An online book value discovery method based on mixed characteristics
A technology of mixing features and discovery methods, applied in the field of information processing, can solve the problems of inability to recommend the latest book information, difficulties, and increased computational complexity, and achieve the effect of avoiding changes in user interests and achieving good results.
Active Publication Date: 2019-04-23
BEIJING UNIV OF TECH
View PDF7 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in this era of big data with increasing information volume, it is extremely difficult to obtain the latest book information content or other online product information content that changes with time, which makes the content filtering method based on book information ineffective. recommend the latest book information for this user
For the second collaborative filtering method, as time changes, users' interests also change, and the credibility and sparsity problems also increase with time, making the computational complexity continue to increase. This is also a collaborative filtering method. Problems with filtering
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
[0083] The specific embodiment of the present invention is described in further detail in conjunction with the accompanying drawings, and the following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.
[0084] Its specific implementation steps are as follows:
[0085] Step (1) Collect the book feature data of an online book mall
[0086] This patent downloaded 100,000 Amazon book feature data by using the API provided by Amazon, and recorded as D={bf 1 , bf 2 ,...,bf n}. b f i (i=1,2,3,...,100000) represents feature data of a certain book.
[0087] The book feature bf can be expressed in the following form:
[0088] bf = {name, class, price, public_time, sale_time, times, paper_num, press, author, comment_num, good_comment_num, status, ranking, comment_set}.
[0089] The semantic description of the feature symbols is shown in Table 1:
[0090] Table 1 Semantic description of book feature symbols
...
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 belongs to the technical field of computer software, and provides an online book value discovery method based on mixed characteristics. The method comprises the steps of analyzing various characteristic indexes of an online book, and constructing an online book value discovery model in combination with a machine learning algorithm; firstly, collecting the online book data, analyzingthe value characteristics such as comments, prices and publishing time of books through a statistical method, and determining the characteristic that the value of the books is greatly influenced; secondly, analyzing each class of books in time dimension according to the determined characteristics, and establishing a book value discovery model. The book value discovery model can be used for value discovery of online books in time dimension, experimental analysis takes a Marson book website as an example, and the effectiveness of the method is explained.
Description
technical field [0001] The invention belongs to the technical field of information processing, and relates to an online book value discovery method based on mixed features. Background technique [0002] With the continuous and rapid development of the Internet, buying books online has become the first choice for people to buy books in their daily life, but online books lack the previous physical purchase experience. It becomes difficult to buy a book that is valuable to me. Users mainly select books through book reviews and content brief information. However, the authenticity of book reviews and the one-sided content introduction will have an impact on the value of a book. Existing technologies are generally book recommendation methods based on user interest analysis, and rarely involve user-independent book value discovery methods. [0003] The current mainstream book recommendation method is mainly to recommend books to users based on the personal interests of specific ...
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): G06Q30/06
CPCG06Q30/0629G06Q30/0631
Inventor 刘磊孙应红陈浩吴爽侯良文李静
Owner BEIJING UNIV OF TECH