Unlock instant, AI-driven research and patent intelligence for your innovation.
Social network zombie account detection method and device
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of social network and detection method, applied in data exchange network, special data processing application, instrument, etc., can solve the problems of low detection rate, detection efficiency and accuracy, achieve low cost, improve detection efficiency, The effect of improving the detection rate and accuracy rate
Active Publication Date: 2015-09-09
NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
View PDF5 Cites 14 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0003] Existing methods are mostly based on the attention graph model or the interaction graph model, and detect zombie accounts based on interactive features, and their detection rate, detection efficiency, and accuracy are low
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
no. 1 example
[0064] In the first embodiment of the present invention, a social network zombie account detection method, such as figure 1 shown, including the following specific steps:
[0065] Step S101, extract hierarchical features from the zombie account sample set and the normal account sample set, and establish classifiers for each layer hierarchically based on the extracted hierarchical features;
[0066] Specifically, the hierarchical features include the following four levels of features:
[0067] Features of the first layer: account profile features;
[0068] The characteristics of the remaining layers are: Weibo content characteristics, posting time characteristics, and posting behavior consistency characteristics.
[0069] Further, the characteristics of the account data include:
[0070] The sum of the length of the characters and numbers in the user's nickname occupies the proportion of the total length of the user's nickname;
[0071] Whether to fill in the home address; ...
no. 3 example
[0116] The third embodiment of the present invention, this embodiment is on the basis of the above-mentioned embodiments, using the C4.5 decision tree classification model algorithm to establish classifiers for each layer as an example, combined with the attached Figure 3-4An application example of the present invention is introduced.
[0117] image 3 is a schematic diagram of the training process of the embodiment of the present invention. Such as figure 1 As shown, the training process of the embodiment of the present invention involves the following specific steps:
[0118] Step 1. Data Collection
[0119] a) Select a sample set of zombie accounts and related features;
[0120] b) Select a normal account sample set and related features;
[0121] Step 2. Calculate the hierarchical features of zombie accounts and normal accounts respectively, as follows:
[0122] a) Account data characteristics, including:
[0123] User nickname: the ratio of the length of characters...
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 social networkzombie account detection method and device. The zombie account detection is carried out by using a hierarchical heuristic approach; Account information characteristics, microblog content characteristics, posting time characteristics, posting behavior consistency characteristics of an account to be detected are successively judged according to the computation time costs; if the judgment succeeds, the computation is stopped, otherwise, the next layer of characteristic computation will be continued. In consideration of the fact that most zombie accounts are generated and maintained by automatic programs with low cost and can be detected by a judging method with lower cost, the method provided by the invention can significantly improve the detection efficiency. Besides, by adopting multidimensional characteristics such as account information, the microblog contents and behavior characteristics in the social network zombie account detection method, the detection rate and the accuracy rate of zombie accounts can be improved.
Description
technical field [0001] The invention relates to the technical field of Internet social networking, in particular to a method and device for detecting social network zombie accounts. Background technique [0002] Due to its concise content, convenient interaction, and rapid dissemination, social networks have rapidly developed into an important social media for people to express their views, express their emotions, and transmit information. Social networks represented by Sina Weibo, Twitter, and Facebook have played an important role in promoting the fermentation and outbreak of a large number of social events, so social networks are one of the essential data sources for current public opinion analysis. As a public opinion dissemination platform, social network is also an important means of network marketing, which contains huge economic value, so zombie accounts emerged as the times require. Zombie accounts refer to accounts that have applied for accounts but basically do no...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04L12/26H04L29/06G06F17/30
Inventor 刘玮王丽宏张同虎
Owner NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
Login to View More 
Login to View More