CN114647782A - Book recommendation method of bookshelf page, computing device and storage medium - Google Patents
Book recommendation method of bookshelf page, computing device and storage medium Download PDFInfo
- Publication number
- CN114647782A CN114647782A CN202210310431.2A CN202210310431A CN114647782A CN 114647782 A CN114647782 A CN 114647782A CN 202210310431 A CN202210310431 A CN 202210310431A CN 114647782 A CN114647782 A CN 114647782A
- Authority
- CN
- China
- Prior art keywords
- book
- recommended
- bookshelf
- books
- sequencing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a book recommendation method, a computing device and a storage medium for bookshelf pages, wherein the method comprises the following steps: receiving bookshelf page access operation of a user; the method comprises the steps of obtaining the sequencing characteristics of the bookshelf books of a user, inputting the sequencing characteristics of the bookshelf books into a preset sequencing model for calculation, and determining the sequencing score of each book to be recommended of the user according to the calculation result; and screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and presenting at least one book to be recommended in the book recommendation position of the bookshelf page. By the method, the book recommendation positions are arranged in the bookshelf pages, so that books can be recommended on the bookshelf pages, and meanwhile, the sequencing of the books to be recommended of the user is determined according to the sequencing of the books on the bookshelf of the user, so that the sequencing of the books to be recommended is more suitable for the hobbies of the user, and the recommendation effect of the book recommendation positions can be improved.
Description
Technical Field
The invention relates to the technical field of Internet, in particular to a book recommendation method, a computing device and a storage medium for bookshelf pages.
Background
Currently, with the popularization of mobile terminals and the development of electronic book reading platforms, more and more users use the electronic book reading platforms to read electronic books. The electronic book reading platform can recommend books for users, generally, books can be recommended in a mode of pushing messages to the users, the pushing messages are easy to ignore or even clear by the users, the platform can also set special book recommendation pages to display a large number of books for the users to browse and screen, the users who are concentrated on reading often can search the books in a precise searching mode, and the users rarely browse the books and recommend the pages to search the books. In a word, the recommendation success rate of the existing book recommendation mode is low, and the recommendation effect is poor.
Disclosure of Invention
In view of the above problems, the present invention has been made to provide a book recommendation method of bookshelf pages, a computing device and a storage medium that overcome or at least partially solve the above problems.
According to an aspect of the present invention, there is provided a book recommendation method for bookshelf pages, including:
receiving bookshelf page access operation of a user;
acquiring the sorting characteristics of the bookshelf books of the user, inputting the sorting characteristics of the bookshelf books into a preset sorting model for calculation, and determining the sorting score of each book to be recommended for the user according to the calculation result;
screening at least one book to be recommended according to the sequence of the ranking score of each book to be recommended from high to low, and presenting at least one book to be recommended in the book recommendation position of the bookshelf page.
According to yet another aspect of the present invention, there is provided a computing device comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to:
receiving bookshelf page access operation of a user;
the method comprises the steps of obtaining the sequencing characteristics of the bookshelf books of a user, inputting the sequencing characteristics of the bookshelf books into a preset sequencing model for calculation, and determining the sequencing score of each book to be recommended of the user according to the calculation result;
and screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and presenting at least one book to be recommended in the book recommendation position of the bookshelf page.
According to yet another aspect of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to:
receiving bookshelf page access operation of a user;
the method comprises the steps of obtaining the sequencing characteristics of the bookshelf books of a user, inputting the sequencing characteristics of the bookshelf books into a preset sequencing model for calculation, and determining the sequencing score of each book to be recommended of the user according to the calculation result;
and screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and presenting at least one book to be recommended in the book recommendation position of the bookshelf page.
According to the book recommendation method, the computing device and the storage medium of the bookshelf page, the method comprises the following steps: receiving bookshelf page access operation of a user; the method comprises the steps of obtaining the sequencing characteristics of the bookshelf books of a user, inputting the sequencing characteristics of the bookshelf books into a preset sequencing model for calculation, and determining the sequencing score of each book to be recommended of the user according to the calculation result; and screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and presenting at least one book to be recommended in the book recommendation position of the bookshelf page. By the method, the book recommendation positions are arranged in the bookshelf pages, so that books can be recommended on the bookshelf pages, and meanwhile, the sequencing of the books to be recommended of the user is determined according to the sequencing of the books on the bookshelf of the user, so that the sequencing of the books to be recommended is more suitable for the hobbies of the user, and the recommendation effect of the book recommendation positions can be improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating a book recommendation method for bookshelf pages according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a book recommendation method for bookshelf pages according to another embodiment of the invention;
a schematic diagram of a bookshelf page in an embodiment of the application is shown in fig. 3;
fig. 4 is a schematic structural diagram of a computing device provided in an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 is a flowchart illustrating a book recommendation method for a bookshelf page according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
step S110, receiving the bookshelf page access operation of the user.
The bookshelf page access operation is used for opening a bookshelf page, a bookshelf inlet control is arranged in the electronic book reading platform, a user can jump to the bookshelf page by triggering the bookshelf inlet control in a clicking mode or the like, and when the trigger operation of the user on the bookshelf inlet control is detected, the bookshelf page access operation of the user is determined to be received.
And step S120, obtaining the sequencing characteristics of the bookshelf books of the user, inputting the sequencing characteristics of the bookshelf books into a preset sequencing model for calculation, and determining the sequencing scores of the books to be recommended for the user according to the calculation result.
The bookshelf book refers to a book added to a bookshelf, for example, the book is automatically added to the bookshelf after a user performs a payment operation on the book, the book is automatically added to the bookshelf after the user performs a reading trial triggering operation on the book, and the book is added to the bookshelf after the user performs an addition triggering operation on the book.
The bookshelf pages are used for presenting books of the bookshelf, specifically presenting covers and basic information of the books of the bookshelf, a user can jump to the book reading pages to read by clicking the book covers, and the bookshelf pages are pages with high use frequency in the actual use process of the user. The books on the bookshelves are sorted according to specific factors, for example, the books on the bookshelves are sorted according to the latest reading time, the closer the latest reading time is to the current time, the more forward the bookshelves are sorted, or the books on the bookshelves are sorted according to the reading frequency, the more forward the bookshelves are sorted, and in short, the sorting of the books on the bookshelves can indirectly represent the preference degree of the user on the books on the bookshelves. The sequencing characteristics of the bookshelf books can be determined according to sequencing information which is determined by the book type and the sequencing factors and is used for representing the book of the type.
Each book to be recommended for a user refers to a book screened from a book pool by combining multiple reference information, for example, the reference information includes: book preference information and/or book popularity information of the user, and the like.
The preset ranking model is used for calculating the ranking score of each book to be recommended, and is obtained by training sample data with a promoting specified index as a target, for example, a model for ranking trained with a promoting click rate, a conversion rate and/or a new user retention rate as a target.
When a user accesses the bookshelf page, the sequencing characteristics of the bookshelf books of the user are obtained for real-time calculation, the sequencing characteristics of the bookshelf books are input into a preset sequencing model for calculation, and sequencing scores of the books to be recommended are obtained according to the calculation result. The calculation may be performed locally at the terminal, or the ranking characteristic may be sent to a recommendation engine of the server for calculation, which is not limited in the present invention. As can be seen, in the method of this embodiment, the order of each book to be recommended for the user is determined according to the order of the books on the bookshelves of the user, and since the order of each book on the bookshelves can represent the preference degree of the user for each book on the bookshelves, the order of each book to be recommended determined in this way can be in accordance with the preference of the user.
Step S130, screening at least one book to be recommended according to the sequence of the ranking scores of the books to be recommended from high to low, and presenting the at least one book to be recommended in the book recommending position of the bookshelf page.
The bookshelf page also comprises book recommendation positions, the book recommendation positions are a display area, and the number of the book recommendation positions can be one or more, and the book recommendation positions are used for presenting books to be recommended for a user. Specifically, books to be recommended are screened according to the sequence of the ranking scores of the books to be recommended from high to low, the screened books to be recommended are presented in the book recommending position, and the books to be recommended with higher ranking scores are presented preferentially.
According to the book recommendation method for bookshelf pages provided by the embodiment, bookshelf page access operation of a user is received; the method comprises the steps of obtaining the sequencing characteristics of the bookshelf books of a user, inputting the sequencing characteristics of the bookshelf books into a preset sequencing model for calculation, and determining the sequencing score of each book to be recommended of the user according to the calculation result; and screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and presenting at least one book to be recommended in the book recommendation position of the bookshelf page. By the method, the book recommendation positions are arranged in the bookshelf pages, so that books can be recommended on the bookshelf pages, and meanwhile, the sequencing of the books to be recommended of the user is determined according to the sequencing of the books on the bookshelf of the user, so that the sequencing of the books to be recommended is more suitable for the hobbies of the user, and the recommendation effect of the book recommendation positions can be improved.
Fig. 2 shows a flowchart of a book recommendation method for bookshelf pages according to another embodiment of the present invention, as shown in fig. 2, the method includes the following steps:
and step S210, receiving the bookshelf page access operation of the user.
The detailed description of the embodiments may refer to the description in the foregoing embodiments, and is not repeated herein.
Step S220, obtaining the sorting characteristics of the bookshelf books of the user, inputting the sorting characteristics of the bookshelf books into a preset sorting model for calculation, and determining the sorting scores of the books to be recommended for the user according to the calculation result.
The preset ranking model is used for calculating ranking scores of books to be recommended for the user, and specifically comprises the following steps: a ranking model of the duration index dimension and/or a ranking model of the retention index dimension. The ranking model of the duration index dimension is a ranking model with the index of the promoted duration dimension as a target, and includes a ranking model with the promoted click rate as a target and/or a ranking model with the promoted conversion rate as a target, and the ranking model of the reserved index dimension is a ranking model with the promoted reserved rate as a target.
The ranking model with the click rate being promoted as the target may be a DIN (Deep Interest Network) model or an iterated dienn (Deep Interest Evolution Network) model thereof, the ranking model with the conversion rate being promoted as the target may be a DNN (Deep Neural Networks) model, and the ranking model with the index dimension being preserved may be a Deep factor decomposition (fm) model. Of course, the invention does not limit the model type of the ranking model of each index dimension.
In an optional manner, the ranking model of the duration index dimension is specifically a multi-objective model, that is, a multi-objective model with a click rate improvement as a target and a conversion rate improvement as a target.
When the number of the preset sequencing models comprises a plurality of dimensionalities of the sequencing models, each sequencing model outputs the score of each book to be recommended, and the output results of the sequencing models are fused to obtain the final sequencing score of each book to be recommended. Specifically, the method comprises the following steps: respectively inputting the sequencing characteristics of the books on the bookshelf into any sequencing model for calculation to obtain the initial score of each book to be recommended calculated by the sequencing model; and calculating a weighted sum of the initial scores of any book to be recommended calculated by each sequencing model according to the weight values corresponding to each sequencing model to obtain the sequencing score of the book to be recommended. For example, the initial scores of book a to be recommended calculated by model M1, model M2, and model M3 are: f1, F2, and F3, wherein the weight values of the model M1, the model M2, and the model M3 are: w1, W2, and W3, the calculation method of the ranking score F of the book a to be recommended is as follows: F1W 1+ F2W 2+ F3W 3. Through the method, the books to be recommended can be sorted by taking indexes for improving multiple dimensions as targets.
The weight values corresponding to the sorting models can be set according to actual service needs, the recommended purpose is more important than the index of which dimensionality is improved, and a larger weight value is set for the sorting model of the dimensionality. In an optional mode, whether the user is a new user is judged, and if yes, the weight value of the sorting model of the retention index dimension is improved. For a new user, the purpose of recommending books is more focused on leaving the new user to remain, so the weight value of the ranking model of the dimension of the retention index is set to be larger.
Step S230, screening at least one book to be recommended according to the sequence of the ranking scores of the books to be recommended from high to low, presenting the at least one book to be recommended in the book recommendation position of the bookshelf page, and displaying recommendation identification information at a preset position of the book recommendation position of the bookshelf page.
The book recommendation position is a display area in a bookshelf page and used for displaying at least one book to be recommended of a user, and recommendation identification information is displayed at a preset position of the book recommendation position and used for informing the user that the book displayed in the area is the recommended book. Of course, besides the book recommendation position area, the book page also includes a display position of the bookshelf book for displaying each bookshelf book of the user.
Preferably, the number of the book recommendation positions is one, and one exclusive book recommendation position is arranged in the bookshelf page, so that compared with a mode of arranging a plurality of book recommendation positions, the recommendation content exposed to a user is reduced, the user can be prevented from feeling upset, and the user experience and the recommendation effect are improved.
Fig. 3 shows a schematic diagram of bookshelf pages in the embodiment of the application, a book recommendation position 31 is the same as a display position 33 of a bookshelf book in size, a recommendation mark 32 is arranged at the upper right corner of the book recommendation position 31, the book recommendation position 31 is arranged at the first position of a first layer of bookshelves, each layer of bookshelves contains a plurality of display positions 33 of bookshelf books, the book recommendation position 31 is used for presenting book covers and book information of the book to be recommended, the display positions of the bookshelf books are used for presenting book covers and book information of the bookshelf books, a user can very intuitively distinguish the recommended books from the bookshelf books through the recommendation mark 32, and a circle in fig. 3 represents an access entry control of each functional page of an electronic book reading platform.
In an alternative mode, the specific implementation manner of screening at least one book to be recommended according to the sequence of the ranking scores of the books to be recommended from high to low is as follows: according to the sequence from high to low of the ranking scores of the books to be recommended, the next book to be recommended of the book to be recommended which is visited by the user last time is screened out, the book to be recommended which is visited by the user last time is also achieved through the book recommendation position, for example, when the user last visits the recommended landing page of the book to be recommended which is ranked the Nth position through the book recommendation position of the bookshelf page, the book to be recommended which is screened out and ranked the (N + 1) th position is displayed in the book recommendation position when the user visits the bookshelf page this time, and therefore repeated recommendation can be avoided.
In an optional mode, a recommended book list for a user is updated regularly, the recommended book list contains a plurality of books to be recommended, when a bookshelf page access operation of the user is received, whether the recommended book list of the user is updated or not is judged, if the recommended book list of the user is updated, the ranking score of each book to be recommended in the latest recommended book list is calculated, and the book to be recommended with the first ranking is screened out and presented in a book recommendation position. And if the book list is not updated, screening out the next book to be recommended of the book to be recommended which is accessed by the user last time in the unrefreshed book list and presenting the next book to be recommended in the book recommending position. The method provides a recommendation implementation mode of the book recommendation position in a scene that the book to be recommended is updated regularly, and the book to be recommended of the user is updated regularly, so that the book to be recommended is more suitable for the real-time preference of the user.
Step S240, in response to a book access operation of the user to any book to be recommended in the book recommendation position, skipping to display a recommended landing page associated with the book to be recommended.
If the user is interested in the books to be recommended presented in the book recommendation position, book access operation is executed in the book recommendation position, and then the user can jump to a recommendation landing page of the accessed books to be recommended, wherein the recommendation landing page can be a book detail page, a book reading page and the like, so that the user can further know the detailed content of the recommended books, and the recommendation effect of the book recommendation position is enhanced.
Step S250, responding to a bookshelf page returning operation executed by a user in the recommended landing page, jumping to display bookshelf pages, and replacing at least one book to be recommended after the book to be recommended from high to low according to the sequencing score of the book to be recommended from high to low to present in a book recommending position.
The recommended landing page comprises an entrance control used for returning to the bookshelf page, and the bookshelf page returning operation executed by the user in the recommended landing page is the touch operation of the user on the entrance control used for returning to the bookshelf page. And responding to the bookshelf page returning operation of the user, skipping to display the bookshelf page, and replacing the book to be recommended presented in the book recommending position.
For example, when a user executes a book access operation when an S-th ranked book to be recommended is presented in the book recommendation position, the recommendation landing page for presenting the S-th ranked book to be recommended is skipped, the user clicks an entry control for returning to a bookshelf page in the recommendation landing page, the bookshelf page is skipped, and the book recommendation position of the bookshelf page is replaced by the S + T ranked book to be recommended, wherein T is an integer greater than or equal to 1. By the method, repeated recommendation can be avoided, meanwhile, the books to be recommended can be presented in sequence, and the recommendation effect of the book recommendation position can be improved.
Preferably, the books to be recommended next to the book to be recommended (the book to be recommended for which the book access operation is directed) are presented in the book recommendation position in the order of the ranking score of each book to be recommended from high to low. Following the above example, the book to be recommended that is sorted in the S +1 th order is presented in the book recommendation position instead.
In an optional mode, in order to improve the accuracy of the ranking model, sample data is acquired according to the behavior data of the user, and the ranking model is trained and updated according to the sample data.
Specifically, the training and updating manner of the ranking model for the retention index dimension is as follows: after skipping to display a recommended landing page (a book to be recommended for book access operation) associated with the book to be recommended, if a reading request of a user for the book to be recommended is received within a preset time period, taking the user and the book to be recommended as positive retention samples; and extracting the sequence characteristics of the preserved positive sample, and training and updating the sequencing model of the preserved index dimension according to the sequence characteristics of the preserved positive sample. If the user visits a recommended landing page associated with the book to be recommended and requests to read the book to be recommended within a preset time period (for example, 24 hours), the user is indicated as a recommended retention user, the user and the book to be recommended are taken as positive retention samples, and the ranking model of the retention index dimension is trained and updated according to the sequence features (including user features, book features, cross features and the like) of the positive retention samples, so that the prediction effect of the ranking model of the retention index dimension is continuously improved.
In another optional mode, at least one book to be recommended is screened according to the sequence from high to low of the sequencing score of each book to be recommended, after at least one book to be recommended is presented in the book recommending position of the bookshelf page, the book list page of each book to be recommended is jumped to display in response to the book list access operation of the user on each book to be recommended; and sequentially presenting the books to be recommended on the book list page according to the sequence of the sequencing scores of the books to be recommended from high to low. In the method, the bookshelf pages also comprise book list access inlets, the book list pages comprising the books to be recommended can be displayed in a skipping mode through the book list access inlets, the books to be recommended in the book list pages are displayed in an arrangement mode according to the sequence from high to low in the ranking score, the books to be recommended in the book recommendation positions are used as interest points, a user is attracted to skip to the book list pages comprising all the books to be recommended through the book list pages, and the recommendation effect of the book list pages can be further improved.
Preferably, the book recommendation bit contains a book list access entry. Therefore, the user can jump to a book list page through the book recommendation position, so that the recommendation form of the book recommendation position is enriched, and the recommendation effect of the book recommendation position is further improved.
According to the book recommendation method for the bookshelf pages, when a user accesses the bookshelf pages, the sorting features of the books on the bookshelf of the user are extracted, the sorting features are input into a preset sorting model to calculate the sorting scores of the books to be recommended, at least one book to be recommended is screened according to the sorting scores from high to low and is presented in the book recommendation positions of the book pages, the effect of recommending the books on the bookshelf pages can be achieved, the sorting of the books to be recommended of the user is determined according to the sorting of the books on the bookshelf of the user, the sorting of the books to be recommended of the user is enabled to be more suitable for the liking of the user, and the recommendation effect is improved; on the other hand, the sequencing scores of the books to be recommended are determined by setting the sequencing models with multiple dimensions and integrating the calculation results of the sequencing models with multiple dimensions, so that the sequencing of each book to be recommended can meet the requirement for improving multiple dimension indexes; on the other hand, by setting the access entry of the book to be recommended and/or the book list access entry in the book recommendation position, different book recommendation modes can be realized, and the recommendation effect of the book page and the book recommendation position can be improved.
The embodiment of the invention provides a nonvolatile computer storage medium, wherein at least one executable instruction is stored in the computer storage medium, and the computer executable instruction can execute the book recommendation method of the bookshelf page in any method embodiment.
The executable instructions may be specifically configured to cause the processor to perform the following operations:
receiving bookshelf page access operation of a user;
the method comprises the steps of obtaining the sequencing characteristics of the bookshelf books of a user, inputting the sequencing characteristics of the bookshelf books into a preset sequencing model for calculation, and determining the sequencing score of each book to be recommended of the user according to the calculation result;
and screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and presenting at least one book to be recommended in the book recommendation position of the bookshelf page.
In an alternative, the executable instructions cause the processor to:
screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, displaying the at least one book to be recommended in the book recommendation position of the bookshelf page, responding to the book access operation of a user to any book to be recommended in the book recommendation position, and jumping to display a recommended landing page related to the book to be recommended;
responding to a bookshelf page returning operation executed by a user in the recommended landing page, jumping to display bookshelf pages, and replacing at least one book to be recommended after the book to be recommended from high to low according to the sequence of the sequencing scores of the books to be recommended to present in the book recommending position.
In an alternative, the executable instructions cause the processor to:
screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, displaying the at least one book to be recommended in the book recommending position of the bookshelf page, responding to the book list access operation of the user on the books to be recommended, and jumping to display the book list page of each book to be recommended;
and sequentially presenting the books to be recommended on the book list page according to the sequence of the sequencing scores of the books to be recommended from high to low.
In an alternative, the book recommendation bit contains a book list access entry.
In an alternative, the executable instructions cause the processor to:
and replacing the next book to be recommended of the book to be recommended with the book to be recommended from the high ranking score to the low ranking score of the book to be recommended in the book recommendation position.
In an alternative mode, the preset ordering model includes: a ranking model of the duration index dimension and/or a ranking model of the retention index dimension.
In an alternative, the executable instructions cause the processor to:
inputting the sorting characteristics of the books on the bookshelf into any sorting model for calculation to obtain the initial score of each book to be recommended calculated by the sorting model;
and calculating a weighted sum of the initial scores of any book to be recommended calculated by each sequencing model according to the weight values corresponding to each sequencing model to obtain the sequencing score of the book to be recommended.
In an alternative, the executable instructions cause the processor to:
after skipping to display a recommended landing page associated with the book to be recommended, if a reading request of a user for the book to be recommended is received within a preset time period, taking the user and the book to be recommended as a positive retention sample;
and extracting the sequence characteristics of the retained positive sample, and training and updating the sequencing model of the retained index dimension according to the sequence characteristics of the retained positive sample.
In an alternative form, the executable instructions cause the processor to:
and displaying the recommendation identification information at a preset position of the book recommendation position of the bookshelf page.
By the method, the book recommendation positions are arranged in the bookshelf pages, so that books can be recommended on the bookshelf pages, and meanwhile, the sequencing of the books to be recommended of the user is determined according to the sequencing of the books on the bookshelf of the user, so that the sequencing of the books to be recommended is more suitable for the hobbies of the user, and the recommendation effect of the book recommendation positions can be improved.
Fig. 4 is a schematic structural diagram of an embodiment of a computing device according to the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.
As shown in fig. 4, the computing device may include: a processor (processor)402, a Communications Interface 404, a memory 406, and a Communications bus 408.
Wherein: the processor 402, communication interface 404, and memory 406 communicate with each other via a communication bus 408. A communication interface 404 for communicating with network elements of other devices, such as clients or other servers. The processor 402 is configured to execute the program 410, and may specifically execute the relevant steps in the above-described embodiment of the book recommendation method for bookshelf pages of a computing device.
In particular, program 410 may include program code comprising computer operating instructions.
The processor 402 may be a central processing unit CPU or an application Specific Integrated circuit asic or one or more Integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 406 for storing a program 410. Memory 406 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 410 may specifically be configured to cause the processor 402 to perform the following operations:
receiving bookshelf page access operation of a user;
acquiring the sorting characteristics of the bookshelf books of the user, inputting the sorting characteristics of the bookshelf books into a preset sorting model for calculation, and determining the sorting score of each book to be recommended for the user according to the calculation result;
screening at least one book to be recommended according to the sequence of the ranking score of each book to be recommended from high to low, and presenting at least one book to be recommended in the book recommendation position of the bookshelf page.
In an alternative, the program 410 causes the processor 402 to:
screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, displaying the at least one book to be recommended in the book recommendation position of the bookshelf page, responding to the book access operation of a user to any book to be recommended in the book recommendation position, and jumping to display a recommended landing page related to the book to be recommended;
responding to a bookshelf page returning operation executed by a user in the recommended landing page, jumping to display bookshelf pages, and replacing at least one book to be recommended after the book to be recommended from high to low according to the sequence of the sequencing scores of the books to be recommended to present in the book recommending position.
In an alternative, the program 410 causes the processor 402 to:
screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, displaying the at least one book to be recommended in the book recommending position of the bookshelf page, responding to the book list access operation of the user on the books to be recommended, and jumping to display the book list page of each book to be recommended;
and sequentially presenting the books to be recommended on the book list page according to the sequence of the sequencing scores of the books to be recommended from high to low.
In an alternative, the book recommendation bit contains a book list access entry.
In an alternative, the program 410 causes the processor 402 to:
and replacing the next book to be recommended of the book to be recommended with the book to be recommended from the high ranking score to the low ranking score of the book to be recommended in the book recommendation position.
In an alternative mode, the preset ordering model includes: a ranking model of the duration index dimension and/or a ranking model of the retention index dimension.
In an alternative, the program 410 causes the processor 402 to:
inputting the sorting characteristics of the books on the bookshelf into any sorting model for calculation to obtain the initial score of each book to be recommended calculated by the sorting model;
and calculating a weighted sum of the initial scores of any book to be recommended calculated by each sequencing model according to the weight values corresponding to each sequencing model to obtain the sequencing score of the book to be recommended.
In an alternative, the program 410 causes the processor 402 to:
after skipping to display a recommended landing page associated with the book to be recommended, if a reading request of a user for the book to be recommended is received within a preset time period, taking the user and the book to be recommended as a positive retention sample;
and extracting the sequence characteristics of the retained positive sample, and training and updating the sequencing model of the retained index dimension according to the sequence characteristics of the retained positive sample.
In an alternative, the program 410 causes the processor 402 to: and displaying the recommendation identification information at a preset position of the book recommendation position of the bookshelf page.
By the method, the book recommendation positions are arranged in the bookshelf pages, so that books can be recommended on the bookshelf pages, and meanwhile, the sequencing of the books to be recommended of the user is determined according to the sequencing of the books on the bookshelf of the user, so that the sequencing of the books to be recommended is more suitable for the hobbies of the user, and the recommendation effect of the book recommendation positions can be improved.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
The invention discloses: A1. a book recommendation method for bookshelf pages comprises the following steps:
receiving bookshelf page access operation of a user;
obtaining the sequencing characteristics of the bookshelf books of the user, inputting the sequencing characteristics of the bookshelf books into a preset sequencing model for calculation, and determining the sequencing score of each book to be recommended of the user according to the calculation result;
and screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and presenting the at least one book to be recommended in the book recommendation position of the bookshelf page.
A2. The method according to a1, wherein after the at least one book to be recommended is screened in the order of the ranking score of each book to be recommended from high to low, and the at least one book to be recommended is presented in the book recommendation position of the bookshelf page, the method further includes:
responding to the book access operation of a user to any book to be recommended in the book recommending position, and skipping and displaying a recommended landing page related to the book to be recommended;
responding to a bookshelf page returning operation executed by a user in the recommended landing page, skipping and displaying the bookshelf page, and replacing at least one book to be recommended after the book to be recommended from high to low according to the sequencing score of the book to be recommended from the high to low in sequence to present in the book recommending position.
A3. The method according to a1, wherein after the at least one book to be recommended is screened in the order of the ranking score of each book to be recommended from high to low, and the at least one book to be recommended is presented in the book recommendation position of the bookshelf page, the method further includes:
responding to the book list access operation of the user to each book to be recommended, and skipping to display the book list page of each book to be recommended;
and sequentially presenting the books to be recommended on the book list page according to the sequence of the sequencing scores of the books to be recommended from high to low.
A4. The method of a3, wherein the book recommendation bit contains a book list access entry.
A5. The method according to a2, wherein the replacing of the order of the ranking score of each book to be recommended from high to low by at least one book to be recommended ranked after the book to be recommended in the book recommendation position further comprises:
and replacing the book to be recommended with the next book to be recommended in the book recommendation position according to the sequence of the sequencing scores of the books to be recommended from high to low.
A6. The method of any of a1-a5, wherein the pre-set ordering model comprises: a ranking model of the duration index dimension and/or a ranking model of the retention index dimension.
A7. The method according to a6, wherein the inputting the sorting features of the bookshelf books into a preset sorting model for calculation, and the determining the sorting scores of the books to be recommended for the user according to the calculation result further includes:
inputting the sorting characteristics of the books on the bookshelf to any sorting model for calculation to obtain the initial score of each book to be recommended calculated by the sorting model;
and calculating a weighted sum of the initial scores of any book to be recommended calculated by each sequencing model according to the weight values corresponding to each sequencing model to obtain the sequencing score of the book to be recommended.
A8. The method according to A6, wherein after jumping to show the recommended landing page associated with the book to be recommended, the method further comprises:
if a reading request of the user for the book to be recommended is received within a preset time period, taking the user and the book to be recommended as positive retention samples;
and extracting the sequence characteristics of the retained positive sample, and training and updating the sequencing model of the retained index dimension according to the sequence characteristics of the retained positive sample.
A9. The method of any one of a1-A8, wherein the method further comprises:
and displaying recommendation identification information at a preset position of a book recommendation position of the bookshelf page.
B10. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to:
receiving bookshelf page access operation of a user;
obtaining the sequencing characteristics of the bookshelf books of the user, inputting the sequencing characteristics of the bookshelf books into a preset sequencing model for calculation, and determining the sequencing score of each book to be recommended of the user according to the calculation result;
and screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and presenting the at least one book to be recommended in the book recommendation position of the bookshelf page.
B11. The computing device of B10, the executable instructions further cause the processor to:
screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and after the at least one book to be recommended is presented in the book recommendation position of the bookshelf page, responding to the book access operation of a user on any book to be recommended in the book recommendation position, and jumping to display a recommended landing page related to the book to be recommended;
responding to a bookshelf page returning operation executed by a user in the recommended landing page, skipping and displaying the bookshelf page, and replacing at least one book to be recommended after the book to be recommended from high to low according to the sequencing score of the book to be recommended from the high to low in sequence to present in the book recommending position.
B12. The computing device of B10, the executable instructions further cause the processor to:
screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and after the at least one book to be recommended is presented in the book recommending position of the bookshelf page, responding to the book list access operation of the user on the books to be recommended, and jumping to display the book list page of each book to be recommended;
and sequentially presenting the books to be recommended on the book list page according to the sequence of the sequencing scores of the books to be recommended from high to low.
B13. The computing device of B12, wherein the book recommendation bit includes a book list access entry therein.
B14. The computing device of B11, the executable instructions further cause the processor to:
and replacing the book to be recommended with the next book to be recommended in the book recommendation position according to the sequence of the sequencing scores of the books to be recommended from high to low.
B15. The computing device of any of B10-B14, wherein the preset ordering model comprises: a ranking model of the duration index dimension and/or a ranking model of the retention index dimension.
B16. The computing device of B15, the executable instructions further cause the processor to:
inputting the sorting characteristics of the books on the bookshelf to any sorting model for calculation to obtain the initial score of each book to be recommended calculated by the sorting model;
and calculating a weighted sum of the initial scores of any book to be recommended calculated by each sequencing model according to the weight values corresponding to each sequencing model to obtain the sequencing score of the book to be recommended.
B17. The computing device of B15, the executable instructions further cause the processor to:
after skipping to display a recommended landing page associated with the book to be recommended, if a reading request of the user for the book to be recommended is received within a preset time period, taking the user and the book to be recommended as positive retention samples;
and extracting the sequence characteristics of the retained positive sample, and training and updating the sequencing model of the retained index dimension according to the sequence characteristics of the retained positive sample.
B18. The computing device of any one of B10-B17, the executable instructions further cause the processor to:
and displaying recommendation identification information at a preset position of a book recommendation position of the bookshelf page.
C19. A computer storage medium having stored therein at least one executable instruction causing a processor to perform operations corresponding to the book recommendation method for bookshelf pages as described in any of a1-a 9.
Claims (10)
1. A book recommendation method for bookshelf pages comprises the following steps:
receiving bookshelf page access operation of a user;
obtaining the sequencing characteristics of the bookshelf books of the user, inputting the sequencing characteristics of the bookshelf books into a preset sequencing model for calculation, and determining the sequencing score of each book to be recommended of the user according to the calculation result;
and screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and presenting the at least one book to be recommended in the book recommendation position of the bookshelf page.
2. The method of claim 1, wherein after the at least one book to be recommended is screened in the order of the ranking score of each book to be recommended from high to low and is presented in the book recommendation position of the bookshelf page, the method further comprises:
responding to the book access operation of a user to any book to be recommended in the book recommending position, and skipping and displaying a recommended landing page related to the book to be recommended;
and responding to a bookshelf page returning operation executed by a user in the recommended landing page, skipping and displaying the bookshelf page, and replacing at least one book to be recommended after the book to be recommended from high to low according to the sequence of the sequencing score of each book to be recommended from high to low to present in the book recommending position.
3. The method of claim 1, wherein after the at least one book to be recommended is screened in the order of the ranking score of each book to be recommended from high to low and is presented in the book recommendation position of the bookshelf page, the method further comprises:
responding to the book list access operation of the user to each book to be recommended, and skipping to display the book list page of each book to be recommended;
and sequentially presenting the books to be recommended on the book list page according to the sequence of the sequencing scores of the books to be recommended from high to low.
4. The method of claim 3, wherein the book recommendation bit includes a book list access entry therein.
5. The method of claim 2, wherein replacing at least one book to be recommended, which is ranked after the book to be recommended, with the high-to-low ranking of the ranking scores of the books to be recommended in the book recommendation position further comprises:
and replacing the book to be recommended with the next book to be recommended in the book recommendation position according to the sequence of the sequencing scores of the books to be recommended from high to low.
6. The method of any of claims 1-5, wherein the pre-set ordering model comprises: a ranking model of the duration index dimension and/or a ranking model of the retention index dimension.
7. The method of claim 6, wherein the inputting the sorting features of the bookshelf books into a preset sorting model for calculation, and the determining the sorting scores of the books to be recommended for the user according to the calculation result further comprises:
inputting the sorting characteristics of the books on the bookshelf to any sorting model for calculation to obtain the initial score of each book to be recommended calculated by the sorting model;
and calculating a weighted sum of the initial scores of any book to be recommended calculated by each sequencing model according to the weight values corresponding to each sequencing model to obtain the sequencing score of the book to be recommended.
8. The method of claim 6, wherein after skipping to show the recommended landing page associated with the book to be recommended, the method further comprises:
if a reading request of the user for the book to be recommended is received within a preset time period, taking the user and the book to be recommended as positive retention samples;
and extracting the sequence characteristics of the retained positive sample, and training and updating the sequencing model of the retained index dimension according to the sequence characteristics of the retained positive sample.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to:
receiving bookshelf page access operation of a user;
obtaining the sequencing characteristics of the bookshelf books of the user, inputting the sequencing characteristics of the bookshelf books into a preset sequencing model for calculation, and determining the sequencing score of each book to be recommended of the user according to the calculation result;
and screening at least one book to be recommended according to the sequence of the sequencing scores of the books to be recommended from high to low, and presenting the at least one book to be recommended in the book recommendation position of the bookshelf page.
10. A computer storage medium having stored therein at least one executable instruction causing a processor to perform operations corresponding to the book recommendation method for bookshelf pages according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210310431.2A CN114647782A (en) | 2022-03-28 | 2022-03-28 | Book recommendation method of bookshelf page, computing device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210310431.2A CN114647782A (en) | 2022-03-28 | 2022-03-28 | Book recommendation method of bookshelf page, computing device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114647782A true CN114647782A (en) | 2022-06-21 |
Family
ID=81995375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210310431.2A Pending CN114647782A (en) | 2022-03-28 | 2022-03-28 | Book recommendation method of bookshelf page, computing device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114647782A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114925285A (en) * | 2022-06-30 | 2022-08-19 | 抖音视界(北京)有限公司 | Book information processing method, device, equipment and storage medium |
| CN114925285B (en) * | 2022-06-30 | 2024-07-16 | 抖音视界有限公司 | Book information processing method, device, equipment and storage medium |
-
2022
- 2022-03-28 CN CN202210310431.2A patent/CN114647782A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114925285A (en) * | 2022-06-30 | 2022-08-19 | 抖音视界(北京)有限公司 | Book information processing method, device, equipment and storage medium |
| CN114925285B (en) * | 2022-06-30 | 2024-07-16 | 抖音视界有限公司 | Book information processing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110012356B (en) | Video recommendation method, device and equipment and computer storage medium | |
| CN110619076B (en) | Search term recommendation method and device, computer and storage medium | |
| CN105912669B (en) | Method and device for complementing search terms and establishing individual interest model | |
| CN106445963B (en) | Advertisement index keyword automatic generation method and device of APP platform | |
| CN108648058B (en) | Product sorting method and device, electronic equipment and storage medium | |
| CN108512883B (en) | Information pushing method and device and readable medium | |
| CN113987387A (en) | Page display method, electronic equipment and computer storage medium | |
| CN110968765B (en) | Book searching method, computing device and computer storage medium | |
| CN111984169B (en) | Electronic book page display method, computing equipment and computer storage medium | |
| CN111131419A (en) | Information pushing method and server based on book pages | |
| CN110990701B (en) | Book searching method, computing device and computer storage medium | |
| CN112650946B (en) | Product information recommendation method, device, system and storage medium | |
| CN111444447A (en) | Content recommendation page display method and device | |
| CN111552795B (en) | Book list page display method, electronic equipment and storage medium | |
| CN111723294A (en) | AI-based RPA robot intelligent recommendation method, device and equipment | |
| CN105243135A (en) | Method and apparatus for showing search result | |
| CN116225567A (en) | Page loading method and device, storage medium and computer equipment | |
| CN113656549B (en) | Content searching method of electronic book, electronic device and computer storage medium | |
| CN114647782A (en) | Book recommendation method of bookshelf page, computing device and storage medium | |
| CN115238194A (en) | Book recommendation method, computing device and computer storage medium | |
| CN110633408A (en) | Recommendation method and system for intelligent business information | |
| CN110275986B (en) | Video recommendation method based on collaborative filtering, server and computer storage medium | |
| CN111078972B (en) | Questioning behavior data acquisition method, questioning behavior data acquisition device and server | |
| CN111611481A (en) | Book recommendation method, computing device and computer storage medium | |
| CN110333927B (en) | Interface skipping method and device, server and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |