Unlock instant, AI-driven research and patent intelligence for your innovation.

Book recommendation sorting model training method, computing equipment and storage medium

A sorting model and technology of books, applied in the field of information processing, can solve problems such as poor recommendation effect, achieve the effect of improving book recommendation effect and increasing interaction time

Active Publication Date: 2020-05-08
ZHANGYUE TECH CO LTD
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method of book recommendation does not fully consider whether the recommended books can attract users to spend a long time reading. Users are likely to stop reading after reading a recommended book for only a few minutes. , resulting in poor recommendation results for book recommendations

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Book recommendation sorting model training method, computing equipment and storage medium
  • Book recommendation sorting model training method, computing equipment and storage medium
  • Book recommendation sorting model training method, computing equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] figure 1 A schematic flowchart showing a method for training a book recommendation ranking model according to Embodiment 1 of the present invention, as shown in figure 1 As shown, the method includes the following steps:

[0022] Step S101, acquiring interactive behavior data of users in the user collection with respect to books in the book collection.

[0023] The user set includes multiple users in the book reading platform, and these multiple users can be all users in the book reading platform, or some users, which are not specifically limited here. The book collection includes multiple books provided by the book reading platform. The user's interaction behavior data with respect to books is the data used to describe the interaction between the user and the book, and may specifically include: the user's book reading data, book review data, book download data, etc. for the book. In step S101, interactive behavior data such as book reading data, book review data, an...

Embodiment 2

[0035] figure 2 A schematic flowchart showing a method for training a book recommendation ranking model according to Embodiment 2 of the present invention, as shown in figure 2 As shown, the method includes the following steps:

[0036] Step S201, acquiring interactive behavior data of users in the user collection with respect to books in the book collection.

[0037] Among them, interactive behavior data such as book reading data, book review data, and book download data of each user in the user collection for books in the book collection can be obtained from the book reading platform. The interaction behavior data at least includes: user ID, book ID interacted by the user, interaction start time, interaction end time and other data. Specifically, the user ID may be the user's account on the book reading platform, such as a mobile phone number, user name, email address, WeChat account and other third-party platform accounts.

[0038] Step S202, for any user, analyze the ...

Embodiment 3

[0058] image 3 It shows a schematic flowchart of a method for recommending books according to Embodiment 3 of the present invention, as shown in image 3 As shown, the method includes the following steps:

[0059] Step S301, acquiring the interaction behavior data of the user to be recommended with respect to the books in the book collection, and determining a third subset of books that the user to be recommended interacted with before the current moment.

[0060] Among them, interactive behavior data such as book reading data, book review data, and book download data of the user to be recommended for the books in the book collection can be obtained from the book reading platform. After obtaining the interactive behavior data of the user to be recommended, data analysis is performed on the interactive behavior data of the user to be recommended to obtain the books that the user to be recommended has interacted with before the current moment, and the books that the user to be...

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

No PUM Login to View More

Abstract

The invention discloses a book recommendation sorting model training method, computing equipment and a storage medium. The method comprises the steps of obtaining interaction behavior data of users ina user set for books in a book set; for any user, determining a first book subset, a second book subset and an interaction duration label of each second book; calculating a first feature vector of the first book subset and a second feature vector of each second book; calculating the similarity between each second feature vector and the first feature vector; and performing training according to the similarity between each second feature vector of each user and the first feature vector and the interaction duration label of each second book to obtain a book recommendation sorting model. According to the scheme, the interaction duration between the user and the books is fully considered in the model training process, the obtained book recommendation sorting model can accurately sort the booksbased on the interaction duration, and the interaction duration of the user for the recommended books can be improved.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a method for training a book recommendation sorting model, a computing device and a storage medium. Background technique [0002] Books in the form of e-books are favored by a large number of users due to their advantages such as easy access. Most of the book reading platforms recommend books according to the similarity of the full text of the books. In the prior art, generally several books having a high degree of similarity in book content to books that the user has read are used as recommended books and presented to the user. However, this method of book recommendation does not fully consider whether the recommended books can attract users to spend a long time reading. Users are likely to stop reading after reading a recommended book for only a few minutes. , resulting in poor recommendation effects for book recommendations. Contents of the invention [000...

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
no application Login to View More
IPC IPC(8): G06F16/9536G06F16/9537G06F16/335
CPCG06F16/9536G06F16/9537G06F16/335
Inventor 王海璐冯丽洋李帆曹雯潇
Owner ZHANGYUE TECH CO LTD