Multimode heterogeneous association entity recognition method based on cross-network representation learning

Abstract

The invention provides a multimode heterogeneous association entity recognition method based on cross-network representation learning. The method comprises the following steps: giving two multimode heterogeneous information networks, wherein EA and EB are an entity set, RA and RB are an entity relationship set, and TA and the TB are entity type sets; cA and CB are an entity relationship type set;setting two entities EAi belonging to EA and EBj belonging to EB, establishing a multimode relationship transition probability Mij between the EAi and the EBj through an iterative method based on a random walk path set between the EAi and the EBj, and obtaining multimode heterogeneous feature vectors of the EAi and the EBj through Mij by utilizing target function learning; and when it is judged that the EAi and the EBj have multimode heterogeneous consistency, attribute consistency and environment consistency at the same time, determining that the EAi and the EBj are associated entities. According to the method, multimode heterogeneous characteristics of the multimode heterogeneous information network are fully analyzed, and a multimode heterogeneous information network formalized description method and a multimode heterogeneous associated entity recognition model and method based on cross-network representation learning are formed.

Description

technical field [0001] The invention relates to the technical field of multi-mode heterogeneous information network associated entity recognition, in particular to a multi-mode heterogeneous associated entity recognition method based on cross-network representation learning. Background technique [0002] Multi-mode heterogeneous information network (Building Information Model / Modelling, Building Information Modeling) is a digital expression of the physical and functional characteristics of building facilities. It has become an important part of the modernization of my country's construction industry and the construction of smart cities. [0003] Multimodal heterogeneous information network associated entity recognition aims to find data entities that refer to the same object in the real world in different multimodal heterogeneous information networks. Accurate and comprehensive multi-mode heterogeneous information network related entity recognition will realize the organic i...

AI Technical Summary

Problems solved by technology

[0026] ① Lack of multi-mode heterogeneous feature modeling

Most of the existing methods design related entity recognition models and methods in single-mode or homogeneous scenarios for specific domains, which do not incorporate multi-modal or (and) heterogeneous features, and the quality of related entity recognition cannot meet the requirements of multi-mode for whole-process integration applications. Heterogeneous Multimodal Heterogeneous Information Network Linked Entity Recognition

[0027] ②Insufficient computing power of massive entities

Many associated entity recognition methods cannot handle massive amounts of data, making them unable to be directly applied to associated entity recognition in multimodal heterogeneous information networks with massive entities

[0028] ③Strong dependence on prior related entities

[0030] At present, there is no multimodal heterogeneous information network associated entity recognition method for multimodal heterogeneous features in the prior art

Images