Knowledge Graph Updating for Conversational Media Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional media guidance applications fail to consider users' casual references to media assets during conversational communication, leading to less relevant recommendations.
Innovation Solution
A media guidance application updates a knowledge graph based on user communications, such as text messages or verbal conversations, by isolating terms, identifying candidate components, and adjusting association strengths based on user input to enhance recommendation relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional media guidance applications base recommendations only on user's known interests, then the system complexity remains low, but the recommendation relevance deteriorates because casual references during conversational communication are not considered
Solution Approach 1:
The system performs preliminary actions by continuously monitoring and analyzing user communications (emails, text messages, social media posts, voice calls) to extract terms and update the knowledge graph in advance. This allows the system to proactively identify user interests from casual references before formal queries are made, improving recommendation relevance without requiring complex real-time processing during user interactions
Solution Approach 2:
The patent introduces a knowledge graph as an intermediary layer between user communications and recommendation generation. The knowledge graph stores extracted terms and their relationships, serving as a mediator that bridges casual user references and formal recommendation requests. This intermediary structure organizes unstructured communication data into structured knowledge, enabling relevant recommendations while maintaining manageable system complexity through modular architecture
2Loss of information
If the system monitors all user communications to extract terms, then the information completeness improves, but the processing time and computational resources increase
Solution Approach 1:
The system applies extraction by isolating specific terms from user communications using templates and heuristics. Instead of processing entire communications, the system extracts only relevant terms (e.g., movie titles, show names) from emails, text messages, social media posts, and voice calls. This selective extraction maintains information completeness for recommendation purposes while significantly reducing processing time and computational resource requirements
Solution Approach 2:
The system uses partial action by applying template matching and heuristic analysis only to communications that contain potential media asset references. Rather than uniformly processing all user communications with full NLP pipelines, the system selectively applies term extraction techniques based on communication type and content indicators, reducing overall processing time while maintaining completeness of extracted information
Data Source
AI summary
Methods and systems are disclosed herein for updating a knowledge graph based on a user confirmation. A media guidance application receives a user communication and isolates a term of the user communication. The media guidance application identifies a candidate component of a knowledge graph associated with the term. The media guidance application requests user input directed to confirming whether the term is associated with the candidate component. In response to receiving the user input, the media guidance application modifies a strength of association between the term and the component.