A key user discovery method for subfield and wide-area socialization
By acquiring user information and social content, calculating recognition levels, and utilizing graph convolutional neural networks, the problem of quantifying user influence has been solved, enabling accurate analysis and marketing planning of user influence on e-commerce platforms, thereby enhancing brand awareness and economic benefits.
CN119579339BActive Publication Date: 2025-11-04CHONGQING UNIV OF POSTS & TELECOMM
Patent Information
- Application Number
- CN202411613141.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-13
- Publication Date
- 2025-11-04
- Estimated Expiration
- 2044-11-13
Smart Images

Figure CN119579339B_ABST
Abstract
The application belongs to the technical field of internet application, and particularly relates to a key user discovery method for subfield and wide-area socialization, which comprises the following steps: obtaining user basic information, user historical behavior and user social content under a current topic, and extracting field information and social information from the user basic information, the user historical behavior and the user social content; calculating field recognition degrees of one user to another user according to the field information and the social information, and establishing a topic propagation network by taking the users as nodes and the field recognition degrees as edge weights; in the topic propagation network, obtaining structural features of nodes by walking based on a bias sampling strategy; and establishing a two-layer graph convolutional neural network, which comprises a cascaded first graph convolutional layer, a Dropout layer and a second graph convolutional layer, and inputting the structural features of the nodes into the network to predict whether the nodes have influence; the application can discover key users for specific fields, select key users with more influence for customers to promote products, and improve the effectiveness of advertisement delivery.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Key user mining method, device and equipment oriented to guide topic network
CN118606380A
Social network node importance ranking method based on adaptive propagation mode
CN118779838A