Method, device, equipment and readable medium for keyword extraction based on artificial intelligence
A technology of artificial intelligence and extraction methods, applied in knowledge expression, probabilistic network, calculation model, etc., can solve the problems that keywords cannot be obtained keywords, keyword accuracy is poor, and the probability of high-frequency word generation is high
Active Publication Date: 2017-09-29
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF3 Cites 19 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] However, the keyword extraction method based on the above has a serious tendency to high-frequency words, because under each topic, if the word appears more times, the corresponding probability will be higher, so based on the above formula After calculation, the generation probability of high-frequency words will be even greater, resulting in most of the recalled results being high-frequency words under a certain topic
However, high-frequency words appear widely in different documents, and are not good keywords in many cases, such as words such as "we", "you" and the like in documents. Therefore, the extraction of keywords in the prior art The scheme cannot obtain effective keywords, and the accuracy of the extracted keywords is poor
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
[0054] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0055] figure 1 It is a flowchart of an embodiment of the artificial intelligence-based keyword extraction method of the present invention. Such as figure 1 As shown, the artificial intelligence-based keyword extraction method of this embodiment may specifically include the following steps:
[0056] 100. Predict the distribution probability of the target document in each of the multiple topics based on the topic model;
[0057] The execution subject of the keyword extraction method based on artificial intelligence in this embodiment is an artificial intelligence-based keyword extraction device, which can be an electronic entity device or a software-integrated device .
[0058] The artificial intelligence-based keyword extraction method of t...
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 provides a method, a device, equipment and a readable medium for keyword extraction based on artificial intelligence. The method includes the steps that based on a topic model, the distribution probability of each of a plurality of topics in a target file is obtained; the correlation between the word vector of each word in several words in the target file and a topic vector of the corresponding topic in several topics is calculated, wherein the word vector of each word and the topic vector of each topic are generated on the basis of a word vector model; according to the distribution probability of each word in the corresponding topic and the correlation between the word vector of each word and the topic vector of the corresponding topic in the topics, words serving as key words of the target file are extracted from the several words. According to the distribution probability of each word in the corresponding topic and the correlation between the word vector of each word and the topic vector of the corresponding topic in the topics, the key words are extracted, and the extracted key words can thus better fit the topics of target file, are more effective and more accurate.
Description
【Technical field】 [0001] The present invention relates to the field of computer application technology, in particular to an artificial intelligence-based keyword extraction method, device, device and readable medium. 【Background technique】 [0002] Artificial Intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems, etc. [0003] In the current era of information explosion, it is impossible for users to browse all documents that may contain relevant information, and keywords are the most important and concise sum...
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): G06F17/27
CPCG06F40/289G06F40/284G06N20/00G06N5/022G06N7/01G06F18/2431G06F16/337
Inventor 连荣忠陈泽裕姜迪蒋佳军何径舟
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD