Teaching interaction system and interaction method based on virtual digital human

Abstract

The invention discloses a teaching interaction system and method based on a virtual digital human, and the system comprises an information collection module, an information processing module and a review analysis module, and the information collection module is used for collecting the interaction information of a target student and the virtual digital human; the interaction information comprises teaching information of each specified course node of the virtual digital person in a course learning cycle and in-class response information of a target student of the specified course node; the information processing module is used for extracting corresponding teaching information according to the in-class response information and then importing the teaching information into a knowledge warm-and-fault set, and the knowledge warm-and-fault set stores the teaching information corresponding to the specified course node; and the review analysis module is used for inserting the teaching information in the knowledge fault set into the next course learning cycle. Through application of the artificial intelligence technology, accurate mastering of the learning condition of the student and personalized teaching are realized, and improvement of the learning efficiency and effect of the student is facilitated.

Description

Technical Field

[0001] The present application belongs to the field of interactive technology, and in particular relates to a teaching interactive system and an interactive method based on a virtual digital human. Background Art

[0002] With the rapid development of information technology and artificial intelligence, the traditional education model is gradually integrating more high-tech elements in order to improve teaching efficiency and learning effects. In the tide of digital education, the concept of virtual teachers has emerged and has gradually become an important part of modern distance education and online learning platforms. Virtual teachers can not only simulate the teaching behavior of human teachers, but also provide personalized teaching plans and feedback through intelligent analysis of students' learning data.

[0003] However, the existing virtual teaching system still has some shortcomings, such as the personalized adaptation of teaching content and the dynamic adjustment of the learning process, which need to be improved. In terms of personalized adaptation of teaching content, although some systems can adjust the difficulty or provide different forms of explanations according to students' answers, these systems often do not deeply explore the students' mastery of various knowledge points, resulting in the inability to accurately formulate review plans and tutoring materials for students.

[0004] In order to dynamically adjust the learning process, traditional systems rely more on preset teaching processes and rarely consider students' actual performance and progress in the learning process. This may cause students to need to repeat the same content after mastering certain knowledge points, resulting in a waste of time and resources.

[0005] Therefore, there is an urgent need for a technical solution for virtual digital human interaction in digital education that can solve the above problems. Summary of the invention

[0006] In order to solve the shortcomings of the prior art, the present application provides a teaching interaction system and method based on virtual digital humans, which can ensure the authenticity of students through secondary verification, intelligently collect and process learning interaction information, and dynamically adjust the teaching content according to the students' in-class response information, ultimately achieving personalized learning experience and efficient knowledge review. The design and implementation of this system will help improve the teaching quality of online learning platforms and better meet the needs of modern education and personalized learning.

[0007] The technical effects to be achieved by this application are achieved through the following solutions: According to a first aspect of the present application, a teaching interaction system based on a virtual digital human is provided, comprising an information collection module, an information processing module and a review analysis module, wherein: An information collection module is used to collect the interaction information between the target students and the virtual digital human; the interaction information includes the teaching information of the virtual digital human at each designated course node in a course learning cycle, and the in-class response information of the target students at the designated course node; An information processing module is used to extract corresponding teaching information according to the in-class response information, and then import the teaching information into a knowledge review set, wherein the knowledge review set stores the teaching information corresponding to the specified course node; The review analysis module is used to insert the teaching information of the knowledge review into the next course learning cycle.

[0008] Preferably, the teaching information is the voice information of the virtual digital person, and the in-class answer information is the score of the test questions made by the target students based on the course content of the specified course node.

[0009] Preferably, the information processing module extracts the teaching information in the following manner: The score corresponding to the in-class response information is marked as YF, and YF is compared with the preset score threshold FP: If YF≤FP, extract the teaching information of the corresponding specified course node; If YF>FP, the teaching information of the corresponding specified course node will not be extracted.

[0010] Preferably, the review analysis module is further used to obtain new in-class response information corresponding to the specified course node of the teaching information, and transmit the new in-class response information to the information processing module; Among them, the new in-class response information is the test score of the target students in the next course learning cycle based on the teaching information; The information processing module removes the teaching information in the knowledge review set according to the new in-class response information.

[0011] Preferably, the elimination process is as follows: The score corresponding to the new in-class response information is marked as YF0, and YF0 is compared with the preset score threshold FP: If YF0>FP, the corresponding teaching information will be eliminated from the knowledge review set; If YF0≤FP, the corresponding teaching information in the knowledge review set will not be eliminated.

[0012] Preferably, it also includes: a verification login module, which is used to log in to the virtual digital human interaction platform according to the account registration information of the target student, and establish the interaction between the virtual digital human and the target student according to the account registration information; The secondary verification module is used to identify the authenticity of the target student through biometric technology; wherein the biometric technology uses the physiological characteristics of the target student to identify the authenticity of the target student.

[0013] Preferably, it also includes: The inductive analysis module is used to summarize and analyze the difficulty of the designated course nodes in each course learning cycle based on the teaching information in the corresponding knowledge review set of several target students, and calculate the difficulty coefficient of each designated course node; The review analysis module is also used to determine the minimum number of insertion times of the knowledge review concentrated teaching information in other multiple course learning cycles according to the difficulty coefficient of the knowledge review concentrated teaching information.

[0014] Preferably, the specific method for summarizing and analyzing the difficulties is: Select a course learning cycle and uniquely code each designated course node in the course learning cycle; Extract the number of identical coding marks in the corresponding knowledge review sets of several target students; At the same time, in the corresponding knowledge review sets of all target students, the number of times the teaching information corresponding to the same coding mark is inserted in other course learning cycles is obtained, and the average number of times the teaching information corresponding to the same coding mark in the corresponding knowledge review sets of each target student is inserted in other course learning cycles is calculated; Then, the difficulty coefficient Ui of each designated course node is calculated through Ui=MSi*β1+MCPi*β2; In the formula, MSi represents the number of simultaneous coding marks in the corresponding knowledge review sets of all target students, MCPi represents the average number of insertions of the teaching information corresponding to the same coding mark in other course learning cycles, β1 and β2 are preset proportional coefficients, which are used to adjust the proportions of MSi and MCPi respectively when calculating Ui.

[0015] Preferably, the method for determining the number of insertions is: multiplying the difficulty coefficient by a preset insertion factor to obtain a result value, and rounding the result value upward to obtain the number of insertions.

[0016] According to a second aspect of the present application, there is provided an interactive method using the above-mentioned teaching interactive system based on virtual digital human, comprising the following steps: Step 1: Log in to the virtual digital human interaction platform based on the target student’s account registration information, and establish interaction between the virtual digital human and the target student based on the account registration information; Step 2: Use the physiological characteristics of the target student through biometric technology to identify the authenticity of the target student; Step 3: Collect the interaction information between the target students and the virtual digital human; Step 4: Extract the corresponding teaching information based on the in-class response information, and import the teaching information into the knowledge review set; Step 5: insert the teaching information in the knowledge review set into the next course learning cycle, and obtain new in-class response information corresponding to the specified course node of the teaching information; Step 6: Eliminate the teaching information in the knowledge review set based on the new in-class response information.

[0017] According to one embodiment of the present application, the beneficial effects of using the teaching interaction system based on virtual digital human are: Personalized teaching: By collecting the interaction information between the target students and the virtual teacher, the system can provide personalized tutoring and review materials based on the students' learning situation. This personalized teaching method helps to improve students' learning efficiency and effectiveness.

[0018] Dynamically adjust teaching content: The system can dynamically adjust teaching content according to students' learning situation. For example, if students have a low level of mastery of a certain knowledge point, the system will extract the teaching content of that knowledge point for students to review; conversely, if students have a high level of mastery of a certain knowledge point, the system will not extract the teaching content of that knowledge point.

[0019] Difficulty identification and analysis: It can summarize and analyze the difficulties of designated course nodes within each course learning cycle, thereby helping teachers understand students' learning difficulties and carry out targeted teaching.

[0020] Improve learning efficiency: Optimize the learning process through intelligent means, so that students can get personalized tutoring and review materials according to their own learning situation, thereby improving learning efficiency.

[0021] Wide range of application scenarios: It can be applied to online learning platforms to assist traditional teaching methods or as a part of distance education, and has a wide range of application scenarios.

[0022] In general, the present invention realizes accurate grasp of students' learning situation and personalized teaching through the application of artificial intelligence technology, which helps to improve students' learning efficiency and effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the existing technical solutions, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0024] Figure 1 This is a structural block diagram of a teaching interaction system based on a virtual digital human in one embodiment of the present application; Figure 2This is a flow chart of an interaction method of a virtual digital human in one embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0026] like Figure 1 As shown, the teaching interaction system based on virtual digital human in one embodiment of the present application includes a verification login module, a secondary verification module, an information collection module, an information processing module, an inductive analysis module and a review analysis module, wherein: A verification login module is used to log in to the virtual digital human interaction platform according to the target student's account registration information, and to establish interaction between the virtual digital human and the target student according to the account registration information, wherein the virtual digital human is a virtual teacher; A secondary verification module is used to identify the authenticity of the target student through biometric technology; wherein the biometric technology uses the physiological characteristics of the target student to identify the authenticity of the target student, such as face recognition, fingerprint recognition, iris recognition or voiceprint recognition; The information collection module is used to collect the interaction information between the target student and the virtual digital human; the interaction information includes the teaching information of the virtual digital human at each designated course node in a course learning cycle, and the in-class answer information of the target student at the designated course node. The teaching information is voice information, and the in-class answer information is the score of the test questions made by the target student based on the course content of the designated course node; An information processing module is used to extract corresponding teaching information according to the in-class response information, and then import the teaching information into a knowledge review set, which stores the teaching information corresponding to the specified course node; The extraction method in this embodiment is: marking the score corresponding to the in-class answer information as YF, and comparing YF with a preset score threshold FP: If YF≤FP, it means that the target students have a low amount of knowledge acquisition about the specified course node, and the teaching information of the corresponding specified course node is extracted; If YF>FP, the teaching information of the corresponding specified course node will not be extracted; A review analysis module is used to insert the teaching information in the knowledge review set into the next course learning cycle, and at the same time obtain new in-class response information corresponding to the specified course node of the teaching information; Among them, the new in-class response information is the test score of the target students in the next course learning cycle based on the teaching information; Then the new in-class response information is transmitted to the information processing module; The information processing module removes the teaching information in the knowledge review set according to the new in-class response information. The specific method is as follows: The score corresponding to the new in-class response information is marked as YF0, and YF0 is compared with the preset score threshold FP: If YF0>FP, the corresponding teaching information will be eliminated from the knowledge review set; If YF0≤FP, it means that the target students have a low amount of knowledge absorption about the specified course node in the next course learning cycle, and the corresponding teaching information in the knowledge review set is not eliminated.

[0027] Through the above scheme, the learning process is optimized in an intelligent way, so that students can get personalized tutoring and review materials according to their own learning situation. This system can be applied to online learning platforms to assist traditional teaching methods or as part of distance education; The design and application of the virtual digital human interaction system reflects the in-depth application of artificial intelligence in the field of education. It provides personalized learning experience by simulating real teaching scenarios, which helps to improve learning efficiency and effectiveness. With the development of technology, such systems may become more intelligent and efficient, and better serve the needs of education and learning.

[0028] In one embodiment of the present application, the summary analysis module is used to summarize and analyze the difficulty of designated course nodes in each course learning cycle based on the teaching information in the knowledge review set corresponding to a number of target students, and calculate the difficulty coefficient of each designated course node; specifically: Take a course learning cycle as an example; Uniquely code and mark each designated course node within the course learning cycle; Then, the number of the same coding mark in the corresponding knowledge review sets of several target students is extracted; At the same time, in the corresponding knowledge review sets of all target students, the number of times the teaching information corresponding to the same coding mark is inserted in other course learning cycles is obtained, and the average number of times the teaching information corresponding to the same coding mark in the corresponding knowledge review sets of each target student is inserted in other course learning cycles is calculated; Then, the difficulty coefficient Ui of each designated course node is calculated through Ui=MSi*β1+MCPi*β2; In the formula, MSi represents the number of simultaneous coding marks in the corresponding knowledge review set of all target students, MCPi represents the average number of insertions of the teaching information corresponding to the same coding mark in other course learning cycles, β1 and β2 are preset proportional coefficients, which are used to adjust the proportion of MSi and MCPi respectively when calculating Ui; The review analysis module is also used to determine the minimum number of insertions of the knowledge review concentrated teaching information in other multiple course learning cycles according to the difficulty coefficient of the knowledge review concentrated teaching information; The number of insertions is the result value obtained by multiplying the difficulty coefficient by the preset insertion factor, rounded up to the nearest integer. By summarizing and analyzing the difficulties students encounter in each course learning cycle, we can more accurately identify the difficulties and weak links in students' learning, so as to provide targeted teaching and improve learning efficiency; In the normal learning process, each student may have different learning difficulties. This method can be used to analyze each student's learning situation in a personalized way, achieve personalized teaching, and improve teaching quality. By calculating the difficulty coefficient of course nodes, teaching resources can be allocated more scientifically. For difficult course nodes, teaching time and teaching resources can be increased, thereby improving teaching effectiveness. By determining the minimum number of times that the knowledge review concentrated teaching information is inserted into other multiple course learning cycles, it can be ensured that students can fully understand and master the knowledge points during the review process, thereby improving the teaching quality.

[0029] like Figure 2 As shown, the interactive method of the teaching interactive system based on virtual digital human comprises the following steps: Step 1: Log in to the virtual digital human interaction platform based on the target student’s account registration information, and establish interaction between the virtual teacher and the target student based on the account registration information; Step 2: Use the physiological characteristics of the target student through biometric technology to identify the authenticity of the target student.

[0030] Step 3: Collect the interaction information between the target students and the virtual teacher, which includes the teaching information of the virtual teacher at each designated course node in a course learning cycle, and the in-class response information of the target students at the designated course node.

[0031] Step 4: Extract the corresponding teaching information based on the in-class response information, and import the teaching information into the knowledge review set; the specific operations include: The score corresponding to the in-class answer information is marked as YF, and compared with the preset score threshold FP; If YF≤FP, it means that the target students have a low amount of knowledge acquisition about the specified course node, and the teaching information of the corresponding specified course node is extracted; If YF>FP, the teaching information of the corresponding specified course node will not be extracted; Step 5: insert the teaching information in the knowledge review set into the next course learning cycle, and obtain new in-class response information corresponding to the specified course node of the teaching information; The new in-class response information is the new score of the test questions made by the target students in the next course learning cycle based on the teaching information; Step 6: Eliminate the teaching information in the knowledge review set according to the new in-class response information; the specific operation is: The score corresponding to the new in-class response information is marked as YF0, and compared with the preset score threshold FP; If YF0>FP, the corresponding teaching information will be removed from the knowledge review set; If YF0≤FP, it means that the target students have a low amount of knowledge absorption about the specified course node in the next course learning cycle, and the corresponding teaching information in the knowledge review set is not eliminated.

[0032] By adopting this method and applying artificial intelligence technology, we can achieve accurate grasp of students' learning situation and personalized teaching, which helps to improve students' learning efficiency and effectiveness.

[0033] It should be noted that the above detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present application belongs.

[0034] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should also be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0036] In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0037] For ease of description, spatially relative terms, such as "above", "above", "on the upper surface of", "above", etc., may be used herein to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" may include both "above" and "below". The device may also be positioned in other different ways, such as rotated 90 degrees or in other orientations, and the spatially relative descriptions used herein are interpreted accordingly.

[0038] In the above detailed description, reference is made to the accompanying drawings, which form a part of this document. In the accompanying drawings, similar symbols typically identify similar components unless the context indicates otherwise. The illustrated embodiments described in the detailed description, drawings, and claims are not meant to be limiting. Other embodiments may be used, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein.

[0039] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A teaching interaction system based on virtual digital human, characterized in that: It includes information collection module, information processing module and review analysis module, among which: An information collection module is used to collect the interaction information between the target students and the virtual digital human; the interaction information includes the teaching information of the virtual digital human at each designated course node in a course learning cycle, and the in-class response information of the target students at the designated course node; An information processing module is used to extract corresponding teaching information according to the in-class response information, and then import the teaching information into a knowledge review set, wherein the knowledge review set stores the teaching information corresponding to the specified course node; The review analysis module is used to insert the teaching information of the knowledge review into the next course learning cycle.

2. The teaching interactive system based on virtual digital human according to claim 1 is characterized in that: The teaching information is the voice information of the virtual digital person, and the in-class answer information is the score of the test questions made by the target students based on the course content of the specified course node.

3. The teaching interactive system based on virtual digital human according to claim 1 is characterized in that: The information processing module extracts the teaching information in the following manner: The score corresponding to the in-class response information is marked as YF, and YF is compared with the preset score threshold FP: If YF≤FP, extract the teaching information of the corresponding specified course node; If YF>FP, the teaching information of the corresponding specified course node will not be extracted.

4. The teaching interactive system based on virtual digital human according to claim 2 is characterized in that: The review analysis module is also used to obtain new in-class response information corresponding to the specified course node of the teaching information, and transmit the new in-class response information to the information processing module; Among them, the new in-class response information is the test score of the target students in the next course learning cycle based on the teaching information; The information processing module removes the teaching information in the knowledge review set according to the new in-class response information.

5. The teaching interactive system based on virtual digital human according to claim 4 is characterized in that: The culling process is as follows: The score corresponding to the new in-class response information is marked as YF0, and YF0 is compared with the preset score threshold FP: If YF0>FP, the corresponding teaching information will be eliminated from the knowledge review set; If YF0≤FP, the corresponding teaching information in the knowledge review set will not be eliminated.

6. The teaching interactive system based on virtual digital human according to claim 1 is characterized in that: Also includes: A verification login module is used to log in to the virtual digital human interaction platform according to the target student's account registration information, and to establish interaction between the virtual digital human and the target student according to the account registration information; The secondary verification module is used to identify the authenticity of the target student through biometric technology; wherein the biometric technology uses the physiological characteristics of the target student to identify the authenticity of the target student.

7. The teaching interactive system based on virtual digital human according to claim 1 is characterized in that: Also includes: The inductive analysis module is used to summarize and analyze the difficulty of the designated course nodes in each course learning cycle based on the teaching information in the corresponding knowledge review set of several target students, and calculate the difficulty coefficient of each designated course node; The review analysis module is also used to determine the minimum number of insertion times of the knowledge review concentrated teaching information in other multiple course learning cycles according to the difficulty coefficient of the knowledge review concentrated teaching information.

8. The teaching interaction system based on virtual digital human according to claim 7 is characterized in that: The specific method of summarizing and analyzing the difficulties is as follows: Select a course learning cycle and uniquely code each designated course node in the course learning cycle; Extract the number of identical coding marks in the corresponding knowledge review sets of several target students; At the same time, in the corresponding knowledge review sets of all target students, the number of times the teaching information corresponding to the same coding mark is inserted in other course learning cycles is obtained, and the average number of times the teaching information corresponding to the same coding mark in the corresponding knowledge review sets of each target student is inserted in other course learning cycles is calculated; Then, the difficulty coefficient Ui of each designated course node is calculated through Ui=MSi*β1+MCPi*β2; In the formula, MSi represents the number of simultaneous coding marks in the corresponding knowledge review set of all target students, MCPi represents the average number of insertions of the teaching information corresponding to the same coding mark in other course learning cycles, β1 and β2 are preset proportional coefficients, and the proportions of MSi and MCPi are adjusted according to needs when calculating Ui.

9. The teaching interaction system based on virtual digital human according to claim 8 is characterized in that: The method for determining the number of insertion times is: multiplying the difficulty coefficient by a preset insertion factor to obtain a result value, and rounding the result value upward to obtain the number of insertion times.

10. A teaching interaction method based on virtual digital human, implemented by the teaching interaction system based on virtual digital human according to any one of claims 1 to 9, characterized in that: The steps include: Step 1: Log in to the virtual digital human interaction platform based on the target student’s account registration information, and establish interaction between the virtual digital human and the target student based on the account registration information; Step 2: Use the physiological characteristics of the target student through biometric technology to identify the authenticity of the target student; Step 3: Collect the interaction information between the target students and the virtual digital human; Step 4: Extract the corresponding teaching information based on the in-class response information, and import the teaching information into the knowledge review set; Step 5: insert the teaching information in the knowledge review set into the next course learning cycle, and obtain new in-class response information corresponding to the specified course node of the teaching information; Step 6: Eliminate the teaching information in the knowledge review set based on the new in-class response information.

Images