Image-text content quality identification method and device based on artificial intelligence
An artificial intelligence, graphic and text technology, applied in the field of artificial intelligence-based graphic and text content quality identification, can solve problems such as insufficient comprehensiveness, low accuracy, and wrong judgment, and achieve the effect of improving accuracy
Pending Publication Date: 2021-09-17
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, due to the supervised image-text recognition technology, such as using fastText, textcnn, bert, etc. to judge the content quality from the perspective of text, the dimensions involved are relatively single and not comprehensive enough
At the same time, when the unsupervised image-text recognition technology judges content quality from the perspective of article lexical diversity or syntactic diversity, it does not introduce different special language scenarios corresponding to different semantic information, which is prone to judgment errors
Therefore, the traditional image-text recognition technology is still relatively low in the accuracy of content quality judgments.
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
[0042] Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the nature of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making.
[0043] Artificial intelligence technology is a comprehensive subject that involves a wide range of fields, including both hardware-level technology and software-level technology. Artificial intelligence basic technologies generally in...
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 relates to an image-text content quality identification method and device based on artificial intelligence. The method comprises the following steps: obtaining a to-be-identified article and extracting article prior features, text content and image-text sequence features of the to-be-identified article; performing feature cross processing on the prior features of the article to obtain a cross prior feature vector; generating a document feature vector of the to-be-identified article according to the text content; carrying out weighting processing on image-text sequence features to obtain a weighting processed image-text sequence feature vector; then carrying out full connection processing on the cross prior feature vector, the document feature vector and the weighting processed image-text sequence feature vector to obtain a comprehensive feature vector of the to-be-identified article; and determining the image-text content quality of the to-be-identified article based on the comprehensive feature vector. According to the method, multiple dimensions of the to-be-identified article are combined to determine and identify the image-text content quality, a one-sided result obtained in a single-dimension judgment mode is avoided, and the accuracy of an image-text content quality judgment result is improved.
Description
technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to an artificial intelligence-based method and device for identifying the quality of graphic content. Background technique [0002] With the continuous development of artificial intelligence technology and the wide application of Internet technology, the way of obtaining and disseminating graphic information through the Internet is becoming more and more popular. However, due to the huge amount of information, it is often difficult to identify high-quality and suitable content and push it to different users. Therefore, it is necessary to improve the convenience for users to obtain high-quality information and for enterprises to promote high-quality business information. [0003] Traditionally, supervised or unsupervised image-text high-quality content recognition technology is mostly used. Among them, supervised image-text recognition technology mainly judg...
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 Applications(China)
IPC IPC(8): G06F16/33G06F40/211G06F40/186G06N3/04
CPCG06F16/3344G06F40/211G06F40/186G06N3/044G06N3/045
Inventor 朱灵子衡阵马连洋
Owner TENCENT TECH (SHENZHEN) CO LTD