Intelligent recommendation method based on teaching big data and server

Abstract

The invention discloses an intelligent recommendation method based on teaching big data and a server, and relates to the technical field of computers. The method comprises the steps of obtaining a teaching interaction record of an offline course; acquiring a teaching video corresponding to the offline course, and identifying the teaching video to obtain an action analysis result and an audio analysis result; calculating a teaching scoring result according to the teaching interaction record, the action analysis result and the audio analysis result; determining at least one target course in a plurality of offline courses according to the teaching scoring result; and recommending an online course obtained by recording the target course in a preset webpage. According to the invention, the recommendation efficiency and accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the computer field, and in particular to an intelligent recommendation method and server based on teaching big data. Background Art

[0002] With the development of computer technology and the change of education methods, people can learn the knowledge they want to know online. On the Internet, there are different courses of various disciplines, and courses in the same field have various choices. It is difficult for users to distinguish or compare the pros and cons of courses.

[0003] At present, the existing technology recommends courses based on data such as course views or user associations after the courses are uploaded. The current solution requires a long time after the courses are online to evaluate the courses, and the recommendations are only based on the relevant data of online users. This is time-consuming, and the one-sided evaluation leads to insufficient accuracy of the recommendations.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the embodiments of the present disclosure is to provide an intelligent recommendation method and server based on teaching big data, which can improve the accuracy of teaching course recommendations.

[0006] A first aspect of the embodiments of the present disclosure provides an intelligent recommendation method based on teaching big data, characterized in that the method includes: Obtain teaching interaction records of offline courses; Obtaining a teaching video corresponding to the offline course, and identifying the teaching video to obtain a motion analysis result and an audio analysis result; Calculate the teaching score result according to the teaching interaction record, the action analysis result and the audio analysis result; Determining at least one target course from a plurality of offline courses according to the teaching evaluation results; An online course obtained by recording the target course is recommended on a preset web page.

[0007] In an exemplary embodiment of the present disclosure, the step of obtaining the teaching interaction record of the offline course includes: Based on a preset teaching platform, obtaining interaction records of interactions conducted through the teaching platform; The teaching interaction record includes at least one of a sign-in record and a speech record.

[0008] In an exemplary embodiment of the present disclosure, the step of identifying the teaching video to obtain the action analysis result includes: Extracting key frames from the teaching video and identifying key points of the human body in the key frames; Obtaining a motion analysis result according to the key points of the human body; The action analysis result includes at least one of the actions of entering a course, leaving a class, and raising a hand.

[0009] In an exemplary embodiment of the present disclosure, the step of identifying the teaching video to obtain an audio analysis result includes: Extracting audio data from the teaching video, and identifying audio features in the audio data, wherein the audio features include at least one of a spectrum feature, an intensity feature, and a speech rate feature; Distinguishing the teacher's voice and the student's voice of the offline course according to the audio features; Based on the duration and frequency of the teacher's voice and the student's voice, the audio analysis result is statistically obtained.

[0010] In an exemplary embodiment of the present disclosure, the step of calculating the teaching score result according to the teaching interaction record, the action analysis result and the audio analysis result includes: Determining a teaching interaction score according to the number of the teaching interaction records; Determining a first teaching state score according to the types and quantities of different actions included in the action analysis results; Determine a second teaching status score according to the duration and frequency of the teacher's voice and the student's voice in the audio analysis result; A teaching score result is calculated based on the teaching interaction score, the first teaching status score, and the second teaching status score.

[0011] In an exemplary embodiment of the present disclosure, the step of determining the teaching interaction score according to the number of the teaching interaction records includes: Determine different types of the teaching interaction records, and configure different weight values ​​based on the different types; The teaching interaction score is calculated based on the various types, corresponding quantities and corresponding weight values ​​of the teaching interaction records.

[0012] In an exemplary embodiment of the present disclosure, the step of determining at least one target course from a plurality of offline courses according to the teaching scoring result includes: At least one target course is obtained by screening the multiple offline courses according to the teaching score results corresponding to the multiple offline courses and in combination with a preset threshold.

[0013] In an exemplary embodiment of the present disclosure, the step of determining at least one target course from a plurality of offline courses according to the teaching scoring result includes: According to the teaching evaluation results corresponding to multiple offline courses, multiple teaching evaluation results are sorted; Combined with a preset value, a corresponding number of target courses are obtained by screening out multiple offline courses.

[0014] In an exemplary embodiment of the present disclosure, the step of recommending the online course obtained by recording the target course in a preset webpage includes: Displaying the online course obtained by recording the target course in a prominent position or in a prominent manner on a preset webpage; The highlighted position includes a top position, and the highlighted manner includes one of highlight display and enlarged display.

[0015] According to a second aspect of an embodiment of the present disclosure, a server is provided, wherein the server includes a processor, a machine-readable storage medium, and a network interface. The machine-readable storage medium, the network interface and the processor are connected via a bus system, the network interface is used to communicate with at least one teaching data capture device, and the machine-readable storage medium is used to store programs, Instructions or codes, the processor is used to execute the program, instructions or codes in the machine-readable storage medium to execute the intelligent recommendation method based on teaching big data of any one of the claims.

[0016] According to a third aspect of an embodiment of the present disclosure, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the method described in the first aspect of the above embodiment is implemented.

[0017] According to a fourth aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, which, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the method described in the first aspect of the above embodiment.

[0018] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects: By using technical means to record the interactions between students and teachers in offline courses, detailed records of teaching interactions can be obtained, which improves the accuracy and authenticity of subsequent analysis and evaluation.

[0019] By combining teaching interaction records, motion analysis results and audio analysis results, and using algorithms and models to calculate, we can get the evaluation results for teaching quality. This scoring result can more accurately reflect the teaching effect, the quality of interaction, the enthusiasm of the teaching environment and other aspects.

[0020] According to the teaching rating results, at least one target course is determined from multiple offline courses: According to the teaching rating results, an offline course with a higher rating is selected as the target course. In this way, a reference-worthy offline course recommendation list can be provided to students or other users to help them choose appropriate courses, saving the user's time and energy costs, and improving the efficiency and accuracy of teaching course recommendations.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0023] Figure 1 A schematic diagram schematically shows an exemplary scenario in which an intelligent recommendation method based on teaching big data according to an embodiment of the present disclosure can be applied; Figure 2 A flowchart of an intelligent recommendation method based on teaching big data according to an embodiment of the present disclosure is schematically shown; Figure 3 A flowchart for determining a teaching interaction score according to an embodiment of the present disclosure is schematically shown; Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0024] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0025] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0026] It should be noted that although the modules of the platform in the present disclosure are described in a specific order in the drawings, this does not require or imply that they must be executed in this specific order, or that all the modules shown must be present to achieve the desired results. Additionally or alternatively, some modules may be omitted, multiple modules may be combined into one module for execution, and / or one module may be decomposed into multiple modules for execution, etc.

[0027] Figure 1 A schematic diagram schematically shows a system architecture of an exemplary application scenario of an intelligent recommendation method based on teaching big data to which an embodiment of the present disclosure can be applied.

[0028] like Figure 1 As shown, the system architecture may include a device 101 and a server 102. Figure 1 The devices and servers in the figure are only illustrative. According to the implementation requirements, there can be any number of devices and servers, such as cluster servers. Among them, the device 101 can be a variety of devices, such as monitoring devices, recording devices, mobile terminal devices and other teaching data capture devices.

[0029] With the development of computer technology and the change of education methods, people can learn the knowledge they want to know online. On the Internet, there are different courses of various disciplines, and courses in the same field have various choices. It is difficult for users to distinguish or compare the pros and cons of courses.

[0030] However, the current existing technology recommends courses based on the number of views or the association between users after the courses are uploaded, for example, videos with a high number of views within a certain period of time are recommended. The current solution requires a long time after the course is launched to evaluate the course, and the recommendation is only based on the limited relevant data of online users. It takes a long time, and the one-sided evaluation leads to insufficient accuracy of the recommendation.

[0031] Therefore, in one embodiment of the present disclosure, see Figure 2 , Figure 2 A flowchart of an intelligent recommendation method based on teaching big data according to an embodiment of the present disclosure is schematically shown. As shown in the figure, the method may include: S210. Obtain teaching interaction records of offline courses.

[0032] In the disclosed embodiment, the teaching interaction record includes at least one of a sign-in record and a speech record, and may also be other different record data.

[0033] There are many ways to obtain offline course teaching interaction records, such as using existing teaching platforms, such as online learning systems or education management systems, to record students' interactive behaviors in class, such as submitting homework, participating in discussions, etc. It can also be recorded through some devices, such as providing students with a clicker, which can be clicked once for each interaction, and finally the interaction records are summarized.

[0034] When using a preset teaching platform to obtain the teaching interaction records of offline courses, it can be done through a variety of channels. Video conferencing function: Many teaching platforms provide video conferencing functions, which can be used to record students' interactive behaviors in the classroom in real time. For example, students can use video conferencing software to operate in the software to answer questions, ask questions, raise their hands, and other operations, and these interactive behaviors can be recorded. It can also be a group discussion function, through which students can discuss and communicate in class. The platform can monitor and record students' interactive behaviors in discussions, such as the number of speeches, reply content, etc. Or interactive tools and functions, such as voting, whiteboard collaboration, real-time Q&A, etc. These tools and functions can record students' interactive behaviors in the classroom and generate corresponding interactive record data.

[0035] S220, obtaining a teaching video corresponding to the offline course, and identifying the teaching video to obtain a motion analysis result and an audio analysis result; In the disclosed embodiment, the teaching video refers to the process of offline teaching, and the content of the shooting may include the teacher, students and the whole picture of the classroom. The step of identifying the teaching video to obtain the action analysis result and the audio analysis result may be performed in real time during the teaching process, or after the teaching is completed, based on the teaching video recognition and analysis.

[0036] Action analysis of teaching videos can be performed through human keypoints detection, also known as human posture estimation, which is a pre-process for human action recognition, behavior analysis, human-computer interaction, etc. in computer vision. Human keypoints detection can be single / multi-person keypoints detection, 2D / 3D keypoints detection, and a preset algorithm is used to track keypoints after keypoints detection, thereby completing human posture tracking.

[0037] The key points of the human body can be represented as 17 joints, namely the nose, left and right eyes, left and right ears, left and right shoulders, left and right elbows, left and right wrists, left and right hips, left and right knees, and left and right ankles. The human body and the corresponding key point positions are detected from the input image, such as the key frames in the teaching video, to perform human key point detection. According to the human key point detection algorithm, 2D key point detection and 3D key point detection can be used according to whether it contains 3D depth information. When there are many students in the classroom, 2D multi-person key point detection (multi-person posture estimation) can be used. For example, the top-down method first performs target detection (people), and then performs single-person key point detection (single-person posture estimation) for each detected person, or the bottm-up method first detects the key points of all people, and then groups and associates the key points.

[0038] By detecting and identifying key points of the human body and tracking them, human posture estimation is obtained to complete motion analysis. The motion analysis results can include course movements, leaving the classroom, and raising hands, and these movements are recorded when they are detected.

[0039] Audio feature extraction and analysis technology can analyze the characteristics of sound, so as to automatically classify and identify audio signals. In the process of audio feature extraction, features can be extracted from the time domain, frequency domain, wavelet transform and other aspects. Among them, time domain features include short-time energy, short-time average zero-crossing rate, etc., and frequency domain features include power spectrum density, spectrum clustering coefficient, etc. The extraction of audio features can be achieved by using machine learning algorithms, such as support vector machines, random forests, neural networks, etc., and effective feature expressions can be obtained by learning and training a large amount of data to achieve tasks such as classification and recognition of audio signals. It is also possible to extract the teacher's voice and the student's voice by segmenting the audio. Signal processing technology can be used, such as threshold-based or model-based voice activity detection algorithms.

[0040] The voices of teachers and students in the classroom can be identified based on one or more of the spectral features, intensity features, and speech rate features. First, the audio needs to be processed and analyzed. This can be achieved by using audio processing libraries or algorithms, such as the librosa library in Python or spectrum analysis algorithms based on FFT (Fast Fourier Transform).

[0041] The audio analysis results are obtained based on the duration and frequency of the teacher's and the student's voices. For example, the teacher speaks for 20 minutes and 213 times, while the student speaks for 3 minutes and 12 times.

[0042] S230. Calculate a teaching score result based on the teaching interaction record, the action analysis result and the audio analysis result.

[0043] In the disclosed embodiment, the teaching interaction score can be determined according to the number of teaching interaction records. For example, the teaching interaction score of the same value can be determined directly according to the number. For example, if 15 interactions are performed, the teaching interaction score is 15. It can also be calculated based on a preset coefficient.

[0044] According to the types and numbers of different actions included in the action analysis results, the first teaching state score is determined. Since the identified actions may have positive or negative meanings for the teaching effect, and the degree of representation is also different. Therefore, based on the types of different actions included in the action analysis results, different scoring values ​​can be assigned. For example, the action of entering the classroom can add one point, the action of leaving the classroom can subtract one point, and the action of raising the hand can add one point. Then, combined with the number of actions, the first teaching state score can be determined. The types of actions contained in the action analysis results are not specifically limited here.

[0045] According to the duration and frequency of the teacher's voice and the student's voice described in the audio analysis results, the second teaching state score is determined. The scoring data can be calculated by designing a scoring model or algorithm, which includes weight setting, feature normalization and other steps. For example, the numerical values ​​of the duration and frequency of the teacher's voice and the student's voice can be directly used as scoring parameters to obtain the second teaching state score. Finally, the teaching score result is calculated based on the teaching interaction score, the first teaching state score, and the second teaching state score. Among them, it can be directly added or different weight values ​​can be configured.

[0046] S240: Determine at least one target course from a plurality of offline courses according to the teaching scoring result.

[0047] Through the above steps, the corresponding teaching rating results are determined for the multiple offline courses that need to be evaluated. It can be that at least one target course is screened out from multiple offline courses based on the teaching rating results corresponding to the multiple offline courses and a preset threshold. For example, the preset threshold is 100, the rating of offline course A is 120, the rating of offline course B is 95, the rating of offline course C is 86, and the rating of offline course D is 75. Then offline course A can be used as the target course.

[0048] Alternatively, at least one target course may be obtained by screening multiple offline courses based on the teaching rating results corresponding to multiple offline courses and a preset threshold. The multiple teaching rating results may be sorted based on the teaching rating results corresponding to multiple offline courses; Alternatively, a preset value may be combined to screen a corresponding number of target courses from multiple offline courses. The disclosed embodiment is not limited here.

[0049] S250: recommending an online course obtained by recording the target course in a preset webpage.

[0050] In the disclosed embodiment, the online course is obtained based on the recording of the offline course, and the recorded content may be only the scene of the teacher teaching, such as the podium and blackboard area, and may not include students and other scenes.

[0051] The recommendation in the preset web page can be that after the target course is determined, the information corresponding to the target course, such as images and text, is displayed at the top of the web page in a prominent position to distinguish the position from other courses. Alternatively, the target course and other courses are displayed crosswise on the page without distinguishing the position area, but displayed in a prominent manner, such as highlighting and enlarging the display, etc.

[0052] Interaction records can be used as an important criterion for evaluating the quality of offline courses. Different interaction records have different significance for teaching evaluation. If each interaction record is used with the same importance to evaluate teaching, the evaluation results will be inaccurate.

[0053] Based on this, the embodiment of the present disclosure also proposes an implementation method of an intelligent recommendation method based on teaching big data. The step of determining the teaching interaction score according to the number of the teaching interaction records includes: S310, determining different types of the teaching interaction records, and configuring different weight values ​​based on the different types; S320. Calculate a teaching interaction score according to the types, corresponding quantities and corresponding weight values ​​of the teaching interaction records.

[0054] In the disclosed embodiment, different weight values ​​are configured based on different types of teaching interaction records. For example, a teaching interaction record may be a record of answering questions, which has a strong correlation with the teacher's teaching ability, classroom activity, student participation, etc., so the weight value may be 1.5. A teaching interaction record may be a discussion record, which has a correlation with the activity of the entire class, so the weight value may be 1.2. The disclosed embodiment does not limit the content and type of teaching interaction records.

[0055] By implementing the embodiments of the present disclosure, the types of teaching interaction records can be distinguished, and weight values ​​can be configured based on different types during data processing. This can take into account the significance of different interaction records for teaching evaluation, making the resulting teaching interaction scores more accurate.

[0056] Based on the same inventive concept as the intelligent recommendation method based on teaching big data in the aforementioned embodiment, the present application provides an intelligent recommendation device based on teaching big data. The specific description of the intelligent recommendation method based on teaching big data in the aforementioned embodiment is also applicable to the intelligent recommendation device based on teaching big data, and the device includes: Interaction record module, used to obtain teaching interaction records of offline courses; A video analysis module is used to obtain the teaching video corresponding to the offline course, and identify the teaching video to obtain action analysis results and audio analysis results; A teaching scoring module, used to calculate a teaching scoring result based on the teaching interaction record, the action analysis result and the audio analysis result; A target course determination module, used to determine at least one target course from a plurality of offline courses according to the teaching scoring result; The recommendation module is used to recommend the online courses recorded by the target courses in a preset web page.

[0057] Figure 4 The structural diagram of the computer system of the electronic device suitable for implementing the disclosed embodiment is shown. It should be noted that the computer system of the electronic device shown is only an example, and the function and scope of use of the disclosed embodiment should not be limited. As shown in the figure, the computer system includes a central processing unit (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) or the program loaded from the storage part into the random access memory (RAM). In the RAM, various programs and data required for system operation are also stored. The CPU, ROM and RAM are connected to each other via a bus. The input / output (I / O) interface is also connected to the bus.

[0058] The following components are connected to the I / O interface: an input section including a keyboard, a mouse, etc.; an output section including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section including a hard disk, etc.; and a communication section including a network interface card such as a LAN card, a modem, etc. The communication section performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as needed. Removable media, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., are installed on the drive as needed so that a computer program read therefrom is installed into the storage section as needed.

[0059] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible embodiments, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0060] The program product may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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. A computer readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program used by or in conjunction with an instruction execution system, device, or device. The program code contained on the readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above. The program code for performing the operation of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0061] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent recommendation method based on teaching big data, characterized in that: The method comprises: Obtain teaching interaction records of offline courses; Obtaining a teaching video corresponding to the offline course, and identifying the teaching video to obtain a motion analysis result and an audio analysis result; Calculate the teaching score result according to the teaching interaction record, the action analysis result and the audio analysis result; Determining at least one target course from a plurality of offline courses according to the teaching evaluation results; An online course obtained by recording the target course is recommended on a preset web page.

2. The method according to claim 1, characterized in that The step of obtaining the teaching interaction record of the offline course includes: Based on a preset teaching platform, obtaining interaction records of interactions conducted through the teaching platform; The teaching interaction record includes at least one of a sign-in record and a speech record.

3. The method according to claim 1, characterized in that The step of identifying the teaching video to obtain the action analysis result includes: Extracting key frames from the teaching video and identifying key points of the human body in the key frames; Obtaining a motion analysis result according to the key points of the human body; The action analysis result includes at least one of the actions of entering a course, leaving a class, and raising a hand.

4. The method according to claim 3, characterized in that The step of identifying the teaching video to obtain an audio analysis result comprises: Extracting audio data from the teaching video, and identifying audio features in the audio data, wherein the audio features include at least one of a spectrum feature, an intensity feature, and a speech rate feature; Distinguishing the teacher's voice and the student's voice of the offline course according to the audio features; Based on the duration and frequency of the teacher's voice and the student's voice, the audio analysis result is statistically obtained.

5. The method according to claim 4, characterized in that The step of calculating the teaching score result according to the teaching interaction record, the action analysis result and the audio analysis result comprises: Determining a teaching interaction score according to the number of the teaching interaction records; Determining a first teaching state score according to the types and quantities of different actions included in the action analysis results; Determine a second teaching status score according to the duration and frequency of the teacher's voice and the student's voice in the audio analysis result; A teaching score result is calculated based on the teaching interaction score, the first teaching status score, and the second teaching status score.

6. The method according to claim 5, characterized in that The step of determining the teaching interaction score according to the number of the teaching interaction records comprises: Determine different types of the teaching interaction records, and configure different weight values ​​based on the different types; The teaching interaction score is calculated based on the various types, corresponding quantities and corresponding weight values ​​of the teaching interaction records.

7. The method according to claim 1, characterized in that The step of determining at least one target course from a plurality of offline courses according to the teaching scoring result comprises: At least one target course is obtained by screening the multiple offline courses according to the teaching score results corresponding to the multiple offline courses and in combination with a preset threshold.

8. The method according to claim 1, characterized in that: The step of determining at least one target course from a plurality of offline courses according to the teaching scoring result comprises: According to the teaching evaluation results corresponding to multiple offline courses, multiple teaching evaluation results are sorted; Combined with a preset value, a corresponding number of target courses are obtained by screening out multiple offline courses.

9. The method according to claim 1, characterized in that: The step of recommending the online course obtained by recording the target course in the preset webpage includes: Displaying the online course obtained by recording the target course in a prominent position or in a prominent manner on a preset webpage; The highlighted position includes a top position, and the highlighted manner includes one of highlight display and enlarged display.

10. A server, characterized in that: The server includes a processor, a machine-readable storage medium and a network interface. The machine-readable storage medium, the network interface and the processor are connected via a bus system. The network interface is used to communicate with at least one teaching data capture device. The machine-readable storage medium is used to store programs, instructions or codes. The processor is used to execute the programs, instructions or codes in the machine-readable storage medium to execute the intelligent recommendation method based on teaching big data according to any one of claims 1 to 9.

Images