Processing method, device, computer equipment and storage medium of historical behavior data

Abstract

The embodiment of the present application provides a historical behavior data processing method, device, computer equipment and storage medium, the method includes: acquiring the user's historical behavior data and entity marks in multiple business lines; The constructed cross-domain knowledge graph converts the entity tags of each business line into knowledge expressions in a unified semantic space; constructs the global heterogeneous behavior graph of the user according to the knowledge expressions of each business line, and according to the The global heterogeneous behavior graph stores the historical behavior data of the user; this technical solution provides unified knowledge expression for the behavior data of multiple different business lines through the cross-domain knowledge graph, and can integrate the same user in other scenarios or business lines Heterogeneous behavior data, whose data storage format can describe the global historical behavior of users in all scenarios or business lines, improves the synergy efficiency and utilization value of historical behavior data.

Description

technical field [0001] The present application relates to the technical field of big data processing. Specifically, the present application relates to a method and device for processing historical behavior data, as well as a computer device and a computer-readable storage medium. Background technique [0002] Using user historical behavior data to conduct correlation analysis is a common method in the e-commerce industry and content distribution industry. This method collects users' historical behavior on the same business line to obtain their potential interest in the business, and uses the user's potential interest for Online search recommendations. For example, on the e-commerce service platform, it is necessary to provide users with accurate interest modeling and search matching according to the user's scene. In the intelligent search business, the user's historical behavior is saved for analysis and utilization to become the efficient output of subsequent algorithms. k...

AI Technical Summary

Problems solved by technology

This data storage format is limited by the data scale and semantics contained in the original business, as well as the inconsistency of user behavior record formats and data security issues on different business lines, and cannot directly integrate the same user in other scenarios or business lines. Heterogeneous behavioral data under the environment, and with the increase of these historical behavioral data, the risk of data security also becomes higher, and also limits the economic utilization value of large-scale data

Images