Entity Relationship Modeling for Enterprise Data Space Construction Driven by a Dynamic Detecting Probe

Abstract

To solve the problem of integrating and fusing scattered and heterogeneous data in the process of enterprise data space construction, we propose a novel entity association relationship modeling approach driven by dynamic detecting probes. By deploying acquisition units between the business logic layer and data access layer of different applications and dynamically collecting key information such as global data structure, related data and access logs, the entity association model for enterprise data space is constructed from three levels: schema, instance, and log. At the schema association level, a multidimensional similarity discrimination algorithm combined with semantic analysis is used to achieve the rapid fusion of similar entities; at the instance association level, a combination of feature vector-based similarity analysis and deep learning is used to complete the association matching of different entities for structured data such as numeric and character data and unstructured data such as long text data; at the log association level, the association between different entities and attributes is established by analyzing the equivalence relationships in the data access logs. In addition, to address the uncertainty problem in the association construction process, a fuzzy logic-based inference model is applied to obtain the final entity association construction scheme.