Question and answer processing methods, devices and computer equipment

Abstract

This application proposes a question-and-answer processing method, apparatus, and computer device. During the process of outputting an explanatory video file for the content to be explained on a playback terminal, such as in virtual network teaching, if user-submitted question-and-answer information is collected, this application, based on artificial intelligence technology, first detects the matching degree between the content to be explained contained in the explanatory video file not yet output by the playback terminal and the question-and-answer information. Based on this matching degree, it controls when and how the playback terminal outputs response information for the question-and-answer information. This avoids directly outputting the response information fed back by the question-and-answer system after collecting the question-and-answer information, which could interfere with the explanatory content output by the playback terminal. This ensures teaching quality while meeting students' questioning needs.

Description

Technical Field

[0001] This application mainly relates to the field of intelligent education applications, and more specifically to a question-and-answer processing method, device, and computer equipment. Background Technology

[0002] With the development of multimedia network technology and artificial intelligence technology, virtual reality teaching has been widely used in intelligent online teaching. Virtual teachers, built based on virtual reality technology, replace real teachers to give lectures, reducing the pressure on teacher resources. Students can also interact and communicate with virtual teachers, such as answering student questions through a question-and-answer system, thereby improving the fun of virtual teaching and improving teaching quality.

[0003] In this scenario, the virtual teacher on the playback terminal delivers a lecture according to a fixed script. Students can ask questions at any time, and the virtual teacher will immediately answer based on the feedback from the question-and-answer system. While this allows for timely responses to student questions, it can lead to disorganized content and reduce the quality of teaching. Summary of the Invention

[0004] In view of this, in order to improve teaching quality, this application proposes a question-and-answer processing method, the method comprising:

[0005] Acquire question and answer information; wherein, the question and answer information is collected during the process of the playback terminal outputting the explanatory video file for the content to be explained;

[0006] The matching degree between the content to be explained contained in the explanation video file not output by the playback terminal and the question and answer information is detected.

[0007] Based on the matching degree, the playback terminal is controlled to output response information for the question and answer information.

[0008] Optionally, controlling the playback terminal to output response information for the question-and-answer information based on the matching degree includes:

[0009] It is determined that the content to be explained in the explanatory video file not output by the playback terminal contains answer content with a matching degree greater than or equal to the matching threshold of the question and answer information;

[0010] After detecting that the playback terminal outputs the answer content, control the playback terminal to interrupt the output of the explanation video file and output the reply information in response to the question and answer information;

[0011] The playback terminal is controlled to stop interrupting and continue outputting the explanatory video file.

[0012] Optionally, the output of response information to the question-and-answer information includes:

[0013] The question-and-answer information is input into a question-and-answer model for processing, and the output is a response generated based on the processing result; or...

[0014] Output a response message generated based on the answer content, relating to the question and answer information; or,

[0015] Based on a preset reply template, a confirmation message is generated to indicate whether the questioner understands the answer content.

[0016] The playback terminal is controlled to output the answer confirmation information;

[0017] In response to the "answered" instruction of the answer confirmation information, the step of controlling the playback terminal to end the interruption is executed, and the output of the explanation video file continues;

[0018] In response to an unanswered instruction regarding the answer confirmation information, output reply information based on the question-and-answer model for the question-and-answer information.

[0019] Optionally, the method further includes:

[0020] Configure question-and-answer identifiers for the question-and-answer information in the explanatory video file containing the answers.

[0021] If the terminal device detects that the explanatory video file it outputs is configured with the question and answer identifier, the step of controlling the playback terminal to interrupt the output of the explanatory video file and outputting reply information for the question and answer information is executed.

[0022] Optionally, the method further includes:

[0023] The playback terminal receives a cancellation request for the question-and-answer identifier; the cancellation request is generated by the playback terminal in response to a cancellation operation performed by the questioner on the question-and-answer information.

[0024] In response to the cancellation request, delete the configured question-and-answer identifier.

[0025] Optionally, if, in the case that the content to be explained contained in the explanatory video file not output by the playback terminal contains answer content with a matching degree greater than or equal to the matching threshold of the question and answer information, the method further includes:

[0026] The playback terminal is controlled to output an answer prompt message; wherein the answer prompt message is used to indicate that the unoutput explanatory video file contains the answer content, and no answer is given to the question and answer information at present.

[0027] Optionally, controlling the playback terminal to output response information for the question-and-answer information based on the matching degree further includes:

[0028] If the content to be explained in the explanatory video file not output by the playback terminal is found to have a matching degree with the question and answer information less than the matching threshold, then output the response information generated based on the question and answer model.

[0029] Optionally, the playback terminal outputs an explanatory video file for the content to be explained, including:

[0030] The receiving terminal device sends a narration request; the narration request carries a user identifier and an identifier of the content to be narrated;

[0031] In response to the explanation request, obtain the historical teaching data associated with the user identifier and the basic content to be explained associated with the content identifier;

[0032] Based on the historical teaching data and the basic content to be explained, generate content to be explained for the user identifier;

[0033] Construct a video explanation file for the content to be explained;

[0034] The instructional video file is sent to the playback terminal for output.

[0035] This application also proposes a question-and-answer processing apparatus, the apparatus comprising:

[0036] The question and answer information acquisition module is used to acquire question and answer information; wherein, the question and answer information is collected during the process of the playback terminal outputting the explanatory video file for the content to be explained;

[0037] The detection module is used to detect the degree of matching between the content to be explained contained in the explanation video file not output by the playback terminal and the question and answer information;

[0038] The response control module is used to control the playback terminal to output response information for the question and answer information based on the matching degree.

[0039] This application also proposes a computer device comprising: at least one memory and at least one processor, wherein:

[0040] The memory is used to store programs that implement the question-and-answer processing method described above;

[0041] The processor is used to load and execute the program stored in the memory to implement the question-and-answer processing method as described above.

[0042] This application also proposes a computer-readable storage medium having a computer program stored thereon, the computer program being loaded and executed by a processor to implement the question-and-answer processing method described above.

[0043] Therefore, this application provides a question-and-answer processing method, apparatus, and computer device. During the process of a playback terminal outputting a video file explaining the content to be explained, such as in virtual network teaching, when user-submitted question-and-answer information is collected, this application first detects the matching degree between the content to be explained contained in the video file not yet output by the playback terminal and the question-and-answer information. Based on this matching degree, it controls when and how the playback terminal outputs response information to the question-and-answer information. This avoids directly outputting the response information fed back by the question-and-answer system after collecting the question-and-answer information, which would interfere with the explanation content output by the playback terminal. This ensures teaching quality while meeting students' questioning needs. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0045] Figure 1 A flowchart illustrating an optional example of the question-and-answer processing method proposed in this application;

[0046] Figure 2 A flowchart illustrating yet another optional example of the question-and-answer processing method proposed in this application;

[0047] Figure 3 A flowchart illustrating yet another optional example of the question-and-answer processing method proposed in this application;

[0048] Figure 4 A flowchart illustrating yet another optional example of the question-and-answer processing method proposed in this application;

[0049] Figure 5 A schematic diagram of an optional example of the question-and-answer processing apparatus proposed in this application;

[0050] Figure 6 A schematic diagram of another optional example of the question-and-answer processing apparatus proposed in this application;

[0051] Figure 7 A schematic diagram of an optional example of the question-answering system proposed in this application;

[0052] Figure 8 A schematic diagram of the hardware structure of an optional example of a computer device suitable for the question-and-answer processing method proposed in this application;

[0053] Figure 9A schematic diagram of the hardware structure of another alternative example of a computer device suitable for the question-and-answer processing method proposed in this application. Detailed Implementation

[0054] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0055] Reference Figure 1 This is a flowchart illustrating an optional example of the question-and-answer processing method proposed in this application. This method can be executed by a server or a terminal with certain data processing capabilities, or it can be implemented through cooperation between the server and the client. This application does not limit the executing entity of the question-and-answer processing method and it can be determined as appropriate. Furthermore, this application is applicable to various question-and-answer scenarios. The following embodiments will use a virtual teaching scenario as an example for illustration. Figure 1 As shown, the method may include:

[0056] Step S11: Obtain question and answer information;

[0057] The embodiments of this application can be applied to virtual online teaching application scenarios based on artificial intelligence technology. In this application scenario, individual users can select online courses according to their personal time, preferences, etc.; for multiple people in the same space, they can select online courses through the playback terminal in that space, so that multiple people can learn together. This application does not limit the virtual online teaching scenario.

[0058] Compared to traditional live or recorded teaching by real teachers, the virtual online teaching scenario proposed in this application can be based on artificial intelligence technology to construct a virtual teacher for the online teaching. Users can set the virtual teacher's attributes (such as gender, voice, appearance, clothing, etc., which are not restricted in this application and can be determined as appropriate). Based on this, a personalized virtual teacher can be constructed so that the virtual teacher can interact with the user in a human-like real-time manner through voice and text, including but not limited to casual chat, knowledge Q&A, discussion and exchange, so as to improve the teaching fun and learning efficiency.

[0059] This application allows users to extract teacher images from text, images, videos, and other materials, and then re-edit them to generate virtual teachers. This application does not restrict the process of creating virtual teachers. Furthermore, for virtual teachers in online courses, users can directly use the default virtual teacher image; this application does not restrict this as well.

[0060] After selecting an online course, corresponding teaching materials can be obtained. Combined with the virtual teacher's attributes, explanatory video files for the content to be explained in the online course can be generated. For example, the server can generate audio data with configured acoustic characteristics (such as the aforementioned timbre) and interactive data of the virtual teacher for different content to be explained (such as body movement data, facial expression data, etc.) based on the configured virtual teacher's attributes and the content to be explained. The corresponding explanatory video files can then be generated based on this information. This application does not restrict the method of generating explanatory video files.

[0061] Afterwards, the server can send the generated instructional video file to the client that has selected the corresponding course, and the client will play the instructional video file. It can be understood that while the client is playing the instructional video file, the content to be explained is presented on the client's instructional interface so that the applicant (such as a student) can intuitively see the content. Simultaneously, the virtual teacher animation configured above can be output on the instructional interface, and the virtual teacher synchronously explains the presented content, that is, outputs the audio data of the presented content (which at least includes the instructional content, and may also include analysis content generated based on the instructional content, etc., as needed). This process is equivalent to a real teacher conducting online teaching. This application will not elaborate on the working principle of how to conduct virtual online teaching by constructing a virtual teacher.

[0062] Based on the above analysis, during the virtual teacher's teaching process, students (i.e., the users receiving instruction) can ask questions at any time. A local audio acquisition device (such as the student's terminal or the teacher's audio acquisition equipment) can collect the student's output question-and-answer audio signals and send them to the server to request corresponding response information. Therefore, the question-and-answer information obtained in step S11 of this application embodiment is collected during the playback of the video file explaining the content to be explained by the terminal. It can be question-and-answer audio signals or question-and-answer text information obtained by semantic recognition of the audio signals. The content of both is the same, and this application does not limit the file format of the question-and-answer information.

[0063] Step S12: Detect the matching degree between the content to be explained and the question and answer information contained in the explanation video file not output by the playback terminal;

[0064] Step S13: Based on the matching degree, control the playback terminal to output response information for the question and answer information.

[0065] To address the issue of question-and-answer systems directly outputting corresponding responses after acquiring question-and-answer information, which interferes with the virtual teacher's teaching process and reduces teaching quality, this application proposes to detect whether the content to be explained by the virtual teacher yet to be covered involves the answer to the question-and-answer information. Based on the detection results, the playback terminal can then control when and how to output the response to the question-and-answer information. This approach not only resolves the aforementioned interference in question-and-answer communication but also prevents the virtual teacher from repeatedly responding to the question-and-answer information, thus ensuring teaching quality.

[0066] Therefore, after obtaining the question and answer information from the questioner during the lecture, it is possible to determine the content to be explained contained in the unoutput lecture video file. The matching degree between the determined content to be explained and the question and answer information can be detected. For example, based on artificial intelligence technologies such as speech technology, natural language processing technology and / or machine learning algorithms, it can be detected whether the content to be explained contains the knowledge points involved in the question and answer information. If it does, the answer content for the knowledge points involved in the content to be explained can be further detected to answer the student's question. For example, based on the detection principle of the question and answer system, the matching degree between the answer content and the above-mentioned question and answer information can be obtained.

[0067] In some other embodiments, this application may also obtain the response information of the question and answer information through a question and answer system, and compare the response information with the above-mentioned answer content not output by the playback terminal, such as semantic similarity comparison, and the obtained comparison result represents the matching degree between the answer content and the question and answer information. This application does not limit the implementation method of the above step S12, including but not limited to the implementation method described above.

[0068] As analyzed above, the matching degree detected in step S12 of this application represents the probability that the content to be explained in the explanatory video file not yet output by the playback terminal can provide a response to the question. The higher the matching degree, the more likely the content to be explained is to answer the questioner's question (i.e., provide a response). In this case, after receiving the question-and-answer information, it is not necessary to immediately provide feedback from the question-and-answer system. Instead, the questioner can be informed that the relevant knowledge points will be explained later, and the answer will not be provided for now. For example, a response prompt message such as "This question involves knowledge points that will be explained later in this lesson; we will explain them in a moment. The teacher will continue the explanation" can be output to control the playback terminal to continue outputting the received explanatory video file, avoiding repeated answers to the question-and-answer information.

[0069] Conversely, the lower the detected matching degree, the more likely the content to be explained may not be able to answer students' questions. In this case, to reduce the waiting time for questioners and avoid confusion in the teaching content caused by answering questions, the playback terminal can be controlled to pause the output of the explanation video file and directly call the question-and-answer system to output the reply information of the question and answer. After answering the questioner's question, the playback terminal can be triggered to continue outputting the explanation video file, that is, to continue online teaching. However, it is not limited to this reply information output control method. For example, according to the teaching schedule, the questions and answers of each questioner can also be uniformly replied after the teaching ends. This application will not provide detailed examples here.

[0070] Reference Figure 2 This is a flowchart illustrating another optional example of the question-answering processing method proposed in this application. This embodiment can be an optional refined implementation of the question-answering processing method described above, but it is not limited to the refined implementation method described in this embodiment. Figure 2 As shown, the method may include:

[0071] Step S21: Obtain question and answer information;

[0072] Step S22: Detect the matching degree between the content to be explained and the question and answer information contained in the explanation video file not output by the playback terminal;

[0073] The implementation process of steps S21 and S22 can be referred to, but is not limited to, the description of the corresponding parts of the above embodiments. This embodiment will not describe them in detail.

[0074] Step S23: Determine that the content to be explained in the explanation video file not output by the playback terminal contains answer content with a matching degree greater than or equal to the matching threshold with the question and answer information, and control the playback terminal to continue outputting the explanation video file.

[0075] Based on the description of the relevant sections in the above embodiments, since the degree of matching between the content to be explained in the explanatory video file not output by the playback terminal and the question-and-answer information can indicate whether the content to be explained can answer the questioner's question, it can be determined whether it is necessary to call the question-and-answer system to obtain the response information for the question-and-answer information. Therefore, this application can predetermine the minimum matching degree of the explanatory content with the question-and-answer information that can serve as the answer content for the question-and-answer information, that is, predetermine the minimum matching degree of the explanatory content used to characterize the answer content that can serve as the answer content for the question-and-answer information, which is the matching threshold.

[0076] The aforementioned matching threshold can be obtained through experience, experimentation, or prediction based on artificial intelligence technology. This application does not limit the value of the matching threshold or the method of obtaining it. Furthermore, the predetermined value of the aforementioned matching threshold may be different or the same for different question-and-answer scenarios or different types of explanatory video files; this application does not impose any restrictions on this.

[0077] Based on the analysis of the matching threshold above, after obtaining the matching degree through step S22, the matching degree can be compared with the preset matching threshold. If the matching degree is greater than or equal to the matching threshold, it can be considered that the content to be explained contained in the explanation video file not yet output by the playback terminal can be used as or obtain the response information of the question and answer information. In other words, if the virtual teacher has not yet explained the knowledge points involving the question and answer information, in order to avoid repeated answers, the question and answer information can be temporarily left unanswered, and the playback terminal can continue to output the explanation video file.

[0078] Conversely, if the content to be explained in the explanatory video file not output by the playback terminal matches the question and answer information less than the above-mentioned matching threshold, it can be considered that the content not yet explained by the virtual teacher cannot answer the questioner's question. In this case, the question and answer system can be invoked, that is, the question and answer information is input into the pre-trained question and answer model, and the response information is output by the playback terminal. This application does not describe in detail the training process of the question and answer model of the question and answer system.

[0079] Specifically, when the detected matching degree is less than the aforementioned matching threshold, to avoid confusion in the explanation content caused by the playback terminal simultaneously outputting response information and the explanation video file, the playback terminal can pause the output of the explanation video file while outputting the response information. If an interrupt command for the explanation video file is executed, the interrupt is terminated upon detecting the playback terminal outputting response information, and the playback terminal is controlled to continue outputting the explanation video file. It should be noted that the implementation method for pausing the output of the explanation video file and resuming the output of the explanation video file after outputting response information includes, but is not limited to, the interrupt signal control implementation method described in this application.

[0080] Step S24: After detecting that the playback terminal outputs the answer content, control the playback terminal to interrupt the output of the explanation video file and output the reply information for the question and answer information;

[0081] Step S25: Control the playback terminal to end the interruption and continue outputting the explanation video file.

[0082] In practical applications of this application, after seeing or hearing the above-mentioned answers, the questioner may correctly understand and resolve the previously raised questions and answers without the need for the virtual teacher to provide further answers. In other cases, after receiving the above-mentioned answers, the questioner may not understand them and may not be able to resolve the previously raised questions and answers, requiring the virtual teacher to explain the questions and answers again based on the answers.

[0083] Therefore, after the virtual teacher explains the above answers according to the preset lecture notes, the subsequent explanation can be paused, i.e., the playback terminal interrupts the output of the explanation video file, and asks the questioner whether they understand the above Q&A information and whether a response is still needed. This application can output this inquiry as a response to the Q&A information. Optionally, the response information output in this scenario can be generated according to a preset response template based on the questioner's user identifier, Q&A information, etc., such as a response with content like "Does student XX understand the previously raised question?" This application does not restrict the content of the response information output in this scenario or its generation method, and can be determined as appropriate.

[0084] In some embodiments, following the above analysis, after receiving the response information, the questioner can provide feedback information based on the actual situation, such as audio data containing phrases like "I understand the question I asked earlier" or "I don't understand the relevant knowledge points explained by the teacher; could the teacher explain them again?" This application does not limit the content of this feedback information and can be determined as needed. Afterwards, the system can determine whether a further explanation is needed based on this feedback information. If so, it indicates that the questioner did not understand, and the system can output a response based on the question-and-answer model or a response generated based on the answer content. If not, it indicates that the questioner already understands and no further explanation is needed; the virtual teacher can continue explaining the subsequent content, i.e., controlling the playback terminal to continue outputting the explanation video file.

[0085] In some other embodiments, after the playback terminal outputs the answer, regardless of whether the questioner understands the answer and resolves the previously raised question, this application can also directly output, as described above, reply information based on a question-and-answer model or reply information generated based on the answer content. For example, it can output "The question asked by student XX just now relates to the part we just explained. Now let's look at this question... (the answer to the question)," but it is not limited to this type of reply information.

[0086] In addition, regarding whether the playback terminal has finished playing the above-mentioned answer content, that is, whether the virtual teacher has finished explaining the above-mentioned answer content, in some embodiments, when determining the above-mentioned answer content, this application can record the output end time of the answer content. In this way, the playback terminal can determine whether the explanation of the answer content has been completed by detecting whether the playback time of the statistically recorded explanation video file has reached the output end time.

[0087] In some other embodiments, this application may also use semantic recognition methods to determine whether the explanation video file output by the playback terminal contains complete answer content; optionally, this application may also add question-and-answer tags to the detected answer content, and determine whether the playback of the answer content has been completed by detecting whether the explanation video file output by the playback terminal contains the question-and-answer tags. This application does not limit the implementation method of detecting whether the playback terminal has finished playing the answer content, including but not limited to the implementation methods described above.

[0088] In summary, in this embodiment of the application, during virtual network teaching, after a student raises a question, in order to avoid directly answering the question and interfering with the original explanation, thus reducing teaching quality, this application will detect whether the content that the virtual teacher has not yet explained contains an answer to the question. If it does, the question will not be answered temporarily, and the virtual teacher will continue to explain the content as planned. After explaining the answer, the subsequent explanation can be interrupted, the response information for the question can be output, and then the explanation can continue. This ensures that while answering student questions, the teaching plan is reliably and effectively completed, thus guaranteeing teaching quality.

[0089] Reference Figure 3 This is a flowchart illustrating another optional example of the question-and-answer processing method proposed in this application. This embodiment can be another optional refined implementation of the question-and-answer processing method described above, such as refining the step of outputting response information for question-and-answer information as described in the above embodiment. However, it is not limited to the refined processing method described in this embodiment. For the implementation process of other steps of the question-and-answer processing method, please refer to the description of the corresponding parts of the above embodiment, which will not be repeated in this embodiment. Figure 3 As shown, the method may include:

[0090] Step S31: Based on the preset reply template, generate a confirmation message indicating whether the questioner understands the answer content.

[0091] In conjunction with the description of the above embodiments, after the playback terminal outputs the answer content that matches the question and answer information in the teaching plan (i.e., the preset teaching handout), since the answer content may or may not solve the student's question, in order to avoid repeated answers, this application can first ask the student whether the answer content that has been explained can solve their question, that is, whether the questioner understands the answer content. This application does not limit the method of generating the question information that represents this meaning or its content.

[0092] In some embodiments, as described in step S31, this application may call a preset reply template configured for the situation to obtain the user identification information (such as name) of the questioner regarding the question and answer information. Based on the user identification information and the question and answer information, according to the preset reply template, a confirmation message regarding whether the questioner understands the answer content can be generated, such as "Does XX understand the question xx that XX asked just now?", but it is not limited to the confirmation message regarding the answer content.

[0093] Step S32: Control the playback terminal to output the answer confirmation information;

[0094] Step S33: In response to the "answered" instruction confirming the solution information, control the playback terminal to end the interruption and continue outputting the explanation video file;

[0095] Step S34: In response to the unanswered instruction for the answer confirmation information, output the reply information based on the question-answering model.

[0096] Following the analysis above, after receiving confirmation of an answer to a question, if the user has already understood it, there is no need for the virtual teacher to provide further explanation. Instead, audio data or input commands representing that the question has been resolved can be output, thereby generating a "answered" command in response to the confirmation. This triggers the virtual teacher to continue explaining the subsequent content. Conversely, if the user does not understand the question, an "unanswered" command representing that the question has not been resolved can be input. In response to this "unanswered" command, the question and answer information is input into a pre-trained question-and-answer model, which outputs a response to the question and answer information. Alternatively, a response can be generated based on the aforementioned answer content. This application does not elaborate on the process of generating such a response.

[0097] Therefore, after outputting the answer content that matches the question and answer information, this application determines whether it is necessary to answer the question again by asking the questioner whether they understand it. This ensures a reliable answer to the questioner's question while avoiding repeated answers.

[0098] In some embodiments proposed in this application, the method of controlling the playback terminal to interrupt the output of the explanatory video file differs from the above. Figure 3The described implementation method allows for direct input of question-and-answer information into a question-and-answer model for processing, outputting response information generated based on the processing results. In some other embodiments, this application can also directly generate response information for the question-and-answer information based on the aforementioned answer content, and directly output the response information generated according to this method when the playback terminal interrupts the output of the explanatory video file. Therefore, it is evident that, given the playback terminal's output of the aforementioned answer content, the implementation method for outputting response information is not unique; any of the methods described above can be flexibly selected based on the scenario requirements, but it is not limited to the various implementation methods described above.

[0099] Reference Figure 4 This is a flowchart illustrating another optional example of the question-answering processing method proposed in this application. This embodiment can be another optional refined implementation of the question-answering processing method described above. This method can be executed by a server, such as... Figure 4 As shown, the method may include:

[0100] Step S41: Receive a narration request sent by the terminal device;

[0101] In this embodiment, the explanation request may carry, but is not limited to, a user identifier and a content identifier requested for explanation, so that the server can obtain the content to be explained for the user making the teaching request. The implementation method for the terminal device responding to the user's selection of candidate courses and generating an explanation request (i.e., a teaching request) for the selected course can be referred to, but is not limited to, the description in the corresponding parts of the above embodiments.

[0102] Step S42: Respond to the explanation request, obtain the historical teaching data associated with the user identifier, and the basic content to be explained associated with the content identifier;

[0103] Step S43: Based on historical teaching data and the basic content to be explained, generate the content to be explained for the user identifier;

[0104] This application proposes to provide targeted teaching for different applicants (such as different students or different classes) to improve the quality of teaching. Therefore, after the server responds to the received teaching request, it can analyze and determine the learning progress and learning effect of the applicant based on the historical teaching data of the user identification relationship, such as the learning content of the last course and the completion status of the assignments for the course. Based on this, the basic content to be taught associated with the content identification (such as teaching materials with fixed content configured for the course) can be processed to obtain the teaching content suitable for the applicant, that is, exclusive teaching materials suitable for each student's individual learning situation or each class's learning situation.

[0105] It should be noted that this application does not limit the method for generating the aforementioned exclusive teaching materials. In some embodiments, a teaching material generation model trained using artificial intelligence technology can be used to generate content to be explained, i.e., teaching material content, with different content identifiers for different user identifiers. The implementation process will not be detailed in this application.

[0106] Step S44: Construct a video file to explain the content to be explained;

[0107] Step S45: Send the explanation video file to the playback terminal, and the playback terminal outputs the explanation video file.

[0108] Based on the above description of the process of generating instructional video files, and following the method described above, after obtaining the exclusive lecture notes for different students or classes, the exclusive instructional video files for each applicant can be constructed by combining the character attributes of the virtual teacher configured for that applicant. The construction process will not be described in detail.

[0109] It should be noted that the method for obtaining the explanatory video file for the content to be explained output by the playback terminal includes, but is not limited to, the method described in this embodiment. In some embodiments, for the same course, fixed lecture notes, i.e., the basic content to be explained, can be pre-configured. Regardless of which course applicant selects the course, the basic content to be explained can be retrieved. Combined with the configured virtual teacher's character attributes, a corresponding explanatory video file can be constructed, or combined with the default character attributes of the virtual teacher, a general explanatory video file for the course can be constructed, etc.

[0110] Step S46: Receive Q&A information sent by the playback terminal;

[0111] Step S47: Detect the matching degree between the content to be explained and the question and answer information contained in the explanation video file not output by the playback terminal;

[0112] Step S48: Determine that the content to be explained in the explanatory video file not output by the playback terminal contains answer content with a matching degree greater than or equal to the matching threshold that matches the question and answer information.

[0113] During the output of the video file on the playback terminal, i.e., during the virtual teacher's lecture, when a student asks a question, the playback terminal or a separate audio acquisition device can collect the corresponding question and answer information and send it to the server. The server then uses the method described in the corresponding part of the above embodiment to detect whether the content not explained by the virtual teacher contains answers to the question and answer information. This determines whether the virtual teacher should temporarily stop teaching and answer the student's question, or temporarily not answer the student's question and continue teaching. The implementation process will not be described in detail in this embodiment.

[0114] Step S49: Configure question and answer tags for the explanation video file containing the answer content;

[0115] Step S410: If the terminal device detects that the explanation video file output by the terminal device is configured with a question and answer identifier, the transmission of the explanation video file to the playback terminal is interrupted, and a response message for the question and answer information is generated.

[0116] Step S411: Send the reply information to the playback terminal, and the playback terminal outputs the reply information;

[0117] Step S412: Continue sending the explanation video file to the playback terminal, and the playback terminal will continue to output the explanation video file.

[0118] If the server determines that the virtual teacher has not yet explained the content (i.e., the video file not yet output by the playback terminal) contains answers to questions and answers, it can temporarily refrain from answering the questions and continue teaching. However, to avoid forgetting to answer the questions and answers later and affecting the teaching quality, this application embodiment proposes to configure a question and answer identifier for the question and answer information at the location of the answer content in the background. In this way, during the output of the video file by the playback terminal, the server can detect whether the currently output video file has a question and answer identifier. If not, it controls the playback terminal to continue outputting the subsequent content of the video file according to the original plan; if so, it means that a student asked a question about this part of the content, and the explanation can be paused and the corresponding reply information can be output. Regarding the method for generating the reply information, please refer to the description of the corresponding part of the above embodiment.

[0119] It should be noted that this application does not limit the content of the question-and-answer identifier configured above; it can be a specific identifier or text information, etc. Furthermore, in a virtual online teaching scenario, the aforementioned question-and-answer identifier can be recorded at the corresponding location in the explanation video file on the server side. The explanation video file output by the terminal device will not display this question-and-answer identifier, thus avoiding interference with students viewing the content.

[0120] In some further embodiments of this application, during the virtual online teaching process described in the above embodiments, if the questioner understands the answers provided by the virtual teacher or has obtained answers through other channels, the virtual teacher does not need to answer the previously raised questions again. The questioner can interact with the explanation interface of the playback terminal through voice, text, or buttons, generating a cancellation request for the aforementioned question-and-answer identifier. That is, the playback terminal responds to the questioner's cancellation operation on the question-and-answer information, generates the cancellation request, and sends it to the server. Upon receiving the cancellation request, the server can delete the configured corresponding question-and-answer identifier. In this way, the server does not need to generate the aforementioned reply information and send it to the playback terminal output, and can continue to send the subsequent content of the explanation video file to the playback terminal.

[0121] Reference Figure 5 This is a schematic diagram of an optional example of the question-and-answer processing device proposed in this application. The device can be implemented on the server side or the playback terminal side, such as... Figure 5 As shown, the device may include:

[0122] The question and answer information acquisition module 11 is used to acquire question and answer information; wherein, the question and answer information is collected during the process of the playback terminal outputting the explanatory video file for the content to be explained;

[0123] The first detection module 12 is used to detect the matching degree between the content to be explained contained in the explanation video file not output by the playback terminal and the question and answer information;

[0124] The response control module 13 is used to control the playback terminal to output response information for the question and answer information based on the matching degree.

[0125] In some embodiments, such as Figure 6 As shown, the above-mentioned response control module 13 may include:

[0126] The first determining unit 131 is used to determine that the content to be explained contained in the explanation video file not output by the playback terminal contains answer content with a matching degree greater than or equal to the matching threshold of the question and answer information.

[0127] Interruption processing unit 132 is used to detect that after the playback terminal outputs the answer content, control the playback terminal to interrupt the output of the explanation video file;

[0128] The first output unit 133 is used to output response information for the question and answer information when the playback terminal interrupts the output of the explanation video file;

[0129] The interruption termination processing unit 134 is used to control the playback terminal to terminate the interruption and continue outputting the explanatory video file;

[0130] The second determining unit 135 is used to determine that the content to be explained contained in the explanation video file not output by the playback terminal has a matching degree with the question and answer information that is less than a matching threshold.

[0131] The second output unit 136 is used to output response information based on the question-and-answer model generated for the question-and-answer information.

[0132] Optionally, the first output unit 133 may include:

[0133] The first output subunit is used to input the question-and-answer information into the question-and-answer model for processing, and output response information generated based on the processing result; or...

[0134] The second output subunit is used to output response information generated based on the answer content in response to the question and answer information.

[0135] In one possible implementation, the first output unit 133 described above may include:

[0136] The answer confirmation information generation unit is used to generate answer confirmation information based on a preset reply template to indicate whether the questioner understands the answer content.

[0137] A confirmation information output unit is used to control the playback terminal to output the confirmation information.

[0138] The first response unit is used to respond to the answered instruction of the answer confirmation information, trigger the interruption end processing unit 134 to control the playback terminal to end the interruption and continue to output the explanation video file;

[0139] The second response unit is used to respond to the unanswered instruction of the answer confirmation information and output the reply information based on the question-answering model.

[0140] In some other embodiments, the above-described apparatus may further include:

[0141] The answer prompt information output module is used to control the playback terminal to output answer prompt information when, in the content to be explained contained in the explanation video file that has not been output by the playback terminal, there is answer content with a matching degree greater than or equal to the matching threshold of the question and answer information; wherein, the answer prompt information is used to indicate that the explanation video file that has not been output contains the answer content, and no answer is given to the question and answer information at present.

[0142] In some other embodiments, the above-described apparatus may further include:

[0143] The question-and-answer identifier configuration module is used to configure question-and-answer identifiers for the question-and-answer information in the explanatory video file containing the answer content;

[0144] The second detection module is used to detect that the explanation video file output by the terminal device is configured with the question and answer identifier, trigger the interrupt processing unit 132 to control the playback terminal to interrupt the output of the explanation video file, and output the reply information for the question and answer information.

[0145] In some other embodiments, such as on the server side, the above-described apparatus may further include:

[0146] The cancellation request receiving module is used to receive a cancellation request sent by the playback terminal for the question-and-answer identifier; the cancellation request is generated by the playback terminal in response to the cancellation operation performed by the questioner on the question-and-answer information;

[0147] The question-and-answer identifier deletion module is used to delete the configured question-and-answer identifier in response to the cancellation request.

[0148] In some other embodiments, such as on the server side, the above-described apparatus may further include:

[0149] The explanation request receiving module is used to receive explanation requests sent by terminal devices; the explanation request carries a user identifier and an identifier of the content to be explained;

[0150] The explanation request response module is used to respond to the explanation request, obtain the historical teaching data associated with the user identifier, and the basic content to be explained associated with the content identifier;

[0151] The content to be explained module is used to generate content to be explained for the user identifier based on the historical teaching data and the basic content to be explained.

[0152] The video file construction module is used to construct video files for explaining the content to be explained.

[0153] The video file transmission module is used to send the video file to the playback terminal for output.

[0154] It should be noted that the various modules and units in the above-mentioned device embodiments can all be stored in the memory as program modules. The processor executes the above-mentioned program modules stored in the memory to realize the corresponding functions. The functions realized by each program module and its combination, as well as the technical effects achieved, can be referred to the description of the corresponding part of the above-mentioned method embodiments. This embodiment will not repeat them here.

[0155] This application also provides a computer-readable storage medium on which a computer program can be stored. The computer program can be called and loaded by a processor to implement the various steps of the question-and-answer processing method described in the above embodiments. The implementation process will not be described in detail in the embodiments of this application.

[0156] Reference Figure 7 The diagram below illustrates an optional example of the question-and-answer processing system proposed in this application. The system may include, but is not limited to, the playback terminal 21 and the server 22, wherein:

[0157] The playback terminal 21 can be an electronic device with the function of outputting explanatory video files, such as a smartphone, tablet computer, augmented reality (AR) device, virtual reality (VR) device, in-vehicle device, desktop computer, projection device, etc., which can be determined according to the question and answer application scenario.

[0158] In practical applications of this application, users can apply for virtual online teaching for a certain course through a question-and-answer client in a playback terminal or other electronic device, such as a teaching client or various communication clients capable of remote communication, according to the method described in the above embodiments. If necessary, users can also configure various character attributes of the virtual teacher through the configuration interface of the virtual teacher for the virtual online teaching output by the question-and-answer client. The implementation process is not detailed in this application.

[0159] Server 22 can be a service device that supports virtual network teaching functions. It can be an independent physical server or a server cluster composed of multiple physical servers; it can also be a cloud server that can realize cloud computing services. It can realize data communication with playback terminals or other electronic devices through wired or wireless communication networks to realize the transmission of data such as explanation video files, Q&A information, and reply information.

[0160] In this embodiment, the playback terminal 21 can receive the explanation video file sent by the server in real time and output the explanation video file through the video player. During this period, if a student asks a question, the playback terminal 21 or the audio acquisition device in its environment can collect the question and answer information and send the question and answer information to the server so that the server can execute the question and answer processing method proposed in this application to realize virtual network online teaching. This method can be applied to live teaching scenarios as well as recorded teaching scenarios.

[0161] In some other embodiments, the server 22 may also send the generated video file containing the complete content to be explained in the course to the playback terminal 21 for storage, so that the playback terminal 21 can execute the question-and-answer processing method proposed in this application to realize virtual network teaching such as recorded teaching scenarios. The implementation process can be referred to the description of the corresponding part of the above embodiments, and will not be repeated in this embodiment.

[0162] It is understood that if the playback terminal 21 is a projection device, the server 22 can send the explanation video file to the control device (such as a teaching computer device) in the environment where the projection device is located, and then the control device can transmit it to the playback terminal 21 for output. In this case, the control device, the playback terminal and the server 22 can cooperate to implement the proposed question and answer processing method. The implementation process is not described in detail in this application embodiment.

[0163] in addition, Figure 7 The system architecture shown does not constitute a limitation on the question-and-answer processing system in the embodiments of this application. In practical applications, the system may include more than Figure 7 The more or fewer devices shown, such as databases, independent audio acquisition devices, and the aforementioned control devices, are not listed here in this application.

[0164] Reference Figure 8 This is a schematic diagram of the hardware structure of an optional example of a computer device suitable for the question-and-answer processing method proposed in this application. The computer device can be a playback terminal or a server. This application uses a server as an example for structural description. Figure 8 As shown, the computer device may include at least one memory 31 and at least one processor 32, wherein:

[0165] The memory 31 can be used to store a program that implements the above question-and-answer processing method; the processor 32 can be used to load and execute the program stored in the memory 31 to implement each step of the question-and-answer processing method implemented on the corresponding computer device side. The implementation process can be referred to the description of the corresponding part of the above method embodiment, which will not be repeated in this embodiment.

[0166] In this embodiment, memory 31 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device. Processor 32 may be a central processing unit (CPU), application-specific integrated circuit (ASIC), digital signal processor (DSP), application-specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA), or other programmable logic device.

[0167] Understandable. Figure 8 The structure of the computer device shown does not constitute a limitation on the computer device in the embodiments of this application. In practical applications, the computer device may include more than Figure 8 The diagram shows additional components, or combinations of certain components, such as various types of communication interfaces, and in cases where the computer device is a playback terminal. Figure 9 As shown, the computer device may also include at least one input device such as a camera or microphone; at least one output device such as a display or speaker; a sensor module composed of various sensors; a power management module; an antenna, etc., which will not be listed here.

[0168] Finally, it should be noted that, regarding the above embodiments, unless the context explicitly indicates an exception, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, and these steps and elements do not constitute an exclusive list; the method or apparatus may also include other steps or elements. An element defined by the phrase "comprising an..." does not exclude the presence of other identical elements in the process, method, product, or apparatus that includes the element.

[0169] In the description of the embodiments of this application, unless otherwise stated, " / " means "or", for example, A / B can mean A or B; "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more.

[0170] The terms used in this application, such as "first" and "second," are for descriptive purposes only, used to distinguish one operation, unit, or module from another, and do not necessarily require or imply any such actual relationship or order between these units, operations, or modules. Furthermore, they should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature.

[0171] Furthermore, the various embodiments in this specification are described in a progressive or parallel manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus, system, and computer equipment disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0172] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A question-and-answer processing method, the method comprising: Acquire question and answer information; wherein, the question and answer information is collected during the process of the playback terminal outputting the explanatory video file for the content to be explained; The matching degree between the content to be explained contained in the explanation video file not output by the playback terminal and the question and answer information is detected. Based on the matching degree, the playback terminal is controlled to output response information for the question and answer information; The step of controlling the playback terminal to output response information for the question-and-answer information based on the matching degree includes: It is determined that the content to be explained in the explanatory video file not output by the playback terminal contains answer content with a matching degree greater than or equal to the matching threshold of the question and answer information; After detecting that the playback terminal outputs the answer content, control the playback terminal to interrupt the output of the explanation video file and output the reply information in response to the question and answer information; The playback terminal is controlled to stop interrupting and continue outputting the explanatory video file; If the content to be explained in the explanatory video file not output by the playback terminal is found to have a matching degree with the question and answer information less than the matching threshold, then output the response information generated based on the question and answer model.

2. The method according to claim 1, wherein outputting response information for the question-and-answer information includes: The question-and-answer information is input into the question-and-answer model for processing, and the response information generated based on the processing result is output. or, Output the response information generated based on the answer content in response to the question and answer information; or, Based on a preset reply template, a confirmation message is generated to indicate whether the questioner understands the answer content. The playback terminal is controlled to output the answer confirmation information; In response to the "answered" instruction of the answer confirmation information, the step of controlling the playback terminal to end the interruption is executed, and the output of the explanation video file continues; In response to an unanswered instruction regarding the answer confirmation information, output reply information based on the question-and-answer model for the question-and-answer information.

3. The method according to claim 1, further comprising: Configure question-and-answer identifiers for the question-and-answer information in the explanatory video file containing the answers. If the terminal device detects that the explanatory video file output by the terminal device is configured with the question and answer identifier, the step of controlling the playback terminal to interrupt the output of the explanatory video file and output the reply information in response to the question and answer information is executed.

4. The method according to claim 3, further comprising: Receive a cancellation request sent by the playback terminal for the question-and-answer identifier; The cancellation request is generated by the playback terminal in response to the cancellation operation performed by the questioner on the question and answer information; In response to the cancellation request, delete the configured question-and-answer identifier.

5. The method according to claim 1, wherein, in the case that the content to be explained contained in the explanation video file not output by the playback terminal contains answer content with a matching degree greater than or equal to the matching threshold of the question and answer information, the method further includes: The playback terminal is controlled to output an answer prompt message; wherein the answer prompt message is used to indicate that the unoutput explanatory video file contains the answer content, and no answer is given to the question and answer information at present.

6. The method according to any one of claims 1 to 5, wherein the playback terminal outputs an explanatory video file for the content to be explained, comprising: Receive explanation requests sent by terminal devices; The explanation request carries a user identifier and an identifier for the content to be explained; In response to the explanation request, obtain the historical teaching data associated with the user identifier and the basic content to be explained associated with the content identifier; Based on the historical teaching data and the basic content to be explained, generate content to be explained for the user identifier; Construct a video explanation file for the content to be explained; The instructional video file is sent to the playback terminal for output.

7. A question-and-answer processing apparatus, the apparatus comprising: The question and answer information acquisition module is used to acquire question and answer information; wherein, the question and answer information is collected during the process of the playback terminal outputting the explanatory video file for the content to be explained; The detection module is used to detect the degree of matching between the content to be explained contained in the explanation video file not output by the playback terminal and the question and answer information; The response control module is used to control the playback terminal to output response information for the question and answer information based on the matching degree. The response control module, based on the matching degree, controls the playback terminal to output response information for the question and answer information, including: determining that the content to be explained in the explanatory video file not output by the playback terminal contains answer content with a matching degree greater than or equal to the matching threshold of the question and answer information; detecting that the playback terminal outputs the answer content, controlling the playback terminal to interrupt the output of the explanatory video file and output the response information for the question and answer information; controlling the playback terminal to end the interruption and continue outputting the explanatory video file; If the content to be explained in the explanatory video file not output by the playback terminal is found to have a matching degree with the question and answer information less than the matching threshold, then output the response information generated based on the question and answer model.

8. A computer device comprising: At least one memory and at least one processor, wherein: The memory is used to store a program that implements the question-and-answer processing method as described in any one of claims 1 to 6; The processor is configured to load and execute the program stored in the memory to implement the question-and-answer processing method as described in any one of claims 1 to 6.

Images