Course recommendation method, system, terminal and storage medium

Abstract

The present invention discloses a course recommendation method, system, terminal and storage medium, the method comprising: obtaining the user's historical meeting data, the historical meeting data including the active time, number of interactions, subjective rating after the meeting and the meeting start time period when attending each meeting; determining the user's content tag of interest based on the historical meeting data and the preset content tags of the attended meeting, the content tag of interest is the preset content tag corresponding to the maximum value obtained by scoring the preset content tags based on the historical meeting data; pushing the target course matching the content tag of interest to the user from the current training meeting. The technical solution of the present application can achieve targeted recommendation of training courses based on the user's characteristics in a video training meeting.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a course recommendation method, system, terminal and storage medium. Background Art

[0002] In recent years, companies have actively encouraged employees to participate in online video training meetings in order to strengthen talent training. Video conferencing refers to a meeting in which people in two or more locations have face-to-face conversations through communication equipment and the Internet. Depending on the number of participating locations, video conferencing can be divided into point-to-point conferencing and multi-point conferencing. At present, since video training meetings directly share videos or share the speaker's screen, it is impossible to push learning courses in a targeted manner during video training meetings. Summary of the invention

[0003] The embodiments of the present application provide a course recommendation method, system, terminal and storage medium, aiming to solve the problem that learning courses cannot be pushed in a targeted manner in video training conferences.

[0004] The present application embodiment provides a course recommendation method, the course recommendation method comprising:

[0005] Obtain the user's historical meeting data, which includes the active time, number of interactions, subjective ratings after the meeting, and the meeting start time period during each meeting;

[0006] Determine the user's content tag of interest based on the historical meeting attendance data and preset content tags of the attended meeting, where the content tag of interest is a preset content tag corresponding to the maximum value obtained by scoring the preset content tags based on the historical meeting attendance data;

[0007] A target course matching the content-of-interest tag is pushed to the user from the current training meeting.

[0008] In one embodiment, after the step of pushing the target course matching the interesting content tag to the user from the current training meeting, the following steps are included:

[0009] Determine all users to whom the target course is pushed;

[0010] The virtual room of the target course is recommended to all the users, so that the users can enter the virtual room through the shortcut entrance of the target course.

[0011] In one embodiment, after the step of recommending the virtual room of the target course to all the users, the method further includes:

[0012] Determine the most active virtual room and the real-time hot topics in the virtual room;

[0013] Pushing the real-time hot topic to the initiating conference terminal of the current training conference, so that the initiating conference terminal determines adjustment suggestions for the conference content of the current training conference based on the real-time hot topic;

[0014] Alternatively, the real-time hot topic is pushed to a receiving conference terminal of the current training conference, and a dialog box between users is established at the receiving conference terminal, so that the real-time hot topic can be discussed at the receiving conference terminal based on the dialog box.

[0015] In one embodiment, the step of determining the user's content tags of interest based on the historical conference attendance data and preset content tags of the attended conferences includes:

[0016] The weight values ​​of the historical conference attendance data are used to optimize the scores of the corresponding historical conference attendance data to obtain target scores of the historical conference attendance data;

[0017] Determine the score of the preset content tag of the conference associated with each of the historical conference attendance data by using the weighted value of the target score of each of the historical conference attendance data;

[0018] The preset content label corresponding to the maximum value among the scores is determined as the content label of interest to the user.

[0019] In one embodiment, before the step of optimizing the scores of the corresponding historical conference attendance data using the weight values ​​of the historical conference attendance data to obtain the target scores of the historical conference attendance data, the step further includes:

[0020] Generate a judgment matrix according to the scores of each of the historical meeting attendance data;

[0021] The judgment matrix is ​​used to perform a square root operation to obtain a weight value corresponding to each of the historical meeting attendance data.

[0022] In one embodiment, after the step of performing a square root operation using the judgment matrix to obtain a weight value corresponding to each of the historical conference attendance data, the step further includes:

[0023] Determine the maximum eigenvalue in the eigenvector of each of the historical conference attendance data;

[0024] Determine a consistency index and a random consistency index based on the maximum eigenvalue and the historical meeting attendance data;

[0025] Determining a consistency ratio according to a ratio of the consistency index to the random consistency index;

[0026] When the consistency ratio is less than a preset value, the weight values ​​are determined to be consistent, and the step of using the weight values ​​of each of the historical meeting attendance data to optimize the corresponding scores of the historical meeting attendance data to obtain the target scores of each of the historical meeting attendance data is performed.

[0027] In one embodiment, the step of obtaining the user's historical conference attendance data includes:

[0028] Obtain the user's active time, number of interactions, subjective ratings after the meeting, and meeting start time for each meeting;

[0029] The historical meeting attendance data of the user is determined according to the average of the active duration, the number of interactions, the subjective score after the meeting, and the start time period of the meeting.

[0030] In addition, to achieve the above purpose, the present invention also provides a course recommendation system, which includes:

[0031] An acquisition module is used to acquire the user's historical meeting data, wherein the historical meeting data includes the active time, number of interactions, subjective rating after the meeting, and the meeting start time period when attending each meeting;

[0032] A determination module, configured to determine a content tag of interest to the user based on the historical meeting attendance data and preset content tags of the attended meeting, wherein the content tag of interest is a preset content tag corresponding to a maximum value obtained by scoring the preset content tags based on the historical meeting attendance data;

[0033] A push module is used to push a target course matching the content-of-interest tag to the user from a current training session.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also provides an intelligent terminal, which includes: a memory, a processor, and a course recommendation program stored in the memory and executable on the processor, and the course recommendation program implements the steps of the above-mentioned course recommendation method when executed by the processor.

[0035] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which a course recommendation program is stored, and when the course recommendation program is executed by a processor, the steps of the above-mentioned course recommendation method are implemented.

[0036] A technical solution of a course recommendation method, system, terminal and storage medium provided in the embodiments of the present application adopts the method of obtaining the user's historical meeting data, wherein the historical meeting data includes the active time, number of interactions, subjective rating after the meeting and the starting time period of the meeting; the user's content tag of interest is determined according to the historical meeting data and the preset content tags of the attended meetings, and the content tag of interest is the preset content tag corresponding to the maximum value obtained by scoring the preset content tags according to the historical meeting data; the technical solution of pushing the target course matching the content tag of interest to the user from the current training meeting, can achieve targeted course recommendation because the target course can be determined in combination with the user's historical meeting data. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of the structure of an intelligent terminal involved in an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of a flow chart of a first embodiment of a course recommendation method of the present invention;

[0039] Figure 3 This is a functional module diagram of the course recommendation system of the present invention;

[0040] Figure 4 This is a schematic diagram of a video conferencing module of the present invention;

[0041] Figure 5 A schematic diagram of a chat interaction interface of the course recommendation method of the present invention;

[0042] Figure 6 It is a schematic diagram of the overall flow of the course recommendation method of the present invention.

[0043] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings are only an embodiment diagram, not the entire invention. DETAILED DESCRIPTION

[0044] In order to solve the problem that learning courses cannot be pushed in a targeted manner in video training meetings. This application proposes a course recommendation method, which obtains the user's historical meeting data, and the historical meeting data includes the active time, number of interactions, subjective scores after the meeting, and the start time period of the meeting when attending each meeting; according to the historical meeting data and the preset content tags of the attended meetings, the user's content tags of interest are determined, and the content tags of interest are preset content tags corresponding to the maximum value obtained by scoring the preset content tags according to the historical meeting data; a technical solution for pushing target courses matching the content tags of interest to the user from the current training meeting. Since the target course can be determined in combination with the user's historical meeting data, targeted course recommendations can be achieved.

[0045] In order to better understand the above technical solution, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0046] like Figure 1 As shown, Figure 1 It is a schematic diagram of the structure of the hardware operating environment involved in the embodiment of the present invention.

[0047] It should be noted that Figure 1 This is a structural diagram of the hardware operating environment of the smart terminal.

[0048] like Figure 1 As shown, the intelligent terminal may include: a processor 1001, such as a CPU, a memory 1005, a user interface 1003, a network interface 1004, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0049] Those skilled in the art will understand that Figure 1The structure of the smart terminal shown in the figure does not constitute a limitation on the smart terminal, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0050] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module and a course recommendation program. The operating system is a program that manages and controls the hardware and software resources of the intelligent terminal, the course recommendation program and the operation of other software or programs.

[0051] exist Figure 1 In the smart terminal shown, the user interface 1003 is mainly used to connect to the terminal and communicate data with the terminal; the network interface 1004 is mainly used for the background server and communicates data with the background server; the processor 1001 can be used to call the course recommendation program stored in the memory 1005.

[0052] In this embodiment, the intelligent terminal includes: a memory 1005, a processor 1001, and a course recommendation program stored in the memory and executable on the processor, wherein:

[0053] When the processor 1001 calls the course recommendation program stored in the memory 1005, the following operations are performed:

[0054] Obtain the user's historical meeting data, which includes the active time, number of interactions, subjective ratings after the meeting, and the meeting start time period during each meeting;

[0055] Determine the user's content tag of interest based on the historical meeting attendance data and preset content tags of the attended meeting, where the content tag of interest is a preset content tag corresponding to the maximum value obtained by scoring the preset content tags based on the historical meeting attendance data;

[0056] A target course matching the content-of-interest tag is pushed to the user from the current training meeting.

[0057] When the processor 1001 calls the course recommendation program stored in the memory 1005, it also performs the following operations:

[0058] Determine all users to whom the target course is pushed;

[0059] The virtual room of the target course is recommended to all the users, so that the users can enter the virtual room through the shortcut entrance of the target course.

[0060] When the processor 1001 calls the course recommendation program stored in the memory 1005, it also performs the following operations:

[0061] Determine the most active virtual room and the real-time hot topics in the virtual room;

[0062] Pushing the real-time hot topic to the initiating conference terminal of the current training conference, so that the initiating conference terminal determines adjustment suggestions for the conference content of the current training conference based on the real-time hot topic;

[0063] Alternatively, the real-time hot topic is pushed to a receiving conference terminal of the current training conference, and a dialog box between users is established at the receiving conference terminal, so that the real-time hot topic can be discussed at the receiving conference terminal based on the dialog box.

[0064] When the processor 1001 calls the course recommendation program stored in the memory 1005, it also performs the following operations:

[0065] The weight values ​​of the historical conference attendance data are used to optimize the scores of the corresponding historical conference attendance data to obtain target scores of the historical conference attendance data;

[0066] Determine the score of the preset content tag of the conference associated with each of the historical conference attendance data by using the weighted value of the target score of each of the historical conference attendance data;

[0067] The preset content label corresponding to the maximum value among the scores is determined as the content label of interest to the user.

[0068] When the processor 1001 calls the course recommendation program stored in the memory 1005, it also performs the following operations:

[0069] Generate a judgment matrix according to the scores of each of the historical meeting attendance data;

[0070] The judgment matrix is ​​used to perform a square root operation to obtain a weight value corresponding to each of the historical meeting attendance data.

[0071] When the processor 1001 calls the course recommendation program stored in the memory 1005, it also performs the following operations:

[0072] Determine the maximum eigenvalue in the eigenvector of each of the historical conference attendance data;

[0073] Determine a consistency index and a random consistency index based on the maximum eigenvalue and the historical meeting attendance data;

[0074] Determining a consistency ratio according to a ratio of the consistency index to the random consistency index;

[0075] When the consistency ratio is less than a preset value, the weight values ​​are determined to be consistent, and the step of using the weight values ​​of each of the historical meeting attendance data to optimize the corresponding scores of the historical meeting attendance data is performed to obtain the target scores of each of the historical meeting attendance data.

[0076] When the processor 1001 calls the course recommendation program stored in the memory 1005, it also performs the following operations:

[0077] Obtain the user's active time, number of interactions, subjective ratings after the meeting, and meeting start time for each meeting;

[0078] The historical meeting attendance data of the user is determined according to the average of the active duration, the number of interactions, the subjective score after the meeting, and the start time period of the meeting.

[0079] The technical solution of the present application will be introduced below in the form of embodiments.

[0080] like Figure 2 As shown, in the first embodiment of the present application, the course recommendation method of the present application includes the following steps:

[0081] Step S110, obtaining the user's historical meeting data, wherein the historical meeting data includes the active time, number of interactions, subjective ratings after the meeting, and the meeting start time period when attending each meeting.

[0082] In this embodiment, the historical meeting attendance data is the information when the user attended the historical training meeting. The historical meeting attendance data includes at least the meeting ID of each historical training meeting attended by the user, the active time span of the user in each historical training meeting, the number of interactions of the user in each historical training meeting, the subjective score of the user after the end of each historical training meeting, and the meeting start time period time of the user in each historical training meeting. The historical meeting attendance data of each historical training meeting attended by the user participating in the current training meeting can be obtained. The historical meeting attendance data can be bound to the user account and the meeting ID. The historical meeting attendance data can be uploaded to the cloud for storage after the user finishes attending the meeting, or stored in the local database after the user finishes attending the meeting. The user's historical meeting attendance data can be obtained from the cloud or the local database based on the user identity.

[0083] Step S120, determining the user's content tag of interest based on the historical meeting data and preset content tags of the attended meeting, wherein the content tag of interest is a preset content tag corresponding to the maximum value obtained by scoring the preset content tags based on the historical meeting data.

[0084] In this embodiment, each historical training meeting has a corresponding preset content tag, and the preset content tag is determined according to the meeting theme content of the historical training meeting. A preset content tag system is established through the meeting theme content, so that each training meeting has a corresponding preset content tag Tag. And establish an association between the preset content tag corresponding to the user's historical training meeting and the historical attendance data of the historical training meeting. For example, TagN: [Span, Frequency, Score, Time].

[0085] In this embodiment, after obtaining the historical attendance data of the historical training conferences attended by the user, the user's content tags of interest are determined based on the historical attendance data and the preset content tags of the conferences attended. Specifically, the rating values ​​of the preset content tags of each conference attended by the user are calculated based on the historical attendance data, the preset content tag corresponding to the maximum rating value is obtained from the rating values ​​of the preset content tags of all conferences, and the preset content tag corresponding to the maximum rating value is determined as the user's content tag of interest.

[0086] Step S130: Pushing a target course matching the content-of-interest tag to the user from the current training meeting.

[0087] In this embodiment, after obtaining the user's content tag of interest, the target course associated with the content tag of interest is obtained. The target course associated with the content tag of interest is pushed to the user in the current training meeting. Thus, the effect of recommending the corresponding target course according to the characteristics of each user in the current training meeting is achieved.

[0088] Specifically, after determining the user's content of interest tags, when a video training meeting has a gap in the sharing process, or when the training meeting is detected to be paused, or when the current bandwidth is detected to be reduced, the video conference training recommendation module will obtain the target course that matches the user's content of interest tags from the cloud. Specifically, matching the current user's content of interest tags, the video conference training recommendation module will obtain the target course that matches the user's content of interest tags from the cloud, and push the target course to the user. Figure 4 , conferences attended by different users have different preset content tags, so as to achieve the purpose of pushing target courses according to user characteristics.

[0089] In this embodiment, refer to Figure 4After pushing the target course, the recommended course sub-screen can be displayed on the current conference display interface. If the user is interested in the target course, by clicking the target course play button, the sub-screen will be expanded on the current video conference main interface to play the target course, ensuring that the user can conduct selective learning and training without affecting the current video conference. If the user refuses to click the target course play button, the sub-screen will be hidden.

[0090] In the above-mentioned technical scheme of the present embodiment, since the user's content tags of interest are determined based on the user's historical attendance data and the preset content tags of the meetings attended by the user, and then the target courses associated with the user's content tags of interest are pushed in the current training meeting, the target courses can be determined in combination with the characteristics of different users, thereby realizing targeted course recommendations.

[0091] In one embodiment, obtaining the user's historical conference attendance data specifically includes the following steps:

[0092] Step S111, obtaining the user's active time, number of interactions, subjective score after the meeting, and meeting start time period when participating in each meeting;

[0093] Step S112, determining the historical meeting attendance data of the user according to the active duration, the number of interactions, the subjective score after the meeting, and the average of the meeting start time period.

[0094] In this embodiment, the active time of the user corresponding to the historical training meeting, the number of interactions of the user, the post-meeting score of the user, and the meeting start time associated with the user can be stored in the cloud server or the local server after the end of the historical training meeting. In the current training meeting, when the current training meeting is stuck or paused, the active time, number of interactions, post-meeting score, and meeting start time corresponding to the historical training meeting associated with the user's account can be obtained from the cloud server or the local server to further determine the historical meeting data.

[0095] In this embodiment, since the same conference theme content may exist in all historical training meetings attended by the same user, that is, the same preset content tag exists. Therefore, after obtaining the active time of the user corresponding to each historical training meeting, the number of interactions of the user, the post-meeting score of the user, and the meeting start time associated with the user, the historical training meetings with the same preset content tag are classified. Then, the historical meeting data is determined according to the historical training meetings under different preset content tags after classification. For example, the average value of all historical training meetings under each category can be taken to determine the historical meeting data of the user. For example, the user has participated in the meeting with the preset content tag TagA N times, and the calculation is as follows: TagA: [Span1+…+SpanN / N, Frequency1+…+FrequencyN / N, core1+…+ScoreN / N, Time1+…+TimeN / N], that is, TagA: [SpanAVG, FrequencyAVG, ScoreAVG, TimeAVG]. The preset content tags of the user are calculated in sequence, which are referred to as follows: TagX: [SpanAVG, FrequencyAVG, ScoreAVG, TimeAVG]. In this way, there are a total of X preset content tags for the user, and each preset content tag contains different historical meeting data Span, Frequency, Score, and Time.

[0096] According to the above technical solution, this embodiment can specifically determine the historical attendance data of each historical training meeting attended by the user based on the relevant information of the historical training meetings of the user.

[0097] In one embodiment, determining the user's content tags of interest based on the historical conference attendance data and preset content tags of the attended conferences specifically includes the following steps:

[0098] Step S121, using the weight value of each of the historical conference attendance data to optimize the corresponding score of the historical conference attendance data, to obtain the target score of each of the historical conference attendance data;

[0099] Step S122, determining the score of the preset content tag of the conference associated with each of the historical conference attendance data by using the weighted value of the target score of each of the historical conference attendance data;

[0100] Step S123: determining the preset content label corresponding to the maximum value among the scores as the content label of interest to the user.

[0101] In this embodiment, after determining the preset content label, each historical meeting attendance data under the preset content label can be scored based on experience, that is, the score of each historical meeting attendance data can be determined. However, since the weight values ​​of each historical meeting attendance data are different, it is necessary to further optimize the score of the corresponding historical meeting attendance data in combination with the weight value of the historical meeting attendance data after determining the score of the historical meeting attendance data, so as to obtain the target score of each historical meeting attendance data. Each historical meeting attendance data has a corresponding weight value, which can be determined according to the AHP hierarchical analysis method.

[0102] In this embodiment, after determining the target score of each historical meeting data, the target score of each historical meeting data is added to obtain a weighted value, that is, the score corresponding to the preset content tag of the meeting associated with each historical meeting data is determined according to the weighted value of the target score of each historical meeting data.

[0103] In this embodiment, after obtaining the scores corresponding to the preset content tags corresponding to the respective conferences, the preset content tag corresponding to the maximum score is determined as the user's interested content tag.

[0104] According to the above technical solution, this embodiment uses the weight value of each historical meeting data to optimize the score of the historical meeting data, and then determines the score of the preset content tag of the meeting associated with each historical meeting data according to the weighted value of the target score obtained after the optimization of each historical meeting data. The preset content tag with the largest score is determined as the user's content tag of interest, thereby determining the user's content tag of interest.

[0105] In one embodiment, before the step of using the weight value of each of the historical conference attendance data to optimize the score of the corresponding historical conference attendance data and obtaining the target score of each of the historical conference attendance data, the weight value of each of the historical conference attendance data is determined, which specifically includes the following steps:

[0106] Step S210, generating a judgment matrix according to the scores of each of the historical meeting attendance data;

[0107] Step S220: Perform a square root operation using the judgment matrix to obtain a weight value corresponding to each of the historical conference attendance data.

[0108] In this embodiment, after determining the preset content label, each historical meeting data under the preset content label can be scored according to experience, that is, the score of each historical meeting data can be determined. Taking the four historical meeting data of Span, Frequency, Score, and Time in this application as an example, by scoring the above four historical meeting data (the lowest is 1 point and the highest is 5 points), and combining the expert scoring, the following judgment matrix table is finally obtained:

[0109] Time Span Frequency Score Time 1.000 0.250 0.333 0.500 Span 4.000 1.000 1.000 1.000 Frequency 3.000 1.000 1.000 1.000 Score 2.000 1.000 1.000 1.000

[0110] After obtaining the judgment matrix, a square root operation is performed according to the scores of the historical meeting attendance data in the judgment matrix to obtain the weight value corresponding to each historical meeting attendance data. The square root operation is an AHP hierarchical analysis operation. The AHP hierarchical analysis operation is as follows:

[0111]

[0112] From the above table, we can see that a 4-order judgment matrix is ​​constructed for a total of 4 items, namely Time, Span, Frequency, and Score, and the AHP hierarchical method is used to study it. The characteristic vector obtained by analysis is (0.452, 1.414, 1.316, 1.189), and the corresponding weight values ​​of Time, Span, Frequency, and Score are 10.336%, 32.352%, 30.107%, and 27.205%, respectively.

[0113] In one embodiment, after the judgment matrix is ​​used to perform a square root operation to obtain the weight values ​​corresponding to each of the historical conference attendance data, that is, after the weight values ​​corresponding to each of the historical conference attendance data are determined, the consistency of the weight values ​​needs to be checked, which specifically includes the following steps:

[0114] Step S230, determining the maximum eigenvalue in the eigenvector of each of the historical conference attendance data;

[0115] In this embodiment, after determining the weight value of each historical conference attendance data, it is also necessary to determine whether the weight value is consistent. Specifically, after determining the feature vector of each historical conference attendance data, the maximum feature root is determined according to the feature vector. For example, the maximum feature root determined by the feature vector in the above embodiment is 4.046.

[0116] Step S240, determining a consistency index and a random consistency index based on the maximum eigenvalue and the historical meeting attendance data;

[0117] In this embodiment, after determining the maximum eigenvalue, the consistency index (i.e., CI) is further calculated based on the maximum eigenvalue. Wherein, CI = (maximum eigenvalue - n) / (n - 1), the CI value is used for the consistency check of the subsequent weight value, and n represents the number of historical meeting data. The above consistency index calculation formula can be used to obtain a consistency index of 0.015.

[0118] In this embodiment, while determining the consistency index, a random consistency index (i.e., RI) can also be determined. The random consistency index corresponding to the historical meeting attendance data can be searched in a preset random consistency table. Among them, the random consistency table stores the mapping relationship between the number of historical meeting attendance data and the random consistency index. When the number of historical meeting attendance data is determined, the corresponding random consistency index can be determined. For example, when the number of historical meeting attendance data determined above is 4, the corresponding random consistency index obtained by the search is 0.890.

[0119] Step S250: determining a consistency ratio according to a ratio of the consistency index to the random consistency index.

[0120] In this embodiment, after obtaining the consistency index and the random consistency index, the consistency ratio (CR) is determined according to the ratio between the consistency index and the random consistency index. The consistency index obtained above is 0.015, the random consistency index is 0.890, and the consistency ratio obtained is 0.017.

[0121] Step S260, when the consistency ratio is less than a preset value, it is determined that the weight values ​​are consistent, and step S121 is executed to optimize the scores of the corresponding historical conference attendance data using the weight values ​​of the historical conference attendance data to obtain target scores of the historical conference attendance data;

[0122] In this embodiment, after obtaining the consistency ratio, the smaller the consistency ratio is, the better the consistency of the judgment matrix is. Generally, if the consistency ratio is less than the preset value of 0.1, the judgment matrix satisfies the consistency test; if the consistency ratio is greater than the preset value of 0.1, it means that there is no consistency, and the judgment matrix should be properly adjusted and analyzed again. The consistency index calculated for the 4th-order judgment matrix is ​​0.015, and the random consistency index table lookup is 0.890. Therefore, the calculated consistency ratio is 0.017<0.1, which means that the judgment matrix satisfies the consistency test and the calculated weight value is consistent. The target score of the historical meeting data is determined based on the score of the historical meeting data and the weight value of the historical meeting data.

[0123] In this embodiment, the weight values ​​corresponding to Span, Frequency, Score, and Time are determined by the AHP hierarchical analysis method. For each preset content tag TagX, the weight value can be used to optimize the score of the corresponding historical meeting data to obtain the target score of each historical meeting data; the target score of each historical meeting data is weighted and summed to calculate the score of the preset content tag of the meeting associated with each historical meeting data, for example:

[0124] Performance=Span*0.3235+Frequency*0.3011+Score*0.2720+Time*0.1034.

[0125] Based on the above technical solution, this application implements consistency verification of the weight values ​​of historical attendance data.

[0126] In one embodiment, the course recommendation method further includes:

[0127] Step S110, obtaining the user's historical meeting data, wherein the historical meeting data includes the active time, number of interactions, subjective rating after the meeting, and meeting start time period when attending each meeting;

[0128] Step S120, determining the user's content tag of interest based on the historical meeting data and the preset content tags of the attended meeting, wherein the content tag of interest is the preset content tag corresponding to the maximum value obtained by scoring the preset content tags based on the historical meeting data;

[0129] Step S130, pushing a target course matching the content tag of interest to the user from the current training meeting;

[0130] Step S140, determining all users to whom the target course is pushed;

[0131] Step S150, recommending the virtual room of the target course to all the users, so that the users can enter the virtual room through the shortcut entrance of the target course.

[0132] In this embodiment, by recording the target courses recommended by all current users, a recommended course list List[CourseA, CourseB, ..., CourseN] for the current training meeting can be obtained, where CourseA is the target course of user A, and CourseN is the target course of user N. The users who participate in the target course CourseA are counted and analyzed, and a virtual room RoomA is established based on this, which is a shortcut entry to the target course. The entry can be a display interface of the target course or a control that is used to link the display interface of the target course. The shortcut entry to the target course can be displayed on the current video conference display interface of the user's terminal device. Room RoomA contains all users currently participating in the target course CourseA, and a user list PeersA[A1, A2, ..., An] is obtained. Similarly, a room RoomN is created, and its corresponding user list PeersN[N1, N2, ..., Nn]. Finally, the rooms [RoomA, RoomB, ..., RoomN] corresponding to the current N target courses can be generated in real time. Through program processing, these virtual room information are pushed to each receiving conference terminal. For user A, the corresponding receiving conference terminal will display the room information of the current participating course [RoomA, RoomB, ...RoomN]. User A is interested in the relevant content of the recommended course CourseB, and can click on the room information of RoomB to enter the chat interaction interface of RoomB. For details, refer to Figure 5 .

[0133] In this embodiment, in Room B, user A can ask other users in the current Room B for information about Course B, or can consult other information. For each user, the theme of the corresponding target course can reflect the tag attribute used by the user. According to the theme of the user's target course and the theme of the meeting the user attends, all users in the meeting can be divided into topics, thereby dividing M communication room topics, where M<=N, N is the number of users, that is, the number of target courses. When specifically dividing, the similarity of each user's topic features can be determined by calculating the feature similarity distance, so that those with a smaller similarity distance can be divided into the same room.

[0134] According to the above technical solution, this embodiment pushes training courses according to user characteristics during the gap period of the video conference, and creates virtual rooms according to the target courses, so that users who participate in the recommended course learning can choose to enter different rooms for communication and interaction.

[0135] In one embodiment, the course recommendation method further includes:

[0136] Step S110, obtaining the user's historical meeting data, wherein the historical meeting data includes the active time, number of interactions, subjective rating after the meeting, and meeting start time period when attending each meeting;

[0137] Step S120, determining the user's content tag of interest based on the historical meeting data and the preset content tags of the attended meeting, wherein the content tag of interest is the preset content tag corresponding to the maximum value obtained by scoring the preset content tags based on the historical meeting data;

[0138] Step S130, pushing a target course matching the content tag of interest to the user from the current training meeting;

[0139] Step S140, determining all users to whom the target course is pushed;

[0140] Step S150, recommending the virtual room of the target course to all the users, so that the users can enter the virtual room through the quick entrance of the target course;

[0141] Step S160, determining the virtual room with the highest current activity and the real-time hot topics in the virtual room;

[0142] Step S170, pushing the real-time hot topic to the initiating conference terminal of the current training conference, so that the initiating conference terminal determines adjustment suggestions for the conference content of the current training conference based on the real-time hot topic;

[0143] Alternatively, in step S180, the real-time hot topic is pushed to a receiving conference terminal of the current training conference, and a dialog box is established between users at the receiving conference terminal, so that the real-time hot topic can be discussed at the receiving conference terminal based on the dialog box.

[0144] In this embodiment, refer to Figure 6 , by real-time monitoring of the number of people in each recommended room, the amount of speech, the length of the room, and other indicators, the virtual room of the target course with the highest current activity is calculated, such as the activity of room RoomA, ActivationA, so that the activity list List[ActivationA, ActivationB, ..., ActivationM] of all rooms can be obtained, and the room with the highest activity RoomActivationMax is selected. By counting and analyzing the speeches, comments in the room, and the topic of the current room, a real-time hot topic can be determined. This real-time hot topic will be pushed to the terminal that initiated the current meeting, which is the terminal where the conference host is located. The conference host can choose to appropriately adjust the current conference content based on the current real-time hot topic.

[0145] Alternatively, you can choose to push the current real-time hot topic to the receiving conference terminal of the current training conference, which is the terminal where other users participating in the current training conference are located except the conference host. A dialog box for user dialogue is established on each receiving conference terminal, so that users can discuss and communicate based on the dialog box, thereby maximizing learning efficiency.

[0146] According to the above technical solution, this embodiment obtains the most active virtual room and the real-time hotspot of the current room through data statistical analysis, and the program pushes the real-time hotspot to the conference initiating terminal or receiving conference terminal of the current training meeting, thereby improving the learning efficiency of the participants and livening up the learning atmosphere.

[0147] The embodiment of the present invention provides an embodiment of the course recommendation method. It should be noted that although a logical order is shown in the flow chart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0148] like Figure 3 As shown, the present application provides a course recommendation system, which includes:

[0149] The acquisition module 10 is used to obtain the user's historical meeting data, and the historical meeting data includes the active time, number of interactions, subjective score after the meeting, and the meeting start time period when participating in each meeting. In one embodiment, the acquisition module 10 is used to obtain the active time, number of interactions, subjective score after the meeting, and the meeting start time period when the user participates in each meeting; the user's historical meeting data is determined according to the average of the active time, the number of interactions, the subjective score after the meeting, and the meeting start time period.

[0150] The determination module 20 is used to determine the user's content tag of interest based on the historical meeting data and the preset content tags of the attended meetings. The content tag of interest is the preset content tag corresponding to the maximum value obtained by scoring the preset content tags based on the historical meeting data. In one embodiment, the determination module 20 is used to optimize the score of the corresponding historical meeting data using the weight value of each of the historical meeting data to obtain the target score of each of the historical meeting data; determine the score of the preset content tag of the meeting associated with each of the historical meeting data by the weighted value of the target score of each of the historical meeting data; and determine the preset content tag corresponding to the maximum value in the score as the user's content tag of interest. In one embodiment, the determination module 20 is used to generate a judgment matrix based on the score of each of the historical meeting data; and perform a square root operation using the judgment matrix to obtain the weight value corresponding to each of the historical meeting data. In one embodiment, the determination module 20 is used to determine the maximum eigenroot value in the eigenvector of each of the historical meeting attendance data; determine a consistency index and a random consistency index based on the maximum eigenroot value and the historical meeting attendance data; determine a consistency ratio according to the ratio of the consistency index to the random consistency index; when the consistency ratio is less than a preset value, determine that the weight value is consistent, and execute the step of using the weight value of each of the historical meeting attendance data to optimize the corresponding score of the historical meeting attendance data to obtain the target score of each of the historical meeting attendance data.

[0151] The push module 30 is used to push the target course matching the content-of-interest tag to the user from the current training meeting.

[0152] In one embodiment, after the push module 30, a recommendation module is also connected, and the recommendation module is used to determine all users to push the target course; recommend the virtual room of the target course to all the users, so that the users can enter the virtual room through the shortcut entrance of the target course.

[0153] In one embodiment, a second push module is connected after the recommendation module, and the second push module is used to determine the virtual room with the highest current activity and the real-time hot topics in the virtual room; push the real-time hot topics to the initiating conference terminal of the current training meeting, so that the initiating conference terminal can determine adjustment suggestions for the meeting content of the current training meeting based on the real-time hot topics; or, push the real-time hot topics to the receiving conference terminal of the current training meeting, and establish a dialog box between users at the receiving conference terminal, so that the receiving conference terminal can discuss the real-time hot topics based on the dialog box.

[0154] The specific implementation of the course recommendation system of the present invention is basically the same as the various embodiments of the above-mentioned course recommendation method, and will not be repeated here.

[0155] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium, which stores a course recommendation program. When the course recommendation program is executed by a processor, it implements the various steps of the course recommendation method described above and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0156] Since the storage medium provided in the embodiments of the present application is the storage medium used to implement the method of the embodiments of the present application, based on the method introduced in the embodiments of the present application, the person skilled in the art can understand the specific structure and deformation of the storage medium, so it is not repeated here. All storage media used in the methods of the embodiments of the present application belong to the scope of protection of this application.

[0157] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0158] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0159] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0161] It should be noted that in the claims, any reference signs placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0162] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0163] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A course recommendation method, characterized in that: The course recommendation method includes: Obtain the user's historical meeting data, which includes the active time, number of interactions, subjective ratings after the meeting, and the meeting start time period during each meeting; Determine the user's content tag of interest based on the historical meeting attendance data and preset content tags of the attended meeting, where the content tag of interest is a preset content tag corresponding to the maximum value obtained by scoring the preset content tags based on the historical meeting attendance data; Pushing a target course matching the content-of-interest tag to the user from a current training session; The sub-screen of the target course is displayed on the display interface of the current training meeting, and when a click operation of a play button of the target course is received, the target course is simultaneously played on the sub-screen.

2. The course recommendation method according to claim 1, characterized in that: After the step of pushing the target course matching the interested content tag to the user from the current training meeting, the method further includes: Determine all users to whom the target course is pushed; The virtual room of the target course is recommended to all the users, so that the users can enter the virtual room through the shortcut entrance of the target course.

3. The course recommendation method according to claim 2, characterized in that: After recommending the virtual room of the target course to all the users, the method further includes: Determine the most active virtual room and the real-time hot topics in the virtual room; Pushing the real-time hot topic to the initiating conference terminal of the current training conference, so that the initiating conference terminal determines adjustment suggestions for the conference content of the current training conference based on the real-time hot topic; Alternatively, the real-time hot topic is pushed to a receiving conference terminal of the current training conference, and a dialog box between users is established at the receiving conference terminal, so that the real-time hot topic can be discussed at the receiving conference terminal based on the dialog box.

4. The course recommendation method according to claim 1, characterized in that: The step of determining the user's content tags of interest based on the historical meeting attendance data and preset content tags of the attended meetings includes: The weight values ​​of the historical conference attendance data are used to optimize the scores of the corresponding historical conference attendance data to obtain target scores of the historical conference attendance data; Determine the score of the preset content tag of the conference associated with each of the historical conference attendance data by using the weighted value of the target score of each of the historical conference attendance data; The preset content label corresponding to the maximum value among the scores is determined as the content label of interest to the user.

5. The course recommendation method according to claim 4, characterized in that: Before the step of optimizing the scores of the corresponding historical conference attendance data by using the weight values ​​of the historical conference attendance data to obtain the target scores of the historical conference attendance data, the method further includes: Generate a judgment matrix according to the scores of each of the historical meeting attendance data; The judgment matrix is ​​used to perform a square root operation to obtain a weight value corresponding to each of the historical meeting attendance data.

6. The course recommendation method according to claim 5, characterized in that: After the step of using the judgment matrix to perform a square root operation to obtain a weight value corresponding to each of the historical meeting attendance data, the method further includes: Determine the maximum eigenvalue in the eigenvector of each of the historical conference attendance data; Determine a consistency index and a random consistency index based on the maximum eigenvalue and the historical meeting attendance data; Determining a consistency ratio according to a ratio of the consistency index to the random consistency index; When the consistency ratio is less than a preset value, the weight values ​​are determined to be consistent, and the step of using the weight values ​​of each of the historical meeting attendance data to optimize the corresponding scores of the historical meeting attendance data to obtain the target scores of each of the historical meeting attendance data is performed.

7. The course recommendation method according to claim 1, characterized in that: The step of obtaining the user's historical conference attendance data includes: Obtain the user's active time, number of interactions, subjective ratings after the meeting, and meeting start time for each meeting; The historical meeting attendance data of the user is determined according to the average of the active duration, the number of interactions, the subjective score after the meeting, and the start time period of the meeting.

8. A course recommendation system, characterized in that: The course recommendation system includes: An acquisition module is used to acquire the user's historical meeting data, wherein the historical meeting data includes the active time, number of interactions, subjective rating after the meeting, and the meeting start time period when attending each meeting; A determination module, configured to determine a content tag of interest to the user based on the historical meeting attendance data and preset content tags of the attended meeting, wherein the content tag of interest is a preset content tag corresponding to a maximum value obtained by scoring the preset content tags based on the historical meeting attendance data; A push module, used for pushing a target course matching the content-of-interest tag to the user from a current training session; The sub-screen of the target course is displayed on the display interface of the current training meeting, and when a click operation of a play button of the target course is received, the target course is simultaneously played on the sub-screen.

9. An intelligent terminal, characterized in that: The intelligent terminal includes: a memory, a processor, and a course recommendation program stored in the memory and executable on the processor. When the course recommendation program is executed by the processor, the steps of the course recommendation method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a course recommendation program, and when the course recommendation program is executed by a processor, the steps of the course recommendation method described in any one of claims 1 to 7 are implemented.

Images