A Soft Advertising Detection and Ad Extraction Method Based on Graph Network Structure Analysis
A technology of network structure analysis and network structure, which is applied in the field of software detection and advertisement extraction based on graph network structure analysis, can solve the problems of unsuitable identification and detection, and achieve the effect of improving accuracy, good management and supervision
Active Publication Date: 2021-07-13
XI AN JIAOTONG UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, this method pays more attention to the characteristics of the URL, and is not suitable for the identification and detection of the software released on the WeChat official account platform.
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
[0044] The present invention will be described in detail below in conjunction with the accompanying drawings.
[0045] The present invention proposes a soft advertising detection and advertisement extraction method based on graph network structure analysis, including the following steps:
[0046] In the present invention, TF-IDF is term frequency-inverse document frequency.
[0047] Step 1: Calculate the TF-IDF feature vector: First, segment each article in the corpus, then calculate the TF-IDF value of each word, and obtain the TF-IDF feature of each article according to the TF-IDF value of each word vector;
[0048] The formula for calculating TF-IDF eigenvalues is as follows:
[0049]
[0050] Among them, tfidf(w) is the TF-IDF value of word w, #(w,A) indicates the word frequency of word w in article A, N w is the number of words in article A, |D| is the number of articles in the corpus, I(w,A) is an indicator function, when the word w is in article A, the function ...
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 present invention discloses a soft advertising detection and advertisement extraction method based on graph network structure analysis, which converts an article into a sentence graph network structure and a word graph network structure, and constructs two kinds of graphs with sentences and words as nodes respectively. network structure; then some network structure attribute features are extracted from these two graph network structures, and combined with the TF‑IDF feature vector of each article, and the SVM classifier is trained to identify and detect software based on the marked labels in the corpus. When extracting soft advertisement content, the semantic importance of the word and the influence of the word node in the word graph network structure are taken into account, and the advertisement content in the soft advertisement can be extracted accurately, which effectively helps the social network The platform supervises and manages advertorials.
Description
technical field [0001] The invention belongs to the field of text classification and advertisement content extraction, and in particular relates to a software advertisement detection and advertisement extraction method based on graph network structure analysis. Background technique [0002] With the rapid development of Internet technology, various social networking platforms have greatly changed and enriched our lives. In August 2012, WeChat launched the WeChat public account platform subscription function, users can send articles, pictures and other information to the subscribers of the public account. Benefiting from the huge influence of the WeChat official account platform, some official accounts have gained tens of thousands of fans and established an intimate relationship with audience fans. In recent years, many enterprises and merchants have also focused their attention on this, using the WeChat public account platform for brand promotion, which has also produced a...
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): G06F16/35G06F40/205G06F40/289
CPCG06F16/355G06F16/353G06F40/205G06F40/289
Inventor 王晨旭梁潇
Owner XI AN JIAOTONG UNIV