A deep learning-based user literature reading interest analysis method
A reading interest and deep learning technology, applied in text database query, special data processing application, unstructured text data retrieval and other directions, can solve the problem of not satisfying the accurate analysis of users' reading interest, achieve high practical value and improve accuracy Effect
Active Publication Date: 2022-01-28
北京起创科技有限公司
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
By recording the various operations performed by the user in the webpage, such as whether to save the label, whether to copy, whether to visit and judge the user's interest, etc., and give different weights to comprehensively analyze the user's reading interest, this method is due to the use of It just uses the traditional method based on statistical learning to analyze user interest, which cannot be analyzed on the semantic level, and cannot meet the needs of accurate analysis of user reading interest.
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
[0081] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.
[0082] Such as Figure 1-5 Shown, the present invention comprises the steps:
[0083] Step 1: Collect all historically browsed document sets and browsing behavior records of users, and calculate the document weight according to the browsing time of each document, specifically as figure 2 Shown:
[0084] Step 1.1: Collect user history browsing literature collection D={d 1 , d 2 ,...,d G}, where G is a global variable and an integer, representing the total number of documents in the document set D;
[0085] Step 1.2: Get document set D={d 1 , d 2 ,...,d G} and store the keywords of all documents in the keyword set KW={data mining, information retrieval, personalization, personalized recommendation, rough set, text classification, SVM, personalization system, recommendation system, information extraction, information gain} , where p is 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 discloses a method for mining user's reading interest based on deep learning, wherein a method for mining user's reading interest based on deep learning is adopted to collect users' historical document browsing logs, and calculate the duration and last Different weights are given to each document based on the distance between the time of reading the document and the current standard time. Secondly, the word segmentation results of the document titles that the user has browsed in history are expanded through the word vector model based on deep learning. The invention is used to tap the potential reading interests of users, improve the accuracy of document recommendation, and improve the efficiency of user information retrieval.
Description
technical field [0001] The invention belongs to the field of data analysis, and in particular relates to a deep learning-based analysis method for users' literature reading interest. Background technique [0002] At present, with the increasing number of documents on the Internet, more and more users feel that it is very difficult to obtain a large number of documents that are really helpful to them. Compared with the field of e-commerce, user personal interest analysis has been applied to most e-commerce websites, such as Taobao, Amazon, YouTube, etc., have embedded user preference analysis modules in their recommendation services and achieved good results . [0003] However, in the field of document retrieval, an information retrieval method based on information matching is adopted. According to the search keywords entered by the user each time, the most matching documents in the database are pushed to the user. The content of the recommended literature generated by this...
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): G06F16/9535G06F16/33G06F16/36
CPCG06F16/3344G06F16/3346G06F16/36G06F16/9535
Inventor 朱全银唐海波严云洋李翔胡荣林瞿学新邵武杰许康赵阳钱凯高阳
Owner 北京起创科技有限公司