Companion Device Content Selection Using Social Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users find it difficult to access relevant secondary content while watching television, as existing systems rely heavily on closed-caption text and programming information, failing to capture tangentially related topics of interest.
Innovation Solution
A content-selection process that analyzes primary content, including closed-caption text, video, and audio, along with external inputs like social networking data and user profiles, to identify and present relevant secondary content items on companion devices, enhancing the user experience without distracting from the primary content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing systems rely on closed-caption text and programming information to generate secondary content, then the system complexity remains low, but the relevance and accuracy of secondary content to user interests deteriorates
Solution Approach 1:
The patent combines multiple data sources including closed-caption text, programming information, social networking data, and user profile information into a unified content selection system. This integration allows the system to capture tangentially related topics and improve secondary content relevance by leveraging diverse information sources together rather than relying on单一 source
Solution Approach 2:
The patent introduces social networking data as an intermediary layer that connects primary content with user interests. By analyzing social interactions, comments, and shared content related to the TV program, the system can identify topics of user interest that are tangentially related to the content, thereby improving relevance without requiring direct analysis of all possible user preferences
2Adaptability or versatility
If the system analyzes only closed-caption text and programming information, then the processing time is short, but the ability to capture tangentially related topics of interest deteriorates
Solution Approach 1:
The system performs preliminary analysis of social networking data and user profiles in advance, building knowledge bases of user interests and topic associations before the user actually views the content. This pre-processing allows the system to quickly match primary content with relevant secondary content during actual viewing, reducing real-time processing requirements while maintaining high adaptability to user interests
Solution Approach 2:
The patent divides the content analysis into multiple independent modules: closed-caption text analysis, programming information processing, social networking data analysis, and user profile matching. Each module processes specific types of data independently, allowing parallel processing and reducing overall processing time while comprehensively capturing various aspects of user interests
Data Source
Figure 1
Figure 2
Figure 3
AI summary
While a user views a primary content item (for example, a movie on a television screen), secondary content items are selected and presented to the user, either on the same screen or on a screen of the user's companion device. To choose selections that are relevant to the user's current interests, the selection process considers information beyond the realm of primary and secondary content. Over time, the selection process learns to make more relevant selections by monitoring selection choices made by other systems.