Cross-platform data matching method, device, computer equipment and storage medium

Abstract

The present invention relates to a cross-platform data matching method, which specifically includes the following steps: receiving a data matching request sent by a terminal; acquiring group behavior data corresponding to a first user group on a first social network platform, learning the group behavior data, Obtain the group feature distribution function; obtain the associated users and corresponding behavior data of the specified root node user in the second social network platform; learn the behavior data of the root node user, and generate the group feature distribution function after matching the root node user; Carry out behavioral learning on the behavior data of the associated users; calculate the maximum entropy value of the group feature distribution function after matching the associated users, and determine the associated user with the largest corresponding maximum entropy value as the matching user of the first user group; The user is the current root node user, and the next matching user is determined until the determined matching users meet the set quantity conditions, and the group matching is completed. The above method can realize data matching of different social network platforms.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a cross-platform data matching method, device, computer equipment and storage medium. Background technique [0002] Social networks have become "sensors" that perceive individuals' online behaviors. A large number of social "sensors" can perceive information at different levels of users, including name, age, gender, spending power, making friends habits, payment habits, shopping tendencies, and views on certain things. , attitudes towards goods and services, etc. [0003] In the application of financial big data, the same real users are connected in different social networks, and the content published by the same user on different social network platforms is likely to be different (different themes, such as food social network and picture social network) It is difficult to match information; the scale of published content is different, such as the content density of a ...

AI Technical Summary

Problems solved by technology

[0003] In the application of financial big data, the same real users are connected in different social networks, and the content published by the same user on different social network platforms is likely to be different (different themes, such as food social network and picture social network) It is difficult to match information; the scale of published content is different, such as the content density of a new platform and a platform that has been used for a long time is different), then, it is difficult to match user identities with these different contents, which eventually leads to cross-platform data fusion Obstacles, so that big data analysis is limited to a single social network platform, the analysis effect is poor, and big data cannot be fully utilized

Images