Hyper-personalized Knowledge Graph Weighting for Chatbot Personalization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated systems, such as chatbots, use static decision trees that are generic to all users, failing to provide personalized interactions and tailored information.
Innovation Solution
A computer-implemented personalized knowledge graph (PKG) platform that interacts with users by generating a hyper-personalized knowledge graph (hpKG) through knowledge graph weighting, using user-specific data, domain-specific knowledge, and iterative questioning to create a unique knowledge graph tailored to each user within a domain.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If static decision trees are used in automated systems, then the system structure is simple and easy to implement, but the system cannot provide personalized interactions and generic to all users
Solution Approach 1:
The patent transforms the static decision tree into a dynamic knowledge graph that evolves during user interactions. The system starts with an initial knowledge graph and iteratively expands it by adding nodes and edges based on user responses, making the system structure adaptive and personalized rather than fixed and generic
Solution Approach 2:
The patent applies different weighting values to different nodes and edges in the knowledge graph based on user-specific data and interaction history. This creates locally optimized paths for different users, allowing personalized routing decisions while maintaining the overall graph structure
2Loss of information
If generic decision trees are used for all users, then the system is easy to operate and maintain, but the information provided is not tailored to individual user needs
Solution Approach 1:
The patent changes the parameters of the knowledge graph by assigning dynamic weights to nodes and edges based on user profiles, interaction history, and relevance scoring. This allows the same knowledge graph structure to provide different information paths for different users based on their specific needs and context
3Adaptability or versatility
If static routing scripts are used, then the system requires minimal computational resources, but the system cannot adapt to user-specific contexts and provide customized interactions
Solution Approach 1:
The patent implements feedback loops where user responses are continuously analyzed and used to update the knowledge graph. The system processes user answers, determines relevance, and iteratively expands the knowledge graph with new nodes and edges, creating an adaptive automation that learns from interactions
Data Source
AI summary
Implementations include providing, by the PKG platform, an initial knowledge graph based on user-specific data associated with a user, and a domain-specific knowledge graph, receiving, by the PKG platform, data representative of at least one answer provided from the user to a respective question, providing, by the PKG platform, an expanded knowledge graph based on the initial knowledge graph, the expanded knowledge graph including one or more nodes and respective edges based on the data, generating, by the PKG platform, a weighted knowledge graph based a groundtruth knowledge graph, and a targeted knowledge graph, the groundtruth knowledge graph including one or more true answers, and the targeted knowledge graph including the at least one answer provided from the user, and generating, by the PKG platform, the hyper-personalized knowledge graph (hpKG) based on the weighted knowledge graph, the hpKG being unique to the user within a domain.