A large-scale knowledge map fusion method based on reduced anchor points

Abstract

The invention provides a large-scale knowledge map fusion method based on reduced anchor points, which comprises the following steps: large-scale knowledge map analysis and pretreatment; constructionof a reduction set: calculating the similarity of semantic description documents between entities in two knowledge maps; determining positive reduction anchor points and negative reduction anchor points; hybrid matching algorithm: predicing a large number of matching positions in subsequent matching computation according to the reduced anchor points; matching result extraction. The invention can effectively handle the large-scale knowledge fusion task in practical application, and has good effect and performance. The invention does not need to divide the large knowledge map in the matching process, thereby avoiding the semantic information loss caused by the division failure of the large knowledge map, ensuring the accuracy and recall rate of the matching result, and having the matching efficiency equal to that of the dividing and treating method adopted for dividing the knowledge map.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and relates to a knowledge map fusion method, more specifically, to a large-scale knowledge map fusion method based on reduced anchor points. Background technique [0002] In the past decade, knowledge graphs have played a pivotal role in knowledge representation and modeling. Through arduous efforts, people have established many large-scale knowledge graphs describing general knowledge, and applied them to applications such as machine translation, information retrieval, and knowledge reasoning. At the same time, researchers in many fields have also established many domain knowledge graphs in order to integrate, summarize and share professional knowledge in the field. The size of these knowledge graphs is becoming larger and larger with the growth of human knowledge. In recent years, the intersection of knowledge in different fields and the interaction between systems based on di...

AI Technical Summary

Problems solved by technology

In terms of the quality of the fusion results, reducing the time complexity and space complexity of the fusion method may also reduce the quality of the fusion results

Many excellent fusion methods are often complicated. If you use simplified fast algorithms to replace large-scale knowledge map fusion, or set some parameters that cannot take advantage of the algorithm in order to improve efficiency, you may not get satisfactory fusion results.

Some algorithms adopt a divide-and-conquer strategy to convert the large-scale knowledge map fusion problem into multiple small-scale knowledge map fusion problems, but the process of divide-and-conquer will separate the original adjacent entities and destroy the integrity of the semantic information of some entities , so the matching quality of this part of the entity at the boundary position cannot be guaranteed

Images