Method, device and storage medium for establishing knowledge system

Abstract

The invention provides a method, a device and a storage medium for establishing a knowledge system, wherein, structured data and unstructured data are obtained from industry data, wherein, the structured data comprises entity names of entities and attribute information corresponding to entity names; The knowledge map is constructed according to the structured data. The knowledge map includes the attributes and attribute values of entities and the relationships among entities. According to the unstructured data, the map epitaxial layer associated with the knowledge map is constructed. The map epitaxial layer includes question answering layer, knowledge paragraph layer and reasoning layer. The knowledge system obtained by the method is a composite layered system, comprising a knowledge map layer and a map epitaxial layer, wherein the data of the map epitaxial layer and the data of the knowledge map layer are mutually fused, so that the knowledge system has higher industry data conversionrate, and can support the industry application of AI.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of information processing, and in particular, to a method, device and storage medium for establishing a knowledge system. Background technique [0002] At present, more and more industries need the overall existing knowledge of informatization, form a knowledge system, accumulate industry experience, and provide intelligent AI applications that can empower the industry and reduce the labor cost of the industry based on the knowledge system. Knowledge graph is a relatively popular organizational form of knowledge system in the industry in recent years. Many industry customers with certain technical strength expect or are working on the graphization of industry knowledge system. [0003] The industry knowledge system is often extremely complex, and it is difficult for a single knowledge representation to cover the needs of the upper layer application of industry knowledge. Current bi...

AI Technical Summary

Problems solved by technology

[0005] The above three solutions have the following problems: the limitation of application ability, the simplification of the expression form of the knowledge system, and often can only meet the application requirements of a single scene; the semantic understanding ability is low; the industry data conversion rate is poor; the knowledge information density is low, and the knowledge lacks semantics level, it is difficult to support more AI-based industry applications

Images