Course recommendation method, course recommendation device and storage medium

By obtaining the user's personal learning information and current environmental information, we generate course recommendations that meet the actual learning situation, and solve the problem of poor course recommendation results based on popularity recommendations in the existing technology, and improve the effectiveness of recommendations and user experience.

CN119089036AInactive Publication Date: 2024-12-06GUANGZHOU XUESHENG TECHNOLOGY CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411079294.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing course recommendation methods are usually recommended based on specific popularity, and do not consider the actual learning status of students, resulting in poor course recommendation results.

Method used

By receiving the user's natural language information and operation information, obtaining the user's personal learning information and current environmental information, and generating course recommendations that conform to the user's actual learning ability and status based on this information.

Benefits of technology

It improves the effectiveness of course recommendations, makes users more willing to click and use recommended courses, and improves the accuracy and user experience of course recommendations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089036A_ABST
    Figure CN119089036A_ABST
Patent Text Reader

Abstract

The invention discloses a course recommendation method, course recommendation equipment and a storage medium, and relates to the technical field of information recommendation, and the course recommendation method comprises the steps that when natural language information and operation information of a user are received, user information of the user and current environment information are acquired; determining personal learning information of the user according to the user information; and outputting a recommended course corresponding to the natural language information according to the personal learning information and the current environment information. When course recommendation is carried out based on the natural language information of the user, the personal learning information and the current environment information of the user are obtained, the to-be-recommended content is processed based on the personal learning information and the current environment information, then the course information meeting the actual condition and actual demand of the user is output, and the effectiveness of course recommendation is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of information recommendation, and in particular to a course recommendation method, a course recommendation device and a storage medium. Background Art

[0002] Existing course recommendation methods use algorithms to recommend suitable courses for students. Recommendations are usually made based on students’ learning history, test scores, basic information such as age, education, and basic attributes of courses such as difficulty and hours. However, existing course recommendation methods usually make recommendations based on specific popularity. For example, when students choose to study English, the most popular CET-4 or CET-6 English learning courses are recommended, without considering the students’ actual learning situation, resulting in poor course recommendation results.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a course recommendation method, a course recommendation device and a storage medium, aiming to solve the technical problem of poor course recommendation effect.

[0005] To achieve the above objectives, the present application proposes a course recommendation method, which comprises:

[0006] When receiving the user's natural language information and operation information, obtaining the user's user information and current environment information;

[0007] Determine the user's personal learning information based on the user information;

[0008] According to the personal learning information and the current environment information, the recommended courses corresponding to the natural language information are output.

[0009] In one embodiment, the step of determining the user's personal learning information based on the user information includes:

[0010] Determine the historical learning data, course learning progress, course learning score, and learning behavior and preference information associated with the user according to the user information;

[0011] The user's personal learning information is determined based on the historical learning data, the course learning progress, the course learning score, and the learning behavior and preference information.

[0012] In one embodiment, the step of outputting the recommended courses corresponding to the natural language information according to the personal learning information and the current environment information includes:

[0013] Determine learning characteristic information and historical learning information of the personal learning information;

[0014] Determine a parameter sorting priority of the learning feature information, the historical learning information, and the current environment information;

[0015] Generating a target recommended course set according to the natural language information, and sorting the target recommended course set based on the parameter sorting priority;

[0016] Outputting a preset number of courses in the target recommended course set after sorting processing to the recommendation interface.

[0017] In one embodiment, the current environment information includes a current location, and the step of outputting a recommended course corresponding to the natural language information according to the personal learning information and the current environment information includes:

[0018] parsing the natural language information, and when the location information or the associated information of the current location exists in the parsed natural language information, generating a first recommended course set according to the natural language information and the personal learning information;

[0019] Selecting a target recommended course from the first recommended course set based on the current location for recommendation; or

[0020] A second recommended course set is generated according to the natural language information and the current location, and a target recommended course is selected from the second recommended course set for recommendation based on the personal learning information.

[0021] In one embodiment, the current environment information includes current time information, and the step of outputting the recommended course corresponding to the natural language information according to the personal learning information and the current environment information includes:

[0022] Determine the learning duration associated with the current time information according to the personal learning information;

[0023] generating a third recommended course set according to the natural language information and the learning duration;

[0024] A target recommended course is selected from the third recommended course set based on the personal learning information for recommendation.

[0025] In one embodiment, when the natural language information and operation information of the user are received, before the step of obtaining the user information and current environment information of the user, the step further includes:

[0026] In response to the start instruction, outputting a course learning interface;

[0027] When receiving the user's natural language information and operation information, the step of obtaining the user's user information and current environment information includes:

[0028] The operation information and the natural language information corresponding to the custom scenario input by the user in the course learning interface are received, and the user information and the current environment information are acquired.

[0029] In one embodiment, after the step of outputting the recommended courses corresponding to the natural language information according to the personal learning information and the current environment information, the method further includes:

[0030] In response to the operation instruction of the recommended course, determining a target course associated with the operation instruction;

[0031] When receiving a course return instruction from the user within a preset period of time, outputting a course feedback interface;

[0032] When the feedback information received on the course feedback interface is information for adjusting recommended courses, the personal learning information is adjusted based on the feedback information, and the step of outputting the recommended courses corresponding to the natural language information based on the personal learning information and the current environment information is performed.

[0033] In one embodiment, after the step of outputting the recommended courses corresponding to the natural language information according to the personal learning information and the current environment information, the method further includes:

[0034] In response to the selection instruction of the recommended course, the course content associated with the recommended course is output, and an evaluation module is started;

[0035] Acquire learning information corresponding to the course content, and generate an evaluation result based on the learning information;

[0036] Auxiliary courses associated with the recommended courses are generated and output based on the evaluation results.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a course recommendation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the course recommendation method described above.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the course recommendation method described above are implemented.

[0039] One or more technical solutions proposed in this application have at least the following technical effects:

[0040] After receiving the natural language information and operation information, the user's personal learning information is determined based on the user information. The personal learning information includes learning feature information such as the user's learning level, learning purpose and available learning time, as well as historical learning information such as the courses the user has learned, subject scores and learning time. Then, the current environment information is obtained so that based on the personal learning information, current environment information, natural language information and operation information, the course information that is in line with the user's actual learning ability and current actual learning status is recommended to the user, so that the user is more willing to click on the course to study or use it, thereby improving the effectiveness of the course recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 A flowchart of a first embodiment of the method for applying for course recommendation is provided;

[0044] Figure 2 A schematic diagram of an exemplary operation interface of a learning interface of a course recommendation program provided for the course recommendation method of the present application;

[0045] Figure 3 A schematic diagram of an exemplary operation interface for inputting information after selecting a custom scenario in a learning interface of a course recommendation program provided for the course recommendation method of the present application;

[0046] Figure 4 A flowchart of a second embodiment of the present application course recommendation method;

[0047] Figure 5 A flowchart of a third embodiment of the method for applying for course recommendation;

[0048] Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the course recommendation method in the embodiment of the present application.

[0049] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0051] The main solution of the embodiment of the present application is: upon receiving the natural language information and operation information of the user, obtaining the user information and current environment information of the user;

[0052] Determine the user's personal learning information based on the user information;

[0053] According to the personal learning information and the current environment information, the recommended courses corresponding to the natural language information are output.

[0054] In this embodiment, for the convenience of description, the course recommendation device is used as the execution subject for explanation below.

[0055] The existing course recommendation method uses algorithms to recommend suitable courses for students. Recommendations are usually made based on students' learning history, test scores, basic information such as age, education, and basic attributes of courses such as difficulty and hours. However, the existing course recommendation method usually makes recommendations based on specific popularity. For example, when students choose to study English, the most popular CET-4 or CET-6 English learning courses are recommended, without considering the students' actual learning situation, resulting in poor course recommendation results.

[0056] The present application provides a solution. After receiving the user's natural language information and operation information, the user's personal learning information is determined based on the user information. The personal learning information includes the user's actual learning status such as learning level, learning purpose, available learning time, courses learned, scores of the courses and other parameters. At the same time, the current environment information is obtained. The current environment information can filter and optimize the course content desired by the user. Finally, based on the personal learning information and the current environment information, the recommended courses corresponding to the natural language information and the operation information are generated, so that the user can select the recommended courses based on the actual situation, thereby improving the effectiveness of the course recommendation.

[0057] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0058] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a course recommendation device, etc. The following takes the course recommendation device as an example to illustrate this embodiment and the following embodiments.

[0059] This application embodiment provides a course recommendation method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the course recommendation method.

[0060] In this embodiment, the application carriers of the course recommendation method include but are not limited to applications, online education platforms, official websites, social media and forums, emails and notifications, wearable devices and smart assistants. Among them, the recommended courses can cover multiple fields, including but not limited to courses for improving professional skills such as programming courses, design courses, academic education courses such as mathematics, physics and foreign languages, personal development courses, health and sports courses, children's education courses and hobby courses. For ease of description, the following takes foreign language learning courses as an example, based on English learning courses, and applications as application carriers to illustrate the embodiments of this application. Specifically, the course recommendation method includes steps S10 to S30:

[0061] Step S10, when receiving the user's natural language information and operation information, obtaining the user's user information and current environment information;

[0062] It should be noted that the current environment information includes the current location, time, and network status. User information includes historical learning data, course learning progress, course learning scores, learning behavior and preference information, and other parameters that can characterize the user's current knowledge level, learned course data, and learning preferences. Natural language information includes text information and voice question and answer information entered by the user in the course learning program. The text information and voice question and answer information can be input by the user based on actual needs, or can be selected / input in response to the question and answer content of the recommendation interface.

[0063] In an optional implementation, after the user starts the course learning program, the operation interface can be as follows: Figure 2 As shown, the bottom navigation bar of the operation interface includes function pages such as "Schedule, Study, Campus, Community, My", and in the page corresponding to the "Study" column, the top navigation bar includes multiple learning columns such as "Courses, Reading, Dialogue, Vocabulary", and the corresponding interface in the "Dialogue" column includes the learning content of existing scenes 1-3 and the learning content of custom scenes. Among them, the user clicks the button of the custom scene and enters the corresponding information according to the pop-up prompt content, thereby obtaining the user's natural language information and operation information.

[0064] based on Figure 2 In the operation interface shown, for example, the user clicks "Learning" in the bottom navigation bar, then clicks "Dialogue" in the top navigation bar, and then clicks "Customize Scene" to pop up the following Figure 3The interface for users to input natural language information and operation information includes a text box for users to input natural language information, a "Please enter a custom scene" selection box for providing random topics, an exit box for "Confirm" the currently set scene and exit the scene. Here, the user's natural language information includes the user's Figure 3 The specific text content of the custom scene entered in the interface shown. In addition, if there are text prompts or voice question and answer prompts in the interface, the natural language information also includes the voice question and answer information entered by the user, and the operation information entered by the user refers to the operation of clicking OK after entering the natural language information.

[0065] Specifically, in this embodiment, the course learning program can respond to the user's start instruction and then output Figure 2 As shown in the course learning interface, the user can select a custom scenario in the dialog box column of the learning interface according to the actual situation, and enter the corresponding natural language information and operation information so that the course learning program can output the course the user wants.

[0066] For example, the user's current course is an IELTS course. In the custom scenario information filling interface, the natural language information entered by the user in the interface is "generate courses on local history and culture" and then clicks the "OK" command. The course learning program can respond to the information and recommend corresponding English courses and English conversations.

[0067] Among them, when making course recommendations, it is usually recommended by an algorithm, and the keywords of natural language information are extracted based on the algorithm and courses are recommended. For example, after receiving natural language information and operation information, keywords are extracted based on the natural language information, and then the most popular English courses are recommended. For example, if the natural language information is "courses on the history and culture of place A", the current courses generated at this time include the most popular "Simulated dialogue course on the history and culture of place A" and "Writing tutorials related to the history and culture of place A", but what the user actually needs is a course on the culture of place A. At this time, the recommended course is not selected because it does not meet the actual needs of the user, and the course recommendation effect is poor.

[0068] Based on this, in this embodiment, through the AI ​​(Artificial Intelligence) recommendation method, semantic analysis is performed based on the received natural language information, and user information and current environmental information such as current location, current time or upcoming course examination information are obtained. Auxiliary analysis and decision-making are performed based on the acquired parameters to generate recommended courses that meet the actual situation of the user and improve the course recommendation effect. Therefore, after receiving the natural language information and operation information, it is necessary to obtain the user's user information and current environmental information, so as to determine the user's actual knowledge level based on the learning data, learning preferences and learning scores in the user information, and further screen the recommended English courses according to the current environmental information, thereby improving the effectiveness of the recommended courses.

[0069] Exemplarily, in the process of obtaining user information, the user's login information can be used to collect the user's previously completed courses, browsing records and search history, and track the user's current course progress, including completed chapters and remaining content, collect the user's ratings and feedback on the courses they have taken, as well as the grades of quizzes and homework within the course, and finally obtain and analyze the user's login time, learning frequency, and preferred learning content type (video, text, interactive, etc.).

[0070] Step S20, determining the user's personal learning information according to the user information;

[0071] It should be noted that personal learning information includes the user's learning characteristic information, parameters that represent the user's actual learning status, such as learning level, learning purpose, available learning time, etc., as well as the user's historical learning information, including courses learned, scores of courses learned, and historical learning time of courses. Among them, learning level refers to the user's ability to master a course, such as the user's English level is at the level of "college level 4 and 6", and learning purpose includes the learning plan and learning interests selected by the user in the course learning program, including examinations such as starting from a certain period of time to study abroad, workplaces such as job interviews, workplace socializing, and interests such as travel, film and television art, and self-development. Available learning time can screen the content quality of the recommended courses, that is, the learning time of the course. Based on this, the user's personal learning information is determined through user information, so that the AI ​​system of the course learning program can select courses that meet the user's actual needs based on these parameter information, and teach students in accordance with their aptitude, avoiding recommending the most popular courses that do not meet the user's needs.

[0072] Based on this, in this embodiment, after obtaining the user information of the user, the information is processed by the AI ​​system, that is, the historical learning data, course learning progress, course learning score, learning behavior and preference information associated with the user are determined according to the user information. In addition, the user's browsing history, etc. are also included. Subsequently, the personal learning information of the user is determined according to the historical learning data, the course learning progress, the course learning score, and the learning behavior and preference information. For example, according to the historical learning data, course learning score, etc., the courses learned, the scores of the learned courses, and the historical learning time of the courses in the user's historical learning information are analyzed, and according to the learning behavior, preference information, and course learning progress, etc., the learning level, learning purpose, and available learning time in the user's learning feature information are analyzed.

[0073] In this process, the acquired user information is input into the AI ​​system, which is then analyzed by the AI ​​system to obtain personal learning information so that the recommended courses can be screened based on personal information, thereby improving the effectiveness of course recommendations.

[0074] Step S30: outputting the recommended courses corresponding to the natural language information according to the personal learning information and the current environment information.

[0075] In this embodiment, after the AI ​​system obtains the user's personal learning information and current environment information, it can further screen and process the courses corresponding to the natural language information, thereby improving the effectiveness of the courses.

[0076] After the AI ​​system collects the user's personal learning information and current environment information, it determines the user's learning level, that is, the user's English level score, and the user's preferred learning time from the personal learning information. For example, the user's learning level is A2 elementary, and can communicate in simple English. At the same time, the user's learning time is concentrated between 8 pm and 12 pm. The current environment information obtained includes the current time and current location.

[0077] Therefore, as an optional implementation, in the process of outputting the recommended courses corresponding to the natural language information based on the personal learning information and the current environment information, a recommended course set can be generated through the natural language information, and then the recommended course set generated by the natural language information is sorted and filtered based on the learning feature information and the historical learning information in the personal learning information. In addition, further filtering can be performed through the current environment information.

[0078] Specifically, the learning feature information and historical learning information of personal learning information can be determined. The learning feature information includes parameters that meet the user's subjective needs, such as learning ability, learning purpose, and available learning time. The historical learning information includes the courses that the user has learned, the scores of the courses that have been learned, and the historical learning time of the courses, etc., which meet the user's objective needs. Further, the parameters that meet the user's objective needs also include the time and location information in the current environmental information, such as selecting content that meets the local cultural characteristics based on the location. Then, it is necessary to determine the parameter sorting priority of the learning feature information, historical learning information, and current environmental information. Preferably, in this embodiment, when sorting the parameters, the order of sorting priority is: learning feature information (learning level / learning purpose / available learning time and other subjective needs) -> historical learning information (learned courses, course scores, decide whether to strengthen review or learn new content) -> current environmental information (time and place, need to reflect some specific knowledge such as content linked to local cultural characteristics). After obtaining the parameter sorting priority, a target recommended course set is generated according to the natural language information, and the target recommended course set is sorted based on the parameter sorting priority. Finally, a preset number of target recommended course sets after sorting are output to the recommendation interface. It can be understood that when recommending based on the AI ​​system, compared with the traditional method of relying on the user's historical behavior data for recommendation, such as purchase history, browsing history and other objective data for recommendation, when screening and sorting the course set selected by natural language information, the user's subjective and objective factors in the personal learning feature information are used to process the recommended content, and it can recommend courses that meet the user's needs / expectations based on the user's subjective needs and objective learning information, thereby improving the effectiveness of course recommendations.

[0079] In another optional implementation method of outputting recommended courses, the AI ​​system based on the course learning program can first parse the natural language information, and the parsing process includes semantic parsing to obtain keywords and context-aware processing. When the parsed natural language information contains information related to the current environmental information, such as location information or time information, such as information related to place names and time-related information, based on the key features of the natural language information, combined with the location information or time information, the courses are searched and matched in the database to obtain a set of recommended courses, and then the content of the recommended course set is sorted and scored according to the personal learning information, and the highest-scoring courses are output as recommended courses in a pop-up window. That is, when making course recommendations, they can be screened according to the current location in the current environmental information and the user's learning level in the personal learning information.

[0080] Specifically, as an optional implementation method for recommending courses based on the current location and personal learning information, the current environment information includes the current location. The AI ​​system first parses the natural language information, that is, performs semantic analysis on the natural language information, and then, when there is location information or information related to the current location in the natural language information and operation information, it can output recommended courses based on the current location and personal learning information. For example, if the natural language information is "generate courses on local history and culture", the AI ​​system parses it and obtains the location information of "local area". At this time, the current environment information obtained is place A. Based on this, the AI ​​system first generates recommended courses based on the natural language information and operation information, and then further screens the recommended courses based on place A in the current environment information and the user's personal learning information.

[0081] For example, a user needs to obtain an English course in a museum. After the user's natural language information is "museum learning information", the AI ​​recommendation system pulls multiple courses that meet the requirements from the database based on the current location and the characteristics of the natural language information, and then further sorts and filters based on the user's learning level such as the user's vocabulary. Finally, multiple target courses with higher sorting priority that meet the requirements are output for recommendation. In addition, recommendation processing can also be performed based on the time information and personal learning information in the current environmental information. For example, the user's preferred learning time at the current time is determined based on personal learning information, and then courses that meet the learning time and the user's learning level are recommended based on the learning time, that is, the sorting processing of recommended courses based on learning time.

[0082] In another optional implementation, in addition to sorting the recommended course set, one or more target courses can be selected for recommendation. Specifically, when the location information or the associated information of the current location exists in the parsed natural language information and the operation information, a first recommended course set is generated based on the natural language information and the personal learning information, and then a target recommended course is selected from the first recommended course set based on the current location for recommendation, or a course search and matching is performed in the database based on the natural language information and the current location information to generate a second recommended course set, and a target recommended course is selected from the second recommended course set based on the personal learning information for recommendation. In the process of selecting the target course, one or more target courses that meet the learning level are selected based on the learning level of the personal learning information, and the selected target course is output. It should be noted that when selecting or sorting courses from the recommended course set, the courses are usually sorted with a higher priority based on the existing learning feature information in the personal learning information, such as the learning level, learning purpose, and available learning time, and other subjective learning needs of the user. Secondly, the historical learning information in the personal learning information, such as the courses learned, the course ratings, and the content of the courses that have been learned to determine whether to strengthen the course practice or learn new courses, is sorted. Finally, the first recommended course set output has been sorted based on the personal learning information. That is, when performing course screening, the recommended sorting is prioritized based on the user's existing information features, and the importance of the sorting is also different. Secondly, the sorting recommendation is based on other parameters.

[0083] In addition, when selecting target recommended courses from the recommended course set for recommendation, in addition to filtering based on the current location of the current environmental information, it can also be filtered in combination with the current time of the current environmental information. First, the average learning time of the user is determined based on the current time, and then the target recommended courses that meet the time are filtered, or the learning time and the characteristics of the natural language information are combined to match the courses in the database to obtain a recommended course set. Finally, the courses are sorted and filtered based on the user's learning level in the personal learning information.

[0084] For example, a user is at an airport B1 in a foreign country B and wants to know how to get to city C. Based on this, the natural language information entered by the user in the application is "generate a course for asking for directions at an airport". At this time, in the current environment information, the current location is airport B, and in the user's learning level, the skill level is A2 elementary. At this time, the AI ​​system selects a number of recommended course sets about asking for directions at the airport in B from the database based on the natural language information and the current location in the current environment information, such as a number of "Training dialogues for asking for directions at airport B1 in B", "Live demonstration of asking for directions at large airport B1 in B", and a number of "Teaching for asking for directions at large airport B1 in B". Based on this, after obtaining the selected courses, since the user's skill level is A2 elementary, the AI ​​system selects a target course that meets the user's personal learning information, that is, the user's current ability, from the recommended course set for recommendation, that is, in the program homepage or operation interface, recommends "Training dialogues for asking for directions at airport B" and "Teaching for asking for directions at large airport B1 in B" that meet the current user's skill level, so that the user can choose a course based on actual needs. The sorting priority of these recommended course sets is not only based on the learning level in the learning feature information, but also based on the learning time, historical learning information, etc. In addition, the AI ​​system analyzes the user's natural language information and operation information to determine that the user needs a museum history explanation course. In the environmental information obtained, the current location is a museum in a certain place. Based on this, the AI ​​system generates courses that meet the user's actual needs, such as history explanation courses related to the museum or dialogue training courses related to the museum's objects, and recommends these courses to improve the effectiveness of course recommendations.

[0085] Furthermore, in order to improve transparency and user trust, after the AI ​​system outputs recommended courses, it can provide reasons for the recommendation, such as "Based on your current location, you may be interested in this course" and "Based on your personal learning information, this course is more suitable for you."

[0086] When recommending courses, the recommendation interface can display these courses in the form of cards, including the course cover, title, introduction, estimated learning time, user interest level and reason for recommendation, etc. The recommendation interface can be a separate pop-up interface or can be located in the location of the recommendation column.

[0087] Through the AI ​​system recommendation method, not only the user's behavior patterns and interests are taken into account, but also the user's learning habits and contextual information, thereby providing more accurate and personalized course recommendations, increasing the user's click-through rate, and thus improving the effectiveness of course recommendations.

[0088] Furthermore, after generating and outputting the recommended course, the course content associated with the recommended course can be output in response to the selection instruction of the recommended course, and the evaluation module can be started, wherein the course content generally includes training content, learning content, dialogue content, and explanation content, etc., and then the learning information corresponding to the course content is obtained, and the learning information includes the learning results and training results of the user in learning the course, etc., and then the evaluation results for evaluating the user's current status are generated based on the learning information, and the auxiliary courses associated with the recommended course are generated and output based on the evaluation results. After the user completes the learning training of the recommended course, further auxiliary courses can be output according to the training evaluation results, so that the user can conduct simple course auxiliary learning or review processing to improve the effectiveness of course recommendations. Among them, auxiliary courses refer to courses that diagnose the weak links of users through comprehensive analysis of their training evaluation results, and provide specialized exercises and online interactive courses in a targeted manner.

[0089] It should be noted that when selecting recommended courses based on natural language information, current environment information, and learning feature information and historical learning information in personal learning information, the selection can be screened and processed in any combination, that is, the selected parameters for sorting can be freely combined, and then the sorting recommendation can be made based on the selected parameters, wherein the combination selection can be made by the AI ​​system. In addition, when recommending courses based on personal learning information, current environment information and natural language information, the natural language information input by the user usually expresses the user's learning demands, that is, it contains specific cultural learning needs. Therefore, when recommending courses or selecting recommended course sets, matching and screening processing is usually performed based on the personal learning information obtained from the user information, that is, the recommendation priority of personal learning information is usually higher than the current environment information. In the current environment information, if the user arrives at a certain place, the recommendation priority can be adjusted based on the location of the place, and in the output recommended course set, the main recommendation priority is personal learning information.

[0090] This embodiment provides a course recommendation method. After the application is started, natural language information and operation information are obtained, user information and current environment information are obtained to generate personal learning information based on the user information, determine the current location of the current environment information, and then filter the recommended courses generated by the AI ​​system based on the natural language information based on the personal learning information and the current environment information, or associate with the natural language information based on one of the personal learning information and the current location and generate a recommended course set, and then sort or directly filter the recommended course set based on another parameter of the personal learning information and the current location, and finally output courses with high sorting priority or selected courses for recommendation, so that the recommended courses meet the user's learning status and current needs, thereby improving the effectiveness of course recommendations.

[0091] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be repeated hereafter. On this basis, the current environment information also includes the current time information, and recommendations can be made based on the average learning time of the user at the current time, thereby improving the recommendation effect. For details, please refer to Figure 4 , step S30 includes steps S31 to S33:

[0092] Step S31, determining the learning duration associated with the current time information according to the personal learning information;

[0093] In this embodiment, in addition to sorting and filtering recommended courses or selecting courses based on location information, it can also be processed based on the current time. Specifically, it is necessary to determine the learning time associated with the user at the current time based on personal learning information, where the learning time is the average learning time at this time point in the current week. By obtaining the learning time, courses that match the user's actual learning time can be selected from the recommended course set for recommendation.

[0094] Step S32, generating a recommended course set according to the natural language information and the learning time;

[0095] Step S33: selecting a target recommended course from the recommended course set based on the personal learning information for recommendation.

[0096] In this embodiment, the learning time associated with the current time information is determined based on the personal learning information, and after a recommended course set is generated through the learning time and the key features corresponding to the parsed natural language information, a target recommended course is selected from the recommended course set based on the personal learning information for recommendation, wherein one or more target courses that meet the learning level and the available learning time can be selected based on the learning level and the available learning time of the personal learning information, and finally the selected target courses are output.

[0097] Exemplarily, the user's natural language information is "generate a learning course for the museum in place C", and in the current environment information, the current time is 8 o'clock in the evening. Based on the analysis of the user's personal learning information, it is found that the user's learning time at the current time is one hour. Based on this, the AI ​​system generates a set of recommended courses with a duration of less than one hour, such as "Explanation Course of the Museum in Place C", "Writing Course Taking the Museum in Place C as an Example", and "Simulated Dialogue Course Based on the Museum in Place C", based on the features of "Place C", "Museum" and "Learning Course" in the natural language information, combined with the learning time. At the same time, the user's learning level is A2, and the AI ​​system selects "Simulated Dialogue Course Based on the Museum in Place C" and other related courses that meet the user's learning level from the recommended course set for recommendation.

[0098] Based on this, the recommended course set generated by the AI ​​system is screened and processed through the time information in the current environmental information and the learning level in the personal learning information, so as to select courses that meet the user's actual needs and actual learning status for recommendation, thereby improving the effectiveness of course recommendations.

[0099] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can refer to the above introduction, and will not be repeated later. Figure 5 , after step S30, further comprising steps S40 to S60:

[0100] Step S40, responding to the operation instruction of the recommended course and determining the target course associated with the operation instruction;

[0101] In this embodiment, after outputting the recommended courses, it is necessary to track the user's learning status in real time, so as to determine whether the currently recommended course is valid based on the learning status. For example, after the user clicks on recommended course A, if he exits within ten seconds and re-enters the natural language information and operation information to re-recommend the course, it means that the currently recommended course does not meet the user's needs.

[0102] Step S50, when a course return instruction from the user is received within a preset period of time, a course feedback interface is output;

[0103] In this embodiment, the preset time period is a time period preset by the system, such as ten seconds, twenty seconds or one minute. At this time, when a course return instruction is received within the preset time period, it is necessary to confirm whether the poor effect of the course recommendation causes the user to be unable to study, or whether the user temporarily interrupts the study. Based on this, it is necessary to output a course feedback interface and obtain the user's feedback information based on the interface.

[0104] Step S60, when the feedback information received in the course feedback interface is information for adjusting recommended courses, adjust the personal learning information based on the feedback information, and execute the step of outputting the recommended courses corresponding to the natural language information based on the personal learning information and the current environment information.

[0105] The feedback information for adjusting the recommended course information may be adjusting the course difficulty of the recommended course, adjusting the learning time of the recommended course, etc. Based on this, in this embodiment, after receiving the operation, the user's personal learning information may be updated based on the user's adjustment operation, for example, based on the course difficulty and learning time selected by the user, the user's actual learning level and learning time in the time period in the personal learning information may be adjusted, thereby improving the effectiveness of subsequent course recommendations. At the same time, after adjusting the personal learning information, the action of step S30 may be executed to output courses that meet the user's needs.

[0106] For example, in the recommended "Simulated Dialogue Course Based on the Museum in Site C", the vocabulary used in the course is relatively common and simple, and cannot effectively improve the user's learning level. At this time, the user performs a return operation and enters feedback information in the feedback interface to increase the learning difficulty of the recommended course so that the recommendation is in line with the user's actual learning situation.

[0107] Optionally, if the received feedback information is information about temporary departure, it is necessary to save the learning progress of the current course for the user so that the course information can continue to be output after the user starts the application again.

[0108] This embodiment provides a course recommendation method. After outputting recommended courses based on personal learning information and current environment information, the method tracks the user's current learning status in real time, and when the user performs a course return operation, collects the reason why the user performs the operation through a feedback interface, optimizes the user's personal learning information based on the user's instructions for adjusting the recommended course information entered in the feedback interface, and re-recommends courses based on the personal learning information to ensure that the recommended courses are in line with the user's actual situation and improve the effectiveness of the recommendation.

[0109] It should be noted that the above embodiments are only used to understand the present application and do not constitute a limitation on the course recommendation method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0110] The present application provides a course recommendation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the course recommendation method in the first embodiment described above.

[0111] Reference below Figure 6 , which shows a schematic diagram of the structure of a course recommendation device suitable for implementing the embodiment of the present application. The course recommendation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The course recommendation device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0112] like Figure 6 As shown, the course recommendation device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the course recommendation device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the course recommendation device to communicate with other devices wirelessly or by wire to exchange data. Although the course recommendation device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided alternatively.

[0113] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0114] The course recommendation device provided by the present application adopts the course recommendation method in the above embodiment, which can solve the technical problem of poor course recommendation effect. Compared with the prior art, the beneficial effects of the course recommendation device provided by the present application are the same as the beneficial effects of the course recommendation method provided by the above embodiment, and the other technical features in the course recommendation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0115] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0116] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present 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. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0117] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the course recommendation method in the above-mentioned embodiment.

[0118] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0119] The computer-readable storage medium may be included in the course recommendation device; or may exist independently without being assembled into the course recommendation device.

[0120] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the course recommendation device, the course recommendation device:

[0121] When receiving the user's natural language information and operation information, obtaining the user's user information and current environment information;

[0122] Determine the user's personal learning information based on the user information;

[0123] According to the personal learning information and the current environment information, the recommended courses corresponding to the natural language information are output.

[0124] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various 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 the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession 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 block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0126] The modules involved in the embodiments of the present application may be implemented by software or hardware, wherein the name of the module does not limit the unit itself in some cases.

[0127] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned course recommendation method, and can solve the technical problem of poor course recommendation effect. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the course recommendation method provided in the above-mentioned embodiment, and will not be repeated here.

[0128] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A course recommendation method, characterized in that: The method comprises: When receiving the user's natural language information and operation information, obtaining the user's user information and current environment information; Determine the user's personal learning information based on the user information; According to the personal learning information and the current environment information, the recommended courses corresponding to the natural language information are output.

2. The method according to claim 1, characterized in that The step of determining the user's personal learning information according to the user information comprises: Determine the historical learning data, course learning progress, course learning score, and learning behavior and preference information associated with the user according to the user information; The user's personal learning information is determined based on the historical learning data, the course learning progress, the course learning score, and the learning behavior and preference information.

3. The method according to claim 1, characterized in that The step of outputting the recommended courses corresponding to the natural language information according to the personal learning information and the current environment information comprises: Determine learning characteristic information and historical learning information of the personal learning information; Determine a parameter sorting priority of the learning feature information, the historical learning information, and the current environment information; Generating a target recommended course set according to the natural language information, and sorting the target recommended course set based on the parameter sorting priority; Outputting a preset number of courses in the target recommended course set after sorting processing to the recommendation interface.

4. The method according to claim 1, characterized in that The current environment information includes a current location, and the step of outputting a recommended course corresponding to the natural language information according to the personal learning information and the current environment information includes: parsing the natural language information, and when the location information or the associated information of the current location exists in the parsed natural language information, generating a first recommended course set according to the natural language information and the personal learning information; Selecting a target recommended course from the first recommended course set based on the current location for recommendation; or A second recommended course set is generated according to the natural language information and the current location, and a target recommended course is selected from the second recommended course set for recommendation based on the personal learning information.

5. The method according to claim 1, characterized in that The current environment information includes current time information, and the step of outputting the recommended course corresponding to the natural language information according to the personal learning information and the current environment information includes: Determine the learning duration associated with the current time information according to the personal learning information; generating a third recommended course set according to the natural language information and the learning duration; A target recommended course is selected from the third recommended course set based on the personal learning information for recommendation.

6. The method according to claim 1, characterized in that When the natural language information and operation information of the user are received, before the step of obtaining the user information and current environment information of the user, the step further includes: In response to the start instruction, outputting a course learning interface; When receiving the user's natural language information and operation information, the step of obtaining the user's user information and current environment information includes: The operation information and the natural language information corresponding to the custom scenario input by the user in the course learning interface are received, and the user information and the current environment information are acquired.

7. The method according to claim 1, characterized in that After the step of outputting the recommended courses corresponding to the natural language information according to the personal learning information and the current environment information, the method further includes: In response to the operation instruction of the recommended course, determining a target course associated with the operation instruction; When receiving a course return instruction from the user within a preset period of time, outputting a course feedback interface; When the feedback information received on the course feedback interface is information for adjusting recommended courses, the personal learning information is adjusted based on the feedback information, and the step of outputting the recommended courses corresponding to the natural language information based on the personal learning information and the current environment information is performed.

8. The method according to claim 1, characterized in that After the step of outputting the recommended courses corresponding to the natural language information according to the personal learning information and the current environment information, the method further includes: In response to the selection instruction of the recommended course, the course content associated with the recommended course is output, and an evaluation module is started; Acquire learning information corresponding to the course content, and generate an evaluation result based on the learning information; Auxiliary courses associated with the recommended courses are generated and output based on the evaluation results.

9. A course recommendation device, characterized in that: The course recommendation device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the course recommendation method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the course recommendation method according to any one of claims 1 to 8 are implemented.

Citation Information

Cited By

  • Remote education resource recommendation method and system

    CN119377484A

  • Intelligent curriculum recommendation method and device based on scene self-adaption and storage medium

    CN121304299A