Teaching resource allocation method, system and device and readable storage medium

Abstract

A teaching resource allocation method, system and device and a readable storage medium relate to the technical field of data processing, and comprise the following steps: constructing a virtual digital person corresponding to a teacher, and using the digital person to process teaching content to obtain teaching data to give lessons; acquiring data of students in real time in the teaching process, and parameterizing the students to obtain second parameters; according to the second parameter, the matching degree of the student and the teacher is obtained according to a matching degree threshold value, and meanwhile the attention point of the student is obtained; associating the student with the teacher according to the matching degree, and optimizing the teaching process of the digital person based on the attention point of the student; and after optimization, if the knowledge conversion rate of the student is increased, the optimization content is sent to the corresponding teacher, and if the knowledge conversion rate of the student is not changed or reduced, the optimization content is not sent, the teacher and the student are mutually matched through parameterization of the teacher and the student, mismatching of teaching resources is effectively avoided, and the teaching efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a teaching resource allocation method, system and device and a readable storage medium. BACKGROUND

[0002] In the traditional teaching mode, teachers are the core teaching resources in the teaching process. The traditional teaching mode adopts the interactive form of "teacher one-way output and student passive reception". Due to the differences between different students and different teachers, there is a matching problem between teachers and students. The teacher-student matching is long-term on the level of geographical proximity or administrative arrangement. Students lack a mechanism to choose a suitable teacher according to their own characteristics, and teachers also have difficulty in breaking through the class size limit to implement precise teaching. This resource mismatch directly leads to the loss of teaching efficiency and the lack of education equity.

[0003] At present, with the progress of technology, intelligent recommendation, adaptive learning, big data analysis and other technologies have gone from theory to practice. These tools effectively alleviate the matching dilemma of traditional education by precisely matching teacher and student characteristics, dynamically adjusting teaching strategies, and providing process evaluation. SUMMARY

[0004] The embodiments of the present application provide a teaching resource allocation method, system, device and readable storage medium. By parameterizing the teachers and students, the teacher and student are matched with each other, the mismatch of teaching resources is effectively avoided, and the efficiency of teaching is improved.

[0005] A teaching resource allocation method, comprising: obtaining data of at least one teacher, parameterizing the teacher to obtain a first parameter; using the first parameter to construct a digital person corresponding thereto, and matching the corresponding teaching content based on the first parameter; using the digital person to process the teaching content to obtain teaching data, and teaching the students according to the teaching data; parameterizing the students in real time during the teaching process to obtain a second parameter; According to the second parameter, the matching degree of the student and the teacher is obtained according to the matching degree threshold, and the attention point of the student is obtained; According to the matching degree, the student and the teacher are associated, and the teaching process of the digital person is optimized based on the attention point of the student.

[0006] Further, the first parameter includes teaching parameters and individual characteristic parameters, wherein the teaching parameters are suitable for representing the teaching process of the teacher, and the individual characteristic parameters are suitable for representing the affinity of the teacher.

[0007] Further, the process of obtaining the teaching parameters comprises: Acquire the teaching video generated by the teacher and the teaching content corresponding to the teaching video; Extract the audio stream from the teaching video; Obtain the speech data of the teaching process from the audio stream and perform semantic recognition to obtain the first recognition result; Based on the teaching content, analyze the first recognition result to obtain the teaching parameters, including analogy transfer parameters, case teaching parameters, questioning skill parameters, and rhythm control parameters.

[0008] Further, the process of obtaining personalized feature parameters includes: Acquire the teaching video of the teacher; Extract the audio stream and continuous single-frame pictures from the teaching video; Obtain the speech data of the teaching process from the audio stream and perform sound affinity evaluation to obtain the second recognition result; Obtain the body movement stream of the teaching process from the continuous single-frame pictures and perform visual affinity evaluation to obtain the third recognition result.

[0009] Further, the process of obtaining the second parameter includes: Capture image data during the student's teaching process, and based on the captured image data, recognize the student's facial movements and body movements; Based on facial movement recognition, obtain recognition result one, including the student's expression, gaze, and head posture; Based on movement recognition, obtain recognition result two, including body posture dynamics, hand gestures, and action frequency; Generate test content based on the teaching content to test the student and obtain result three; According to result one, result two and result three, analyze the student's second parameter, including emotional state parameter, participation state parameter, physiological state parameter, and knowledge transformation parameter.

[0010] Further, according to the set filtering threshold, analyze the emotional state parameter, participation state parameter, physiological state parameter, and knowledge transformation parameter, evaluate the matching degree between the student and the teacher, and in the set monitoring period, when the average matching degree is higher than the set matching degree threshold, associate the student with the teacher, and when the average matching degree is lower than the set matching degree threshold, disassociate the student with the teacher.

[0011] Further, according to the set attention point threshold, monitor the emotional state parameter, participation state parameter, physiological state parameter, and knowledge transformation parameter, and in combination with the teaching process, identify the student's attention point.

[0012] A teaching resource allocation system, comprising: The data acquisition module is suitable for acquiring the data of the teacher and the data of the student, and parameterizing respectively; The digital human generation module is suitable for generating a digital human corresponding to the teacher according to the acquired data of the teacher; The teaching module is suitable for teaching the student by using the generated digital human; The student evaluation module is suitable for evaluating the state of the student according to the acquired student data; The matching degree calculation module is suitable for calculating the matching degree between the teacher and the student according to the acquired data of the student; The association module is suitable for associating or disassociating the student and the teacher according to the matching degree; The optimization module is suitable for identifying the attention point of the student according to the acquired student data and the teaching process, and optimizing the digital human based on the attention point.

[0013] A teaching resource allocation device comprises: A memory is configured to store a program; A processor is configured to execute the program, and the program causes the processor to execute the teaching resource allocation method.

[0014] A readable storage medium stores a computer program, and the computer program causes the teaching resource allocation method to be executed when the computer program is executed on a computer.

[0015] The above technical solution provided by the embodiments of the present application has at least the following beneficial effects: 1. By parameterizing the teacher and the student, the mutual matching of the teacher and the student is realized, the mismatch of the teaching resources is effectively avoided, and the teaching effect is improved.

[0016] 2. In the mutual matching process of the teacher and the student, the teaching process can be optimized according to the feedback of the student, and the teaching effect is improved.

[0017] Other features and advantages of the present application will be described in the following description, and some will become apparent from the description, or will be understood by those skilled in the art through implementation of the present application. The purpose and other advantages of the present application can be achieved and obtained by the structure specifically pointed out in the written description, claims, and drawings.

[0018] The technical solutions of the present application will be further described in detail below by means of the drawings and examples. DETAILED DESCRIPTION

[0019] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, and are used to explain the present application together with embodiments of the present application, and do not constitute a limitation on the present application. In the drawings: Figure 1A teaching resource allocation method flowchart disclosed by the embodiment of the present application is shown in the figure; Figure 2 A teaching parameter acquisition flowchart disclosed by the embodiment of the present application is shown in the figure; Figure 3 A personalized feature parameter acquisition flowchart disclosed by the embodiment of the present application is shown in the figure; Figure 4 A second parameter acquisition flowchart disclosed by the embodiment of the present application is shown in the figure; Figure 5 A teaching resource allocation system structure diagram disclosed by the embodiment of the present application is shown in the figure.

[0020] Reference signs: 1, data acquisition module; 2, digital human generation module; 3, teaching module; 4, student evaluation module; 5, matching degree calculation module; 6, correlation module; 7, optimization module. DETAILED DESCRIPTION

[0021] Exemplary embodiments of the present disclosure will be described in greater detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art.

[0022] Figure 5 A teaching resource allocation system structure diagram is shown in the figure, wherein the teaching resource allocation system further comprises an image acquisition device such as a camera and an audio acquisition device such as a pickup suitable for capturing images and voices of teachers and students for capturing images and voices of teachers and students.

[0023] The camera and the pickup are in communication connection with a computer device suitable for uploading the captured images and voices to the computer device, and the computer device has a memory and a processor, the memory is suitable for storing the captured images, voices and programs, and the processor is used to execute the programs to process the captured images and voices.

[0024] The teaching resource allocation system further comprises: The data acquisition module 1 is suitable for acquiring data of teachers and data of students and parameterizing respectively.

[0025] The data acquisition process of the teacher includes acquiring image data of the teaching process of the teacher through a multi-angle camera array, including facial expressions, hand gestures and blackboard behaviors; simultaneously acquiring voice data of the teaching process through a microphone, including recording speech speed, tone change and special expression method, generating video data with synchronous audio track.

[0026] The teacher is parameterized using the obtained image data and sound data to obtain first parameters, including teaching parameters and personalized characteristic parameters.

[0027] The teaching parameters are suitable for representing the teaching process of the teacher, and the teaching parameters include analogy transfer parameters, case teaching parameters, questioning skill parameters, and rhythm control parameters.

[0028] 1. The analogy transfer parameter acquisition process includes: The collected voice data is converted into text using existing voice recognition technology; The analogy words are detected (such as keyword detection of "like" and "equivalent to"); The sentences before and after the analogy words are recognized (such as "electric current is equivalent to water flow"); The concepts of the preceding and following sentences are logically analyzed, and the analogy transfer item is evaluated to obtain the analogy transfer parameter, i.e., the evaluation value.

[0029] 2. The case teaching parameter acquisition process includes: The collected voice data is converted into text using existing voice recognition technology; The text is analyzed to identify the proportion of teaching cases; The proportion of teaching cases is the case teaching parameter.

[0030] 3. The questioning skill parameter acquisition process includes: The voice data of the teacher is analyzed using interrogative words to identify the interrogative voice segments; The types of the interrogative segments are classified, including closed type (containing "whether" and similar keywords), application type (containing "how to solve" and similar keywords), explanation type (containing "why" and similar keywords), and innovation type (containing "hypothesis" and similar keywords); The length of the silent segment from the end of the question to the teacher's self-answer or the student's response is identified, and the number of interrogative voice segments per unit time is detected; The above interrogative voice segments are used to locate the follow-up voice segments associated with them; The time interval between the interrogative voice segments and the follow-up voice segments and the core concept correlation degree are analyzed; The high-order question proportion parameter ((explanation type + innovation type) / total number of questions), effective waiting time ratio (proportion of questions waiting for more than 3 seconds), and follow-up correlation degree (core concept correlation degree between preceding and following questions) are obtained, which are the questioning skill parameters.

[0031] 4. The rhythm control parameter acquisition process includes: A subject knowledge graph is constructed according to the teaching content; According to the discipline knowledge graph planning benchmark explanation path and the time proportion; The above benchmark is used to detect the teaching process of the teacher, and the teaching process of the teacher is evaluated according to the benchmark explanation path and the time proportion, and a score is obtained, that is, the rhythm control parameter.

[0032] Among them, the personalized feature parameter is suitable for representing the affinity of the teacher, and the personalized feature parameter includes sound affinity and body affinity.

[0033] 1. The sound affinity parameterization process includes evaluating the obtained teacher's speech data from three dimensions of acoustic features, prosodic features and emotion transmission.

[0034] Among them, the collection index of acoustic features is average fundamental frequency and spectral tilt, which is obtained by extracting through existing Praat speech analysis software; the collection index of prosodic features is smile voice detection, wherein the smile voice detection utilizes an existing neural network model for identification; the collection index of emotion transmission is positive emotion concentration and soothing phrase frequency, wherein the positive emotion concentration is identified by using existing BERT speech emotion recognition technology, and the soothing phrase frequency is obtained by statistical method.

[0035] The data acquisition process of the student includes obtaining the image of the student in the teacher's teaching process through a multi-angle camera array, including facial expression, hand gesture, body posture action.

[0036] The digital human generation module 2 is suitable for generating a digital human corresponding to the teacher according to the obtained teacher's data.

[0037] The digital human construction process includes: According to the obtained image data, a digital human image corresponding to the teacher is constructed; Based on the teaching parameters and the personalized feature parameters, the teaching ability and the personalization of the digital human are set.

[0038] The teaching module 3 is suitable for using the produced digital human to teach the students.

[0039] The digital human processes the teaching content based on the teaching ability to obtain teaching data, including: The knowledge graph construction of the teaching content decomposes the original teaching material into a knowledge node network, and assigns the explanation time.

[0040] Teaching strategy injection, teachers with strong analogy ability: match life analogy for abstract concepts, teachers with strong case teaching: insert cases that meet the cognitive level, teachers with high questioning skills: set guiding questions at key nodes.

[0041] Pace control, based on the teaching content, the knowledge graph obtained, the explanation path and the time proportion, control the teaching pace.

[0042] The student evaluation module 4 is adapted to evaluate the state of the student according to the collected student data.

[0043] The images of the students in the teaching process of the teacher are acquired by the multi-angle camera array, including facial expressions, gestures, body postures, and the real-time state of the students is analyzed.

[0044] Including facial data analysis, body movement analysis.

[0045] Using existing recognition models, the images of the students are recognized, the facial expressions and body postures of the current students are analyzed, the current state of the students is judged through the analysis of the expressions, including confusion (frowning), understanding (leaning forward), distraction (eye wandering) and the like.

[0046] Using existing recognition models, the images of the students are recognized, the body postures and gestures of the current students are analyzed, the current state of the students is judged through the analysis of the gestures, including positive state (note-taking action), negative state (frequent leaning back) and the like.

[0047] It also includes generating test content based on teaching content to test students, combining the above-identified state to obtain the current state of the students, i.e. parameterizing the students, including emotional state parameters, participation state parameters, physiological state parameters, and knowledge conversion parameters.

[0048] The emotional state parameter includes a learning pleasure index; the participation state parameter includes visual concentration; the physiological state parameter includes fatigue; and the knowledge conversion parameter includes the understanding degree of the teaching content.

[0049] The above-mentioned emotional state parameter, participation state parameter, and physiological state parameter are obtained by recognizing the posture and expression of the student through existing image recognition technology, and the knowledge conversion parameter is obtained by using the test generated according to the teaching process.

[0050] The matching degree calculation module 5 is adapted to calculate the matching degree of the teacher and the student according to the obtained student data.

[0051] According to the set filtering threshold, the emotional state parameter, the participation state parameter, the physiological state parameter, and the knowledge conversion parameter are analyzed to evaluate the matching degree of the student and the teacher.

[0052] The filtering threshold includes an emotional state parameter filtering threshold, a participation state parameter filtering threshold, a physiological state parameter filtering threshold, and a knowledge conversion parameter filtering threshold. When all the above parameters are higher than the filtering threshold, it is determined that the matching is matched, otherwise it is determined that the matching is not matched.

[0053] The association module 6 is adapted to associate or disassociate the student and the teacher according to the matching degree.

[0054] Within the set monitoring period, the student and the teacher are associated when the average matching degree is higher than the set matching degree threshold, and are disassociated when the average matching degree is lower than the set matching degree threshold.

[0055] After disassociation, a new digital human is used to teach the student until a digital human corresponding to the teacher is matched.

[0056] If there is no matched digital human, the digital human with the highest matching degree is selected according to the matching program and is associated with the student.

[0057] When the digital human a is teaching, the student's emotional state parameter, participation state parameter, physiological state parameter, and knowledge conversion parameter are compared with the emotional state parameter screening threshold, participation state parameter screening threshold, physiological state parameter screening threshold, and knowledge conversion parameter screening threshold, respectively. The emotional state parameter (learning pleasure index 3), the emotional state parameter screening threshold (learning pleasure index 5), and the rest of the parameters are in a normal state.

[0058] When the digital human b is teaching, the student's emotional state parameter, participation state parameter, physiological state parameter, and knowledge conversion parameter are compared with the emotional state parameter screening threshold, participation state parameter screening threshold, physiological state parameter screening threshold, and knowledge conversion parameter screening threshold, respectively. The emotional state parameter (learning pleasure index 4), the emotional state parameter screening threshold (learning pleasure index 5), and the rest of the parameters are in a normal state.

[0059] When no corresponding digital human is matched, the digital human b is associated with the student.

[0060] The optimization module 7 is adapted to identify the student's attention points according to the obtained student data and the teaching process, and optimize the digital human based on the attention points.

[0061] During the teaching process of the digital human, the parameters of the student are detected; When any of the emotional state parameter, participation state parameter, physiological state parameter, and knowledge conversion parameter changes positively, the changed position is marked according to the progress of the teaching process; The teaching process of the marked position is analyzed to identify the teaching content of the corresponding position digital human, including analogy transfer process, case teaching process, questioning process, and pronunciation; The attention points of the student are identified according to the above content, and the teaching process is adjusted mechanically in the subsequent teaching process of the digital human, such as increasing the analogy transfer process or case teaching process or questioning process or adjusting the pronunciation method.

[0062] After optimization, if the knowledge conversion rate of the student increases, the optimized content is sent to the corresponding teacher to improve the teaching ability of the teacher, and if the knowledge conversion rate of the student does not change or decreases, the optimized content is not sent.

[0063] As shown in the Figure 1 A teaching resource allocation method comprises: S1, obtaining data of at least one teacher, parameterizing the teacher to obtain a first parameter, wherein the first parameter comprises a teaching parameter and a personalized characteristic parameter, wherein the teaching parameter is adapted to represent the teaching process of the teacher, and the personalized characteristic parameter is adapted to represent the affinity of the teacher.

[0064] As shown in the Figure 2 S10, the process of obtaining the teaching parameter comprises: S101, obtaining a teaching video generated by the teacher and teaching content corresponding to the teaching video.

[0065] S102, extracting an audio stream from the teaching video.

[0066] S103, obtaining voice data of the teaching process from the audio stream and performing semantic recognition to obtain a first recognition result.

[0067] S104, analyzing the first recognition result based on the teaching content to obtain the teaching parameter, including analogy transfer parameter, case teaching parameter, questioning skill parameter, and rhythm control parameter.

[0068] As shown in the Figure 3 S11, the process of obtaining the personalized characteristic parameter comprises: S111, obtaining a teaching video of the teacher.

[0069] S112, extracting an audio stream and a continuous single frame picture from the teaching video.

[0070] S113, obtaining voice data of the teaching process from the audio stream and performing sound affinity evaluation to obtain a second recognition result.

[0071] S114, obtaining a body movement stream of the teaching process from the continuous single frame picture and performing visual affinity evaluation to obtain a third recognition result.

[0072] S2, constructing a digital person corresponding to the first parameter using the first parameter, and matching the corresponding teaching content based on the first parameter.

[0073] S3, using the digital person to process the teaching content to obtain teaching data, and teaching the student according to the teaching data.

[0074] S4, parameterizing the student to obtain a second parameter by collecting data of the student in real time during the teaching process.

[0075] As Figure 4 shown in S41, the process of obtaining the second parameter includes: S411, capturing image data in the teaching process of the student, and recognizing the facial action and body action of the student based on the captured image data.

[0076] S412, obtaining a recognition result one based on facial action recognition, including the expression, gaze and head posture of the student.

[0077] S413, obtaining a recognition result two based on action recognition, including body posture dynamics, gestures and action frequency.

[0078] S414, generating test content based on the teaching content to test the student and obtaining a result three.

[0079] S415, analyzing the second parameter of the student including the emotional state parameter, the participation state parameter, the physiological state parameter and the knowledge conversion parameter according to the result one, the result two and the result three.

[0080] S5, obtaining the matching degree of the student and the teacher according to the second parameter and the matching degree threshold, and obtaining the attention point of the student.

[0081] According to the set screening threshold, the emotional state parameter, the participation state parameter, the physiological state parameter and the knowledge conversion parameter are analyzed to evaluate the matching degree of the student and the teacher.

[0082] According to the set attention point threshold, the emotional state parameter, the participation state parameter, the physiological state parameter and the knowledge conversion parameter are monitored, and the attention point of the student is recognized in combination with the teaching process.

[0083] S6, associating the student and the teacher according to the matching degree, and optimizing the teaching process of the digital person based on the attention point of the student.

[0084] In the set monitoring period, when the average matching degree is higher than the set matching degree threshold, the student and the teacher are associated, and when the average matching degree is lower than the set matching degree threshold, the student and the teacher are disassociated.

[0085] S7, after optimization, if the knowledge conversion rate of the student increases, the optimization content is sent to the corresponding teacher, and if the knowledge conversion rate of the student does not change or decreases, the optimization content is not sent.

[0086] A teaching resource allocation device, comprising: a memory for storing a program; a processor for executing the program, the program causing the processor to execute the above-mentioned teaching resource allocation method.

[0087] A readable storage medium, wherein a computer program is stored, the computer program makes the teaching resource allocation method be executed when running on a computer.

[0088] The beneficial effects of the above technical solutions provided by the embodiments of the present application at least include: 1. By parameterizing the teachers and students, the teachers and students are matched with each other, the mismatch of teaching resources is effectively avoided, and the teaching effect is improved.

[0089] 2. In the process of matching the teachers and students with each other, the teaching process can be optimized according to the feedback of the students, and the teaching effect is improved.

[0090] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application will be realized and achieved by means of the structures particularly pointed out in the written description and claims hereof as well as the appended drawings.

[0091] 3. The teaching resource allocation method is suitable for online teaching or offline teaching. When online teaching is adopted, the teachers can be parameterized to generate corresponding digital persons, and the digital persons are used to complete the teaching work, so that the allocation of educational resources can be maximized. The digital persons teach the students in a one-to-one manner, each student is allocated a digital person for teaching, when offline teaching is adopted, the students are screened through the digital persons, the teachers are associated with the matched students, the students are taught, the teachers can be selected according to the characteristics of the students, the teachers and students are matched with each other, the mismatch of teaching resources is effectively avoided, and the efficiency of teaching is improved.

[0092] 4. In the teaching process, when online teaching is adopted, the attention points of the students can be recognized according to the monitoring of the teaching process, and the digital persons are optimized based on the attention points, so that the digital persons match the characteristics of the students, and the technical effect of improving the teaching efficiency is achieved. When offline teaching is adopted, the students are screened through the digital persons, the attention points of all the students are collected, the teaching process of the teachers can be adjusted according to the analysis of the attention points, and the technical effect of improving the teaching efficiency is achieved.

[0093] It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary methods. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes can be rearranged while remaining within the scope of the present disclosure. The accompanying method claims present elements of the various steps in exemplary order and are not intended to be limited to the specific order or hierarchy presented.

[0094] In the detailed description above, various features are grouped together in single embodiments for the purpose of streamlining the disclosure. This method of disclosure should not be interpreted as reflecting a necessity to disclose features in any single patent. Rather, according to the inventive concept, features can be combined in any single patent in one or more claims. Thus, the disclosure hereof is to be understood as being illustrative of the inventive concept and not a limitation thereof. For example, not every aspect of the creative process is described with every embodiment. It is contemplated that the creative process is a dynamic process that will necessitate implementation of new techniques by those skilled in the art. Those skilled in the art will appreciate that, in the development of this creative process, numerous implementation-specific decisions can be made. These implementation-specific decisions can vary from one implementation to another, and from one environment to another. Those skilled in the art will appreciate that such a development effort might be time-consuming, but that, otherwise, such efforts would not be a contribution to the art of the present disclosure, and would form no part of this disclosure. In this regard, details are not provided hereinafter in order to not unnecessarily obscure the disclosure. Other steps will readily occur to those skilled in the art. In the art and practice contributing to the disclosure, modifications

[0095] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0096] The steps of a method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium can be integral to the processor. The processor and the storage medium can reside in an ASIC. The ASIC can reside in a user terminal. In the alternative, the processor and the storage medium can reside as discrete components in a user terminal. The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other variations without departing from the scope of the disclosure. For example, one of ordinary skill in the art will immediately appreciate that the disclosure can be implemented in network computing environments with many types of computer system configurations, including, but not limited to, distributed computing environments, multiprocessor systems, microprocessor-based or programmable consumer electronics, networked personal computers, minicomputers, mainframe computers, and the like. The disclosure can also be practiced in distributed computing environments where tasks are performed by local and remote processing

[0097] For a software implementation, the techniques described herein can be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes can be stored in memory units and executed by processors. The memory unit can be implemented within the processor or external to the processor, in which case it can be communicatively coupled to the processor via various means as is known in the art.

[0098] The above description includes examples of one or more embodiments. Of course, not all possible combinations of components or methods described above can be claimed as an embodiment or employed as described above, but one of ordinary skill in the art will recognize that missing elements can be claimed and combinations of elements can be used based on an embodiment as described herein. Embodiments described herein aim to encompass all such changes, modifications and variations falling within the scope of the appended claims. Further, with respect to the use of the term "comprising" in the specification and claims, the use of this term is intended to capture the inclusion of one or more elements, but not preclude the inclusion of additional elements. Further, the use of the term "or" in the specification and claims is intended to capture the inclusion of one or more elements, but not preclude the inclusion of additional elements.

Claims

1. A method of allocating teaching resources, characterized by, The application comprises the following steps: Obtaining data of at least one teacher, parameterizing the teacher to obtain a first parameter; Using the first parameter to construct a digital human corresponding thereto, and matching the corresponding teaching content based on the first parameter; Using the digital human to process the teaching content to obtain teaching data, and teaching the student according to the teaching data; Obtaining the second parameter by parameterizing the student in real time during the teaching process; According to the second parameter, the matching degree between the student and the teacher is obtained according to the matching degree threshold, and the attention point of the student is obtained; According to the matching degree, the student and the teacher are associated, and the teaching process of the digital human is optimized based on the attention point of the student; After optimization, if the knowledge conversion rate of the student increases, the optimization content is sent to the corresponding teacher, and if the knowledge conversion rate of the student does not change or decreases, the optimization content is not sent.

2. The method of claim 1, wherein, The first parameter comprises teaching parameters and individualized characteristic parameters, wherein the teaching parameters are suitable for representing the teaching process of the teacher, and the individualized characteristic parameters are suitable for representing the affinity of the teacher.

3. The method of claim 2, wherein, The process of obtaining the teaching parameters comprises the following steps: Obtaining a teaching video generated by the teacher and teaching content corresponding to the teaching video; Extracting an audio stream from the teaching video; Obtaining voice data of the teaching process from the audio stream and performing semantic recognition to obtain a first recognition result; Analyzing the first recognition result based on the teaching content to obtain the teaching parameters, including analogy transfer parameters, case teaching parameters, questioning skill parameters, and rhythm control parameters.

4. The method of claim 2, wherein, The process of obtaining the individualized characteristic parameters comprises the following steps: Obtaining a teaching video of the teacher; Extracting an audio stream and continuous single-frame pictures from the teaching video; Obtaining voice data of the teaching process from the audio stream and performing sound affinity evaluation to obtain a second recognition result; Obtaining a body action stream of the teaching process from the continuous single-frame pictures and performing visual affinity evaluation to obtain a third recognition result.

5. The method of claim 1, wherein, The process of obtaining the second parameter comprises the following steps: Capturing image data of the student during the teaching process, and recognizing the facial action and body action of the student based on the captured image data; Based on the facial action recognition, a first recognition result is obtained, including the expression, gaze and head posture of the student; Based on the action recognition, a second recognition result is obtained, including the body posture dynamics, hand gestures and action frequency; Generating test content based on the teaching content to test the student, and obtaining a third result; Analyzing the first result, the second result and the third result to obtain the second parameter of the student, including the emotional state parameter, the participation state parameter, the physiological state parameter and the knowledge conversion parameter.

6. The method of claim 5, wherein, According to the set screening threshold, the emotional state parameter, the participation state parameter, the physiological state parameter and the knowledge conversion parameter are analyzed to evaluate the matching degree between the student and the teacher, and in the set monitoring period, when the average matching degree is higher than the set matching degree threshold, the student and the teacher are associated, and when the average matching degree is lower than the set matching degree threshold, the student and the teacher are disassociated.

7. The method of claim 5, wherein, According to the set attention point threshold, the emotional state parameter, the participation state parameter, the physiological state parameter and the knowledge conversion parameter are monitored, and the attention point of the student is identified in combination with the teaching process.

8. A teaching resource allocation system characterized by, The application comprises the following steps: The data acquisition module is suitable for acquiring the data of the teacher and the data of the student, and parameterizing respectively; The digital human generation module is suitable for generating the digital human corresponding to the teacher according to the acquired data of the teacher; The teaching module is suitable for teaching the student by using the generated digital human; The student evaluation module is suitable for evaluating the state of the student according to the acquired data of the student; The matching degree calculation module is suitable for calculating the matching degree of the teacher and the student according to the acquired data of the student; The association module is suitable for associating or disassociating the student and the teacher according to the matching degree; The optimization module is suitable for identifying the attention point of the student according to the acquired data of the student and the teaching process, and optimizing the digital human based on the attention point.

9. An educational resource allocation apparatus characterized by comprising: It comprises: A memory for storing a program; A processor for executing the program, which causes the processor to execute the teaching resource allocation method according to any one of claims 1-7.

10. A readable storage medium characterized by: The computer program stored therein makes the teaching resource allocation method according to any one of claims 1-7 be executed when the computer program runs on the computer.

Images