Personalized book recommendation method, device, terminal device and storage medium

Abstract

The present application relates to the field of intelligent education technology, and discloses a personalized book recommendation method, device, terminal device and storage medium. The method includes: obtaining multi-dimensional configuration rules input by a user; collecting student information of each student in real time, and generating and updating corresponding student portraits according to the student information of each student; generating a corresponding book recommendation list for each student according to the configuration rules, each student portrait and a preset recommendation strategy; collecting feedback information of each student on their respective recommendation lists, and dynamically adjusting the recommendation strategy according to the feedback information. The present application allows book recommendations to take into account the personalized needs of students, and can optimize recommended books based on student feedback.

Description

Technical Field

[0001] The present application relates to the field of intelligent education technology, and in particular to a personalized book recommendation method, apparatus, terminal device and storage medium. Background Art

[0002] The book recommendation systems currently on the market usually use recommendation algorithms based on the user's historical reading habits, such as collaborative filtering and content recommendation. These algorithms mainly rely on the user's past behavior and interests for recommendation. Although they can meet personalized needs, they are difficult to adapt to the strict teaching objectives in the field of education. For example, teachers may require students to learn specific topics or skills at a specific stage, but traditional recommendation algorithms cannot incorporate these teaching objectives into the recommendation process. Therefore, it is not possible to make recommendations based on teaching rules, and it is impossible to achieve personalized recommendations while meeting the needs of teaching objectives. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a personalized book recommendation method, apparatus, terminal device and storage medium, which can effectively solve the problem of being unable to implement personalized recommendations.

[0004] In a first aspect, an embodiment of the present application provides a personalized book recommendation method, comprising:

[0005] Get multi-dimensional configuration rules input by users;

[0006] Collect student information of each student in real time, and generate and update corresponding student portraits according to the student information of each student;

[0007] Generate a corresponding book recommendation list for each student according to the configuration rules, each student portrait and the preset recommendation strategy;

[0008] Collect feedback information from each student on the recommendation list, and dynamically adjust the recommendation strategy based on the feedback information.

[0009] In some embodiments, the student information includes personal information, learning progress and learning performance;

[0010] Generating and updating corresponding student portraits according to the student information of each student includes:

[0011] Determine the learning ability of each of the students based on the personal information to establish an initial profile;

[0012] According to the learning progress and the learning performance collected in real time, on the basis of the initial portrait, the learning ability is updated, and the learning personality is added and updated, so as to update the initial portrait to obtain the student portrait.

[0013] In some embodiments, the method further comprises:

[0014] According to the learning progress, respectively determine the subject learning progress of the current student in each subject;

[0015] According to the subject learning progress and the learning performance, the initial portrait is updated to generate a student portrait for each student in each subject.

[0016] In some embodiments, the configuration rules include learning objectives and recommendation priorities;

[0017] Generating a corresponding book recommendation list for each student according to the configuration rules, each student portrait and the preset recommendation strategy includes:

[0018] According to the recommendation priority, books matching the student profile are selected from the books related to the learning objectives, and all matching books are summarized into a recommendation list.

[0019] In some embodiments, selecting books matching the student profile from books related to the learning goal according to the recommendation priority includes:

[0020] Identify learning objectives with the same recommended priority;

[0021] Filtering books that contain all learning objectives in each of the recommendation priorities, matching the filtered books with the student portraits, and determining the matching degree of each book;

[0022] A preset number of books before the matching degree is selected from each of the recommendation priorities as matching books.

[0023] In some embodiments, collecting feedback information from each student on the respective recommendation list and dynamically adjusting the recommendation strategy according to the feedback information includes:

[0024] Obtaining feedback information of students on reading each book in the recommendation list, wherein the feedback information includes one or more combinations of reading time, reading completion and book marks of each book;

[0025] According to the existing book tags, adjusting the recommendation weight of each book;

[0026] According to the existing reading time and the reading completion, the rules that meet the requirements in the configuration rules are determined, and the recommendation weights of related books of the rules that do not meet the requirements are increased.

[0027] In some embodiments, the method further includes: receiving an input update configuration rule, and generating a new recommendation list according to the update configuration rule and the adjusted recommendation strategy.

[0028] In a second aspect, the present application also provides a personalized book recommendation device, comprising:

[0029] A rule configuration module is used to obtain multi-dimensional configuration rules input by users;

[0030] The portrait module is used to collect the student information of each student in real time, and generate and update the corresponding student portrait according to the student information of each student;

[0031] A recommendation module, used to generate a corresponding book recommendation list for each student according to the configuration rules, each student portrait and a preset recommendation strategy;

[0032] The feedback optimization module is used to collect feedback information from each student on the respective recommendation lists, and dynamically adjust the recommendation strategy according to the feedback information.

[0033] In a third aspect, the present application further provides a terminal device, the terminal device comprising a processor and a memory, the memory storing a computer program, and the processor being configured to execute the computer program to implement the personalized book recommendation method.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium storing a computer program, which, when executed on a processor, implements the personalized book recommendation method.

[0035] The embodiments of the present application have the following beneficial effects:

[0036] This application receives input configuration rules and collects student information so that book recommendations can take into account both students' personalized needs and set configuration rules, and can optimize the books recommended next time based on students' feedback, so that students can be recommended books that are more in line with their interests and can meet their learning requirements, thereby achieving personalized recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A flowchart of a personalized book recommendation method according to an embodiment of the present application is shown;

[0039] Figure 2An interactive schematic diagram of a personalized book recommendation method according to an embodiment of the present application is shown;

[0040] Figure 3 A structural schematic diagram of a personalized book recommendation device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0042] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0043] Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present application are intended only to indicate specific features, numbers, steps, operations, elements, components or a combination of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or a combination of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or a combination of the foregoing items. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions and cannot be understood as indicating or implying relative importance.

[0044] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0045] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0046] In order to configure a recommendation system based on teaching rules to achieve personalized recommendations and meet the needs of teaching objectives, this application provides a personalized book recommendation method, which generates a student portrait by receiving input configuration information and obtaining student information, and then makes recommendations based on the student portrait and configuration information. After the recommendation, the recommendation strategy can be automatically adjusted based on the feedback content to optimize the recommendation effect.

[0047] The personalized book recommendation method is described below in conjunction with some specific embodiments.

[0048] Figure 1 A flow chart of a personalized book recommendation method according to an embodiment of the present application is shown. Exemplarily, the personalized book recommendation method includes steps S100 to S400.

[0049] Step S100: obtaining a multi-dimensional configuration rule input by a user.

[0050] This embodiment is applied to teaching-related scenarios, such as online teaching systems and other learning software and systems that can lead or guide learning.

[0051] Configuration rules are configuration rules set for multiple dimensions such as students' study plans and study directions, and can be input by administrator-level users such as teachers through the provided input interface. The configuration rules are set for each student and are mainly used to provide directional guidance for subsequent book recommendations.

[0052] Configuration rules include learning goals and recommendation priorities. The learning goal is the type of knowledge that the student needs to learn at the moment. There can be many types of knowledge. For example, the current subject can be used as the learning goal, such as mathematics, Chinese, science, etc. The recommendation priority is the priority of each learning goal. For example, if a student is good at mathematics but poor at Chinese, the priority of Chinese can be set to the highest, followed by other subjects such as mathematics.

[0053] Among them, the learning goal can also be a more detailed learning purpose. For example, for Chinese learning, it can be further configured as a detailed learning goal such as recognizing common vocabulary, classical Chinese, ancient poetry, etc. These learning goals are completely customized by the user.

[0054] Step S200, collect the student information of each student in real time, and generate and update the corresponding student portrait according to the student information of each student.

[0055] Student information includes personal information of students (such as age, gender, grade, etc.) as well as learning progress and performance. The student portrait is analyzed based on the student's personal information to obtain an initial portrait, because from personal information such as age, gender, grade, etc., we can know the student's current learning stage, and thus know the student's current theoretical learning ability. At this time, in the absence of data related to the student's learning progress and learning performance, a rough initial portrait can be generated. It can be understood that the initial portrait at this time is not accurate. For example, the initial portrait of a third-grade primary school student may only be based on the average learning ability of third-grade students, and cannot represent the student's true learning ability.

[0056] As students continue to learn, data related to their learning progress and performance can be collected in real time. In this way, the learning ability can be updated based on the initial portrait. At the same time, the student's learning personality data can be added and updated based on the learning performance, so that the initial portrait is continuously updated to obtain a multi-dimensional data set to generate the student portrait. It can be seen that the student portrait will be continuously updated based on the information collected in real time.

[0057] Learning progress can include data such as students' grades that reflect the quality of their learning. Learning performance can be data that reflects students' personal character, such as their daily classroom performance or interest subjects, such as whether they pay attention in class and how they are when studying.

[0058] Learning progress and learning performance are data obtained by collecting students' learning status after using this system, specifically, the students' vocabulary mastery, favorite subjects, etc. Based on the learning progress and the learning performance, the learning ability can be updated, and the learning ability and learning personality can be added and updated.

[0059] Among them, learning ability is initially generated based on personal information, and then updated based on the student’s learning progress. It is used to reflect relevant measurement data such as whether the student’s learning has improved.

[0060] Learning progress is used to reflect the speed of students' learning. Therefore, learning quality can also be judged through learning progress. For example, students' learning progress can be quantified and graded to reflect the quality of students' learning.

[0061] Learning personality is used to show what direction students tend to lean towards when studying, such as what subjects they like, whether they are quiet or lively in class, whether they concentrate, etc. These can be used to determine students' learning personality.

[0062] Based on the above three dimensions, the students' learning status can be fully reflected. It not only focuses on what students have learned and where they have learned, but also pays attention to students' personality preferences. The resulting student portrait is more comprehensive and can give more effective recommendation results when used for subsequent book recommendations.

[0063] Among them, student portraits are generated for each student separately, so each student portrait can take into account the individual differences of the students, thereby providing data support for subsequent personalized recommendations.

[0064] In addition, students need to learn multiple subjects, so this embodiment will also determine the learning progress of each subject according to the learning progress, and then generate a student portrait of the student in each subject based on the initial portrait and the learning performance. In this way, when recommending books, targeted matching can be performed based on the differences in the student portraits of each subject to increase the matching degree of the matched data.

[0065] Step S300, generating a corresponding book recommendation list for each student according to the configuration rules, each student portrait and the preset recommendation strategy.

[0066] Once the student profile is determined, a recommendation list can be generated for each student based on pre-configured configuration rules.

[0067] It can be understood that the configuration rules are some requirements set by teachers based on the students' learning goals. The student portrait mainly reflects the current learning status and learning style of the students. This embodiment will provide students with a corresponding recommendation list based on the requirements in the configuration rules and the style of the student portrait itself.

[0068] For example, according to the recommendation priority, books matching the student profile are selected from the books related to the learning objectives, and all matching books are summarized into a recommendation list.

[0069] These books can be firstly established in a book database, and the book attributes recorded in the book database are recorded respectively. When matching, the learning objectives and recommendation priorities are considered, and according to the recommendation priorities, books matching the student profile are selected from the books related to the learning objectives, and all matching books are summarized into a recommendation list.

[0070] Learning objectives with the same recommendation priority can be determined. Books covering all learning objectives in each recommendation priority are screened, and the screened data are matched with the student portrait to determine the matching degree of each book.

[0071] A preset number of books before the matching degree is selected from each of the recommendation priorities as matching books.

[0072] For example, in the configuration rules, if computing and literacy are both the first priority, and vocabulary and pronunciation are the second priority, then when matching books, first consider books that have both computing elements and literacy elements, and then consider books that have only computing or literacy elements. The second priority can also be filtered in this way, so that the two priorities can filter out several books respectively, and these books are matched with the student's student portrait. When matching, the matching degree of each dimension of the student portrait and the book can be scored. For example, in the above example, the student portrait has three dimensions, and three matching scores can be obtained for each dimension. In this way, a total score can be calculated, which is the matching degree between the book and the student portrait.

[0073] After determining the matching degree of each book, you can sort them according to the matching degree, and the books in each priority level are sorted and compared separately. Then the books with the top matching degrees can be used as the books in the recommendation list.

[0074] The number of books left in each priority level can be preset through prior data, for example, 3 books are left in each priority level, or 3 books are left in the first priority level and 2 books are left in the second priority level, etc.

[0075] Among them, priority is given to matching books that contain all learning objectives in the same recommendation priority in order to achieve the effect of combining knowledge systems in different fields. For example, when recommending animal-themed books, the system can combine scientific knowledge with language learning objectives and recommend books that can both enhance language comprehension ability and cultivate scientific interest.

[0076] The recommendation strategy here also takes into account the students' learning personality. When matching, for students who love to play, we will tend to recommend books that combine study and play. If the students already like reading, we can recommend books with more literary qualities, so that the recommended books can be more in line with the students' preferences and play a positive feedback.

[0077] Step S400, collecting feedback information from each student on the recommendation list, and dynamically adjusting the recommendation strategy according to the feedback information.

[0078] The feedback information from students will also be collected in real time. The feedback information is mainly collected by checking in regularly. Students can provide feedback on the web page or app through the feedback interface provided. The recommendation strategy will be adjusted based on the feedback information.

[0079] Among them, the feedback information includes the reading time, reading completion and book marks of each book. The book marks are students' feedback on whether they like the book, whether it is interesting, etc., which can reflect the students' likes and dislikes of the book. Based on this feedback information, strategies can be adjusted.

[0080] For example, the recommendation weight of each book may be adjusted according to the book tag.

[0081] Book tags directly indicate students' likes and dislikes of the book. It is understandable that when a student does not like a book, he may not like books of this type. Then, when recommending books to the student in the future, the recommendation weight of books of this type that he does not like can be reduced. Similarly, if the student likes the book, the recommendation weight of books of this type can be increased.

[0082] Reading time and reading completion can be used to determine whether students have met the standard for studying a book. For example, if a student only spent 1 hour to finish a book that is estimated to take 20 hours to read, then although the reading completion is 100%, it is obvious that the student did not read the book carefully in such a short time, and this will be judged as not meeting the standard. Only when both the reading time and reading completion meet the standard, will the student be considered to have completed the reading of the book.

[0083] According to the reading time and the reading completion, the rules that meet the requirements in the configuration rules are determined, and the recommendation weights of related books of the rules that do not meet the requirements are increased.

[0084] For example, for a student, 6 books are recommended at one time, 3 books of the first priority and 3 books of the second priority. If the student has finished reading the books of the second priority but not the books of the first priority, then the books related to the second priority can be not recommended or recommended less in the next recommendation, and the books of the first priority can be recommended instead. Similarly, if the books of the first priority are finished but the books of the second priority are not finished, the recommendation weight of the books of the first priority will be reduced, and the books of the second priority will be recommended first.

[0085] It can be seen that the above-mentioned method of adjustment through feedback information makes the subsequent recommended books for students more and more in line with students' learning needs and interests according to their current reading situation, so that in the subsequent book recommendations, while taking into account the learning purpose, books that students are more interested in can also be recommended to ensure the fun of learning.

[0086] In order to better illustrate the technical solution of this embodiment, Figure 2 The figure is a schematic diagram of an application scenario of this embodiment.

[0087] Teachers can configure rules to allow the system to automatically recommend books to students. The system then recommends books to students based on the configured rules. After reading the books, students give feedback on their reading experience. The system modifies the recommendation logic based on the feedback and then makes the next round of book recommendations to ensure that the books recommended next time are more in line with students' needs. At the same time, it can be seen from this process that when receiving students' feedback information to modify strategies and configuration rules, it is still possible to receive configuration rules set by teachers. This can also ensure that the configuration rules can change with the teacher's teaching plan, making book recommendations more flexible.

[0088] The personalized book recommendation method of this embodiment combines the teaching needs of the teacher side and the learning style of the student side, so that when recommending books, not only whether it fits the teaching requirements is considered, but also the students' own interests and hobbies can be considered. The recommended books are more targeted and easier for students to accept. At the same time, when recommending books, books across multiple fields will be recommended as much as possible to cultivate students' broader thinking. Then, by collecting feedback information and adjusting the recommendation strategy, it is ensured that each recommended book is more in line with the students' current needs and fits the students' interests and hobbies, so that the students' learning efficiency is improved and the recommended books are more easily accepted by students.

[0089] Figure 3 The following is a schematic diagram of the structure of a personalized book recommendation device according to an embodiment of the present application. Exemplarily, the device includes:

[0090] The rule configuration module 10 is used to obtain the multi-dimensional configuration rules input by the user.

[0091] The portrait module 20 is used to collect the student information of each student in real time, and generate and update the corresponding student portrait according to the student information of each student.

[0092] The recommendation module 30 is used to generate a corresponding book recommendation list for each student according to the configuration rules, each student portrait and a preset recommendation strategy.

[0093] The feedback optimization module 40 is used to collect feedback information from each student on the respective recommendation list, and dynamically adjust the recommendation strategy according to the feedback information.

[0094] The present application also provides a terminal device, which includes a processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the personalized book recommendation method.

[0095] The present application also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed on a processor, the personalized book recommendation method is implemented.

[0096] It can be understood that the device of this embodiment corresponds to the method of the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described repeatedly here.

[0097] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU) and a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or at least one of other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application.

[0098] The memory may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The memory is used to store a computer program, and the processor may execute the computer program accordingly after receiving an execution instruction.

[0099] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0100] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0101] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.

[0102] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A personalized book recommendation method, characterized in that: include: Get multi-dimensional configuration rules input by users; Collect student information of each student in real time, and generate and update corresponding student portraits according to the student information of each student; Generate a corresponding book recommendation list for each student according to the configuration rules, each student portrait and the preset recommendation strategy; Collect feedback information from each student on the recommendation list, and dynamically adjust the recommendation strategy based on the feedback information.

2. The personalized book recommendation method according to claim 1, characterized in that: The student information includes personal information, learning progress and learning performance; Generating and updating corresponding student portraits according to the student information of each student includes: Determine the learning ability of each of the students based on the personal information to establish an initial profile; According to the learning progress and the learning performance collected in real time, on the basis of the initial portrait, the learning ability is updated, and the learning personality is added and updated, so as to update the initial portrait to obtain the student portrait.

3. The personalized book recommendation method according to claim 2, characterized in that: Also includes; According to the learning progress, respectively determine the subject learning progress of the current student in each subject; According to the subject learning progress and the learning performance, the initial portrait is updated to generate a student portrait for each student in each subject.

4. The personalized book recommendation method according to claim 1, characterized in that: The configuration rules include learning objectives and recommendation priorities; Generating a corresponding book recommendation list for each student according to the configuration rules, each student portrait and the preset recommendation strategy includes: According to the recommendation priority, books matching the student profile are selected from the books related to the learning objectives, and all matching books are summarized into a recommendation list.

5. The personalized book recommendation method according to claim 4, characterized in that: The selecting, according to the recommendation priority, books matching the student profile from books related to the learning objective includes: Identify learning objectives with the same recommended priority; Filtering books that contain all learning objectives in each of the recommendation priorities, matching the filtered books with the student portraits, and determining the matching degree of each book; A preset number of books before the matching degree is selected from each of the recommendation priorities as matching books.

6. The personalized book recommendation method according to claim 1, characterized in that: The collecting of feedback information from each student on the respective recommendation lists and dynamically adjusting the recommendation strategy according to the feedback information includes: Obtaining feedback information of students on reading each book in the recommendation list, wherein the feedback information includes one or more combinations of reading time, reading completion and book marks of each book; According to the existing book tags, adjusting the recommendation weight of each book; According to the existing reading time and the reading completion, the rules that meet the requirements in the configuration rules are determined, and the recommendation weights of related books of the rules that do not meet the requirements are increased.

7. The personalized book recommendation method according to claim 1, characterized in that: Also includes: An input update configuration rule is received, and a new recommendation list is generated according to the update configuration rule and the adjusted recommendation strategy.

8. A personalized book recommendation device, characterized in that: include: A rule configuration module is used to obtain multi-dimensional configuration rules input by users; The portrait module is used to collect the student information of each student in real time, and generate and update the corresponding student portrait according to the student information of each student; A recommendation module, used to generate a corresponding book recommendation list for each student according to the configuration rules, each student portrait and a preset recommendation strategy; The feedback optimization module is used to collect feedback information from each student on the respective recommendation lists, and dynamically adjust the recommendation strategy according to the feedback information.

9. A terminal device, characterized in that: The terminal device comprises a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the personalized book recommendation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The device stores a computer program, which, when executed on a processor, implements the personalized book recommendation method according to any one of claims 1 to 7.

Images