Book recommendation method, computing device and computer storage medium

Abstract

The present invention discloses a book recommendation method, a computing device and a computer storage medium. The method comprises: obtaining user churn data corresponding to the first book according to a user's reading request for a target page of a first book currently being read; determining whether to recommend a book to the user on the target page according to the user churn data; if it is determined to recommend a book to the user on the target page, screening the books to be recommended from the book library; loading and displaying the target page, and displaying the books to be recommended at a preset recommendation position of the target page. In the above manner, the present invention realizes dynamic recommendation of books, and enables the user to switch to reading books by clicking on the books to be recommended displayed at the recommendation position when the user does not want to continue reading the first book, thereby improving the user retention rate and avoiding the problem of user churn due to the user not liking the book currently being read.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a book recommendation method, a computing device and a computer storage medium. Background Art

[0002] With the increasing application of Internet technology, traditional paper reading methods have gradually been replaced by electronic reading methods, and people are increasingly inclined to use the Internet and computer technology to read books through book reading programs or readers.

[0003] Users read books sometimes by searching for books, and sometimes by selecting books through a bookstore. However, after users enter a book and start reading, if they find that they do not like the book, they are likely to end the reading and leave the book reading program or reader, resulting in a high user churn rate. Summary of the invention

[0004] In view of the above problems, the present invention is proposed to provide a book recommendation method, a computing device and a computer storage medium that overcome the above problems or at least partially solve the above problems.

[0005] According to one aspect of the present invention, a book recommendation method is provided, comprising:

[0006] Acquire user churn data corresponding to the first book according to the user's reading request for the target page of the first book currently being read;

[0007] Determine whether to recommend books to users on the target page based on user churn data;

[0008] If it is determined to recommend books to the user on the target page, the books to be recommended are screened from the book library;

[0009] The target page is loaded and displayed, and the books to be recommended are displayed at the preset recommendation position of the target page.

[0010] According to another aspect of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0011] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations:

[0012] Acquire user churn data corresponding to the first book according to the user's reading request for the target page of the first book currently being read;

[0013] Determine whether to recommend books to users on the target page based on user churn data;

[0014] If it is determined to recommend books to the user on the target page, the books to be recommended are screened from the book library;

[0015] The target page is loaded and displayed, and the books to be recommended are displayed at the preset recommendation position of the target page.

[0016] According to another aspect of the present invention, a computer storage medium is provided, in which at least one executable instruction is stored, and the executable instruction enables a processor to perform operations corresponding to the above-mentioned book recommendation method.

[0017] According to the solution provided by the present invention, based on the user's reading request for the target page of the first book currently being read, the user churn data corresponding to the first book is obtained, and it is determined whether to recommend the book to the user on the target page based on the user churn data, thereby realizing dynamic recommendation of books. If it is determined to recommend the book to the user on the target page, the books to be recommended are screened from the book library, the target page is loaded and displayed, and the books to be recommended are displayed at a preset recommendation position on the target page, so that when the user does not want to continue reading the first book, the user can switch to reading the book by clicking on the book to be recommended displayed at the recommendation position, thereby improving the user retention rate and avoiding the problem of user churn due to the user not liking the book currently being read.

[0018] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0020] Figure 1 A schematic diagram showing a flow chart of a book recommendation method according to an embodiment of the present invention;

[0021] Figure 2 A schematic diagram showing a flow chart of a book recommendation method according to another embodiment of the present invention;

[0022] Figure 3 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0023] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0024] Figure 1 FIG. 2 shows a flow chart of a method for recommending books according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0025] Step S101 : acquiring user churn data corresponding to a first book according to a user's reading request for a target page of a first book currently being read.

[0026] Specifically, the user will perform a page-turning operation while reading a book. When the page is turned to the target page of the first book currently being read, it is deemed that the user has triggered a reading request for the target page of the first book currently being read. Based on the user's reading request for the target page of the first book currently being read, user churn data corresponding to the first book is obtained, wherein the user churn data reflects the churn of reading users, and the target page can be the end page of a chapter of the book or the end page of a storyline of the book.

[0027] Normally, every time a user reads a book, the user's reading behavior data will be recorded. Therefore, by analyzing the user's historical reading behavior data, it is possible to analyze which users have churned and which users have retained, thereby determining the user churn data corresponding to the book.

[0028] This embodiment is not limited to turning to the target page by executing a page turning operation. For example, the target page can also be jumped to by page number jumping.

[0029] Step S102: determining whether to recommend books to the user on the target page according to the user churn data.

[0030] The user churn data reflects the loss of reading users. The higher the user churn data, the more lost users there are, and the lower the possibility that the user will continue to read the first book. In order to retain the user, books can be recommended to the user on the target page to guide the user to read other books. The lower the user churn data, the more retained users there are, and the higher the possibility that the user will continue to read the first book. In order to avoid interfering with the user's reading and affecting the user's reading experience, no books will be recommended to the user on the target page. After obtaining the user churn data corresponding to the first book, it can be determined whether to recommend books to the user on the target page based on the user churn data, where the user churn data can be the user churn rate or the number of lost users.

[0031] Step S103: If it is determined to recommend books to the user on the target page, the books to be recommended are screened from the book library.

[0032] If it is determined according to step S102 that books need to be recommended to the user on the target page, the books recommended to the user may be screened from the book library.

[0033] Step S104, loading and displaying the target page, and displaying the books to be recommended at the preset recommendation position of the target page.

[0034] Specifically, a target page is loaded and displayed to the user, wherein a recommendation position is set at a preset position of the target page. Therefore, the recommended books can be displayed at the recommendation position of the target page. If the user does not want to continue reading the first book, the user can switch to reading the book by clicking on the recommended book displayed at the recommendation position, thereby improving the user retention rate and avoiding the problem of user loss due to the user not liking the current book being read.

[0035] The solution provided by the present invention obtains user churn data corresponding to the first book according to the user's reading request for the target page of the first book currently being read, and determines whether to recommend the book to the user on the target page according to the user churn data, thereby realizing dynamic recommendation of books. If it is determined to recommend the book to the user on the target page, the books to be recommended are screened from the book library, the target page is loaded and displayed, and the books to be recommended are displayed at a preset recommendation position on the target page, so that when the user does not want to continue reading the first book, the user can switch to reading the book by clicking on the books to be recommended displayed at the recommendation position, thereby improving the user retention rate and avoiding the problem of user churn due to the user not liking the book currently being read.

[0036] Figure 2 FIG. 2 shows a flow chart of a method for recommending books according to another embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0037] Step S201 , obtaining a user churn rate corresponding to a book chapter according to a user's reading request for the end page of a chapter of a first book currently being read.

[0038] The end-of-chapter page is the last page of each book chapter. Usually, the page number of the end-of-chapter page of each book chapter is known. Therefore, the page number can be used to determine whether the user has read the end-of-chapter page. When the user turns to the end-of-chapter page, it is considered to trigger a reading request for the end-of-chapter page. According to the reading request for the end-of-chapter page, the user churn rate corresponding to the book chapter is obtained, where the user churn rate refers to the proportion of users who churn when reading the book chapter.

[0039] Step S202, determine whether a book is recommended to the user at the end page of the previous chapter; if not, execute step S203; if yes, execute step S212.

[0040] This step determines whether to recommend books to users at the end page of the previous chapter. This is mainly to avoid recommending books to users at the end pages of two consecutive book chapters. Continuous recommendations not only affect the user's reading experience, but also cannot effectively improve the user retention rate, resulting in a waste of recommendation resources.

[0041] Step S203, determining whether the user churn rate is greater than or equal to a preset churn rate threshold; if so, executing step S204 or executing step S209; if not, executing step S212.

[0042] The user churn rate reflects the probability of a reading user churn after reading the chapter of the first book but not continuing to read the next chapter. In order to improve the user retention rate and avoid interfering with user reading, the present embodiment does not recommend books to users at the end page of each chapter of a book, but dynamically selects the end pages of some chapters of a book to recommend books to users. Specifically, the following method can be used to determine whether to recommend books to users at the end page of a chapter: determine whether the user churn rate is greater than or equal to a preset churn rate threshold, wherein the preset churn rate threshold is a pre-set critical value, and the specific value can be flexibly set according to actual needs, for example, set to 0.4 or 0.5.

[0043] If the user churn rate is greater than or equal to the preset churn rate threshold, it indicates that the user is likely to churn after reading the book chapter, and the user can be retained by recommending books to the user on the end-of-chapter page. If the user churn rate is less than the preset churn rate threshold, it indicates that the user is likely to retain after reading the book chapter, and in order not to interfere with the user's reading, the book will not be recommended to the user on the end-of-chapter page. In order to improve the utilization rate of the recommendation position on the end-of-chapter page and further improve user retention and revenue, media information can be recommended to the user on the end-of-chapter page.

[0044] When it is determined that the user churn rate is greater than or equal to the preset churn rate threshold, it can be determined that books need to be recommended to the user at the end of the chapter page. For a certain user, it may be the first day for him to register a book reading program or reader to read books. Here, the user is called a new user. When describing, the new user is represented as the first type; or it may be that he has completed registration and has generated reading behavior. Here, the user is called an old user. When describing, the old user is represented as the second type. For new users and old users, different methods are used here to screen the recommended books:

[0045] Step S204: if the user belongs to the first type, then the number of chapters of the first book that have been read is counted.

[0046] If the user reading the first book belongs to the first type, that is, the user is a new user, it can be determined that the user has less reading behavior and it is not easy to obtain user preferences. Therefore, book recommendations are mainly based on book popularity and similarities between books.

[0047] For the first book currently read by the user, the number of book chapters that the user has read is counted, which is referred to as the number of book chapters that have been read.

[0048] Step S205, determining whether the number of chapters of the book that has been read is greater than or equal to a preset number of chapters; if so, executing step S206; if not, executing step S207.

[0049] For a new user, the number of chapters in the book he has read can reflect whether the first book he is currently reading meets his interests. Here, a preset number of chapters is set based on experience. The preset number of chapters is a critical value used to determine whether the first book meets the user's interests. If the number of chapters in the book he has read is greater than or equal to the preset number of chapters, it can be determined that the first book meets the user's interests. If the number of chapters in the book he has read is less than the preset number of chapters, it can be determined that the first book does not meet the user's interests.

[0050] Step S206, based on a preset similarity algorithm, calculate the similarity between the first book and any second book in the book library, and select from the book library second books whose similarity to the first book is greater than or equal to a preset similarity threshold and whose book popularity is greater than or equal to a preset popularity threshold as books to be recommended.

[0051] If the number of chapters of the book that has been read is greater than or equal to the preset number of chapters, it can be determined that the first book currently being read meets the user's interests. Therefore, the recommended books can be screened according to the similarity between the books and combined with the popularity of the books. Specifically, a preset similarity algorithm can be used, for example, a swing algorithm, an item_cf algorithm, or other similarity algorithms to calculate the similarity between the first book and any second book in the book library. The similarity reflects the similarity between the two books. The higher the similarity, the more similar the two books are, and vice versa.

[0052] After calculating the similarity between the first book and any second book in the book library, the second books in the book library can be sorted in order of similarity from high to low or from low to high, and second books whose similarity to the first book is greater than or equal to a preset similarity threshold are screened out. The screened second books are then sorted according to book popularity, and second books whose book popularity is greater than or equal to the preset popularity threshold are screened out as books to be recommended.

[0053] In addition, this embodiment can also filter the books to be recommended according to the number of recommendation positions. For example, if the number of recommendation positions is 3, then a second book whose similarity with the first book is greater than or equal to a preset similarity threshold can be filtered out. For the filtered second books, the three second books with the highest popularity are filtered out as the books to be recommended.

[0054] Specifically, the following method can be used to calculate the similarity between a first book and any second book in a book library: obtain a set of users who read the first book and a set of users who read the second book, and determine a user intersection set of the first book reading user set and the second book reading user set; determine common book data read by any two users based on user historical reading behavior data of any two users in the user intersection set; calculate the similarity between the first book and the second book based on the common book data of any two users.

[0055] Here, the similarity between the first book and the second book is mainly transmitted through user relationships. In order to measure the similarity between the first book and the second book, two users who have read the first book and the second book are determined. If the two users read fewer books together, the similarity between the first book and the second book is higher. Since each user's reading behavior data is recorded every time he reads a book, such as user ID, book ID, reading time, reading duration, etc., the first book reading user set and the second book reading user set are determined by analyzing the user's historical reading behavior data of users across the entire network, wherein the first book reading user set is a set of all users who read the first book, and the second book reading user set is a set of all users who read the second book. For each user in the first book reading user set, it is determined whether the user exists in the second book reading user set. If so, the user is added to the user intersection set, and finally the user intersection set of the first book reading user set and the second book reading user set is determined. The users in the user intersection set are users who have read both the first book and the second book. Two users are randomly selected from the user intersection set, and the common book data read by the two users is determined based on the user historical reading behavior data of the two users, for example, the number of books read by the two users. The similarity between the first book and the second book is calculated based on the common book data of any two users, for example, the inverse of the common book data of any two users is calculated, and then the similarity between the first book and the second book is calculated by weighted summation, and the weight can be determined based on the total number of books read by the two users.

[0056] Step S207: select a second book from the book library as a book to be recommended according to the popularity of the book.

[0057] Step S208, based on a preset similarity algorithm, calculate the similarity between the first book and any second book in the book library, and select from the book library second books whose similarity to the first book is greater than or equal to a preset similarity threshold and whose book popularity is greater than or equal to a preset popularity threshold as books to be recommended.

[0058] If the number of chapters of the book that has been read is less than the preset number of chapters, it indicates that it cannot be determined whether the first book meets the user's interest. In order to improve the user retention rate, the second book is selected from the book library as the recommended book according to the book popularity. For example, the second books in the book library are sorted from high to low according to the book popularity, and the second books whose book popularity is greater than or equal to the preset popularity threshold are selected, or a specific number of second books are selected, for example, 2 books are selected.

[0059] Based on the popularity of books, some of the books to be recommended can be screened, and the following method can be used to screen another part of the books to be recommended: based on a preset similarity algorithm, the similarity between the first book and any second book in the book library is calculated, and the second books whose similarity to the first book is greater than or equal to the preset similarity threshold and whose book popularity is greater than or equal to the preset popularity threshold are screened from the book library as the books to be recommended. The specific implementation process is shown in step S206, which will not be repeated here. The sum of the second books screened by the two screening methods is used as the books to be recommended to the user on the target page.

[0060] It should be noted that here, the recommended books can be filtered only according to the popularity of the books, or the similarity can be calculated first, and then the recommended books can be filtered based on the similarity and the popularity of the books. There is no specific limitation here.

[0061] Step S209, if the user belongs to the second type, then based on a preset similarity algorithm, the similarity between the first book and any second book in the book library is calculated, and second books whose similarity to the first book is greater than or equal to a preset similarity threshold and whose book popularity is greater than or equal to a preset popularity threshold are selected from the book library as books to be recommended.

[0062] If the user reading the first book belongs to the second type, that is, the user is an old user, here the main purpose is to recommend to the user books that are related to the first book currently being read and that the user is interested in. For example, based on a preset similarity algorithm, the similarity between the first book and any second book in the book library is calculated, and second books whose similarity to the first book is greater than or equal to a preset similarity threshold and whose book popularity is greater than or equal to a preset popularity threshold are selected from the book library as books to be recommended. The specific implementation process is shown in step S206, which will not be repeated here.

[0063] Step S210, determining the user's book preference type based on the user's historical reading behavior data; determining a target user who has the same book preference type as the user; and selecting a second book from the book library as a book to be recommended based on other book preference types of the target user.

[0064] Based on the similarity and book popularity, some books to be recommended can be screened. The following method can also be used to screen another part of the books to be recommended: determine the user's book preference type based on the user's historical reading behavior data; determine the target user who has the same book preference type as the user; and select a second book from the book library as the book to be recommended based on the target user's other book preference types.

[0065] Data analysis is performed on the user's historical reading behavior data to determine the user's corresponding book preference type. The book preference type of each user can be determined through analysis. The book preference type corresponding to each user is different. The target user with the same book preference type as the user is found. The target user may have multiple book preference types at the same time. Therefore, the target user's other book preference types will be used as the basis for recommendation. The second book of the target user's other book preference type in the book can be determined as the book to be recommended. For example, the user is currently reading an urban book, and through analysis it is determined that the target user likes fantasy books in addition to urban books, then a fantasy book can be recommended. In this way, the recommendation diversity for the second type of users can be expanded under the premise of ensuring a certain recommendation accuracy.

[0066] For example, you can select two books for recommendation based on similarity and book popularity, and select one book for recommendation based on book preference type. In addition, this can also be achieved through pre-trained models.

[0067] It should be noted that, for old users, the books to be recommended can be filtered only by the book preference type, or only based on similarity and book popularity, and no specific limitation is made here.

[0068] Step S211, loading and displaying the end page of the chapter, and displaying the books to be recommended at the preset recommendation position of the end page of the chapter.

[0069] Specifically, the end-of-chapter page is loaded and displayed to the user, wherein a recommendation position is set at a preset position of the end-of-chapter page. Therefore, the recommended books can be displayed at the recommendation position of the end-of-chapter page. If the user does not want to continue reading the first book, the user can switch to reading the book by clicking on the recommended book displayed at the recommendation position, thereby improving the user retention rate and avoiding the problem of user loss due to the user not liking the current book being read.

[0070] Step S212, loading and displaying the end page of the chapter, and displaying the media information at the preset recommendation position of the end page of the chapter.

[0071] If it is determined that a book is recommended to the user at the end page of the previous chapter, it indicates that the user churn rate of the previous chapter is also high, and books have been recommended to the user. In order to avoid too frequent book recommendations that affect the user's reading experience, books are usually not recommended in two consecutive chapters. Or, if it is determined that the user churn rate is less than the preset churn rate threshold, it can be determined that the user retention rate is high. In order not to interfere with user reading, this embodiment does not recommend books to the user at the end page of the chapter. Therefore, after loading and displaying the end page of the chapter, media information, such as advertising information, is displayed at the preset recommendation position of the end page of the chapter. By recommending media information, revenue can be increased, and the utilization rate of the recommendation position can be improved.

[0072] For example, if the user churn rate of Chapter 5 is high, you can recommend books at the end of Chapter 5. If the user churn rate of Chapter 6 is low, you will not recommend books at the end of Chapter 6 but advertisements instead. This allows you to dynamically recommend other books to users at the end of the first book based on the user churn rate.

[0073] It should be noted that steps S204 to S210 are optional steps. In this embodiment, when it is determined that the user churn rate is greater than or equal to a preset churn threshold, the similarity between the first book and any second book in the book library can be directly calculated based on a preset similarity algorithm, and a second book whose similarity to the first book is greater than or equal to the preset similarity threshold and whose book popularity is greater than or equal to the preset popularity threshold is selected from the book library as a book to be recommended. No distinction is made between new and old users here.

[0074] The solution provided by the present invention obtains the user churn rate corresponding to a book chapter according to the user's reading request for the end-of-chapter page. If the user churn rate is greater than or equal to a preset churn threshold, it can be determined that the book needs to be recommended to the user on the end-of-chapter page, thereby realizing dynamic recommendation of books. If it is determined to recommend the book to the user on the end-of-chapter page, different screening methods are used for new users and old users to screen the recommended books from the book library, load and display the target page, and display the recommended books at the preset recommendation position of the target page, so that when the user does not want to continue reading the first book, the user can switch to reading the recommended book by clicking on the recommended book displayed at the recommendation position, thereby improving the user retention rate and avoiding the problem of user churn due to the user not liking the currently read book.

[0075] An embodiment of the present invention further provides a non-volatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the book recommendation method in any of the above method embodiments.

[0076] The executable instructions may be used to cause the processor to perform the following operations:

[0077] Acquire user churn data corresponding to the first book according to the user's reading request for the target page of the first book currently being read;

[0078] Determine whether to recommend books to users on the target page based on user churn data;

[0079] If it is determined to recommend books to the user on the target page, the books to be recommended are screened from the book library;

[0080] The target page is loaded and displayed, and the books to be recommended are displayed at the preset recommendation position of the target page.

[0081] In an optional implementation, the user churn data is a user churn rate;

[0082] The executable instructions further cause the processor to:

[0083] Determine whether the user churn rate is greater than or equal to a preset churn rate threshold;

[0084] If yes, it is determined to recommend the book to the user on the target page; if no, it is determined not to recommend the book to the user on the target page.

[0085] In an optional implementation, the executable instructions further cause the processor to perform the following operations:

[0086] If the target page is the end page of a chapter, user churn data corresponding to the book chapter is obtained according to the user's reading request for the end page of the chapter of the first book.

[0087] In an optional implementation, the executable instructions further cause the processor to perform the following operations:

[0088] Determine whether to recommend a book to the user at the end of the previous chapter;

[0089] If so, it is determined not to recommend books to the user on the target page;

[0090] If not, determine whether the user churn rate is greater than or equal to a preset churn rate threshold.

[0091] In an optional implementation, the executable instructions further cause the processor to perform the following operations:

[0092] If it is determined not to recommend books to the user on the target page, the target page is loaded and displayed, and the media information is displayed at a preset recommendation position on the target page.

[0093] In an optional implementation, the executable instructions further cause the processor to perform the following operations:

[0094] Based on a preset similarity algorithm, the similarity between the first book and any second book in the book library is calculated, and a second book whose similarity to the first book is greater than or equal to a preset similarity threshold and whose book popularity is greater than or equal to a preset popularity threshold is selected from the book library as a book to be recommended.

[0095] In an optional implementation, the executable instructions further cause the processor to perform the following operations:

[0096] Obtaining a first book reading user set and a second book reading user set, and determining a user intersection set of the first book reading user set and the second book reading user set;

[0097] Determine the common book data read by any two users according to the historical reading behavior data of any two users in the user intersection set;

[0098] Based on the common book data of any two users, the similarity between the first book and the second book is calculated.

[0099] In an optional implementation, the executable instructions further cause the processor to perform the following operations:

[0100] If the user belongs to the first type, the number of chapters of the first book that have been read is counted;

[0101] If the number of chapters of the book that has been read is less than the preset number of chapters, a second book is selected from the book library as a book to be recommended according to the popularity of the book.

[0102] In an optional implementation, the executable instructions further cause the processor to perform the following operations:

[0103] If the user belongs to the second type, the user's book preference type is determined based on the user's historical reading behavior data;

[0104] Identify target users who have the same book preferences as the user;

[0105] A second book is selected from the book library as a to-be-recommended book according to other book preference types of the target user.

[0106] Figure 3 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

[0107] like Figure 3 As shown, the computing device may include: a processor (processor) 302 , a communication interface (Communications Interface) 304 , a memory (memory) 306 , and a communication bus 308 .

[0108] The processor 302 , the communication interface 304 , and the memory 306 communicate with each other via the communication bus 308 .

[0109] The communication interface 304 is used to communicate with other devices such as clients or other servers.

[0110] The processor 302 is used to execute the program 310, and specifically can execute the relevant steps in the above-mentioned book recommendation method embodiment.

[0111] Specifically, the program 310 may include program codes, which include computer operation instructions.

[0112] The processor 302 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0113] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0114] The program 310 may be specifically configured to enable the processor 302 to perform the following operations:

[0115] Acquire user churn data corresponding to the first book according to the user's reading request for the target page of the first book currently being read;

[0116] Determine whether to recommend books to users on the target page based on user churn data;

[0117] If it is determined to recommend books to the user on the target page, the books to be recommended are screened from the book library;

[0118] The target page is loaded and displayed, and the books to be recommended are displayed at the preset recommendation position of the target page.

[0119] In an optional implementation, the user churn data is a user churn rate;

[0120] The program 310 further causes the processor 302 to perform the following operations:

[0121] Determine whether the user churn rate is greater than or equal to a preset churn rate threshold;

[0122] If yes, it is determined to recommend the book to the user on the target page; if no, it is determined not to recommend the book to the user on the target page.

[0123] In an optional implementation, the program 310 further causes the processor 302 to perform the following operations:

[0124] If the target page is the end page of a chapter, user churn data corresponding to the book chapter is obtained according to the user's reading request for the end page of the chapter of the first book.

[0125] In an optional implementation, the program 310 further causes the processor 302 to perform the following operations:

[0126] Determine whether to recommend a book to the user at the end of the previous chapter;

[0127] If so, it is determined not to recommend books to the user on the target page;

[0128] If not, determine whether the user churn rate is greater than or equal to a preset churn rate threshold.

[0129] In an optional implementation, the program 310 further causes the processor 302 to perform the following operations:

[0130] If it is determined not to recommend books to the user on the target page, the target page is loaded and displayed, and the media information is displayed at a preset recommendation position on the target page.

[0131] In an optional implementation, the program 310 further causes the processor 302 to perform the following operations:

[0132] Based on a preset similarity algorithm, the similarity between the first book and any second book in the book library is calculated, and a second book whose similarity to the first book is greater than or equal to a preset similarity threshold and whose book popularity is greater than or equal to a preset popularity threshold is selected from the book library as a book to be recommended.

[0133] In an optional implementation, the program 310 further causes the processor 302 to perform the following operations:

[0134] Obtaining a first book reading user set and a second book reading user set, and determining a user intersection set of the first book reading user set and the second book reading user set;

[0135] Determine the common book data read by any two users according to the historical reading behavior data of any two users in the user intersection set;

[0136] Based on the common book data of any two users, the similarity between the first book and the second book is calculated.

[0137] In an optional implementation, the program 310 further causes the processor 302 to perform the following operations:

[0138] If the user belongs to the first type, the number of chapters of the first book that have been read is counted;

[0139] If the number of chapters of the book that has been read is less than the preset number of chapters, a second book is selected from the book library as a book to be recommended according to the popularity of the book.

[0140] In an optional implementation, the program 310 further causes the processor 302 to perform the following operations:

[0141] If the user belongs to the second type, the user's book preference type is determined based on the user's historical reading behavior data;

[0142] Identify target users who have the same book preferences as the user;

[0143] A second book is selected from the book library as a to-be-recommended book according to other book preference types of the target user.

[0144] The algorithm or display provided herein is not inherently related to any particular computer, virtual system or other equipment. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious to construct the structure required for this type of system. In addition, the embodiment of the present invention is not directed to any specific programming language yet. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description made to specific languages ​​above is for disclosing the best mode of the present invention.

[0145] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0146] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0147] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0148] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0149] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components according to embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0150] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A book recommendation method, comprising: acquiring user churn data corresponding to a first book currently being read according to a reading request of the user for a target page of the first book currently being read; Determining whether to recommend a book to the user on the target page according to the user churn data; If it is determined to recommend books to the user on the target page, then selecting the books to be recommended from the book library; Loading and displaying the target page, and displaying the books to be recommended at the preset recommendation position of the target page; Wherein, the user churn data is the user churn rate, and the target page is the end page of the chapter; The determining whether to recommend a book to the user on the target page according to the user churn data further includes: Determine whether to recommend a book to the user at the end of the previous chapter; If a book is recommended to the user at the end page of the previous chapter, it is determined not to recommend the book to the user at the target page; If no book is recommended to the user at the end page of the previous chapter, determining whether the user churn rate is greater than or equal to a preset churn rate threshold; If it is greater than or equal to the preset churn rate threshold, it is determined to recommend books to the user on the target page; if it is less than the preset churn rate threshold, it is determined not to recommend books to the user on the target page.

2. The method according to claim 1, wherein: The acquiring the loss data corresponding to the first book according to the user's reading request for the target page of the first book currently being read further comprises: According to the user's reading request for the end page of the chapter of the first book, user churn data corresponding to the book chapter is obtained.

3. The method according to claim 1 or 2, wherein: The method further includes: if it is determined not to recommend a book to the user on the target page, loading and displaying the target page, and displaying media information at a preset recommendation position on the target page.

4. The method according to claim 1 or 2, wherein: The step of screening the books to be recommended from the book library further includes: Based on a preset similarity algorithm, the similarity between the first book and any second book in the book library is calculated, and a second book whose similarity to the first book is greater than or equal to a preset similarity threshold and whose book popularity is greater than or equal to a preset popularity threshold is selected from the book library as a book to be recommended.

5. The method according to claim 4, wherein: The calculating the similarity between the first book and any second book in the book library based on the preset similarity algorithm further includes: Obtaining a first book reading user set and a second book reading user set, and determining a user intersection set of the first book reading user set and the second book reading user set; Determine common book data read by any two users according to the user history reading behavior data of any two users in the user intersection set; Based on the common book data of any two users, the similarity between the first book and the second book is calculated.

6. The method according to claim 1 or 2, wherein: The step of screening the books to be recommended from the book library further includes: If the user belongs to the first type, then counting the number of chapters of the first book that have been read; If the number of chapters of the read book is less than the preset number of chapters, a second book is selected from the book library as a book to be recommended according to the popularity of the book.

7. The method according to claim 1 or 2, wherein: The step of screening the books to be recommended from the book library further includes: If the user belongs to the second type, determining the user's book preference type based on the user's historical reading behavior data; Determine a target user who has the same book preference type as the user; A second book is selected from the book library as a book to be recommended according to other book preference types of the target user.

8. A computing device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations: acquiring user churn data corresponding to a first book currently being read according to a reading request of the user for a target page of the first book currently being read; Determining whether to recommend a book to the user on the target page according to the user churn data; If it is determined to recommend books to the user on the target page, then selecting the books to be recommended from the book library; Loading and displaying the target page, and displaying the books to be recommended at the preset recommendation position of the target page; Wherein, the user churn data is the user churn rate, and the target page is the end page of the chapter; The executable instructions further cause the processor to perform the following operations: Determine whether to recommend a book to the user at the end of the previous chapter; If a book is recommended to the user at the end page of the previous chapter, it is determined not to recommend the book to the user at the target page; If no book is recommended to the user at the end page of the previous chapter, determining whether the user churn rate is greater than or equal to a preset churn rate threshold; If it is greater than or equal to the preset churn rate threshold, it is determined to recommend books to the user on the target page; if it is less than the preset churn rate threshold, it is determined not to recommend books to the user on the target page.

9. The computing device of claim 8, wherein: The executable instructions further cause the processor to perform the following operations: According to the user's reading request for the end page of the chapter of the first book, user churn data corresponding to the book chapter is obtained.

10. The computing device according to claim 8 or 9, wherein: The executable instructions further cause the processor to: If it is determined not to recommend books to the user on the target page, the target page is loaded and displayed, and media information is displayed at a preset recommendation position on the target page.

11. The computing device according to claim 8 or 9, wherein: The executable instructions further cause the processor to perform the following operations: Based on a preset similarity algorithm, the similarity between the first book and any second book in the book library is calculated, and a second book whose similarity to the first book is greater than or equal to a preset similarity threshold and whose book popularity is greater than or equal to a preset popularity threshold is selected from the book library as a book to be recommended.

12. The computing device of claim 11, wherein: The executable instructions further cause the processor to perform the following operations: Obtaining a first book reading user set and a second book reading user set, and determining a user intersection set of the first book reading user set and the second book reading user set; Determine common book data read by any two users according to the user history reading behavior data of any two users in the user intersection set; Based on the common book data of any two users, the similarity between the first book and the second book is calculated.

13. The computing device according to claim 8 or 9, wherein: The executable instructions further cause the processor to perform the following operations: If the user belongs to the first type, then counting the number of chapters of the first book that have been read; If the number of chapters of the read book is less than the preset number of chapters, a second book is selected from the book library as a book to be recommended according to the popularity of the book.

14. The computing device according to claim 8 or 9, wherein: The executable instructions further cause the processor to perform the following operations: If the user belongs to the second type, determining the user's book preference type based on the user's historical reading behavior data; Determine a target user who has the same book preference type as the user; A second book is selected from the book library as a book to be recommended according to other book preference types of the target user.

15. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to perform operations corresponding to the book recommendation method according to any one of claims 1 to 7.

Images