system
The system addresses the challenge of constructing knowledge graphs with personalized data by using AI to extract, model, and update entities, ensuring high-quality and responsive knowledge graph performance.
JP2026107127APending Publication Date: 2026-06-30SOFTBANK GROUP CORP
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- SOFTBANK GROUP CORP
- Filing Date
- 2024-12-18
- Publication Date
- 2026-06-30
AI Technical Summary
Technical Problem
Conventional technologies face difficulties in constructing knowledge graphs that utilize personalized data effectively and maximizing the performance of agent services.
Method used
A system comprising an extraction unit, modeling unit, hierarchical unit, supplementation unit, and update unit, which automatically extracts entities, models relationships, hierarchizes entities based on importance, supplements missing information, and updates the knowledge graph using AI and feedback loops.
Benefits of technology
Enables the construction of a high-quality knowledge graph that enhances the utilization of personalized data by entities, improving accuracy and responsiveness to user needs through dynamic updates and feedback mechanisms.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure 2026107127000001_ABST
Abstract
The system according to this embodiment aims to automatically build and update a high-quality knowledge graph by utilizing personalized data. [Solution] The system according to the embodiment comprises an extraction unit, a modeling unit, a hierarchical unit, a supplementation unit, an update unit, and a feedback unit. The extraction unit extracts entities. The modeling unit models the relationships between the entities extracted by the extraction unit. The hierarchical unit hierarchizes the entities modeled by the modeling unit based on their importance. The supplementation unit supplements any missing information in the entities hierarchized by the hierarchical unit. The update unit automatically updates the knowledge graph based on the entity information supplemented by the supplementation unit. The feedback unit improves the accuracy of the knowledge graph updated by the update unit.
Need to check novelty before this filing date? Find Prior Art