Course recommendation method and course recommendation device

Abstract

The invention discloses a course recommendation method and a course recommendation device, and the method comprises the steps: determining a plurality of questions according to user learning information, the user learning information comprises a target subject and a target difficulty level of a user, and the plurality of questions are associated with the target difficulty level under the target subject; in response to an operation of selecting at least one question in the plurality of questions by a user, determining at least one knowledge point tag, the at least one knowledge point tag corresponding to the at least one question; according to the at least one knowledge point label, recommended courses are determined, the recommended courses are at least one of target courses, and the target courses correspond to the at least one knowledge point label. In the method, the multiple questions are determined through the user information including the subjects and the difficulty levels, and the questions are strongly associated with the courses through the knowledge point labels, so that the complexity of user operation is reduced, and the accuracy of the course recommendation result is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of learning platforms, and particularly to a course recommendation method and a course recommendation device. Background Art

[0002] Course recommendation methods are crucial in modern education. By providing personalized learning resource recommendations, they help students efficiently master knowledge, not only saving students' time in finding suitable courses but also stimulating their interest in independent learning, thus promoting the improvement of education quality and the realization of the all-round development of students.

[0003] In the prior art, many course recommendations mainly rely on traditional recommendation methods, whose question banks are often fixed. Not only do users need to manually input questions and browse a large amount of content irrelevant to their needs, but there is also a lack of a strong association between questions and course tags. Such a recommendation method not only increases the operation burden on users but also may lead to the generalization of recommendation results and fail to accurately match the specific needs of users. Summary of the Invention

[0004] Embodiments of the present application disclose a course recommendation method and a course recommendation device. Multiple questions are determined based on user learning information including subjects and difficulty levels, and questions are strongly associated with courses through knowledge point tags, which not only reduces the complexity of user operations but also enhances the accuracy of course recommendation results.

[0005] The first aspect of the embodiments of the present application discloses a course recommendation method applied to an electronic device, including:

[0006] Determine multiple questions according to user learning information, where the user learning information includes the user's target subject and target difficulty level, and the multiple questions are associated with the target difficulty level under the target subject;

[0007] In response to an operation of the user selecting at least one question from the multiple questions, determine at least one knowledge point tag corresponding to the at least one question;

[0008] Determine the recommended courses according to the at least one knowledge point tag, where the recommended courses are at least one of the target courses corresponding to the at least one knowledge point tag.

[0009] As an optional implementation manner, in the first aspect of this embodiment, determining the recommended courses according to the at least one knowledge point tag includes:

[0010] Determine the target courses associated with the at least one knowledge point tag according to the at least one knowledge point tag;

[0011] Determine the recommended courses from the target courses according to the course data and / or the first user behavior data, where the first user behavior data is the data generated when the user uses the electronic device for course recommendation and / or learns based on the recommended courses.

[0012] As an alternative implementation manner, in the first aspect of this embodiment, the determining the recommended courses from the target course package according to the course-related data and the user behavior data includes:

[0013] Sort the target courses in descending order of comprehensive score according to the course data and / or the first user behavior data, and determine the courses in the top K positions as the recommended courses, where K is an integer greater than or equal to 1.

[0014] As an alternative implementation manner, in the first aspect of this embodiment, the course data includes course scores, and the first user behavior data includes at least one of the following: question selection frequency, course completion rate, course click frequency, course playback progress, single learning duration of the course, average learning duration of the course, user's score feedback on the course, wrong question distribution.

[0015] As an alternative implementation manner, in the first aspect of this embodiment, the determining multiple questions according to the user learning information includes:

[0016] Determine the multiple questions from the question bank according to the user learning information, where the question bank includes questions associated with different subjects and different difficulty levels, and each question corresponds to one or more knowledge point tags.

[0017] As an alternative implementation manner, in the first aspect of this embodiment, update the question bank according to the second user behavior data, where the second user behavior data is the data generated when at least one user uses the electronic device for course recommendation and / or learns based on the recommended courses.

[0018] As an alternative implementation manner, in the first aspect of this embodiment, when the number of times the first question is detected is greater than or equal to the number threshold, add the first question to the question bank, and the knowledge point tags corresponding to the first question include partial knowledge point tags of all the knowledge point tags and / or newly added knowledge point tags other than all the knowledge point tags.

[0019] As an alternative implementation manner, in the first aspect of this embodiment, when the knowledge point tags corresponding to the first question include newly added knowledge point tags other than all the knowledge point tags, the newly added knowledge point tags are associated with at least one of all the courses.

[0020] As an alternative implementation, in the first aspect of this embodiment, determining multiple questions according to the user learning information includes:

[0021] Determining the multiple questions in response to an operation where the user selects the target subject and the target difficulty level.

[0022] As an alternative implementation, in the first aspect of this embodiment, the target difficulty level is a basic level, an improvement level, or an elite level.

[0023] As an alternative implementation, in the first aspect of this embodiment, the user learning information further includes the user's target grade, and the multiple questions are associated with the target difficulty level under the target grade and the target subject.

[0024] The second aspect of the embodiments of the present application discloses a course recommendation device, including a question acquisition module, a tag acquisition module, and a course recommendation module, where:

[0025] The question acquisition module is configured to determine multiple questions according to the user learning information, where the user learning information includes the user's target subject and target difficulty level, and the multiple questions are associated with the target difficulty level under the target subject;

[0026] The tag acquisition module is configured to determine at least one knowledge point tag in response to an operation where the user selects at least one question among the multiple questions, and the at least one knowledge point tag corresponds to the at least one question;

[0027] The course recommendation module is configured to determine the recommended courses according to the at least one knowledge point tag, and the recommended courses are at least one of the target courses, and the target courses correspond to the at least one knowledge point tag.

[0028] The third aspect of the embodiments of the present application discloses an electronic device, including a memory and a processor, where the memory stores a computer program that can run on the processor, and when the processor executes the program, it implements the method described in the embodiments of the present application.

[0029] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the method provided in the embodiments of the present application.

[0030] Compared with the related art, the embodiments of the present application at least include the following beneficial effects:

[0031] A course recommendation method disclosed in an embodiment of the present application determines multiple questions according to user learning information, where the user learning information includes the user's target subject and target difficulty level, and the multiple questions are associated with the target difficulty level under the target subject; in response to an operation of the user selecting at least one question from the multiple questions, at least one knowledge point label is determined, and the at least one knowledge point label corresponds to the at least one question; according to the at least one knowledge point label, a recommended course is determined, and the recommended course is at least one of the target courses, and the target course corresponds to the at least one knowledge point label. In this method, determining multiple questions through user learning information including the target subject and target difficulty level can enable the user to only determine at least one question relevant to themselves based on these multiple questions, without having to browse too many questions or manually input questions, reducing the complexity of user operations; moreover, in this method, each question is associated with a course through a knowledge point label, which can enable the electronic device to recommend a course associated with the knowledge point label corresponding to the question selected by the user, improving the accuracy of course recommendation and avoiding the generalization of recommended content and being unable to meet user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0033] Figure 1 It is a flowchart of a course recommendation method provided by an embodiment of the present application;

[0034] Figure 2 It is a schematic diagram of a selection interface of an electronic device provided by an embodiment of the present application;

[0035] Figure 3 It is a flowchart of another course recommendation method provided by an embodiment of the present application;

[0036] Figure 4 It is a flowchart of another course recommendation method provided by an embodiment of the present application;

[0037] Figure 5 It is a schematic diagram of a course recommendation interface of an electronic device provided by an embodiment of the present application;

[0038] Figure 6 It is a schematic diagram of another course recommendation interface of an electronic device provided by an embodiment of the present application;

[0039] Figure 7 It is a schematic diagram of the interface when a new user uses the electronic device for the first time provided by an embodiment of the present application;

[0040] Figure 8 A schematic structural diagram of a course recommendation device provided by an embodiment of the present application;

[0041] Figure 9 A schematic diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0042] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0043] It should be noted that the terms "first", "second", and "third" involved in the embodiments of the present application are used to distinguish similar or different objects, and do not represent a specific order for the objects. It can be understood that "first", "second", and "third" can be interchanged with a specific order or sequence when permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0044] It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present application and the accompanying drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products, or devices.

[0045] The course recommendation method plays a crucial role in modern education. With the continuous development of information technology. Traditional learning methods often cannot meet the personalized learning needs of students, while the course recommendation method based on information technology provides customized learning resources for students by deeply analyzing their learning habits, interests, learning progress, and weak knowledge points. Thus, it helps students efficiently master knowledge, avoid wasting time on irrelevant or repetitive learning content, stimulates their interest in independent learning, enhances the enthusiasm and initiative of learning, and further promotes the improvement of education quality and realizes the all-round development of students.

[0046] However, many course recommendation systems in the prior art still rely on traditional recommendation methods and have certain limitations. Traditional recommendation systems usually rely on a fixed question bank and cannot be flexibly adjusted according to the real-time learning needs of students. When students use these systems, they often need to manually input questions, which not only increases the complexity of operation but also makes the user's learning experience cumbersome. More seriously, there is a lack of strong correlation between the questions in the question bank and the course tags, resulting in the difficulty for the recommendation system to accurately understand the learning needs of students. In this case, the recommendation system may recommend a large number of course contents that are irrelevant to the students' needs. As a result, not only can it not effectively improve learning efficiency, but it may also cause students to waste time browsing a large number of irrelevant courses, affecting their learning enthusiasm and concentration. Moreover, due to the static nature of the question bank and the loose relationship between the tags, it cannot provide accurate learning resources, leading to the generalization of the recommendation results and unable to provide truly valuable learning suggestions for students.

[0047] The embodiments of this application disclose a course recommendation method and an electronic device. The method determines multiple questions according to user learning information, where the user learning information includes the user's target subject and target difficulty level, and the multiple questions are associated with the target difficulty level under the target subject; in response to an operation of the user selecting at least one question from the multiple questions, at least one knowledge point tag is determined, and the at least one knowledge point tag corresponds to the at least one question; according to the at least one knowledge point tag, the recommended courses are determined, and the recommended courses are at least one of the target courses, and the target courses correspond to the at least one knowledge point tag. This method determines multiple questions through user information including the subject and difficulty level, and makes the questions and courses strongly correlated through knowledge point tags, not only reducing the complexity of user operation but also enhancing the accuracy of the course recommendation results.

[0048] The course recommendation method provided by the embodiments of this application can be applied to multiple fields and can help students, working professionals, and various learners obtain more efficient and accurate learning resources, improving learning effects and learning interests. For example, online education platforms, vocational training and improvement, higher education and self-study platforms, skill certification and qualification exam training, interdisciplinary learning, and lifelong learning platforms, etc., are not specifically limited here.

[0049] For the above-mentioned course recommendation methods in different fields, the following will be described in detail. For example, in an online education platform, the online education platform can recommend personalized course content for students. In the field of vocational skills training, the course recommendation method can recommend suitable training courses according to the job requirements, career goals, and ability levels of employees. In higher education institutions or self-study platforms, the course recommendation method can be used to recommend suitable courses for students based on their academic backgrounds, learning goals, and learning problems, helping them plan their academic paths. In the field of skills certification and qualification exam training, the course recommendation system can recommend the most relevant courses according to the skill fields they are learning, the current level of knowledge points they have mastered, and the problems they encounter. Interdisciplinary learning and lifelong learning: In the context of interdisciplinary learning and lifelong learning, the learning needs of students or trainees are more diversified. The course recommendation method can recommend cross-field courses according to personal interests, learning goals, and current problems, helping learners expand their knowledge.

[0050] To understand the above course recommendation method more clearly, taking an electronic device as an example as the execution subject, the embodiments of the present application will be described. It should be understood that the execution subject of the embodiments of the present application can be a chip or a processor in the electronic device, etc., which will not be specifically limited here.

[0051] Please refer to Figure 1 , Figure 1 which is a flowchart of a course recommendation method provided by the embodiments of the present application. The flowchart includes at least steps S101-S102.

[0052] Step S101: The electronic device determines multiple questions according to the user's learning information.

[0053] Among them, the user's learning information includes the user's target subject and target difficulty level, and the multiple questions are associated with the target difficulty level under the target subject;

[0054] In some embodiments, for different educational platforms and educational fields, not only the target subject and target difficulty level can be selected, but also the corresponding grade and / or field can be selected.

[0055] Optionally, if the course recommendation method is applicable to an online education platform, when the target subject and target difficulty level are selected, the user can also be allowed to select the target grade they are in, such as the first semester of the first grade, the second semester of the first grade, or the first semester of the third grade, etc., which will not be specifically limited here. In this case, the multiple questions are associated with the target grade and the target difficulty level under the target subject. Thereby increasing the accuracy of course recommendation.

[0056] Optionally, when this course recommendation method is applicable to skill certification and qualification exam training, before selecting the target subject and target difficulty level, the user is also required to select a target field, such as electrician, accounting, etc., which is not specifically limited here. In this case, the multiple questions are associated with the target field and the target difficulty level under the target subject. This increases the accuracy of skill-based course recommendations.

[0057] In some embodiments, the selection of grade or field can be linked to the boot registration information.

[0058] Taking an online education platform as an example, when the online education platform is launched for the first time, the grade information is linked to the boot registration information, and the grade information is set through the personal profile when the user first registers. For example, select "Grade 3, Volume 1 of Primary School". To improve the user experience and the flexibility of the course recommendation method, the grade information can be manually modified later.

[0059] Optionally, in the field of the online education platform, the target subjects can include mathematics, Chinese, and English. This is not specifically limited here.

[0060] Optionally, in the field of skill certification and qualification exam training, the target subject can be multiple target subjects corresponding to the target field. For example, the target subjects in the primary accounting exam can be accounting practice and economic law foundation. This is not specifically limited here.

[0061] Optionally, the target difficulty level can be the basic level, the improvement level, or the elite level, which is not specifically limited here. Recommending courses according to the difficulty level helps to provide a personalized learning experience according to the different learning levels of students. Students can learn within the range suitable for their abilities, avoiding frustration or boredom caused by courses being too difficult or too easy, and at the same time increasing the motivation and interest in learning.

[0062] In some embodiments, the target difficulty level can be determined based on the user's selection on the interface, or can be determined after being evaluated by a corresponding assessment system, in order to align with the difference between the user's own knowledge level and the difficulty level specified by the system. Thus, when the electronic device recommends courses, the recommended courses are more accurate.

[0063] In the embodiments of the present application, the multiple questions are frequently updated and displayed high-frequency questions. It can be understood that high-frequency questions are common questions that users frequently ask or frequently appear. Exemplarily, high-frequency questions refer to the questions ranked at the top according to teaching research and market research for students at the current grade subject difficulty, which can meet the needs of the vast majority of users.

[0064] Compared with many general problems shown in the related art, the number of high-frequency problems is small and can meet the multi-problem needs of large users. Therefore, it is possible to avoid users browsing too much irrelevant information, making the course recommendation method more flexible and improving the user experience.

[0065] In an embodiment of the present application, exemplarily, multiple questions associated with the target difficulty level under the target subject can also be continuously updated and optimized by internal professional teaching and research teachers. In addition, the electronic device can record the learning problems of the user and the overall machine usage situation, and update the questions according to the recorded learning problems of the user and the overall machine usage situation through big data screening. Therefore, the multiple questions can accurately locate the usage needs of the user, so as to recommend more accurate learning courses for the user.

[0066] Step S102: The electronic device determines at least one knowledge point label in response to an operation of the user selecting at least one question from the multiple questions. Wherein, the at least one knowledge point label corresponds to the at least one question.

[0067] Exemplarily, one question can correspond to one knowledge point label or multiple knowledge point labels. Exemplarily, one knowledge point label can correspond to one question or multiple questions.

[0068] Step S103: The electronic device determines the recommended courses according to the at least one knowledge point label.

[0069] Wherein, the recommended courses are at least one of the target courses, and the target courses correspond to the at least one knowledge point label.

[0070] It can be understood that the target courses can include at least one course, and the at least one course corresponds to the at least one knowledge point label. In the case where the target courses include one course, one knowledge point label corresponds to one course. In the case where the target courses include multiple courses, one knowledge point label can correspond to at least one course.

[0071] In an embodiment where the target courses include one course, the recommended course is the one course. In an embodiment where the target courses include multiple courses, the recommended courses are at least one of the multiple courses, such as one or two or three courses, etc. In implementation, exemplarily, the electronic device can determine the target courses according to the at least one knowledge point label, and determine the recommended courses based on the target courses.

[0072] In this method, multiple questions are determined based on the target subject and the target difficulty level of the user's learning information. These multiple questions are associated with the target difficulty level under the target subject, which allows the user to simply select based on the displayed questions without having to browse through excessive questions or manually input questions, reducing the complexity of user operations. Moreover, based on at least one question selected by the user, at least one knowledge point label corresponding to the at least one question is determined, and then the recommended courses are determined according to the at least one knowledge point label. In this way, each question is associated with a course through the knowledge point label. As long as the user selects a certain question, the courses associated with the knowledge point label corresponding to that question will be recommended, improving the accuracy of course recommendations and avoiding the generalization of recommended courses that cannot meet the user's needs.

[0073] In step S101 above, that is, in the step of determining multiple questions based on the user's learning information, in some embodiments, multiple questions are determined in response to the user's operation of selecting the target subject and the target difficulty level.

[0074] Exemplarily, multiple subjects and multiple target difficulty levels can be displayed on the electronic device. The user selects the target subject from the multiple subjects and the target difficulty level from the multiple difficulty levels. In response to the user's operation of selecting the target subject and the target difficulty level, multiple questions are determined.

[0075] In embodiments where the user's learning information includes the target grade, not only multiple subjects and multiple target difficulty levels are displayed on the electronic device, but also multiple grades are displayed. The user selects the target grade from the multiple grades, the target subject from the multiple subjects, and the target difficulty level from the multiple difficulty levels. In response to the user's operation of selecting the target grade, the target subject, and the target difficulty level, multiple questions are determined. In this case, the multiple questions are associated with the target difficulty level under the target grade and the target subject.

[0076] Exemplarily, taking an online education platform for students from grade 1 to grade 6 as an example, the above method is described exemplarily. When the electronic device is started without any previous operations, the user needs to log in and register personal information. At this time, the grade information can be filled in the registration form for personal profile settings, that is, the grade information is set through personal profile settings when the user registers for the first time, such as selecting "Grade 3 - Volume 1". Thereafter, when the electronic device makes course recommendations, this "Grade 3 - Volume 1" is used as the default parameter throughout the selection of subjects, difficulty levels, and questions.

[0077] Please refer to Figure 2 , Figure 2A schematic diagram of a user interface of an electronic device provided by an embodiment of the present application. Interface 11 includes an AI teacher 12, a grade control 13, a subject selection area 14, a difficulty selection area 15, a question area 16, and a generate customized solution control 17. Among them, the grade control 13 is used to display options for multiple grades. The subject selection area 14 includes options for multiple subjects, such as options for Chinese, mathematics, and English. The difficulty selection area 15 includes options for multiple difficulties, such as options for basic, improvement, and excellence. The question area 16 includes multiple questions, and the multiple questions are associated with the grade, subject, and difficulty selected by the user. The grade selected by the user through the grade control 13 is the third grade - first semester (an example of the target grade). The subject selected from multiple subjects is Chinese (i.e., an example of the target subject). The subject selected from multiple difficulty levels is improvement (i.e., an example of the target difficulty level). In response to the user's operation of selecting the third grade - first semester, Chinese, and improvement, multiple questions are displayed in the question area 16, and the multiple questions are associated with the third grade - first semester, Chinese, and improvement. The user selects the question "Writing without method and technique makes the composition like a running account" from multiple questions. The electronic device, in response to the user's operation of selecting "Writing without method and technique makes the composition like a running account", determines at least one knowledge point label corresponding to the question 16. The user can click the generate customized solution control 17. In response to the user's operation, the electronic device determines the target course corresponding to the at least one knowledge point based on the at least one knowledge point label, and further determines the recommended course.

[0078] In some embodiments, when selecting the target subject, the version of the target subject can also be selected, so that the recommended course content can better match the user's needs.

[0079] In the above step of determining multiple questions according to the user's learning information, in some embodiments, the electronic device determines multiple questions from a question bank according to the user's learning information. The question bank includes questions associated with different subjects and different difficulty levels, and each question corresponds to one or more knowledge point labels. The question bank provides a set of predefined questions, which can ensure consistent content and structure among different users, ensure the standardization and consistency of questions, and provide a unified user experience. Secondly, the design of the question bank can reduce the complexity of the electronic device during recommendation because the electronic device only needs to extract questions from the defined question bank instead of generating questions according to the user input each time, thereby improving the efficiency of recommendation and saving resources. In addition, the question bank helps to deeply analyze user behavior and preferences through system data collection, and further optimizes the recommendation algorithm.

[0080] In some embodiments, the question bank includes questions associated with different grades, different subjects, and different difficulty levels, and each question corresponds to one or more knowledge point labels.

[0081] In this way, a three-dimensional problem tag system for the question bank can be established according to the three dimensions of grade, subject, and difficulty. That is, the question bank can be divided into multiple levels to facilitate subsequent querying, management, and optimization.

[0082] Exemplarily, taking an online education platform for students from grade one to grade six as an example, the question bank will be explained in detail.

[0083] Grade dimension: For students in different grades, the question content and difficulty requirements are different. For example, it can be divided into "Grade 3 - Volume 1" and "Grade 5 - Volume 1", etc., without specific limitations here.

[0084] Subject dimension: The subject dimension makes a more detailed division of the question bank to help students select according to the subject. The questions in the question bank will be sorted according to the knowledge systems of different subjects. For example, Chinese, mathematics, English, and science, etc., without specific limitations here.

[0085] Difficulty dimension: The difficulty dimension is an important factor for classifying questions in depth, mainly distinguished according to the learning needs of students and the degree of knowledge they have mastered. Through the classification of difficulty, it can help the system provide more accurate questions according to the learning progress or needs of students. For example, there are three levels: basic, improved, and excellent. This can adapt to students in different learning stages and with different needs.

[0086] In this way, combining the above three dimensions, a label system for an actual question bank is constructed to ensure that users can quickly find questions suitable for themselves.

[0087] In some embodiments, the same question can correspond to a knowledge point label. For example, Grade 3 - Volume 1 → Chinese → Basic, the corresponding question is "The composition can't be written well and is like a running account", and the corresponding knowledge point label is "Rhetoric in writing compositions". Another example, Grade 5 - Volume 2 → Mathematics → Basic, the corresponding question is "Don't understand the mathematics knowledge points", and the corresponding knowledge point label is "Geometric foundation".

[0088] In some other embodiments, the same question can correspond to multiple knowledge point labels. For example: Grade 3 - Volume 1 → Chinese → Basic, the corresponding question is "The composition can't be written well and is like a running account", and the corresponding knowledge point labels are "Rhetoric in writing compositions", "Language expression skills in compositions", and "Emotional rendering in compositions", etc. Grade 5 - Volume 2 → Mathematics → Basic: The corresponding question is "Don't understand the mathematics knowledge points", and the corresponding knowledge point labels are "Geometric foundation", "Fractions and decimals", and "Time and units", etc., without specific limitations here.

[0089] In order to enable the question bank to continuously optimize the design of questions based on user feedback and behavioral data, making the electronic device more intelligent and personalized, so as to better adapt to market changes, improve the user experience and increase user satisfaction, in some embodiments, the electronic device can also update the question bank according to second user behavioral data, where the second user behavioral data is data generated when at least one user uses the electronic device for course recommendation and / or learning based on the recommended courses.

[0090] Optionally, the second user behavioral data may include the question selection frequency, course completion rate, click frequency of the course, play progress of the course, single learning duration of the course, average learning duration of the course, user's rating feedback on the course, wrong question distribution, etc., which are not specifically limited herein.

[0091] The question selection frequency refers to the number of times a user selects or answers a certain question within a period of time. This can be used to analyze which questions or content receive user attention, or which questions are more difficult and require more attempts.

[0092] The course completion rate is measured by the ratio of the course progress completed by the user to the total course progress. It mainly reflects the user's learning perseverance and the attractiveness of the course. A lower completion rate may indicate that the course content is not attractive enough or too difficult.

[0093] The click frequency of the course refers to the number of times a certain course is clicked within a period of time. It can be used to analyze the attractiveness of the course and help the platform optimize course recommendations.

[0094] The play progress of the course refers to the progress when the user watches or learns a certain course. It can help evaluate the learning effect of the course and user engagement.

[0095] The single learning duration of the course refers to the time spent by the user each time learning a certain course. It is mainly used to analyze the learner's concentration and the degree of investment in each learning. If the single learning duration is short, it may indicate that the learner's attention span is short or the course content is too fragmented.

[0096] The average learning duration of the course refers to the time spent by the user on average each time learning the course within a period of time. It is the average value of all single learning durations. This data helps to understand the user's learning habits and the attractiveness of the course. A longer learning duration may indicate that the course content is more complex or requires in-depth learning, while a shorter learning duration may indicate that the course is too simple or the user has insufficient interest.

[0097] User feedback on a course refers to the ratings and feedback users provide after completing a course based on their learning experience. This feedback is typically expressed in the form of star ratings, comments, and suggestions. It can reflect the quality of the course content, the teaching style, and the user's overall learning satisfaction.

[0098] Error distribution refers to the types, distribution, and frequency of incorrect questions a user encounters when answering questions or completing tests. This helps identify which knowledge points or question types a user struggles with, allowing for targeted instructional adjustments or personalized learning suggestions.

[0099] The second user behavior data is data generated when at least one user uses an electronic device to recommend courses and / or studies based on the recommended courses. It can be understood that the second user behavior data is generated based on the behavior data of at least one user, and the at least one user can be the user currently using the electronic device or all users using the electronic device.

[0100] Exemplarily, the second user behavior data is generated based on the behavior data of all users of the electronic device. Specifically, by updating and sorting the data generated by all users of the electronic device when making course recommendations and / or studying based on the recommended courses, it is possible to more accurately determine which questions are the most frequently asked questions. Thus, after determining multiple questions based on the user's target subject and target difficulty, these multiple questions are frequently asked questions, and these multiple frequently asked questions are displayed, thereby improving the accuracy and adaptability of course recommendations for users.

[0101] The selection of frequently asked questions can be updated according to preset rules, ensuring that the selected frequently asked questions meet the user's needs as much as possible. For example, frequently asked questions are retained while infrequent questions are eliminated. This means that when users select questions, questions with the top 20% selection frequency and a course completion rate greater than or equal to 70% are retained; questions with the bottom 10% selection frequency or a completion rate less than 50% are removed from the list. This method eliminates ineffective questions and ensures that the recommended content is close to the user's actual needs.

[0102] In some embodiments, the electronic device can further optimize the ranking of questions in the question library based on the second user behavior data. For example, the electronic device can recalculate and rank the questions based on the composite score of "question selection frequency x course completion rate x user rating feedback on the course." This approach can ensure that when new user behavior data is available, course recommendations generated based on the optimized ranking of the question library can better meet user needs, thereby improving the usability of course recommendations.

[0103] To ensure that the question bank is always consistent with current user needs, trends, and technological developments, thereby enhancing the relevance and accuracy of recommended electronic devices, new questions can be added to the question bank. In some embodiments, when the number of times the first question is detected is greater than or equal to the frequency threshold, the first question is added to the question bank. The knowledge point tags corresponding to the first question include partial knowledge point tags of all knowledge point tags and / or newly added knowledge point tags other than all knowledge point tags.

[0104] It should be understood that in this embodiment, the electronic device can provide an interface for the user to input new questions, and the user can input new questions through this interface. For example, manually input a new interface or input a new question by voice.

[0105] Taking the first question as an example, when the number of times the first question is detected is greater than or equal to the frequency threshold, it is considered that the first question is frequently selected by the user, which means that the first question is a common problem of some users. Therefore, the first question is added to the question bank. Among them, when the knowledge point tags corresponding to the first question include newly added knowledge point tags other than all knowledge point tags, the newly added knowledge point tags are associated with at least one of all courses.

[0106] In this method, new knowledge point tags are added to the new questions, and the newly added knowledge point tags need to be associated with at least one course, so that the questions are associated with the courses through the knowledge point tags. This method not only adds new content by updating the question bank, continuously adapts to market changes and meets user needs, but also always keeps each question associated with the course through the knowledge point tag. As long as the user selects a certain question, courses associated with the knowledge point tags corresponding to the question will inevitably be recommended according to the question, improving the accuracy of course recommendations and avoiding generalization of recommended content.

[0107] In the above step S103, that is, in the step of determining the recommended courses according to at least one knowledge point tag, in some embodiments, the electronic device determines the target courses associated with at least one knowledge point tag according to at least one knowledge point tag; determines the recommended courses from the target courses according to the course data and / or the first user behavior data. The first user behavior data is the data generated when the user uses the electronic device for course recommendation and / or learns based on the recommended courses.

[0108] To understand the above method steps more clearly, please refer to Figure 3 , Figure 3 which is a flowchart of another course recommendation method provided by the embodiments of the present application. The flowchart includes at least steps S201 - S203.

[0109] Step S201: Determine multiple questions according to the user learning information.

[0110] Step S202: In response to an operation where the user selects at least one question among multiple questions, determine at least one knowledge point label.

[0111] Step S203: Based on the at least one knowledge point label, determine the target courses associated with the at least one knowledge point label.

[0112] Among them, one knowledge point label can correspond to multiple courses or one course.

[0113] Step S204: Based on the course data and / or the first user behavior data, determine the recommended courses from the target courses.

[0114] Among them, the first user behavior data is the data generated when the user uses the electronic device for course recommendation and / or learning based on the recommended courses.

[0115] It can be understood that in order to enhance the accuracy of course recommendation for each user, the first user is the user currently using the electronic device, so that more adaptable course recommendations for the user can be generated according to the different behaviors of each user.

[0116] Optionally, the course data includes course ratings, and the first user behavior data includes at least one of the following: question selection frequency, course completion rate, click frequency of the course, playback progress of the course, single learning duration of the course, average learning duration of the course, user's rating feedback on the course, wrong question distribution. By analyzing and sorting these multiple data, the accuracy of course recommendation can be enhanced.

[0117] Optionally, when the user has used the electronic device for course recommendation and / or learning based on the recommended courses, determine the recommended courses from the target courses according to the course data and the first user behavior data. Or, when the user has used the electronic device for course recommendation and / or learning based on the recommended courses, the recommended courses can also be determined from the target courses according to the first user behavior data. There is no specific limitation here.

[0118] Optionally, when the user has not used the electronic device for course recommendation and / or learning based on the recommended courses, determine the recommended courses from the target courses according to the course data.

[0119] In this method, the user obtains all the courses related to the selected questions through the knowledge point labels, and further selects from all these courses to determine the target courses, so that the user does not have to perform complex browsing and screening on many courses, reducing the operation complexity when the user uses the electronic device for course recommendation and / or learning based on the recommended courses.

[0120] In step S204, that is, in the step of determining the recommended courses from the target courses according to the course data and / or the first user behavior data, in some embodiments, the electronic device sorts the target courses in descending order of the comprehensive score according to the course data and / or the first user behavior data, and determines the courses in the first K positions as the recommended courses, where K is an integer greater than or equal to 1.

[0121] To understand the above method steps more clearly, please refer to Figure 4 , Figure 4 which is a flowchart of another course recommendation method provided by an embodiment of the present application. The flowchart at least includes steps S301 - S303.

[0122] Step S301: Determine multiple questions according to the user learning information.

[0123] Step S302: In response to an operation in which the user selects at least one question from the multiple questions, determine at least one knowledge point label.

[0124] Step S303: According to the at least one knowledge point label, determine the target courses associated with the at least one knowledge point label.

[0125] Step S304: Sort the target courses in descending order of the comprehensive score according to the course data and / or the first user behavior data, and determine the courses in the first K positions as the recommended courses.

[0126] Among them, K is an integer greater than or equal to 1. The courses in the first K positions include the courses in the Kth position and all positions before the Kth position.

[0127] In this method, in response to an operation in which the user selects at least one question from the multiple questions, at least one knowledge point label is determined, and according to the at least one knowledge point label, the target courses associated with the at least one knowledge point label are determined. To determine the recommended courses from the target courses, the target courses can be sorted in descending order of the comprehensive score according to the course data and / or the first user behavior data, and the courses in the first K positions are determined as the recommended courses, thereby further screening the target courses associated with the knowledge point labels, selecting the courses with higher scores and more in line with the user's needs, and improving the accuracy of course recommendation.

[0128] In some embodiments, the electronic device can sort the target courses in descending order of the comprehensive score according to the course data and the first user behavior data, and determine the courses in the first K positions as the recommended courses. This embodiment can be applied to the scenario where the user has used the course recommendation method in the electronic device and can generate the first user behavior data.

[0129] Exemplarily, K is equal to 1, that is, the course located at the first 1 position (i.e., the first place) is determined as the recommended course. Of course, in other examples, K can also be 2, 3, 4, 5, etc., which are not specifically limited here.

[0130] When the user obtains multiple courses based on the knowledge point tags related to the question, the target courses are sorted from high to low according to the comprehensive score, and the course at the first 1 position (i.e., the first place) with the highest score is used as the recommended course. In this way, the customer not only does not need to perform complex operations to browse and select multiple courses, but also because the customer behavior and course data are sorted according to the comprehensive score, the courses recommended to the customer are not only of high quality in content, but also meet the user's needs to the greatest extent, improving the accuracy of course recommendation.

[0131] Exemplarily, please refer to Figure 5 , Figure 5 which is a schematic diagram of a course recommendation interface of an electronic device provided by an embodiment of the present application. The figure includes an AI teacher 12, a course recommendation area 18, and an AI in-depth analysis area 19. The course recommendation area 18 is the course recommended by the electronic device according to the user's selection. For example, a student in the "third grade - first semester", who has used the electronic device and currently selects the target subject 14 as English, selects the difficulty level 15 as basic, and selects the question 16 as "having problems with letter pronunciation", the generated customized plan. In addition, the developed plan can also combine the AI large model to deeply analyze the user's question 16 and recommend the course "Master Natural Phonics in 7 Hours".

[0132] Optionally, the AI large model can be GPT series or DeepSeeK, etc., which are not specifically limited here.

[0133] Optionally, in the case where the generated customized plan does not meet the user's needs, the user can also click "Redefine" to reselect the question 16 to generate a customized plan.

[0134] In some other embodiments, the electronic device can also sort the target courses from high to low according to the comprehensive score based on the first user behavior data, and determine the courses at the first K positions as the recommended courses. Similarly, this embodiment can be applied to the scenario where the user has used the course recommendation method in the electronic device and can generate the first user behavior data.

[0135] In some other embodiments, the electronic device may sort the target courses in descending order according to the comprehensive score based on the course data, and determine the courses in the top K positions as the recommended courses. This embodiment can be applied to the scenario where the user has not used the course recommendation method in the electronic device. Since there is no first user behavior data stored in the electronic device, therefore, sorting the target courses in descending order according to the comprehensive score, the courses in the top K positions can be determined as the recommended courses based on the course data.

[0136] Exemplarily, K is 3, that is, the courses in the top 3 positions are determined as the recommended courses. In other examples, K can also be 1, 2, 4, 5, etc., and no specific limitation is made here.

[0137] When the user obtains multiple courses according to the knowledge point tags related to the question, sorting the target courses in descending order according to the comprehensive score, and taking the courses in the top K positions with the highest scores as the recommended courses. In this method, since there is no user behavior data stored in the electronic device and the user's behavior habits cannot be understood, only the course data is sorted according to the comprehensive score. Therefore, the displayed course package can be more than the course package recommended when the user data is stored in the electronic device, so as to increase the accuracy of the recommended course package and better meet the user's needs.

[0138] Exemplarily, please refer to Figure 6 , Figure 6 which is a schematic diagram of another course recommendation interface of the electronic device provided by the embodiment of the present application. This figure includes an AI teacher 12, a course recommendation area 18, and an AI in-depth analysis area 19. The course recommendation area 18 is the courses recommended by the electronic device according to the user's selection. For example, a student in the "third grade - first semester", who has not used this electronic device, but when this student selects the target subject 14 as English, selects the difficulty level 15 as basic, and selects the question 16 as "having problems with letter pronunciation 16", the generated customized solution. Since there is no user behavior record stored in the electronic device, the user's behavior habits cannot be located. A total of 3 course packages are displayed on this course recommendation page for the user to choose from, so as to improve the accuracy of the recommendation.

[0139] Optionally, in the case that the generated customized solution does not meet the user's needs, the user can also click "re-customize" to re-select the question 16 to generate a customized solution.

[0140] In some embodiments, please refer to Figure 7 , Figure 7It is a schematic diagram of an interface when a new user uses the electronic device for the first time provided by an embodiment of the present application, including an AI teacher 12, a customization control 22, and a recommended area 23 for possible problems. By default, the most frequent problems and corresponding preferred course packages within the current grade and subject are recommended in the recommended area 23 for possible problems. If there is no desired option, the customization control can be selected to enter the interface as shown in Figure 2 the displayed interface, where precise positioning of the target subject 14, target difficulty level 15, and related problems 16 can be performed.

[0141] The following is an embodiment of the device of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the device embodiment of the present application, please refer to the method embodiment of the present application.

[0142] Please refer to Figure 8 , which shows a schematic structural diagram of a course recommendation device provided by an exemplary embodiment of the present application. The course recommendation device 40 can be used in an electronic device to execute all or part of the steps executed by the electronic device in the methods provided by the above various embodiments. The course recommendation device 40 includes a problem acquisition module 41, a label acquisition module 42, and a course recommendation module 43.

[0143] The problem acquisition module 41 is configured to determine a plurality of problems according to user learning information, where the user learning information includes the user's target subject and target difficulty level, and the plurality of problems are associated with the target difficulty level under the target subject;

[0144] The label acquisition module 42 is configured to determine at least one knowledge point label in response to an operation of the user selecting at least one problem among the plurality of problems, where the at least one knowledge point label corresponds to the at least one problem;

[0145] The course recommendation module 43 is configured to determine a recommended course according to the at least one knowledge point label, where the recommended course is at least one of the target courses, and the target courses correspond to the at least one knowledge point label.

[0146] Optionally, the user learning information further includes the user's target grade, and the plurality of problems are associated with the target grade and the target difficulty level under the target subject.

[0147] Optionally, the problem acquisition module 41 is further configured to determine the plurality of problems from a problem library according to the user learning information.

[0148] Wherein, the problem library includes problems associated with different subjects and different difficulty levels, and each problem corresponds to one or more knowledge point labels.

[0149] Optionally, the course recommendation device 40 further includes an update module for updating the question bank according to the second user behavior data, where the second user behavior data is data generated when at least one user uses the electronic device for course recommendation and / or learns based on the recommended courses.

[0150] The update module is further configured to add the first question to the question bank when the number of times the first question is detected is greater than or equal to the number threshold, where the knowledge point tags corresponding to the first question include some of the knowledge point tags of all the knowledge point tags and / or newly added knowledge point tags other than all the knowledge point tags.

[0151] Optionally, when the knowledge point tags corresponding to the first question include newly added knowledge point tags other than all the knowledge point tags, the newly added knowledge point tags are associated with at least one of all the courses.

[0152] Optionally, the question acquisition module 41 is further configured to determine the multiple questions in response to an operation in which the user selects the target subject and the target difficulty level.

[0153] Optionally, the target difficulty level is a basic level, an improvement level, or an elite level.

[0154] Optionally, the tag acquisition module 42 is further configured to determine the target courses associated with the at least one knowledge point tag according to the at least one knowledge point tag; and,

[0155] to determine the recommended courses from the target courses according to the course data and / or the first user behavior data, where the first user behavior data is data generated when the user uses the electronic device for course recommendation and / or learns based on the recommended courses.

[0156] Optionally, the course recommendation module 43 is further configured to sort the target courses in descending order of the comprehensive score according to the course data and / or the first user behavior data, and determine the courses in the first K positions as the recommended courses, where K is an integer greater than or equal to 1.

[0157] Optionally, the course data includes course ratings, and the first user behavior data includes at least one of the following: question selection frequency, course completion rate, course click frequency, course playback progress, single-course learning duration, average course learning duration, user's rating feedback on the course, and wrong-question distribution.

[0158] It should be noted that in the embodiments of the present application Figure 8The division of modules by the illustrated course recommendation device is schematic and is only a logical function division. In actual implementation, there may be other division methods. Additionally, in each embodiment of the present application, each functional unit can be integrated in a processing unit, can exist independently physically, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware, can also be implemented in the form of a software functional unit, or can be implemented in the form of a combination of software and hardware.

[0159] It should be noted that in the embodiments of the present application, if the above method is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application, in essence or the part that contributes to the related technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing an electronic device to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), magnetic disks, or optical discs that can store program codes. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0160] The embodiments of the present application provide an electronic device, which can be any possible device such as a learning machine, and its internal structure diagram can be as Figure 9 shown. The electronic device includes a processor 502, a memory, and a network interface 503 connected through a system bus 501. Among them, the processor 502 of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes an internal memory 5041 and a non-volatile storage medium 5042. The non-volatile storage medium 5042 stores an operating system, computer programs, and a database. The internal memory 5041 provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium 5042. The database of the electronic device is used to store data. The network interface 503 of the electronic device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor 502, implements the above method.

[0161] Based on the above course recommendation method and electronic device, the embodiments of the present application also disclose a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements any one of the above-described video generation methods.

[0162] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a magnetic disk, an optical disk, a ROM, etc.

[0163] Any reference to memory, storage, database or other media as used herein may include non-volatile and / or volatile memory. Suitable non-volatile memory may include ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM), which is used as an external cache. By way of illustration and not limitation, RAM can be in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus DRAM (RDRAM) and direct rambus DRAM (DRDRAM).

[0164] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the "in one embodiment" or "in an embodiment" that appears throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. Those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0165] In various embodiments of the present application, it should be understood that the magnitudes of the serial numbers of the above processes do not necessarily imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0166] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0167] In addition, in each embodiment of the present application, each functional unit may be integrated into a processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0168] The term "and / or" in this article is merely a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, object A and / or object B can represent: object A exists alone, object A and object B exist simultaneously, and object B exists alone.

[0169] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, the element defined by the statement "including one..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0170] The methods disclosed in several method embodiments provided by the present application can be arbitrarily combined without conflict to obtain new method embodiments.

[0171] The features disclosed in several product embodiments provided by the present application can be arbitrarily combined without conflict to obtain new product embodiments.

[0172] The features disclosed in several method or device embodiments provided by the present application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0173] The above has introduced in detail the course recommendation method disclosed in the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A course recommendation method, characterized in that, Applied to a course recommendation device, including: Determine multiple questions based on user learning information, where the user learning information includes the user's target subject and target difficulty level, and the multiple questions are associated with the target difficulty level under the target subject; In response to an operation where the user selects at least one question from the multiple questions, determine at least one knowledge point label, where the at least one knowledge point label corresponds to the at least one question; Determine the recommended courses based on the at least one knowledge point label, where the recommended courses are at least one of the target courses, and the target courses correspond to the at least one knowledge point label.

2. The method according to claim 1, wherein The determining the recommended courses based on the at least one knowledge point label includes: Determine the target courses associated with the at least one knowledge point label based on the at least one knowledge point label; Determine the recommended courses from the target courses according to course data and / or first user behavior data, where the first user behavior data is data generated when the user uses the electronic device for course recommendation and / or learns based on the recommended courses.

3. The method according to claim 2, wherein The determining the recommended courses from the target courses according to course-related data and user behavior data includes: Sort the target courses in descending order of comprehensive score according to the course data and / or the first user behavior data, and determine the courses in the top K positions as the recommended courses, where K is an integer greater than or equal to 1.

4. The method according to claim 2 or 3, characterized in that, The course data includes course scores, and the first user behavior data includes at least one of the following: question selection frequency, course completion rate, course click frequency, course playback progress, single-course learning duration, average course learning duration, user's score feedback on the course, wrong-question distribution.

5. The method according to any one of claims 1 to 3, characterized in that, The determining multiple questions based on user learning information includes: Determine the multiple questions from a question bank according to the user learning information, where the question bank includes questions associated with different subjects and different difficulty levels, and each question corresponds to one or more knowledge point labels.

6. The method according to claim 5, wherein The method further includes: Update the question bank according to second user behavior data, where the second user behavior data is data generated when at least one user uses the electronic device for course recommendation and / or learns based on the recommended courses.

7. The method according to claim 5, characterized in that, The method further includes: In the case where the number of times the first question is detected is greater than or equal to the number threshold, add the first question to the question bank, where the knowledge point labels corresponding to the first question include some of the knowledge point labels of all the knowledge point labels and / or newly added knowledge point labels other than all the knowledge point labels.

8. The method according to claim 7, wherein The method further includes: In the case where the knowledge point labels corresponding to the first question include newly added knowledge point labels other than all the knowledge point labels, the newly added knowledge point labels are associated with at least one of all the courses.

9. The method according to any one of claims 1 to 3, characterized in that The determining multiple questions based on user learning information includes: In response to an operation where the user selects the target subject and the target difficulty level, determine the multiple questions.

10. The method according to any one of claims 1 to 3, characterized in that, The target difficulty level is the basic level, the improvement level, or the excellence level.

11. The method according to any one of claims 1 to 3, characterized in that The user learning information further includes the target grade of the user, and the multiple questions are associated with the target difficulty level under the target grade and the target subject.

12. A course recommendation device, characterized in that, Including: A question acquisition module, configured to determine multiple questions according to user learning information, where the user learning information includes the user's target subject and target difficulty level, and the multiple questions are associated with the target difficulty level under the target subject; A label acquisition module, configured to determine at least one knowledge point label corresponding to at least one of the multiple questions in response to an operation of the user selecting at least one of the multiple questions; A course recommendation module, configured to determine a recommended course according to the at least one knowledge point label, where the recommended course is at least one of the target courses, and the target courses correspond to the at least one knowledge point label.

Images