Knowledge Graph Traversal for Guided Content Recommendation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to provide a fully customized and guided content recommendation experience that leverages user intent and session context, failing to preserve in-progress workflows.
Innovation Solution
A computer system utilizing a knowledge graph data structure for efficient real-time traversal, incorporating historical interaction and graph traversal information to recommend content based on user intent and context.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If a chatbot system automatically parses user questions to determine intent and provide responses in real time, then response speed is improved, but the ability to provide fully customized and guided content recommendation experience deteriorates
Solution Approach 1:
The system performs preliminary actions by pre-building a knowledge graph with all possible content items, tasks, and relationships before user interaction. Historical interaction information and user profiles are pre-processed and stored. During real-time interaction, the system only needs to traverse this pre-built structure based on user input, enabling both fast response and highly customized recommendations without the complexity of generating recommendations from scratch in real time.
2Adaptability or versatility
If the system leverages user intent and session context for personalized recommendations, then recommendation quality is improved, but system complexity increases
Solution Approach 1:
The patent introduces a knowledge graph as an intermediary data structure that mediates between user context (intent, session state, profile) and content recommendations. The knowledge graph organizes content items, tasks, and relationships in a structured format that enables efficient querying and traversal. This intermediary structure simplifies the system architecture by providing a clear mapping between user needs and content, reducing the complexity of generating personalized recommendations while maintaining high adaptability.
3Stability of the object's composition
If the system preserves prior state of user interactions to continue in-progress workflows, then user experience continuity is improved, but data management complexity increases
Solution Approach 1:
The system implements continuity of useful action by storing the current state of knowledge graph traversal (graph state) along with historical interaction information. When a user resumes interaction, the system retrieves the saved graph state and continues traversal from the same point, enabling seamless continuation of in-progress workflows. This approach maintains workflow continuity while managing data complexity through structured state preservation rather than complex session management.
Data Source
AI summary
Methods and apparatuses for guided content recommendation using a knowledge graph include a server which determines a user intent associated with a user interaction request. The server determines a graph state associated with a user of a remote device based upon historical traversal information. The server identifies a seed node of a content recommendation knowledge graph based upon the user intent and the graph state. The server generates a digital content display for presentation at the remote device recommended digital content items from the seed node. The server computing device traverses the knowledge graph from the seed node to a connected node based upon a response to the digital content display, including updating the graph state associated with the user of the remote device.