Method and system for generating recommendation book, storage medium and electronic equipment

Abstract

The invention provides a recommendation book generation method and system, a storage medium and electronic equipment. The method comprises the steps that user feature information is determined through a preset method according to user historical data; screening the stack library according to book content feature information and book parameter information corresponding to the user feature information to determine a first book, and adjusting the first book according to historical data to determine a second book; determining advantage features corresponding to different dimensions according to the feature proportion information, and splitting the second book according to the advantage features to determine a first preset number of third books and fourth books; and sorting the third book and the fourth book according to the reading scoring parameter to obtain a first book list, enabling the fourth book to be located behind the third book, and rejecting a part of books in the fourth book to obtain a recommendation book list. The problems that in the prior art, book content cannot be accurately judged through a book recommendation method, and the diversified requirements of users cannot be met due to the fact that the recommended information content is single are solved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, system, storage medium and electronic device for generating a recommended book list. Background Art

[0002] With the continuous development and advancement of science and technology, a variety of electronic devices have gradually appeared in people's lives, bringing great convenience to people's lives. For example, using mobile phones, tablets, e-readers and other terminal devices to read e-books through corresponding reading software or websites, more and more users are accustomed to using terminal devices to select the books they want to read e-books. Among the many types of books, online novels are the most popular type of e-reading.

[0003] In the prior art, reading software or websites usually generate a list of recommended books for users in advance, hoping that users will select and read the e-books on the list, thereby cultivating users' reading habits and increasing user stickiness of the reading software or website.

[0004] However, existing book recommendation lists typically use a user's reading history or search results to determine the types of books a user is interested in. Specifically, they determine the corresponding book tags, then filter existing book lists or books based on these tags to generate a corresponding recommended list and push it to the user. However, existing book tags are typically generated based on the subject matter. Given the vast variety of online novels, a single-dimensional tag makes it difficult to accurately determine the content of a book. Furthermore, this recommendation method results in the user receiving a single piece of recommended information, making the recommended book list unable to meet the diverse needs of users. Summary of the Invention

[0005] Based on this, the purpose of the present invention is to provide a method, system, storage medium and electronic device for generating a recommended book list, aiming to solve the problem that the book list recommendation method in the prior art cannot accurately judge the content of the book and the recommended information content is single, which makes it unable to meet the diverse needs of users.

[0006] A method for generating a recommended book list according to an embodiment of the present invention includes: Determine user feature information using a preset method based on user historical data, where the feature information includes at least book content feature information, book parameter information, and feature ratio information, where the feature ratio information is the ratio information of each feature in different dimensions in the book content feature information; Screening a library to determine a first book based on the book content feature information and the book parameter information corresponding to the user feature information, and adjusting the first book to determine a second book based on the historical data; Determining dominant features corresponding to different dimensions based on the feature proportion information, and dividing the second book based on a first preset number of the dominant features to determine a first preset number of third books and fourth books; The third book and the fourth book are sorted according to the reading score parameters to obtain a first book list, and the fourth book is placed after the third book. Then, some books in the fourth book are eliminated to obtain a recommended book list, so that the difference between the recommended book list and the feature proportion information of the user feature information is less than a preset value.

[0007] In addition, the method for generating a recommended book list according to the above embodiment of the present invention may also have the following additional technical features: Furthermore, the step of determining user characteristic information by a preset method based on user historical data includes: determining a historical target book according to the historical data, and determining first book characteristic information according to an introduction of the historical target book; determining an existing book list containing the historical target book based on the historical target book, and adjusting the first book characteristic information to determine second book characteristic information based on the recommendation of the historical target book in the existing book list, the comments corresponding to the historical target book in the existing book list, and the comments corresponding to the reading area of ​​the historical target book; The second characteristic information is screened according to the user reading data and statistically combined to determine the user characteristic information.

[0008] Furthermore, after the step of eliminating some books from the fourth book to obtain a recommended book list, the following steps are included: screening the existing book list according to the recommended book list to determine a plurality of second book lists, so that each of the second book lists contains at least one book from the recommended book list; The second book list is screened to determine a plurality of associated book lists not greater than a second preset number, so that all books in the plurality of associated book lists include all books in the recommended book list, and the average value of the sum of the reading score parameters of the plurality of associated book lists is the largest.

[0009] Furthermore, the step of determining the historical target book according to the historical data includes: Determining preliminary history books read by all users based on the historical data, and scoring each of the preliminary history books according to a preset formula to determine a user preference score; determining the preliminary history books having the user preference scores greater than a preset threshold as the history target books; The preset formula is: ; in, The user preference scores for historical books are Book status weight parameter, For reading progress, is the number of days since the most recent reading time, is the time attenuation coefficient, , is the weight parameter of progress and time.

[0010] Furthermore, after the step of sorting the third book and the fourth book according to the reading score parameter to obtain a first book list and arranging the fourth book after the third book, the method further includes: A recommended book list with the number of books within a preset range is obtained by eliminating some books from the fourth book according to preset rules. The preset rule is that the sum of the original serial numbers of the books in the recommended book list is minimized on the premise that the difference between the feature proportion information of the recommended book list and the user feature information is less than a preset value.

[0011] Furthermore, an input window is formed on the display interface, and the input window is used for the user to input book information or book list information; Determining whether the information input in the input window is book information; If so, the user characteristic information is determined according to the book information inputted in all the input windows, so as to determine the recommended book list according to the user characteristic information.

[0012] Furthermore, before the step of determining user characteristic information by a preset method based on user historical data, the method further includes: Determine whether the user has corresponding user history data; If yes, executing the step of determining user characteristic information by a preset method based on user historical data; If not, an initial tag is generated for the user to select to determine the tag, and books completed within a preset time period are screened according to the tag to determine a preset number of target completed books for the user to determine whether they have been read, and the sum of the reading score parameters of the target completed books is the largest; The target book is determined according to the user's selection information, and the user characteristic information is determined according to the target book by the preset method, and then the step of screening the library according to the book content characteristic information and the book parameter information corresponding to the user characteristic information is performed to determine the first book.

[0013] Another object of the present invention is to provide a system for generating a recommended book list, the system comprising: A feature information acquisition module is used to determine user feature information using a preset method based on user historical data. The feature information includes at least book content feature information, book parameter information, and feature ratio information. The feature ratio information is the ratio information of each feature in different dimensions in the book content feature information. a second book determining module, configured to screen the library to determine a first book based on the book content characteristic information and the book parameter information corresponding to the user characteristic information, and adjust the first book to determine a second book based on the historical data; a splitting module, configured to determine dominant features corresponding to different dimensions based on the feature proportion information, and split the second book based on a first preset number of the dominant features to determine a first preset number of third books and fourth books; The recommended book list determination module sorts the third book and the fourth book according to the reading score parameter to obtain a first book list, and places the fourth book after the third book, and then eliminates some books from the fourth book to obtain a recommended book list, so that the difference between the recommended book list and the feature proportion information of the user feature information is less than a preset value.

[0014] The present invention can obtain user feature data, i.e., user reading preferences, through user historical data. More specifically, it includes book content feature data and book parameter feature information. The book content feature data includes dimensions such as book subject matter, style, and writing style. It is also necessary to determine the proportion information of each feature in different dimensions. The book parameter information includes parameter information determined by word count, serialization status, and author. Thus, the user's reading preferences can be accurately judged through multiple dimensions and corresponding parameter information. According to the feature information corresponding to the data, a large number of first books that are consistent with the user's reading preferences are determined, and the books that the user has read are removed to determine the second books. Then, based on the user's preference and proportion in the book dimension, a large number of second books are screened, and the corresponding recommended book list is determined based on the reading score parameters. The books in the recommended book list are all high-quality books, and the overall preference style of the book list is consistent with the user. However, the individual books in the book list are not completely consistent with the user's preferences in different book dimensions. This ensures that the recommended book list cannot meet the diverse needs of users and avoids the problem of single recommendation information content in the recommended book list. Therefore, the present invention solves the problem that the book list recommendation method in the prior art cannot accurately judge the content of the book and the recommended information content is single and cannot meet the diverse needs of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Flowchart of the method for generating a recommended book list in the first embodiment of the present invention; Figure 2This is a schematic diagram of the results of the recommended book list generation system in the second embodiment of the present invention; Figure 3 is a schematic structural diagram of an electronic device in a third embodiment of the present invention; The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0016] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0017] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly attached to the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0019] Example 1 See also Figure 1 , shown is a method for generating a recommended book list in the first embodiment of the present invention, which specifically includes steps S01 to S04.

[0020] S01. Determine user feature information using a preset method based on user historical data. The feature information includes at least book content feature information, book parameter information, and feature proportion information. The feature proportion information is the proportion information of each feature of different dimensions in the book content feature information.

[0021] Specifically, a target historical book is determined based on the historical data, and first book characteristic information is determined based on the introduction of the target historical book. Based on the target historical book, an existing book list containing the target historical book is determined, and the first book characteristic information is adjusted to determine second book characteristic information based on the recommendation for the target historical book in the existing book list, the corresponding reviews of the target historical book in the existing book list, and the reviews of the target historical book's reading area. The second characteristic information is filtered and statistically combined based on the user's reading data to determine the user characteristic information. In specific implementations, a user's historical data does not fully reflect the user's reading preferences. Therefore, in specific implementations, it is necessary to filter the historical data to determine the target historical book corresponding to the user's preferences, and then preliminarily determine the first book characteristic information of the target historical book based on the introduction of the target historical book. Authors typically write novels after determining an outline, but during the subsequent serialization process, the content of the novel may be affected and deviate from the outline. Therefore, while the book introduction provides an overview or introduction of the author's own corresponding content, it only preliminarily reflects the specific content bias of the book, i.e., the first book characteristic information. Then, through the comments in the historical book reading area, the recommendations of the historical books corresponding to the book list containing historical books, and the comments about the historical books in the book list, the accurate content overview of the historical books can be determined, and then the first book feature information can be adjusted to determine the second book feature information. It should be noted that the recommendations and comments can be summarized by large language models and deep learning models to obtain the required book content overview. In addition, in the specific implementation, the recommendation in the book list is mainly used, and the comment information is supplemented for summary. This is because the book list recommendation usually provides a relatively comprehensive and fair explanation of the book content, and then the book content is corrected and improved through the public comments on the book list and the comments of fans of the books in the reading area. To ensure the accuracy of the summary of the book content.

[0022] Furthermore, the step of determining the historical target books based on the historical data includes: determining preliminary historical books read by all users based on the historical data, and scoring each of the preliminary historical books according to a preset formula to determine a user preference score; and determining the preliminary historical books having a user preference score greater than a preset threshold as the historical target books; The preset formula is: ; in, The user preference scores for historical books are Book status weight parameter, For reading progress, is the number of days since the most recent reading time, is the time attenuation coefficient, , are weight parameters for progress and time. Specifically, a user's historical data does not fully represent their reading preferences. For example, a user may search for only some books but not read them, or may read only part of them and then stop reading. Alternatively, a user may have read some content in other software or websites, resulting in only the subsequent content being read in this software or website. Alternatively, a book may have been read a long time ago, and the user's reading preferences may have changed. Therefore, it is necessary to evaluate and score the books in the user's historical reading behavior and the corresponding preliminary history books to determine the current user's true reading preferences.

[0023] S02: Screening a library to determine a first book based on the book content feature information and the book parameter information corresponding to the user feature information, and adjusting the first book to determine a second book based on the historical data.

[0024] Specifically, the books in the library are first screened based on their content characteristics, which include subject matter, content style, and writing style. Subject matter includes fantasy, urban, and military. Content styles include dark, passionate, and romantic. Writing styles include colloquial, semi-literary, and translated. The screened books are then required to meet at least one characteristic from each dimension of the content characteristics. A secondary screening is then performed based on the book's parameter information. Specifically, only the information with the largest proportion of the parameter information is used for screening. For example, if the book's status is consistently completed, while the word count and author information fluctuate widely, users are likely to be interested in whether the book is completed. Since the percentage of completed books is 100%, the secondary screening based on the book's status is sufficient. This is because book parameters are not the primary focus of online novel users' reading preferences. Users may focus solely on the book's status, such as serialization, completion, or unfinished. Alternatively, they may focus on the word count, such as whether the book is a short story, a novella, or a novel. Rather than focusing too much on the book's parameter information, this is due to the entertainment nature of online novels, which leads users to focus primarily on the novel's content, with a partial focus on the number of words and status, to determine whether the novel provides sufficient entertainment. Therefore, after filtering through the book's content characteristics and parameter information, the user determines the first book, then removes any books that the user has already read from the first book to avoid the appearance of books that the user has already read, which could affect the user experience.

[0025] S03: determining dominant features corresponding to different dimensions according to the feature proportion information, and dividing the second book into a first preset number of third books and fourth books according to a first preset number of the dominant features.

[0026] Specifically, by identifying the dominant features in the user's profile, i.e., multiple dominant features across different dimensions, such as Xianxia as the subject matter, humor as the content style, and colloquial writing style, all second books are screened based on these three features to determine three third books. The third books ensure that the recommended book list contains corresponding books for the user's preferred reading areas, ensuring that the recommended books meet the user's needs.

[0027] S04, sorting the third book and the fourth book according to the reading score parameter to obtain a first book list, and placing the fourth book after the third book, and then eliminating some books from the fourth book to obtain a recommended book list, so that the difference between the recommended book list and the feature proportion information of the user feature information is less than a preset value.

[0028] Specifically, after sorting the third and fourth books according to the reading score parameter to obtain a first book list and arranging the fourth book after the third book, the step further includes: eliminating some books from the fourth book list according to a preset rule to obtain a recommended book list with a number of books within a preset range. The preset rule is to minimize the sum of the original serial numbers of the books in the recommended book list, provided that the difference between the feature proportion information of the recommended book list and the user feature information is less than a preset value. Furthermore, by screening the books, the overall style of the recommended book list is consistent with the user's preferred style, but individual books in the book list may differ from the user's preferences to avoid a situation where the book list contains a single piece of information. Furthermore, by controlling the sum of the serial numbers, the overall quality of the books in the recommended book list is ensured to be high, with all books having high reading score parameters, thereby ensuring book quality and the user's reading experience. It should be noted that the reading score parameter is determined by comprehensively evaluating the book's reading completion rate, reading volume, book completion time, and book subscription volume, and is used to indicate the user's degree of recognition of the book. The reading completion rate represents the reading progress of all users for the book.

[0029] In addition, after removing some books from the fourth book to obtain a recommended book list, the step includes: screening the existing book list according to the recommended book list to determine multiple second book lists, so that each second book list contains at least one book from the recommended book list; screening the second book list to determine no more than a second preset number of associated book lists, so that all books in the multiple associated book lists contain all books in the recommended book list, and the average value of the sum of the reading score parameters of the multiple associated book lists is the largest. In a specific implementation, in addition to generating a recommended book list, a corresponding associated book list is also generated, so that after the user obtains a book they like from the recommended book list, they can also learn about other books that others think are similar in style or high-quality books based on the associated book list, so that the user does not receive a single piece of information, and can try to read other preferred books, thereby expanding the user's preference range. In addition, when screening the book list, the reading score parameters are combined to screen the book list to ensure that the books in the associated book list are high-quality books, thereby ensuring the user's reading experience.

[0030] In addition, the step of determining user feature information by a preset method based on user historical data includes: Determine whether the user has the corresponding user history data; if so, execute the step of determining user characteristic information according to the user history data by a preset method; if not, generate an initial tag for the user to select to determine the tag, and screen the books completed within a preset time period according to the tag to determine a preset number of target completed books for the user to determine whether they have been read, and the sum of the reading score parameters of the target completed books is maximized; determine the target books according to the user's selection information, and determine the user characteristic information according to the preset method according to the target books, and then execute the step of screening the library according to the book content characteristic information and the book parameter information corresponding to the user characteristic information to determine the first book. Specifically, it is not possible to avoid biased recommendation lists for new users. Therefore, by selecting the completed books corresponding to the tags in recent years according to the tags selected by the new user, and screening the completed books to determine a plurality of books with high quality and popularity for display, the books determined to be read by the user are analyzed and the corresponding book characteristic information is determined according to the books read by the new user, and the user characteristic information is further determined, so that the reading preferences of the new user can be accurately determined to generate a corresponding recommended book list.

[0031] In addition, an input window is formed on the display interface, and the input window is used for the user to input book information or book list information; Determine whether the information input into the input window is book information; if so, determine the user characteristic information based on all the book information input into the input window, so as to determine the recommended book list based on the user characteristic information. In specific implementation, an input window can be generated on the bookshelf of the website or software, that is, displayed as a square box, and the user drags the books on the bookshelf into the input window for input, that is, the user needs to generate a recommended book list with consistent preferences based on these books according to the software or website, and the recommended book list required by the user can be determined based on the information input into the input window according to the above-mentioned recommended book list generation method. This allows users to obtain corresponding recommended book lists based on their actual needs, better meeting the diverse needs of users.

[0032] By way of example and not limitation, in some optional embodiments, the book list's characteristic information is fixed after it is generated. Furthermore, a book list can be dragged into the input window, i.e., the book list can be entered into the input window. The books in the book list may differ from the book list's characteristic information before the corresponding book list is generated. Therefore, when generating a recommended book list based on the book list, the books are first screened based on the book list's characteristic information to determine a second book. Then, the second book is adjusted based on the book characteristic information corresponding to each book in the book list to determine the final recommended book list. The reason a user recommends a book list based on a book list is that the overall style of the book list meets the user's needs, but the content preferences of some books do not match the user's needs. Therefore, a quick preliminary screening is performed based on the book list's characteristic style to obtain multiple books with a consistent overall style. Then, the individual books in the book list are fine-tuned and adjusted to obtain a recommended book list that fully meets the user's preferences. Furthermore, in a specific implementation, when a user drags books or a book list through the input window to generate a corresponding recommended book list, this can be displayed using an integrated animation to enhance the fun and stimulate the user's interest in independently generating a recommended book list. After the recommended book list is generated, the percentage of influence of each input book or book list on the recommended book list can be displayed. This allows users to intuitively feel the correlation between the two and reflects the logic of this recommended book list generation method, strengthening users' trust in the method and the corresponding website or software, thereby improving user stickiness.

[0033] In summary, the method for generating a recommended book list in the above-mentioned embodiment of the present invention can obtain user characteristic data, namely, the user's reading preferences, from the user's historical data. More specifically, it includes book content characteristic data and book parameter characteristic information. The book content characteristic data includes dimensions such as book subject matter, style, and writing style. It is also necessary to determine the proportion information of each characteristic in different dimensions. The book parameter information includes parameter information determined by word count, serialization status, and author. Therefore, the user's reading preferences can be accurately judged through multiple dimensions and corresponding parameter information. The data is filtered based on the characteristic information corresponding to the data, thereby determining a large number of first books that are generally consistent with the user's reading preferences. Books that the user has read are removed to determine second books. The large number of second books are then filtered based on the user's preference and proportion in the book dimension. Combined with the reading score parameters, the corresponding recommended book list is determined. The books in the recommended book list are all high-quality books, and the overall preference and style of the book list are consistent with the user. However, the individual books in the book list are not completely consistent with the user's preferences in different book dimensions. This ensures that the recommended book list cannot meet the diverse needs of users and avoids the problem of single recommendation information content in the recommended book list. Therefore, the present invention solves the problem that the book list recommendation method in the prior art cannot accurately judge the content of the book and the recommended information content is single and cannot meet the diverse needs of users.

[0034] Example 2 See also Figure 2 , which is a structural block diagram of a recommended book list generation system proposed in a second embodiment of the present invention, the recommended book list generation system 200 includes: a feature information acquisition module 21, a second book determination module 22, a splitting module 23, and a recommended book list determination module 24, wherein: A feature information acquisition module 21 is configured to determine user feature information using a preset method based on user historical data. The feature information includes at least book content feature information, book parameter information, and feature ratio information, where the feature ratio information is the ratio of each feature in different dimensions within the book content feature information. A second book determining module 22 is configured to screen the library to determine a first book based on the book content characteristic information and the book parameter information corresponding to the user characteristic information, and adjust the first book based on the historical data to determine a second book; a splitting module 23, configured to determine dominant features corresponding to different dimensions based on the feature proportion information, and split the second book into a first preset number of third books and fourth books based on a first preset number of the dominant features; The recommended book list determination module 24 sorts the third book and the fourth book according to the reading score parameter to obtain a first book list, and places the fourth book after the third book, and then eliminates some books from the fourth book to obtain a recommended book list, so that the difference between the recommended book list and the feature proportion information of the user feature information is less than a preset value.

[0035] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments and will not be described in detail here.

[0036] Example 3 Another aspect of the present invention provides an electronic device, see Figure 3 , shown is a schematic diagram of an electronic device in the third embodiment of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, the method for generating a recommended book list as described above is implemented.

[0037] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0038] The memory 20 includes at least one type of readable storage medium, including flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 20 may be an internal storage unit of the electronic device, such as the hard disk of the electronic device. In other embodiments, the memory 20 may also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Furthermore, the memory 20 may include both an internal storage unit of the electronic device and an external storage device. The memory 20 can be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or is about to be output.

[0039] It should be pointed out that Figure 3 The structure shown does not constitute a limitation to the electronic device. In other embodiments, the electronic device may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0040] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for generating a recommended book list as described above.

[0041] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0042] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0043] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0044] Throughout this specification, references to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. Throughout this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0045] The above embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for generating a recommended book list, characterized in that: The method comprises: Determine user feature information using a preset method based on user historical data, where the feature information includes at least book content feature information, book parameter information, and feature ratio information, where the feature ratio information is the ratio information of each feature in different dimensions in the book content feature information; Screening a library to determine a first book based on the book content feature information and the book parameter information corresponding to the user feature information, and adjusting the first book to determine a second book based on the historical data; Determining dominant features corresponding to different dimensions based on the feature proportion information, and dividing the second book based on a first preset number of the dominant features to determine a first preset number of third books and fourth books; The third book and the fourth book are sorted according to the reading score parameters to obtain a first book list, and the fourth book is placed after the third book. Then, some books in the fourth book are eliminated to obtain a recommended book list, so that the difference between the recommended book list and the feature proportion information of the user feature information is less than a preset value.

2. The method for generating a recommended book list according to claim 1, wherein: The steps of determining user characteristic information by a preset method based on user historical data include: determining a historical target book according to the historical data, and determining first book characteristic information according to an introduction of the historical target book; determining an existing book list containing the historical target book based on the historical target book, and adjusting the first book characteristic information to determine second book characteristic information based on the recommendation of the historical target book in the existing book list, the comments corresponding to the historical target book in the existing book list, and the comments corresponding to the reading area of ​​the historical target book; The second characteristic information is screened according to the user reading data and statistically combined to determine the user characteristic information.

3. The method for generating a recommended book list according to claim 2, wherein: After the step of eliminating some books from the fourth book to obtain a recommended book list, the method includes: screening the existing book list according to the recommended book list to determine a plurality of second book lists, so that each of the second book lists contains at least one book from the recommended book list; The second book list is screened to determine a plurality of associated book lists not greater than a second preset number, so that all books in the plurality of associated book lists include all books in the recommended book list, and the average value of the sum of the reading score parameters of the plurality of associated book lists is the largest.

4. The method for generating a recommended book list according to claim 2, wherein: The step of determining the historical target book according to the historical data includes: Determining preliminary history books read by all users based on the historical data, and scoring each of the preliminary history books according to a preset formula to determine a user preference score; determining the preliminary history books having the user preference scores greater than a preset threshold as the history target books; The preset formula is: ； in, The user preference scores for historical books are Book status weight parameter, For reading progress, is the number of days since the most recent reading time, is the time attenuation coefficient, , is the weight parameter of progress and time.

5. The method for generating a recommended book list according to claim 1, wherein: After the step of sorting the third book and the fourth book according to the reading score parameter to obtain a first book list and placing the fourth book after the third book, the following steps are included: A recommended book list with the number of books within a preset range is obtained by eliminating some books from the fourth book according to preset rules. The preset rule is that the sum of the original serial numbers of the books in the recommended book list is minimized on the premise that the difference between the feature proportion information of the recommended book list and the user feature information is less than a preset value.

6. The method for generating a recommended book list according to claim 1, wherein: An input window is formed on the display interface, wherein the input window is used for the user to input book information or book list information; Determining whether the information input in the input window is book information; If so, the user characteristic information is determined according to the book information inputted in all the input windows, so as to determine the recommended book list according to the user characteristic information.

7. The method for generating a recommended book list according to claim 1, wherein: The step of determining user feature information by a preset method based on user historical data includes: Determine whether the user has corresponding user history data; If yes, executing the step of determining user characteristic information by a preset method based on user historical data; If not, an initial tag is generated for the user to select to determine the tag, and books completed within a preset time period are screened according to the tag to determine a preset number of target completed books for the user to determine whether they have been read, and the sum of the reading score parameters of the target completed books is the largest; The target book is determined according to the user's selection information, and the user characteristic information is determined according to the target book by the preset method, and then the step of screening the library according to the book content characteristic information and the book parameter information corresponding to the user characteristic information is performed to determine the first book.

8. A recommended book list generation system, characterized in that: For implementing the method for generating a recommended book list according to any one of claims 1 to 7, the system comprises: A feature information acquisition module is used to determine user feature information using a preset method based on user historical data. The feature information includes at least book content feature information, book parameter information, and feature ratio information. The feature ratio information is the ratio information of each feature in different dimensions in the book content feature information. a second book determining module, configured to screen the library to determine a first book based on the book content characteristic information and the book parameter information corresponding to the user characteristic information, and adjust the first book to determine a second book based on the historical data; a splitting module, configured to determine dominant features corresponding to different dimensions based on the feature proportion information, and split the second book based on a first preset number of the dominant features to determine a first preset number of third books and fourth books; The recommended book list determination module sorts the third book and the fourth book according to the reading score parameter to obtain a first book list, and places the fourth book after the third book, and then eliminates some books from the fourth book to obtain a recommended book list, so that the difference between the recommended book list and the feature proportion information of the user feature information is less than a preset value.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for generating a recommended book list as described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for generating a recommended book list as claimed in any one of claims 1 to 7 is implemented.

Images