Method and device for determining object features

Abstract

The invention discloses a method and device for determining object features, and the method comprises the steps: determining the incidence relations of each node in each meta-network, wherein each meta-network takes a single association attribute between objects as a basic network, and is obtained by updating of the basic network through the incidence relation, with the same object, of an intermediate medium in different meta-networks, wherein each meta-network has the same object as a node and the single association attributes of each meta-network are different, then for each meta-network, according to the characteristics of the core node of the meta-network, determining the characteristics of a first object in the meta-network through the association relationship of each node in the meta-network, and according to the characteristics of the first object in each meta-network, determining the comprehensive characteristics of the first object in the heterogeneous network, updating the basic network with the single associated attribute among the objects by the intermediate medium, the richness so that effectiveness of the associated attribute in the basic network are improved, and thecomprehensive characteristics of all the objects are determined in the heterogeneous network with the multi-dimensional associated attribute.

Description

technical field [0001] The invention relates to the field of big data, in particular to a method and device for determining object characteristics. Background technique [0002] Compared with traditional payment methods such as cash transactions and bank transfers, online payment has obvious advantages in terms of efficiency and convenience. However, with the development of online payment services, the number of active users is also increasing rapidly, and some unscrupulous users may take advantage of online payment services for gambling and other illegal activities. [0003] In the existing technology, the user can be identified through the network model method to determine whether the user has illegal activities (gambling-related fundraising, etc.). Taking X QuickPass APP (Application, mobile phone software) as an example, the user's bank card is used as The nodes in the meta-network determine the relationship between each bank card, trace through specific bank cards (suc...

AI Technical Summary

Problems solved by technology

However, the above methods are mostly used in homogeneous networks with a single association attribute between objects, and are not suitable for heterogeneous networks with complex and diverse association attributes between objects. At present, the association attributes of objects in the network are complex and diverse, and the objects are single The meta-network of associated attributes lacks the comprehensiveness and richness of determining the characteristics of nodes, and the corresponding network model has low accuracy in determining whether users have illegal activities, and the network model lacks interpretability

Images