Person-Centric Knowledge Graph for Unified Information Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The rapid growth of information across public, semi-private, and private spaces leads to information overload, with existing methods failing to efficiently organize and retrieve relevant information due to segregation and lack of meaningful connections between different data sources, resulting in a cumbersome user experience.
Innovation Solution
A person-centric INDEX system that cross-links data from various spaces to create a unified, dynamic information universe relevant to the individual, using entity and relation extraction, machine learning models, and intent-based card presentation to provide synthetic answers to personal questions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If information is organized in segregated spaces (public, semi-private, private), then information storage capacity increases, but information retrieval efficiency deteriorates
Solution Approach 1:
The patent merges information from multiple segregated spaces (public, semi-private, private) into a unified person-centric knowledge graph. The system integrates emails, contacts, calendar events, social media data, and web information into a single coherent structure centered around the user, eliminating the need to navigate multiple separate spaces and significantly improving information retrieval efficiency.
2Ease of operation
If conventional application-centric organization is used, then information within each application is well-organized, but cross-application information integration deteriorates
Solution Approach 1:
The patent creates a universal person-centric knowledge graph that serves multiple functions across different applications and domains. This knowledge graph structure can handle diverse information types (emails, contacts, events, social media, web data) and support various tasks (question answering, task completion, information retrieval) uniformly, eliminating the need for application-specific organization approaches.
3Loss of information
If manual searching across multiple private spaces is required, then information completeness improves, but user convenience deteriorates
Solution Approach 1:
The system automatically performs the task of integrating information from multiple private spaces without requiring manual user intervention. The person-centric knowledge graph automatically aggregates data from emails, contacts, calendar events, and other private sources, and the system autonomously answers user questions by querying this integrated knowledge base, eliminating the need for users to manually search across multiple applications.
4Loss of information
If interest-centric information organization is used, then information relevance to user interests improves, but accuracy of user profiling deteriorates
Solution Approach 1:
The system performs preliminary action by automatically organizing and structuring information in a person-centric knowledge graph before any user query is made. This pre-organized knowledge structure is built using objective data from multiple sources (emails, contacts, calendar events, social media interactions) rather than relying on user-declared interests, ensuring both high relevance and high accuracy without requiring users to explicitly state their preferences.
Data Source
AI summary
A method, implemented on at least one computing device each of which has at least one processor, storage, and a communication platform connected to a network for providing synthetic answers to a personal question is disclosed. A personal question is received from a person. One or more entities are extracted from the personal question. One or more relations are extracted from the personal question. A model is selected based on the personal question. One or more synthetic answers to the personal question are obtained based on the one or more entities, the one or more relations, and the selected model.