General artificial intelligence knowledge infrastructure (AGI-KI) and multi-modal knowledge processing method

Through the four-layer software architecture of V-UKB, MKRF, and Qiankun Knowledge Core, the problems of fragmentation and disordered storage in multimodal data processing in artificial intelligence systems are solved, enabling plug-and-play multimodal data and cross-modal semantic association, improving the efficiency of neural-symbolic fusion, and dynamically updating the knowledge cycle.

CN122154875APending Publication Date: 2026-06-05莫少强
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
莫少强
Filing Date
2026-03-06
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

In existing technologies, artificial intelligence systems suffer from problems such as interface layer fragmentation, semantic layer breakage, and storage layer disorder in multimodal data processing. This makes it impossible to achieve plug-and-play multimodal data, cross-modal semantic association, and unified integration of knowledge, and the neural-symbolic fusion is inefficient.

Method used

It adopts a four-layer software architecture, including Virtual Unified Knowledge Bus (V-UKB), Multimodal Knowledge Record Format (MKRF), Qiankun Knowledge Core and hierarchical knowledge storage architecture, to achieve unified access to multimodal perception data, standardized representation of cross-modal knowledge and neural-symbolic hybrid intelligent evolution.

Benefits of technology

It achieves plug-and-play functionality for multimodal data, millisecond-level cross-modal time synchronization, a 10-fold improvement in cross-modal semantic retrieval response time, and reduces the dynamic update cycle of knowledge graphs from ten-year levels to second-level. It solves the problems of fragmentation in multimodal data processing and disordered storage, and improves the efficiency of neural-symbolic fusion.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122154875A_ABST
    Figure CN122154875A_ABST
Patent Text Reader

Abstract

The application discloses a general artificial intelligence knowledge infrastructure and a multi-modal knowledge processing method, and belongs to the field of artificial intelligence software systems. In view of the problems of existing multi-modal data semantic fragmentation, fragile knowledge storage format and static and rigid knowledge graph, the application provides a full-stack solution through a four-layer software architecture: a virtual unified knowledge bus (V-UKB) realizes automatic discovery and millisecond to microsecond time synchronization of multi-modal devices; a multi-modal knowledge record format (MKRF) realizes atomic-level fusion of perception data and semantic knowledge, and forms self-description, cross-platform and traceable knowledge units; and a Qian Kun knowledge core realizes neural-symbol hybrid reasoning and dynamic evolution of knowledge. All technical solutions of the application are realized based on general computing devices and open source technologies, do not require special hardware support, and can be widely applied to scenes such as intelligent libraries, long-term archives, cross-modal intelligent retrieval, distributed knowledge services and the like.
Need to check novelty before this filing date? Find Prior Art