Object association identification method and device and storage medium

Abstract

The invention provides an object association recognition method and device and a storage medium, and relates to the field of artificial intelligence, and the method comprises the steps: obtaining target attribute features and target operation sequence data of a to-be-recognized object group; based on a preset sequence pattern library, performing sequence pattern matching on the target operation sequence data to obtain a target operation sequence pattern of the to-be-recognized object group; using a sequence correlation mining network of a preset relation identification model to perform sequence correlation processing on target operation features corresponding to the target operation sequence data to obtain target sequence correlation features of the to-be-identified object group; and utilizing an object group classification network of a preset relation identification model to perform association relation identification on the to-be-identified object group based on the target attribute feature, the target operation feature, the target operation sequence mode and the target sequence correlation feature to obtain an association relation category of the to-be-identified object group. According to the method, the generalization ability and timeliness of object association recognition can be effectively improved.

Description

technical field [0001] The present application relates to the field of artificial intelligence, and in particular to an object association recognition method, device and storage medium. Background technique [0002] With the development of Internet technology, association relationship identification technology has become a necessary link in the construction of object relationship chains, and can be applied to various scenarios such as relationship intimacy identification and relationship network construction. However, some current association relationship identification methods require manual setting of a large number of relationship rules and regular maintenance of the relationship rule library to ensure the accuracy and timeliness of association relationship identification. In various industrial application scenarios where data changes flexibly, It cannot be automated, it is difficult to achieve efficient generalization, and it is susceptible to prior knowledge and subject...

AI Technical Summary

Problems solved by technology

However, some current association relationship identification methods require manual setting of a large number of relationship rules and regular maintenance of the relationship rule library to ensure the accuracy and timeliness of association relationship identification. In various industrial application scenarios where data changes flexibly, It cannot be automated, it is difficult to achieve efficient generalization, and it is susceptible to prior knowledge and subjective factors

Images