Personalized Knowledge Graphs from User Activity for AI Performance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing AI-based systems lack the ability to effectively utilize user activity information to establish personalized knowledge graphs for enhanced performance and user-specific insights.
Innovation Solution
A method is provided to generate action information from user device data, determine sequential activity information, and manage it as a personalized knowledge graph, utilizing AI models and neural networks to process and store user activity patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If user activity information is collected and processed to establish personalized knowledge graphs, then AI model performance and user-specific insights are improved, but system complexity and data processing requirements increase
Solution Approach 1:
The patent segments user activity information into distinct types (location data, usage patterns, preferences) and processes each segment separately through specialized modules. This segmentation allows the system to build personalized knowledge graphs incrementally without overwhelming system complexity, as each data type can be handled by dedicated processing components rather than requiring a monolithic processing system.
Solution Approach 2:
The patent transforms raw user activity data into a structured knowledge graph representation by adding a new dimensional layer of semantic relationships. Instead of processing raw data directly, the system creates a graph structure with nodes and edges that represent entities and their relationships, enabling more efficient querying and inference while reducing the computational burden of raw data processing.
2Measurement precision
If comprehensive user activity data is processed to create personalized knowledge graphs, then user-specific insights and personalization accuracy are improved, but data processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary processing of user activity data by pre-extracting relevant features and pre-structuring data into the knowledge graph format during data collection phases. This preliminary action reduces the computational burden during actual personalization operations, as the data is already prepared and structured rather than requiring intensive processing at query time.
Solution Approach 2:
The patent transforms raw user activity parameters into standardized knowledge graph parameters with defined schemas and relationships. By changing the parameter representation from raw data formats to structured graph parameters, the system enables more efficient storage, retrieval, and processing operations, reducing both processing time and computational resource requirements while maintaining high personalization accuracy.
Data Source
AI summary
A method of establishing a personalized database based on activity information is provided. The method includes generating action information corresponding to a unit operation of a user, based on data obtained by a user device, determining the activity information corresponding to a sequence including a series of sequential pieces of action information, generating episode information based on a plurality of pieces of related activity information, and managing the generated episode information as a personalized knowledge graph, based on a pattern of the generated episode information.