A method for detecting abnormal users in social networks based on graph embedding
A social network and detection method technology, applied in the field of abnormal user detection in social networks based on graph embedding, can solve problems such as single calculation mode and inability to calculate user nodes and community relationships, and achieve the effect of ensuring effectiveness and accuracy
Active Publication Date: 2022-07-15
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This is because the algorithm works with the distance matrix and cannot calculate the relationship between user nodes and communities. It can be considered that the calculation mode of this algorithm is relatively simple
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0038] Below in conjunction with the accompanying drawings and specific embodiments, the present invention will be further clarified. It should be understood that these examples are only used to illustrate the present invention and not to limit the scope of the present invention. Modifications in the form of valence all fall within the scope defined by the appended claims of the present application.
[0039] A method for detecting abnormal users in social networks based on graph embedding. First, input the social network graph, construct an initial user node embedding model according to the attribution value of user nodes and communities in the social network graph, and then construct an initial user node embedding model according to a user node and other Whether the user node has a direct connection relationship defines two constraints and defines the two constraints as the objective function. Then, the derivation formula of the objective function is combined with the embeddi...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for detecting abnormal users in a social network based on graph embedding. An initial user node embedding model is constructed according to the attribution value of user nodes and communities in the social network graph, and then according to a certain user node and other user nodes, an initial user node embedding model is constructed. Establish the objective function, and then obtain the final user node embedding model, select the connection relationship between the final embedding model of a user node and other user nodes to obtain the embedding weighted vector formula, and use the data normalization method to obtain the user node according to the embedding weighted vector formula. The abnormal level formula of , when the abnormal level of the user node is greater than the maximum threshold or less than the minimum threshold, it is defined as an abnormal user node. The method of the invention can effectively improve the effectiveness and accuracy of detecting abnormal user nodes in social networks.
Description
technical field [0001] The invention relates to the field of data mining, in particular to a method for detecting abnormal users in a social network based on graph embedding. Background technique [0002] Researchers in recent years have provided various graph embedding algorithms, such as multidimensional scaling, but they aim to preserve (global) pairwise similarity and are not optimized for the problem of social network user interaction detection. Therefore, they cannot be directly used for anomaly detection problems in social networks. A graph embedding algorithm based on a social network model, where each dimension of the embedding corresponds to a specific user aggregation area in the social network. In other words, the similarity of different user nodes along a particular dimension indicates their similarity to a particular clustered region. Therefore, this embedding embodies the topology of the original social network graph. Because the noise in the embedding seve...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06Q50/00G06F16/901
Inventor 陈志金广华岳文静周传陈璐刘玲
Owner NANJING UNIV OF POSTS & TELECOMM