title, non-actor, and non-genre-specific queries, as existing methods rely on exact and fuzzy text matches, often failing to meet user expectations and returning unhelpful results for unavailable media titles.
Innovation Solution
The method determines relationship scores between user activities, such as plays-related-to-searches and plays-after-searches, using cosine distance and causal analysis to generate relevant search results and content recommendations, incorporating parallel processing for efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If text match methods (exact and fuzzy) are used to generate search results, then the search process is simple and fast, but the search result relevance is poor for non-title, non-actor, and non-genre-specific queries
Solution Approach 1:
The patent transforms the search approach from text-based parameter matching to relationship-based parameter matching. Instead of matching query text against title/actor/genre fields, the system calculates relationship scores between user activities (searches and plays) using causal analysis and cosine distance, fundamentally changing the search parameters from textual to behavioral
Solution Approach 2:
The patent replaces the mechanical text-matching system with a data-driven relationship analysis system. Rather than using string comparison algorithms, the system uses causal analysis to determine relationships between searches and plays, then applies cosine distance calculations to quantify these relationships, substituting mechanical text processing with statistical and mathematical methods
2Measurement precision
If relationship-based search methods are used to improve search result relevance, then the search accuracy improves for non-specific queries, but the computational complexity and processing time increase
Solution Approach 1:
The patent pre-calculates and stores relationship scores between user activities (searches and plays) using causal analysis and cosine distance. By performing these computationally intensive calculations in advance and storing the results, the system avoids repeating complex computations during actual search operations, thus reducing real-time processing time while maintaining high search accuracy
3Ease of operation
If traditional text match search is used, then the system is easy to operate, but it returns unhelpful results when media titles are unavailable
Solution Approach 1:
The patent introduces user activity relationships (searches and plays) as an intermediary between the search query and the media titles. Instead of directly matching queries to unavailable titles, the system uses causal analysis to find relationships between the query and other user activities, then uses these relationships to recommend alternative available titles, providing a mediating layer that maintains user experience even when exact matches are unavailable
Data Source
AI summary
Techniques are described for determining relationships between user activities and determining search results and content recommendations based on the relationships. A plays-related-to-searches application may determine a relationship score between plays of a media title and searches of a query by determining a distance between a projection of the search onto the space of the users and a projection of plays of the media title onto the space of the users. A plays-after-searches application may determine a score for plays of the streaming media title given the search by multiplying a number of times plays of the media title occur after the query is entered by the number of times any play occurs, and dividing by a product of the number of times plays of the media title occur after any query is entered and the number of times plays of any media title occur after the query is entered.