Online interactive method, system, device and storage medium based on data analysis

Abstract

The present invention provides an online interactive method, system, device and storage medium based on data analysis, the method comprising: receiving a question request and corresponding question data from a teacher terminal, parsing the question data to obtain a course ID; querying the ID of the current online student from the course management server according to the course ID; calculating the matching degree between the question data and each current online student; selecting students who answer questions in descending order according to the matching degree, and sending answer reminders to the corresponding student terminals. By adopting the scheme of the present invention, students who answer questions are automatically selected based on data analysis, and answer reminders are automatically sent to student terminals without the need for manual operation by teachers, thereby improving the user experience and improving the pertinence and effectiveness of the interactive process.

Description

Background Art

[0002] Online education means that both teachers and students can enter the classroom on their own user terminals and connect to the server through the Internet to achieve online teaching. During the course, in order to enhance the interactivity of teaching, some question sessions are often added. During the teacher's teaching process, in order to ensure the audio quality, all students will be muted. When a student needs to answer a question, the microphone function corresponding to the student will be turned on. Specifically, during a multi-person interactive class, the teacher will ask each student about a certain knowledge point. Currently, the teacher generally randomly selects a student to answer, or arranges each student to answer in turn. On the one hand, this method requires teachers to manually select students to answer questions, which is more complicated to operate and does not provide a good user experience for teachers. On the other hand, the teacher's questions to students lack pertinence and randomness, and cannot achieve a good interactive effect. Summary of the invention

[0003] In response to the problems in the prior art, the purpose of the present invention is to provide an online interactive method, system, device and storage medium based on data analysis, which automatically selects students who answer questions based on data analysis and automatically sends answer reminders to student terminals without the need for manual operation by the teacher.

[0004] An embodiment of the present invention provides an online interactive method based on data analysis, the method comprising the following steps:

[0005] Receive a question request and corresponding question data from the teacher terminal, and parse the question data to obtain a course ID;

[0006] Query the ID of the current online student from the course management server according to the course ID;

[0007] Calculating the matching degree between the question data and each current online student;

[0008] Students who answer the questions are selected in order from high to low according to the matching degree, and answer reminders are sent to the corresponding student terminals.

[0009] Optionally, the calculating the matching degree between the question data and each current online student comprises the following steps:

[0010] Parsing the question data to obtain the currently used courseware ID;

[0011] Querying from the courseware management server to obtain a plurality of knowledge points corresponding to the courseware ID and keywords of each knowledge point;

[0012] Analyze the question data to obtain question keywords;

[0013] Compare the question keywords with the keywords of each knowledge point corresponding to the courseware ID to determine the knowledge point closest to the question keywords;

[0014] The matching degree between the closest knowledge point and each current online student is calculated as the matching degree between the question data and each current online student.

[0015] Optionally, calculating the matching degree between the closest knowledge point and each current online student includes the following steps:

[0016] Query the category x1 to which the closest knowledge point belongs;

[0017] Obtaining preset weak knowledge point categories x2 and familiar knowledge point categories x3 of each current online student from the user management server;

[0018] According to the preset mapping relationship between the knowledge point category and the knowledge point feature vector, the feature vectors y1, y2 and y3 corresponding to the category x1, category x2 and category x3 are obtained respectively;

[0019] The acquired feature vectors y1, y2 and y3 are combined and input into a trained matching calculation model to obtain a matching value output by the matching calculation model, where the matching calculation model is a model constructed and trained based on deep learning.

[0020] Optionally, after sending the answer reminder to the corresponding student terminal, the following steps are also included:

[0021] Receive student answer confirmation data from the teacher terminal to determine whether the student's answer is correct;

[0022] Sending the student's answer results and the corresponding knowledge point categories to the user management server;

[0023] The user management server is configured to count the knowledge point categories with the most wrong answers and the knowledge point categories with the most correct answers in the course answer data of each student at preset time intervals, and use them as the student's weak knowledge point category x2 and familiar knowledge point category x3 respectively.

[0024] Optionally, calculating the matching degree between the closest knowledge point and each current online student includes the following steps:

[0025] Query the category to which the closest knowledge point belongs, and obtain the historical error rate of the current online student corresponding to the category from the user management server;

[0026] The matching degree between the closest knowledge point and each current online student is determined according to the historical error rate, and the historical error rate is positively correlated with the matching degree.

[0027] Optionally, after sending the answer reminder to the corresponding student terminal, the following steps are also included:

[0028] Receive student answer confirmation data from the teacher terminal to determine whether the student's answer is correct;

[0029] Sending the student's answer results and the corresponding knowledge point categories to the user management server;

[0030] The user management server is configured to determine whether each student has a new answer result for each knowledge point category at a preset interval, and if so, update the student's historical error rate for the knowledge point category according to the new student answer result.

[0031] Optionally, the step of selecting students who answer questions according to the matching degree from high to low includes the following steps:

[0032] Obtaining the importance value of the closest knowledge point in the courseware from the courseware management server;

[0033] According to the mapping relationship between the preset importance value and the number of questioners, the number of questioners m is determined;

[0034] According to the matching degree, m students are selected from high to low.

[0035] Optionally, the determining the number of questioners m and selecting m students from high to low according to the matching degree further includes the following steps:

[0036] Count the number of knowledge points that have been answered in the current courseware (a) and the number of knowledge points that have not been answered (b);

[0037] The remaining time t2 of the plan is calculated using the following formula:

[0038] t2=t1*b / (a+b)

[0039] Among them, t1 is the total duration of the preset course;

[0040] Obtain the remaining time t3 of the current course from the course management server;

[0041] If the remaining time t2 is greater than the remaining time t3, and t2-t3 is greater than the preset time threshold, the number of questioners m is reduced;

[0042] If the remaining time t2 is less than the remaining time t3, and t3-t2 is greater than the preset time threshold, the number of questioners m is increased.

[0043] Optionally, analyzing the question data to obtain question keywords includes segmenting the question data, removing words that meet preset deletion conditions from the segmented results, and using the remaining words as question keywords;

[0044] Comparing the question keywords with the keywords of each knowledge point corresponding to the courseware ID includes the following steps:

[0045] For each knowledge point corresponding to the courseware ID, count the number of keywords n that overlap with the question keyword;

[0046] The knowledge point with the highest number n of overlapping keywords is selected as the closest knowledge point.

[0047] The embodiment of the present invention further provides an online interactive system based on data analysis, which is applied to the online interactive method based on data analysis, and the system includes:

[0048] The first communication module is used to interact with the teacher terminal, receive a question request and corresponding question data from the teacher terminal, and parse the question data to obtain a course ID;

[0049] A second communication module is used to interact with the course management server and query the ID of the current online student from the course management server according to the course ID when the first communication module receives a question request;

[0050] An answer selection module is used to calculate the matching degree between the question data and each current online student, and select the student who answers the question from high to low according to the matching degree;

[0051] The third communication module is used to interact with the student terminal and send the answer reminder to the student terminal selected by the answer selection module.

[0052] The embodiment of the present invention further provides an online interactive device based on data analysis, comprising:

[0053] processor;

[0054] a memory storing executable instructions of the processor;

[0055] Wherein, the processor is configured to perform the steps of the online interactive method based on data analysis by executing the executable instructions.

[0056] An embodiment of the present invention also provides a computer-readable storage medium for storing a program, which, when executed, implements the steps of the online interactive method based on data analysis.

[0057] 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.

[0058] The online interactive method, system, device and storage medium based on data analysis provided by the present invention have the following advantages:

[0059] The present invention solves the problems in the prior art by calculating the matching degree between questions and students based on data analysis, and automatically selecting students to answer questions according to the matching degree. After the students have made their selections, answer reminders are automatically sent to the student terminals without the need for manual operation by teachers, thus reducing the number of manual operation steps for teachers during the teaching process, improving the automation of online courses, enhancing the user experience, and improving the pertinence and effectiveness of the interactive process. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Other features, objectives and advantages of the present invention will become more apparent from a reading of the detailed description of non-limiting embodiments made with reference to the following accompanying drawings.

[0061] Figure 1 is a flow chart of an online interactive method based on data analysis according to an embodiment of the present invention;

[0062] Figure 2 is a structural diagram of an online interactive system based on data analysis according to an embodiment of the present invention;

[0063] Figure 3 is a schematic diagram of data interaction between an online interactive system based on data analysis and various servers according to an embodiment of the present invention;

[0064] Figure 4 is a flow chart of calculating the matching degree between a question and a student according to an embodiment of the present invention;

[0065] Figure 5 is a flow chart of calculating the closest knowledge point and student matching degree according to an embodiment of the present invention;

[0066] Figure 6 is another flow chart for calculating the closest knowledge point and student matching degree according to an embodiment of the present invention;

[0067] Figure 7 is a flow chart of students selecting answers according to an embodiment of the present invention;

[0068] Figure 8 is a flow chart of adjusting the number of students according to course progress according to an embodiment of the present invention;

[0069] Fig. 9 is a schematic diagram of an online interactive device based on data analysis according to an embodiment of the present invention;

[0070] Fig.10 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention. DETAILED DESCRIPTION

[0071] 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 limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0072] 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.

[0073] like Figure 1 As shown, in order to solve the above technical problems, an embodiment of the present invention provides an online interactive method based on data analysis, and the method includes the following steps:

[0074] S100: receiving a question request and corresponding question data from a teacher terminal, and parsing the question data to obtain a course ID; the teacher terminal is a terminal device used by the teacher during class, including but not limited to a mobile phone, tablet computer, laptop computer, etc. used by the teacher;

[0075] The question data may include a course ID and question content, and the question content may be audio collected by a microphone of a teacher's terminal, or text input content collected by a keyboard of a teacher's terminal;

[0076] S200: querying the ID of the current online student from the course management server according to the course ID, wherein the course management server is configured to manage the currently ongoing course and implement interaction between the teacher terminal and the student terminal through the course management server, wherein the current online student is the student currently attending the course;

[0077] S300: Calculating the matching degree between the question data and each current online student;

[0078] S400: Students who answer questions are selected in order from high to low according to the matching degree, and answer reminders are sent to corresponding student terminals. The student terminals are terminal devices used by students during class, including but not limited to mobile phones, tablet computers, laptops, etc. used by students.

[0079] Furthermore, in step S400, after the answer reminder is sent to the corresponding student terminal, the microphone function corresponding to the student terminal of the answering student can be automatically turned on. Automatically turning on the microphone function of the student terminal here can be sending a notification of turning on the microphone function of the student terminal to the course management server, and the course management server is configured to receive the student voice data collected by the microphone of the student terminal from the student terminal, and push it to the teacher terminal, or push it to the teacher terminal and all student terminals currently in class.

[0080] Therefore, the online interactive method of the present invention first obtains the question request and question data sent by the teacher terminal through step S100, and then queries the ID of the current online student through step S200, that is, determines the ID of the student who can currently choose to answer, and then calculates the matching degree between the question and the student through step S300, and automatically selects the student who answers according to the matching degree through step S400, preferably the student with a relatively high matching degree, and after selecting the student who answers, automatically sends the answer reminder to the corresponding student terminal, thereby realizing the automation of the question process without manual operation by the teacher. For the teacher, it is only necessary to issue a question request through a button or a specific operation on the teacher terminal, and record or enter the question content to start the question process, and subsequent operations are all automatically performed. And in the present invention, the student who selects the answer is selected according to the matching degree, preferably the student with a high matching degree, to improve the pertinence of the question and answer, so as to further improve the interactive effect in the online classroom.

[0081] like Figure 2 As shown, the embodiment of the present invention also provides an online interactive system M100 based on data analysis, which is applied to the online interactive method based on data analysis. Figure 3 FIG. 1 is a schematic diagram of data interaction between an online interactive system M100 based on data analysis and various servers of the present invention. The system includes:

[0082] The first communication module M110 is used to interact with the teacher terminal M200, receive a question request and corresponding question data from the teacher terminal, and parse the question data to obtain a course ID;

[0083] The second communication module M120 is used to interact with the course management server M400, and when the first communication module receives a question request, query the ID of the current online student from the course management server M400 according to the course ID;

[0084] The answer selection module M130 is used to calculate the matching degree between the question data and each current online student, and select the student who answers the question from high to low according to the matching degree;

[0085] The third communication module M140 is used to interact with the student terminal M300 and send the answer reminder to the student terminal selected by the answer selection module.

[0086] Therefore, the online interactive system of the present invention first obtains the question request and question data sent by the teacher terminal through the first communication module M100, and then queries the ID of the current online student through the second communication module M200, that is, determines the ID of the student who can currently choose to answer, and then calculates the matching degree between the question and the student through the answer selection module M300, and automatically selects the student who answers according to the matching degree, preferably the student with a relatively high matching degree, and after selecting the student who answers, automatically sends the answer reminder to the corresponding student terminal through the third communication module M300, thereby realizing the automation of the questioning process without the need for manual operation by the teacher.

[0087] like Figure 3 As shown, the online interactive system also communicates and interacts with the courseware management server M500. The courseware management server M500 is configured to manage the data of all coursewares, and the courseware data specifically includes multiple knowledge points preset in the courseware and keywords for each knowledge point. Specifically, the online interactive system may also include a fourth communication module for interacting with the courseware management server M500.

[0088] like Figure 4 As shown, in this embodiment, the step S300: calculating the matching degree between the question data and each current online student includes the following steps:

[0089] S310: parsing the question data to obtain the currently used courseware ID;

[0090] S320: Querying and obtaining multiple knowledge points and keywords of each knowledge point corresponding to the courseware ID from the courseware management server; the courseware management server is configured to pre-store multiple knowledge points and keywords of each knowledge point included in each courseware;

[0091] S330: Analyze the question data to obtain question keywords;

[0092] S340: Compare the question keyword with the keywords of each knowledge point corresponding to the courseware ID to determine the knowledge point closest to the question keyword;

[0093] S350: Calculate the matching degree between the closest knowledge point and each current online student as the matching degree between the question data and each current online student, thereby converting the matching degree between the question and the student into the matching degree between the knowledge point and the student for calculation.

[0094] Therefore, the present invention further converts the matching degree between questions and students into the matching degree between knowledge points and students through the above steps S310-S350, and gives priority to students with high matching degree with knowledge points to ask questions, thereby improving the pertinence of questions asked in interactive classes and enhancing the consolidation effect of questions.

[0095] like Figure 3 As shown, the online interactive system also communicates and interacts with the user management server M600. The user management server M600 is configured to manage the personal data of each student user, for example, it can manage the personal information of each student (including name, gender, hobbies, etc.), and can further manage the historical course data of each student, including the performance of each class, the completion of each homework, etc. Specifically, the online interactive system can also include a fifth communication module for interacting with the user management server M600.

[0096] In one implementation, a machine learning model can be used to calculate the matching degree between knowledge points and students. Specifically, Figure 5 As shown, the step S350: calculating the matching degree between the closest knowledge point and each current online student may include the following steps:

[0097] S351-A: Query the category x1 to which the closest knowledge point belongs. For example, multiple categories are pre-set: present progressive grammar category, past tense grammar category, interview English category, telephone conference language category, etc. The category of each knowledge point can be pre-stored in the courseware management server M500, and the category x1 to which the closest knowledge point belongs can be queried in the courseware management server M500 through the fourth communication module;

[0098] S352-A: Obtaining preset weak knowledge point categories x2 and familiar knowledge point categories x3 of each current online student from the user management server;

[0099] Here, the weak knowledge point category x2 and the familiar knowledge point category x3 may be preset by the user, or may be obtained based on the analysis of the user's historical course data;

[0100] S353-A: According to the preset mapping relationship between the knowledge point category and the knowledge point feature vector, respectively obtain the feature vectors y1, y2 and y3 corresponding to the category x1, category x2 and category x3;

[0101] Here, the mapping relationship between the knowledge point category and the knowledge point feature vector is pre-set, that is, the corresponding feature vector is pre-set for each knowledge point category;

[0102] S354-A: Combine the acquired feature vectors y1, y2 and y3 and input them into a trained matching calculation model to obtain a matching value output by the matching calculation model, where the matching calculation model is a model constructed and trained based on deep learning.

[0103] The matching degree calculation model can be, for example, a convolutional neural network model. After the model is constructed based on the convolutional neural network, multiple combined feature vectors are collected in advance, and the matching degree values ​​are marked and added to the training set. The convolutional neural network model is trained using the training set using a gradient descent method until the loss function value is less than a preset loss threshold, thereby obtaining a trained matching degree calculation model.

[0104] Therefore, the present invention adopts a matching degree calculation model based on machine learning, which can more accurately and quickly calculate the matching degree between knowledge points and students, and then obtain the matching degree between questions and students. It can more objectively and specifically select the most matching students to push answer reminder information.

[0105] When training the matching degree calculation model, the training set can be partially derived from the real historical course data of students, and the matching degree can be manually marked, so as to obtain a more objective and accurate matching degree calculation model. It can also be modified according to the real historical course data of students to obtain a new combined feature vector, and the matching degree can be manually marked, so as to expand the training set of the matching degree calculation model, which is more conducive to the rapid training of the model to convergence.

[0106] In this embodiment, after the step S400: sending the answer reminder to the corresponding student terminal, the following steps are also included:

[0107] S510: receiving the student's answer confirmation data from the teacher terminal, and determining whether the student's answer is correct; after receiving the student's answer data (audio, video or text), the teacher can click the answer confirmation button on the teacher terminal and select whether the answer is correct;

[0108] S520: Send the student's answer result and the corresponding knowledge point category to the user management server. The user management server stores the student's answer result and the corresponding knowledge point category as the student's historical course data.

[0109] The user management server is configured to count the knowledge point categories with the most wrong answers and the knowledge point categories with the most correct answers in the course answer data of each student at preset time intervals, and use them as the student's weak knowledge point category x2 and familiar knowledge point category x3 respectively.

[0110] In another implementation of this embodiment, the matching degree may also be calculated based on the historical error rate of the student's category associated with the closest knowledge point. Figure 6 As shown, the step S350: calculating the matching degree between the closest knowledge point and each current online student may also include the following steps:

[0111] S351-B: Query the category to which the closest knowledge point belongs. Similarly, the category of each knowledge point can be pre-stored in the courseware management server M500, and the category to which the closest knowledge point belongs can be queried in the courseware management server M500 through the fourth communication module;

[0112] S352-B: Obtain the historical error rate of the current online student corresponding to the category from the user management server; the historical error rate is equal to the ratio of the number of times the online student has previously answered questions of the category incorrectly to the total number of times the online student has answered questions of the category;

[0113] S353-B: Determine the matching degree between the closest knowledge point and each current online student according to the historical error rate, wherein the historical error rate is positively correlated with the matching degree. That is, the higher the historical error rate, the higher the matching degree. Specifically, for a student, the historical error rate is proportional to the matching degree. Specifically, the reciprocal of the historical error rate can be used as the matching degree between the closest knowledge point and the student, or the reciprocal of the historical error rate can be further multiplied by a preset coefficient as the matching degree between the closest knowledge point and the student.

[0114] Corresponding to the implementation method of calculating the matching degree between knowledge points and students, the user management server can also be configured to determine whether each student has a new answer result for each knowledge point category at a preset interval, and if so, update the student's historical error rate for the knowledge point category according to the new student answer result, thereby ensuring the real-time update of the historical error rate of each student for each knowledge point category stored in the user management server. If a student previously had a high historical error rate for a category, but now has a lower historical error rate for the category after the update, it means that the student has a better grasp of the knowledge point, and the matching degree of the student with the questions in the category is correspondingly reduced.

[0115] like Figure 7As shown, in this embodiment, the step S400: selecting students who answer questions from high to low according to the matching degree includes the following steps:

[0116] S410: Querying the courseware management server to obtain the importance value of the closest knowledge point in the courseware;

[0117] S420: Determine the number of questions m according to a preset mapping relationship between the importance value and the number of questions asked;

[0118] S430: Select m students from high to low according to the matching degree.

[0119] like Figure 8 As shown, in this embodiment, the step S420: determining the number of questioners m and the step S430: selecting m students from high to low according to the matching degree, further includes the following steps:

[0120] S421: Counting the number a of knowledge points that have been asked questions and the number b of knowledge points that have not been asked questions in the currently used courseware;

[0121] S422: Calculate the remaining time t2 of the plan using the following formula:

[0122] t2=t1*b / (a+b)

[0123] Among them, t1 is the total duration of the preset course;

[0124] S423: Query the course management server to obtain the remaining time t3 of the current course;

[0125] S424: Determine whether the remaining time t2 is greater than the remaining time t3;

[0126] S425: If the remaining time t2 is greater than the remaining time t3, and t2-t3 is greater than the preset time threshold, it means that the current course progress is a bit slow and the course progress needs to be accelerated to prevent the course task from being unable to be completed. The number of questioners m can be reduced, for example, one can be reduced based on the original number of people m, or the reduction range can be selected according to the size of t2-t3. When the time t2-t3 is very long, a few more people can be reduced. By shortening the duration of the interactive session, the course can be completed on time to avoid affecting the normal progress of subsequent knowledge points. When the original number of people m is already 1, there is no need to further reduce it;

[0127] S426: If the remaining time t2 is less than the remaining time t3, and t3-t2 is greater than the preset time threshold, it means that the current course progress is a bit fast and the course progress can be appropriately slowed down. Then the number of questioners m can be increased, for example, one more person can be added based on the original number m, or the increase range can be selected according to the size of t3-t2. When the duration of t3-t2 is very large, a few more people to be asked questions can be added to further increase the duration of the interactive session. When the number m has reached the number of current online students, there is no need to continue to increase the number;

[0128] If the remaining time t2 is equal to the remaining time t3, or the absolute value of the time difference between the remaining time t2 and the remaining time t3 is less than or equal to the preset time threshold, the number of questioners m is kept unchanged.

[0129] Therefore, the present invention can calculate the planned remaining time by comparing the number of completed knowledge points a with the total number of all knowledge points a+b in the courseware, and then judge whether the current course progress meets the planned requirements by comparing the planned remaining time with the actual remaining time. And when the course progress deviates from the predetermined requirements, the course progress can be effectively adjusted by adjusting the number of questions asked to assist teachers in completing teaching tasks.

[0130] In this embodiment, the question data is analyzed to obtain question keywords, including segmenting the question data, removing words that meet the preset deletion conditions in the segmented results, and using the remaining words as question keywords. Here, the question data is segmented. If the question data is in English, the segmentation can be performed based on spaces, punctuation marks, etc. If the question data is in Chinese, the segmentation can be implemented by using methods such as Jieba segmentation. The words that meet the preset deletion conditions here generally refer to preset modal particles, conjunctions, etc.

[0131] The step S340: comparing the question keywords with the keywords of each knowledge point corresponding to the courseware ID, comprises the following steps:

[0132] For each knowledge point corresponding to the courseware ID, the number n of keywords that overlap with the question keyword is counted; the keyword overlap here can include not only the situation where a question keyword and a knowledge point keyword are completely consistent, but also the situation where a question keyword and a knowledge point keyword are pre-defined synonyms or near synonyms;

[0133] The knowledge point with the highest number n of overlapping keywords is selected as the closest knowledge point, so that the matching degree between the question and the student can be converted into the matching degree between the knowledge point and the student for calculation in step S350.

[0134] An embodiment of the present invention also provides an online interactive device based on data analysis, comprising a processor; a memory in which executable instructions of the processor are stored; wherein the processor is configured to execute the steps of the online interactive method based on data analysis by executing the executable instructions.

[0135] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0136] Refer to the following Fig. 9 The electronic device 600 according to this embodiment of the present invention is described. Fig. 9 The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0137] like Fig. 9 As shown, the electronic device 600 is in the form of a general computing device. The combination of the electronic device 600 may include but is not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform combinations (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0138] The storage unit stores a program code, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps of various exemplary embodiments of the present invention described in the above-mentioned online course resource processing method section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 Specifically, the processing unit 610 performs Figure 1 When performing each step in the above-mentioned online interactive method based on data analysis, the specific method of executing the steps can adopt the specific implementation method of each step, which will not be repeated here.

[0139] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0140] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0141] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0142] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0143] The embodiment of the present invention also provides a computer-readable storage medium for storing a program, which implements the steps of the online interactive method based on data analysis when executed. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of various exemplary embodiments of the present invention described in the above-mentioned online course resource processing method section of this specification.

[0144] refer to Fig.10As shown, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0145] The program product may use 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, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, 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.

[0146] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0147] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may 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. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0148] In summary, compared with the prior art, the online interactive method, system, device and storage medium based on data analysis provided by the present invention have the following advantages:

[0149] The present invention solves the problems in the prior art by calculating the matching degree between questions and students based on data analysis, and automatically selecting students to answer questions according to the matching degree. After the students have made their selections, answer reminders are automatically sent to the student terminals without the need for manual operation by teachers, thus reducing the number of manual operation steps for teachers during the teaching process, improving the automation of online courses, enhancing the user experience, and improving the pertinence and effectiveness of the interactive process.

[0150] The above contents are further detailed descriptions of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as falling within the protection scope of the present invention.

Claims

1. An online interactive method based on data analysis, characterized in that: The steps include: Receive a question request and corresponding question data from the teacher terminal, and parse the question data to obtain a course ID; Query the ID of the current online student from the course management server according to the course ID; Parsing the question data to obtain the currently used courseware ID; Querying from the courseware management server to obtain a plurality of knowledge points corresponding to the courseware ID and keywords of each knowledge point; Analyze the question data to obtain question keywords; Compare the question keywords with the keywords of each knowledge point corresponding to the courseware ID to determine the knowledge point closest to the question keywords; Calculating the matching degree between the closest knowledge point and each current online student as the matching degree between the question data and each current online student; Students who answer the questions are selected in order from high to low according to the matching degree between the question data and each current online student, and answer reminders are sent to the corresponding student terminals.

2. The online interactive method based on data analysis according to claim 1, characterized in that: Calculating the matching degree between the closest knowledge point and each current online student includes the following steps: Query the category x1 to which the closest knowledge point belongs; Obtaining preset weak knowledge point categories x2 and familiar knowledge point categories x3 of each current online student from the user management server; According to the preset mapping relationship between the knowledge point category and the knowledge point feature vector, the feature vectors y1, y2 and y3 corresponding to the category x1, category x2 and category x3 are obtained respectively; The acquired feature vectors y1, y2 and y3 are combined and input into a trained matching calculation model to obtain a matching value output by the matching calculation model, wherein the matching calculation model is a model constructed and trained based on deep learning, wherein the matching calculation model constructs a convolutional neural network model, collects multiple combined feature vectors in advance, marks the matching values, adds them to a training set, and uses the training set to train the convolutional neural network model using a gradient descent method until the loss function value is less than a preset loss threshold.

3. The online interactive method based on data analysis according to claim 2, characterized in that: After sending the answer reminder to the corresponding student terminal, the following steps are also included: Receive student answer confirmation data from the teacher terminal to determine whether the student's answer is correct; Sending the student's answer results and the corresponding knowledge point categories to the user management server; The user management server is configured to count the knowledge point categories with the most wrong answers and the knowledge point categories with the most correct answers in the course answer data of each student at preset time intervals, and use them as the student's weak knowledge point category x2 and familiar knowledge point category x3 respectively.

4. The online interactive method based on data analysis according to claim 1, characterized in that: Calculating the matching degree between the closest knowledge point and each current online student includes the following steps: Query the category to which the closest knowledge point belongs, and obtain the historical error rate of the current online student corresponding to the category from the user management server; The matching degree between the closest knowledge point and each current online student is determined according to the historical error rate, and the historical error rate is positively correlated with the matching degree.

5. The online interactive method based on data analysis according to claim 4, characterized in that: After sending the answer reminder to the corresponding student terminal, the following steps are also included: Receive student answer confirmation data from the teacher terminal to determine whether the student's answer is correct; Sending the student's answer results and the corresponding knowledge point categories to the user management server; The user management server is configured to determine whether each student has a new answer result for each knowledge point category at a preset interval, and if so, update the student's historical error rate for the knowledge point category according to the new student answer result.

6. The online interactive method based on data analysis according to claim 1, characterized in that: The step of selecting students who answer questions according to the matching degree from high to low includes the following steps: Obtaining the importance value of the closest knowledge point in the courseware from the courseware management server; According to the mapping relationship between the preset importance value and the number of questioners, the number of questioners m is determined; According to the matching degree, m students are selected from high to low.

7. The online interactive method based on data analysis according to claim 6, characterized in that: The step of determining the number of questioners m and selecting m students from high to low according to the matching degree also includes the following steps: Count the number of knowledge points that have been answered in the current courseware (a) and the number of knowledge points that have not been answered (b); The remaining time t2 of the plan is calculated using the following formula: t2=t1*b / (a+b) Among them, t1 is the total duration of the preset course; Obtain the remaining time t3 of the current course from the course management server; If the remaining time t2 is greater than the remaining time t3, and t2-t3 is greater than the preset time threshold, the number of questioners m is reduced; If the remaining time t2 is less than the remaining time t3, and t3-t2 is greater than the preset time threshold, the number of questioners m is increased.

8. The online interactive method based on data analysis according to claim 1, characterized in that: Analyzing the question data to obtain question keywords includes segmenting the question data, removing words that meet preset deletion conditions from the segmented results, and using the remaining words as question keywords; Comparing the question keywords with the keywords of each knowledge point corresponding to the courseware ID includes the following steps: For each knowledge point corresponding to the courseware ID, count the number of keywords n that overlap with the question keyword; The knowledge point with the highest number n of overlapping keywords is selected as the closest knowledge point.

9. An online interactive system based on data analysis, characterized in that: The online interactive method based on data analysis applied to any one of claims 1 to 8, wherein the system comprises: The first communication module is used to interact with the teacher terminal, receive a question request and corresponding question data from the teacher terminal, and parse the question data to obtain a course ID; A second communication module is used to interact with the course management server and query the ID of the current online student from the course management server according to the course ID when the first communication module receives a question request; An answer selection module is used to parse the question data to obtain the currently used courseware ID, query the courseware management server to obtain multiple knowledge points corresponding to the courseware ID and keywords of each knowledge point, analyze the question data to obtain question keywords, compare the question keywords with the keywords of each knowledge point corresponding to the courseware ID, determine the knowledge point closest to the question keyword, calculate the matching degree between the closest knowledge point and each current online student as the matching degree between the question data and each current online student, and select the student who answers the question from high to low according to the matching degree between the question data and each current online student; The third communication module is used to interact with the student terminal and send the answer reminder to the student terminal selected by the answer selection module.

10. An online interactive device based on data analysis, characterized in that: include: processor; a memory storing executable instructions of the processor; Wherein, the processor is configured to perform the steps of the online interactive method based on data analysis described in any one of claims 1 to 8 by executing the executable instructions.

11. A computer-readable storage medium for storing a program, characterized in that: When the program is executed, the steps of the online interactive method based on data analysis described in any one of claims 1 to 8 are implemented.

Images