A method for automatically acquiring knowledge from multi-source heterogeneous data

Abstract

A method for automatically acquiring multi-source heterogeneous data knowledge disclosed in the present invention aims to provide a method that is more complete, versatile and convenient, and is beneficial to the acquisition of knowledge transfer. The present invention is realized by the following technical solutions: define concept-entity-attribute-relation-label in a top-down or bottom-up manner, obtain the knowledge model of the entity object, and then directly save the data with crawler software, OCR, etc. Recognition software obtains data, obtains knowledge data, and completes the conversion of heterogeneous data sources to heterogeneous knowledge sources; obtains triple instantiation of entity-attribute-relationship in known knowledge mode through structured knowledge generation method; The short-term memory network model (LSTM model) and the publisher-completer collaboration model update knowledge and knowledge models, and obtain the workflow of expanding and supplementing new knowledge. Using the knowledge model formed by knowledge modeling, obtain concepts, entities, relationships, The attribute value instantiates a stream of triples.

Description

technical field [0001] The invention relates to knowledge acquisition technology in many information processing fields such as knowledge engineering, knowledge expression, natural language understanding, information retrieval, information integration and knowledge management, in particular to multi-source heterogeneous data acquisition technology. Background technique [0002] In recent years, with the rapid development of computer and network technology, information has exploded. In the face of massive amounts of information, analysts are often faced with the dilemma of "hungry men don't know how to choose from a buffet". In the process of enterprise informatization construction, due to the phased, technical, and other economic and human factors of the construction of various business systems and the implementation of data management systems, enterprises have accumulated a large number of business data in different storage methods during the development process. Including ...

AI Technical Summary

Problems solved by technology

Because no matter whether it is manual construction or automatic construction of knowledge graphs, there will be such a problem: either the data sources are different, or the construction personnel are different and the methods are different, which will inevitably lead to some conflicts. These conflicts themselves are difficult to intuitive go

The disadvantage is that it does not provide special support for concept, entity and event extraction, and requires a large amount of labeling corpus support, and manually sets the labeling rules

[0006] At present, there is no research on the unified integration and knowledge acquisition of multi-source heterogeneous data in the existing literature.

At the same time, the research on knowledge acquisition methods of multi-source heterogeneous data sources has not formed a perfect system, and many times still rely on the "patchwork" of independent algorithms

The general knowledge acquisition method is often a simple accumulation of data, and its comprehensiveness, convenience, and intelligence are far from enough

Images