Intelligent interactive teaching method and device, equipment and storage medium

Abstract

The invention discloses an intelligent interactive teaching method and device, equipment and a storage medium, and the method comprises the steps: obtaining user information and a function module set of a target teaching application when a user interacts with the target teaching application, and enabling the function module set to comprise at least one interaction function module; determining a function application scheme based on the user information; and based on the function application scheme, selecting a target function module from the function module set, and implementing a function corresponding to the target function module on the target teaching application so as to realize interactive teaching between a user and the target teaching application. According to the application, the target function module suitable for the user is selected from the function module set according to the function application scheme obtained by analyzing the user information, and the function corresponding to the target function module is implemented on the target teaching application, so that the content causing psychological injury to the child is prevented from being displayed to the child.

Description

Technical Field

[0001] This application relates to the field of augmented reality technology, and particularly to an intelligent interactive teaching method, device, equipment and storage medium. Background Art

[0002] With the development of children's education, there are currently many interactive teaching resources for children's education. How to improve the learning quality of children's education is a problem that needs to be solved currently.

[0003] In the related art, an AR (Augmented Reality) preschool education machine is adopted to provide children with interactive videos / or pictures to achieve immersive education and teaching, so as to improve the learning quality of children's education. However, the interactive videos / or pictures all display fixed content. If children feel uncomfortable with the content, there will be a risk of causing psychological harm to children in the immersive teaching experience. Summary of the Invention

[0004] The main purpose of this application is to provide an intelligent interactive teaching method, device, equipment and storage medium, aiming to solve the technical problem of the risk of causing psychological harm to children in the existing technology.

[0005] To achieve the above purpose, this application provides an intelligent interactive teaching method, and the intelligent interactive teaching method includes:

[0006] When a user interacts with a target teaching application, obtain user information and a set of function modules of the target teaching application, where the set of function modules includes at least one module with an interactive function;

[0007] Determine a function application plan based on the user information;

[0008] Based on the function application plan, select a target function module from the set of function modules, and implement the function corresponding to the target function module on the target teaching application to achieve interactive teaching between the user and the target teaching application.

[0009] Optionally, the step of selecting a target function module from the set of function modules based on the function application plan and implementing the function corresponding to the target function module on the target teaching application includes:

[0010] Select a target function module from the set of function modules based on the function application plan, and determine the application degree information of each target function module;

[0011] Implement the functions corresponding to each target function module on the target teaching application based on the application information.

[0012] Optionally, the step of determining a functional application solution based on the user information includes:

[0013] Input the user information into a preset application solution construction model, and based on the application solution construction model, perform functional application analysis on the user information to obtain a functional application solution;

[0014] Among them, the solution construction model is obtained by iteratively training a preset model to be trained based on user information samples and functional application solution labels of the user information samples, so as to obtain an application solution construction model that meets the accuracy conditions.

[0015] Optionally, before the step of inputting the user information into a preset application solution construction model and performing functional application analysis on the user information based on the application solution construction model to obtain a functional application solution, the method includes:

[0016] Obtain user information samples and functional application solution labels of the user information samples;

[0017] Based on the user information samples and the functional application solution labels of the user information samples, iteratively train a preset model to be trained to obtain an application solution construction model that meets the accuracy conditions.

[0018] Optionally, the step of iteratively training a preset model to be trained based on the user information samples and the functional application solution labels of the user information samples to obtain an application solution construction model that meets the accuracy conditions includes:

[0019] Input the user information samples into a preset model to be trained to obtain a predicted functional application solution;

[0020] Calculate the difference between the predicted functional application solution and the functional application solution label of the user information sample to obtain an error result;

[0021] Based on the error result, determine whether the error result meets the error standard indicated by a preset error threshold range;

[0022] If the error result does not meet the error standard indicated by the preset error threshold range, return to the step of inputting the user information samples into a preset model to be trained to obtain a predicted functional application solution, and stop training until the error result meets the error standard indicated by the preset error threshold range, so as to obtain an application solution construction model that meets the accuracy conditions.

[0023] Optionally, the user information includes user age information, and the step of obtaining the user information includes:

[0024] Collect user data, where the user data includes at least one of image data, voice data, and profile data;

[0025] Based on the user data, determine the user age information.

[0026] Optionally, the step of determining the user age information based on the user data includes:

[0027] Based on the age information and / or education information in the profile information, perform an age score on the user to obtain a first score;

[0028] Based on the face information in the image data, perform an age score on the user to obtain a second score;

[0029] Based on the pitch information in the voice information, perform an age score on the user to obtain a third score;

[0030] Based on the first score, the second score, and the third score, determine a score influence value;

[0031] Based on the score influence value, determine the first weight, the second weight, and the third weight corresponding to the profile information, the image information, and the voice information respectively;

[0032] Based on the first score, the second score, the third score, the first weight, the second weight, and the third weight, determine the user age information.

[0033] This application also provides an intelligent interactive teaching device, and the intelligent interactive teaching device includes:

[0034] An acquisition module, configured to acquire user information and a set of function modules of the target teaching application when the user interacts with the target teaching application, where the set of function modules includes modules with at least one interactive function;

[0035] A determination module, configured to determine a function application plan based on the user information;

[0036] An implementation module, configured to select a target function module from the set of function modules based on the function application plan, and implement the function corresponding to the target function module on the target teaching application to achieve interactive teaching between the user and the target teaching application.

[0037] This application also provides an intelligent interactive teaching device, and the intelligent interactive teaching device includes: a memory, a processor, and a program stored on the memory for implementing the intelligent interactive teaching method,

[0038] The memory is used to store a program for implementing the intelligent interactive teaching method;

[0039] The processor is used to execute a program for implementing the intelligent interactive teaching method to implement the steps of the intelligent interactive teaching method.

[0040] The present application also provides a storage medium, on which a program for implementing the intelligent interactive teaching method is stored. The program for implementing the intelligent interactive teaching method is executed by a processor to implement the steps of the intelligent interactive teaching method.

[0041] An intelligent interactive teaching method, device, equipment and storage medium provided by the present application. Compared with the related art in which the interactive video and / or picture display fixed content, if a child feels uncomfortable with the content, it will cause a risk of psychological harm to the child in the immersive teaching experience. In the present application, when a user interacts with a target teaching application, user information and a set of function modules of the target teaching application are obtained, wherein the set of function modules includes at least one module with an interactive function; based on the user information, a function application scheme is determined; based on the function application scheme, a target function module is selected from the set of function modules, and the function corresponding to the target function module is implemented on the target teaching application to realize the interactive teaching between the user and the target teaching application. That is, in the present application, according to the function application scheme obtained by analyzing the user information, a target function module suitable for the user is selected from the set of function modules, and the function corresponding to the target function module is implemented on the target teaching application, so as to avoid displaying content that may cause psychological harm to children. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings here are incorporated into the specification and form a part of this specification, showing the embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0043] Figure 1 It is a schematic diagram of the device structure of the hardware operating environment involved in the solution of the embodiment of the present application;

[0044] Figure 2 It is a schematic flowchart of the first embodiment of the intelligent interactive teaching method of the present application;

[0045] Figure 3 It is a schematic diagram of the modules of the intelligent interactive teaching device of the present application.

[0046] The realization of the purpose of this application, its functional features and advantages will be further described in conjunction with the embodiments and with reference to the accompanying drawings. Detailed implementation manners

[0047] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0048] As Figure 1 shown, Figure 1 is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment solution of this application.

[0049] The terminal in the embodiment of this application can be a PC, or a mobile terminal device with a display function such as a smart phone, a tablet computer, an e-book reader, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, a portable computer, etc.

[0050] As Figure 1 shown, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0051] Optionally, the terminal may further include a camera, an RF (Radio Frequency) circuit, sensors, an audio circuit, a WiFi module, and so on. Among them, the sensors such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. Among them, the ambient light sensor can adjust the brightness of the display screen according to the brightness of the ambient light, and the proximity sensor can turn off the display screen and / or the backlight when the mobile terminal moves to the ear. As a kind of motion sensor, the gravity acceleration sensor can detect the magnitude of the acceleration in each direction (generally three axes). When stationary, it can detect the magnitude and direction of gravity, and can be used for applications that identify the posture of the mobile terminal (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; of course, the mobile terminal can also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, etc., which will not be elaborated here.

[0052] Those skilled in the art can understand that Figure 1 the terminal structure shown in does not constitute a limitation on the terminal, and may include more or fewer components than shown in the figure, or combine some components, or arrange different components.

[0053] As Figure 1 shown, in the memory 1005 as a kind of computer storage medium, there may be an operating device, a network communication module, a user interface module, and an intelligent interactive teaching program.

[0054] In Figure 1 the terminal shown, the network interface 1004 is mainly used to connect to the background server and communicate with the background server for data; the user interface 1003 is mainly used to connect to the client (user side) and communicate with the client for data; and the processor 1001 can be used to call the intelligent interactive teaching program stored in the memory 1005.

[0055] Referring to Figure 2 , the embodiment of the present application provides an intelligent interactive teaching method, and the intelligent interactive teaching method includes:

[0056] Step S100, when the user interacts with the target teaching application, obtain the user information and the function module set of the target teaching application, where the function module set includes at least one module with an interactive function;

[0057] Step S200, based on the user information, determine a functional application solution;

[0058] Step S300, based on the functional application solution, select a target functional module from the functional module set, and implement the function corresponding to the target functional module on the target teaching application to achieve interactive teaching between the user and the target teaching application.

[0059] In this embodiment, the application scenarios are:

[0060] As an example, the scenario of intelligent interactive teaching can be that children use AR devices to interact with smart books. In the related technology, AR (Augmented Reality) preschool teaching machines are used to provide children with interactive videos and / or pictures to achieve immersive education and teaching, so as to improve the learning quality of children's education. However, the interactive videos and / or pictures all display fixed content. If children are uncomfortable with the content, the immersive teaching experience may cause psychological harm to children. For this scenario, the intelligent interactive teaching method of this embodiment selects a target functional module suitable for the user from a set of functional modules through a functional application solution obtained by analyzing user information, and implements the functions corresponding to the target functional module on the target teaching application to avoid showing children content that may cause psychological harm to children.

[0061] As an example, the application scenarios of intelligent interactive teaching include not only the above-mentioned children using AR devices and smart books for interactive teaching, but also various intelligent interactive teaching scenarios, which are not specifically limited here.

[0062] This embodiment aims to avoid showing children content that may cause psychological harm to them.

[0063] In this embodiment, the intelligent interactive teaching method is applied to an intelligent interactive teaching device.

[0064] The specific steps are as follows:

[0065] Step S100, when a user interacts with a target teaching application, obtaining user information and a set of functional modules of the target teaching application, wherein the set of functional modules includes a module of at least one interactive function;

[0066] In this embodiment, the users include children, students, adults, etc., and children are preferably selected in this application; the target teaching application is an application program for teaching purposes, and its specific manifestation forms can be videos or pictures. The corresponding devices for the target teaching application can be AR devices, smart books, mobile phones, computers, televisions, etc., and AR devices or smart books are preferably selected; the user information includes but is not limited to user age, user hobby information, user personality information, and user age is preferably selected; the function module set of the target teaching application includes at least one module with an interaction function. Specifically, the function modules can be a scene model generation module, a character model generation module, and a sound effect generation module. Further subdivided, the character model generation module can also be divided into a model generation module for character A and a model generation module for character B, and the scene model generation module is divided into an X-scene generation module and a Y-scene generation module. The purpose of the function modules is to interact with the user. For example, the scene model generation module is to display a scene picture to the user, and the sound effect generation module is to emit the sound effects or sounds included in the picture to the user.

[0067] Specifically, step S100 includes the following steps S110 - S120:

[0068] Step S110, collect user data, where the user data includes at least one of image data, voice data, and material data;

[0069] In this embodiment, the device collects user data, where the user data includes at least one of image data, voice data, and material data. Specifically, the device includes hardware such as cameras and microphones. Among them, the cameras and microphones can be independent of the application device (both built-in and external are acceptable). The camera is used to collect images of users or audiences in real time, and the microphone is used to collect the voices of users or audiences in real time.

[0070] In this embodiment, the material data includes but is not limited to user age and user education information. For application devices that require logging in to conduct interactive teaching, user materials can be obtained or retrieved from the user login system, etc., and user age, user education information, etc. can be obtained through the user materials.

[0071] Step S120, based on the user data, determine the user age information.

[0072] In this embodiment, the device combines at least one of image data, voice data, and material data to determine the user age information.

[0073] Specifically, step S120 includes the following steps S121 - S126:

[0074] Step S121: Based on the age information and / or educational information in the material information, perform an age score on the user to obtain a first score.

[0075] In this embodiment, the device performs an age score on the user based on the age information and / or educational information in the material information to obtain a first score. Specifically, the age information and / or educational information are input into a preset age prediction model to obtain a score.

[0076] Step S122: Based on the face information in the image data, perform an age score on the user to obtain a second score.

[0077] In this embodiment, the device performs an age score on the user based on the face information in the image data to obtain a second score. Specifically, the device inputs the face information in the image information into a preset minor face recognition model to obtain a first score of the user's age.

[0078] Step S123: Based on the pitch information in the voice information, perform an age score on the user to obtain a third score.

[0079] In this embodiment, the device performs an age score on the user based on the pitch information in the voice information to obtain a third score. Specifically, if the pitch in the pitch information is relatively low, such as lower than a first preset pitch value, it is considered that the age is relatively large; conversely, if the pitch is relatively high, such as higher than a second preset pitch value, it is considered that the age is relatively small. Here, the first preset pitch value is lower than the second preset pitch value. In this embodiment, an age score is performed on the user based on a preset pitch processing model.

[0080] Step S124: Determine a score influence value based on the first score, the second score, and the third score.

[0081] In this embodiment, the device determines a scoring influence value based on the first score, the second score, and the third score. Here, the scoring influence value refers to the influence value among the first score, the second score, and the third score. Since there are significant differences among the first score, the second score, and the third score, that is, the user profile information does not match the determination of the user's portrait and tone regarding age, this application introduces the scoring influence value. The scoring influence value reflects the reliability of the scores. The scoring influence value includes a first influence value between the first score and the second score, a second influence value between the second score and the third score, and a third influence value between the first score and the third score. The larger the scoring influence value, the greater the difference among the scores. For example, if the age information in the profile is 12 years old, the corresponding first score is the age score of 12 years old, the face information in the image data corresponds to the second score of 6 years old, and the tone information in the voice information corresponds to the third score of 5 years old. Then the first influence value is 7, the second influence value is 2, and the third influence value is 8. Combining the above three influence values reflects the reliability of the scores, that is, the larger the influence value, the worse the reliability among the scores. The first influence value and the third influence value are large, and both of them include the first score, while the second influence value is small. Therefore, it indicates that the reliability of the first score is poor, and the reliability of the second score and the third score is strong.

[0082] Step S125: Based on the scoring influence value, determine the first weight, the second weight, and the third weight corresponding to the profile information, the image information, and the voice information respectively;

[0083] In this embodiment, combining the above three influence values reflects the reliability of the scores. According to the reliability of each score, the device determines the first weight, the second weight, and the third weight corresponding to the profile information, the image information, and the voice information respectively. The higher the reliability of the score, the higher the corresponding weight value, and the lower the reliability of the score, the lower the corresponding weight value. For example, if the reliability of the first score is poor and the reliability of the second score and the third score is strong, then the first weight is less than the second weight, and the second weight is less than the third weight.

[0084] Step S126: Based on the first score, the second score, the third score, the first weight, the second weight, and the third weight, determine the user age information.

[0085] In this embodiment, the device calculates the user age based on the first score, the second score, the third score, the first weight, the second weight, and the third weight, and determines the user age information.

[0086] Step S200: Based on the user information, determine the functional application solution;

[0087] In this embodiment, the functional application solution is a solution indicating the combination of functional modules. The device determines the functional application solution based on the user information. Specifically, the device selects the content corresponding to the modules in the functional modules that will not cause psychological harm to users of this age according to the user age. For example, if the user age is 6 years old, the set of functional modules of the target teaching application includes a model generation module for character A, a model generation module for character B, an X-scene generation module, and a Y-sound effect generation module. Among them, the model of character A in the model generation module for character A is not suitable for 6-year-old children to watch. Therefore, in the functional application solution, the model generation module for character B, the X-scene generation module, and the Y-sound effect generation module are selected. That is, when the user interacts with the target teaching application, the target teaching application presents the user with character B, the X-scene, and the Y-sound effect, and removes part of character A, that is, does not present character A.

[0088] In this embodiment, the ways for the device to determine the functional application solution based on the user information include: constructing a pre-trained application solution construction model, matching the user information with it, and obtaining the corresponding functional application solution; or determining the functional application solution according to the mapping between the user information and the corresponding functional modules.

[0089] Specifically, step S200 includes the following step S210:

[0090] In step S210, the user information is input into a preset application solution construction model. Based on the application solution construction model, functional application analysis is performed on the user information to obtain a functional application solution. Among them, the solution construction model is obtained by iteratively training a preset model to be trained based on user information samples and the functional application solution labels of the user information samples, so as to obtain an application solution construction model that meets the accuracy conditions.

[0091] In this embodiment, the device inputs the user information into a preset application solution construction model. Based on the application solution construction model, functional application analysis is performed on the user information to obtain a functional application solution. Specifically, the application solution construction model is a pre-trained deep network learning model. The model is obtained by iteratively training a preset model to be trained based on user information samples and the functional application solution labels of the user information samples, so as to obtain an application solution construction model that meets the accuracy conditions, thereby improving the accuracy of determining the functional application solution.

[0092] In step S300, based on the functional application solution, target functional modules are selected from the set of functional modules, and the functions corresponding to the target functional modules are implemented on the target teaching application to realize the interactive teaching between the user and the target teaching application.

[0093] In this embodiment, based on the function application solution, the device selects target function modules from the function module set, and implements the functions corresponding to the target function modules on the target teaching application to achieve interactive teaching between the user and the target teaching application. For example, if the function generation module of character B, the X-scene generation module, and the Y-sound effect generation module are selected in the function application solution, the device selects the model generation module of character B, the X-scene generation module, and the Y-sound effect generation module from the function module set (including the model generation module of character A, the model generation module of character B, the X-scene generation module, and the Y-sound effect generation module). When the user interacts with the target teaching application, the target teaching application displays character B, the X-scene, and the Y-sound effect to the user, and removes part of character A, that is, does not display character A, that is, implements the functions corresponding to the target function modules to achieve interactive teaching between the user and the target teaching application.

[0094] Specifically, step S300 includes the following steps S310 - S320:

[0095] Step S310, based on the function application solution, selects target function modules from the function module set, and determines the application degree information of each target function module;

[0096] In this embodiment, based on the function application solution, the device selects target function modules from the function module set and determines the application degree information of each target function module. The application degree information of the target function module is that the developer sets at least one application degree for each target function module. For example, the application degree of the model of the lion in the model generation module of the lion includes the model of a gentle lion image (the first degree), the model of a strong lion image (the second degree), and the model of a fierce lion image (the third degree), that is, the application degree refers to different images of the model; it can also be that the application degree of the sound effect in the scene sound effect generation module includes a gentle sound effect (the first degree), a gloomy and mysterious sound effect (the second degree), and a strong and exciting sound effect (the third degree), that is, the application degree refers to different styles of the sound effect.

[0097] Step S320, based on the application information, implements the functions corresponding to each target function module on the target teaching application.

[0098] In this embodiment, the device implements the functions corresponding to each of the target function modules on the target teaching application based on the application information. For example, if the user's age is 6 years old, the function module set of the target teaching application includes a model generation module for a gentle lion image, a model generation module for a fierce lion image, a gentle sound effect generation module, and a gloomy and mysterious sound effect generation module. Since 6-year-old children may feel uncomfortable with fierce lion images and gloomy and mysterious sound effects, the device determines the function application plan as the model generation module for a gentle lion image and the gentle sound effect generation module according to the user age information. Based on the function application plan, the target function modules are selected from the function module set, and the functions corresponding to the target function modules are implemented on the target teaching application, presenting a gentle lion image and gentle sound effects to the user to achieve interactive teaching between the user and the target teaching application.

[0099] Compared with the related art where interactive videos and / or pictures display fixed content, and if children feel uncomfortable with the content, it may pose a risk of psychological harm to children in the immersive teaching experience. In this application, when the user interacts with the target teaching application, user information and the function module set of the target teaching application are obtained, where the function module set includes at least one module with an interactive function; based on the user information, a function application plan is determined; based on the function application plan, target function modules are selected from the function module set, and the functions corresponding to the target function modules are implemented on the target teaching application to achieve interactive teaching between the user and the target teaching application. That is, in this application, through the function application plan obtained by analyzing the user information, suitable target function modules for the user are selected from the function module set, and the functions corresponding to the target function modules are implemented on the target teaching application to prevent showing content that may cause psychological harm to children.

[0100] Based on the above first embodiment, this application also provides another embodiment. The intelligent interactive teaching method includes:

[0101] Before the step S210 of inputting the user information into a preset application plan construction model and performing function application analysis on the user information based on the application plan construction model to obtain a function application plan, the method includes the following steps A100 - A200:

[0102] Step A100, obtaining a user information sample and the function application plan label of the user information sample;

[0103] In this embodiment, the device obtains a user information sample and a functional application scenario label for the user information sample. The user information sample is a sample for training, including a certain amount of user information. The functional application scenario label for the user information sample is a functional application scenario used according to the corresponding user information.

[0104] Step A200: Based on the user information sample and the functional application scenario label for the user information sample, iteratively train a preset model to be trained to obtain an application scenario construction model that meets the accuracy condition.

[0105] In this embodiment, the device iteratively trains a preset model to be trained based on the user information sample and the functional application scenario label for the user information sample to obtain an application scenario construction model that meets the accuracy condition. The model to be trained is a preset initial model that can basically process the user information sample and predict the functional application scenario, and there is only a difference in accuracy compared with the application scenario construction model.

[0106] Specifically, step A200 includes the following steps A210 - A240:

[0107] Step A210: Input the user information sample into the preset model to be trained to obtain a predicted functional application scenario.

[0108] In this embodiment, the device inputs the user information sample into the preset model to be trained to obtain a predicted functional application scenario. The model to be trained is a preset initial model that can basically process the user information sample and predict the functional application scenario, and there is only a difference in accuracy compared with the application scenario construction model. The predicted functional application scenario is the functional application scenario predicted by the model to be trained for the user information sample.

[0109] Step A220: Calculate the difference between the predicted functional application scenario and the functional application scenario label for the user information sample to obtain an error result.

[0110] In this embodiment, the device calculates the difference between the predicted functional application scenario and the functional application scenario label for the user information sample to obtain an error result. This method can also obtain the error result through the convergence of a loss function.

[0111] Step A230: Based on the error result, determine whether the error result meets the error standard indicated by a preset error threshold range.

[0112] In this embodiment, based on the error result, the device determines whether the error result meets the error standard indicated by a preset error threshold range. Among them, the preset error threshold includes a preset mean square error threshold. As is known to those skilled in the art, the smaller the mean square error threshold, the more accurate the model. The determination of whether the training error result meets the error standard indicated by the preset error threshold includes: determining whether the mean square error result is less than the preset mean square error threshold.

[0113] Step A240, if the error result does not meet the error standard indicated by the preset error threshold range, return to the step of inputting the user information sample into a preset model to be trained to obtain a predicted function application solution, until the error result meets the error standard indicated by the preset error threshold range, and then stop training to obtain an application solution construction model that meets the accuracy condition.

[0114] In this embodiment, if the error result does not meet the error standard indicated by the preset error threshold range, return to the step of inputting the function requirement sample into a preset model to be trained to obtain an initial prediction system construction solution and the module adaptability evaluation of the initial prediction system construction solution, until the training error result meets the error standard indicated by the preset error threshold range, and then stop training to obtain a solution construction model that meets the accuracy condition. That is, in this embodiment, through iterative training, the model to be trained is converged until the training error result meets the error standard indicated by the preset error threshold range, and the iterative training is completed.

[0115] This application also provides an intelligent interactive teaching device. Refer to Figure 3 , the intelligent interactive teaching device includes:

[0116] An acquisition module 10, configured to acquire user information and a function module set of the target teaching application when a user interacts with the target teaching application, where the function module set includes at least one module with an interaction function;

[0117] A determination module 20, configured to determine a function application solution based on the user information;

[0118] An implementation module 30, configured to select a target function module from the function module set based on the function application solution, and implement the function corresponding to the target function module on the target teaching application to implement interactive teaching between the user and the target teaching application.

[0119] Optionally, the implementation module 30 includes:

[0120] An application degree determination module, configured to select a target function module from the function module set based on the function application solution, and determine the application degree information of each target function module;

[0121] A function implementation module, configured to implement functions corresponding to each of the target function modules on the target teaching application based on the application information.

[0122] Optionally, the determination module 20 includes:

[0123] An analysis module, configured to input the user information into a preset application solution construction model, and perform function application analysis on the user information based on the application solution construction model to obtain a function application solution; wherein, the solution construction model is obtained by iteratively training a preset model to be trained based on user information samples and function application solution labels of the user information samples, so as to obtain an application solution construction model that meets the accuracy condition.

[0124] Optionally, the intelligent interactive teaching device further includes:

[0125] A sample acquisition module, configured to acquire user information samples and function application solution labels of the user information samples;

[0126] A training module, configured to iteratively train a preset model to be trained based on user information samples and function application solution labels of the user information samples, so as to obtain an application solution construction model that meets the accuracy condition.

[0127] Optionally, the training module includes:

[0128] An input module, configured to input the user information sample into a preset model to be trained to obtain a predicted function application solution;

[0129] A calculation module, configured to perform difference calculation between the predicted function application solution and the function application solution label of the user information sample to obtain an error result;

[0130] A judgment module, configured to judge whether the error result meets the error standard indicated by a preset error threshold range based on the error result;

[0131] An iterative training module, configured to, if the error result does not meet the error standard indicated by the preset error threshold range, return to the step of inputting the user information sample into a preset model to be trained to obtain a predicted function application solution, and stop training until the error result meets the error standard indicated by the preset error threshold range, so as to obtain an application solution construction model that meets the accuracy condition.

[0132] Optionally, the acquisition module 10 includes:

[0133] A collection module for collecting user data, where the user data includes at least one of image data, voice data, and profile data;

[0134] An age determination module for determining user age information based on the user data.

[0135] Optionally, the age determination module includes:

[0136] A first scoring module for scoring the user's age based on the age information and / or educational information in the profile information to obtain a first score;

[0137] A second scoring module for scoring the user's age based on the face information in the image data to obtain a second score;

[0138] A third scoring module for scoring the user's age based on the pitch information in the voice information to obtain a third score;

[0139] A scoring influence value determination module for determining a scoring influence value based on the first score, the second score, and the third score;

[0140] A weight determination module for determining the first weight, the second weight, and the third weight corresponding to the profile information, the image information, and the voice information respectively based on the scoring influence value;

[0141] A user age information determination module for determining user age information based on the first score, the second score, the third score, the first weight, the second weight, and the third weight.

[0142] The specific implementation manner of the intelligent interactive teaching device in this application is basically the same as that of the above-mentioned intelligent interactive teaching method embodiments, and will not be elaborated here.

[0143] Refer to Figure 1 , Figure 1 is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment solution of this application.

[0144] As Figure 1As shown in the figure, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0145] Optionally, the intelligent interactive teaching device may further include a rectangular user interface, a network interface, a camera, an RF (Radio Frequency) circuit, sensors, an audio circuit, a WiFi module, and so on. The rectangular user interface may include a display screen (Display) and an input sub-module such as a keyboard (Keyboard). Optionally, the rectangular user interface may further include a standard wired interface and a wireless interface. The network interface may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0146] Those skilled in the art can understand that Figure 1 the structure of the intelligent interactive teaching device shown in

[0147] does not constitute a limitation on the intelligent interactive teaching device, and may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. Figure 1 As shown in

[0148] the figure, the memory 1005, as a storage medium, may include an operating system, a network communication module, and an intelligent interactive teaching program. The operating system is a program for managing and controlling the hardware and software resources of the intelligent interactive teaching device, and supports the operation of the intelligent interactive teaching program and other software and / or programs. The network communication module is used to realize the communication between the components inside the memory 1005, as well as the communication between the intelligent interactive teaching device and other hardware and software in the intelligent interactive teaching system. Figure 1 In the intelligent interactive teaching device shown in

[0149] the figure, the processor 1001 is used to execute the intelligent interactive teaching program stored in the memory 1005 to implement the steps of the intelligent interactive teaching method described in any one of the above.

[0150] The present application also provides a storage medium, on which a program for implementing the intelligent interactive teaching method is stored. The program for implementing the intelligent interactive teaching method is executed by a processor to implement the following intelligent interactive teaching method:

[0151] When a user interacts with a target teaching application, user information and a set of function modules of the target teaching application are obtained, where the set of function modules includes at least one module with an interactive function;

[0152] Based on the user information, a function application plan is determined;

[0153] Based on the function application plan, a target function module is selected from the set of function modules, and the function corresponding to the target function module is implemented on the target teaching application to realize the interactive teaching between the user and the target teaching application.

[0154] Optionally, the step of selecting a target function module from the set of function modules based on the function application plan and implementing the function corresponding to the target function module on the target teaching application includes:

[0155] Based on the function application plan, a target function module is selected from the set of function modules, and the application degree information of each target function module is determined;

[0156] Based on the application information, the functions corresponding to each target function module are implemented on the target teaching application.

[0157] Optionally, the step of determining a function application plan based on the user information includes:

[0158] The user information is input into a preset application plan construction model, and based on the application plan construction model, function application analysis is performed on the user information to obtain a function application plan;

[0159] Wherein, the plan construction model is obtained by iteratively training a preset model to be trained based on user information samples and function application plan labels of the user information samples, so as to obtain an application plan construction model that meets the accuracy condition.

[0160] Optionally, before the step of inputting the user information into a preset application plan construction model and performing function application analysis on the user information based on the application plan construction model to obtain a function application plan, the method includes:

[0161] User information samples and function application plan labels of the user information samples are obtained;

[0162] Iteratively train a preset model to be trained based on the user information sample and the functional application solution label of the user information sample, and obtain an application solution construction model that meets the accuracy condition.

[0163] Optionally, the step of iteratively training a preset model to be trained based on the user information sample and the functional application solution label of the user information sample, and obtaining an application solution construction model that meets the accuracy condition includes:

[0164] Input the user information sample into the preset model to be trained to obtain a predicted functional application solution;

[0165] Calculate the difference between the predicted functional application solution and the functional application solution label of the user information sample to obtain an error result;

[0166] Based on the error result, determine whether the error result meets the error standard indicated by the preset error threshold range;

[0167] If the error result does not meet the error standard indicated by the preset error threshold range, return to the step of inputting the user information sample into the preset model to be trained to obtain a predicted functional application solution, and stop training until the error result meets the error standard indicated by the preset error threshold range, and obtain an application solution construction model that meets the accuracy condition.

[0168] Optionally, the user information includes user age information, and the step of obtaining the user information includes:

[0169] Collect user data, where the user data includes at least one of image data, voice data, and profile data;

[0170] Based on the user data, determine the user age information.

[0171] Optionally, the step of determining the user age information based on the user data includes:

[0172] Based on the age information and / or education information in the profile information, perform an age score on the user to obtain a first score;

[0173] Based on the face information in the image data, perform an age score on the user to obtain a second score;

[0174] Based on the pitch information in the voice information, perform an age score on the user to obtain a third score;

[0175] Based on the first score, the second score, and the third score, determine a score influence value;

[0176] Based on the scoring influence value, determine the first weight, the second weight, and the third weight corresponding to the material information, the image information, and the voice information respectively;

[0177] Based on the first score, the second score, the third score, the first weight, the second weight, and the third weight, determine the user age information.

[0178] The specific implementation manner of the storage medium of this application is basically the same as that of the above-mentioned embodiments of the intelligent interactive teaching method, and will not be elaborated here.

[0179] This application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned intelligent interactive teaching method are implemented.

[0180] The specific implementation manner of the computer program product of this application is basically the same as that of the above-mentioned embodiments of the intelligent interactive teaching method, and will not be elaborated here.

[0181] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitations, the element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0182] The serial numbers of the above-mentioned embodiments of this application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0183] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of this application.

[0184] The above are only the preferred embodiments of this application, and do not limit the patent scope of this application accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of this application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of this application.

Claims

1. An intelligent interactive teaching method, characterized in that: The intelligent interactive teaching method comprises: When a user interacts with a target teaching application, user information and a set of functional modules of the target teaching application are obtained, wherein the set of functional modules includes a module of at least one interactive function; Determine a function application solution based on the user information; Based on the functional application scheme, a target functional module is selected from the functional module set, and the function corresponding to the target functional module is implemented on the target teaching application to achieve interactive teaching between the user and the target teaching application.

2. The intelligent interactive teaching method according to claim 1, characterized in that: The step of selecting a target functional module from the functional module set based on the functional application scheme, and implementing the function corresponding to the target functional module on the target teaching application includes: Based on the functional application scheme, selecting a target functional module from the functional module set, and determining application degree information of each target functional module; Based on the application information, the functions corresponding to the target functional modules are implemented on the target teaching application.

3. The intelligent interactive teaching method according to claim 1, characterized in that: The step of determining a function application scheme based on the user information includes: Inputting the user information into a preset application solution construction model, and performing functional application analysis on the user information based on the application solution construction model to obtain a functional application solution; The solution construction model is based on user information samples and function application solution labels of the user information samples, and iteratively trains a preset model to be trained to obtain an application solution construction model that meets accuracy requirements.

4. The intelligent interactive teaching method according to claim 3, characterized in that: Before the step of inputting the user information into a preset application solution construction model, and performing functional application analysis on the user information based on the application solution construction model to obtain a functional application solution, the method includes: Obtaining a user information sample and a functional application solution label of the user information sample; Based on the user information samples and the functional application solution labels of the user information samples, the preset model to be trained is iteratively trained to obtain an application solution construction model that meets the accuracy requirements.

5. The intelligent interactive teaching method according to claim 4, characterized in that: The step of iteratively training a preset model to be trained based on the user information sample and the functional application solution label of the user information sample to obtain an application solution construction model that meets the accuracy condition includes: Inputting the user information sample into a preset model to be trained to obtain a prediction function application solution; Calculate the difference between the predicted function application scheme and the function application scheme label of the user information sample to obtain an error result; Based on the error result, determining whether the error result meets an error standard indicated by a preset error threshold range; If the error result does not meet the error standard indicated by the preset error threshold range, return to the step of inputting the user information sample into the preset model to be trained to obtain a prediction function application solution, and stop training until the error result meets the error standard indicated by the preset error threshold range to obtain an application solution construction model that meets the accuracy conditions.

6. The intelligent interactive teaching method according to claim 1, characterized in that: The user information includes user age information, and the step of obtaining the user information includes: Collecting user data, wherein the user data includes at least one of image data, voice data and profile data; Based on the user data, user age information is determined.

7. The intelligent interactive teaching method according to claim 6, characterized in that: The step of determining the user's age information based on the user data comprises: Based on the age information and / or education information in the profile information, performing an age score on the user to obtain a first score; Based on the facial information in the image data, scoring the age of the user to obtain a second score; Based on the tone information in the voice information, scoring the age of the user to obtain a third score; Determining a score impact value based on the first score, the second score, and the third score; Based on the score impact value, determine a first weight, a second weight, and a third weight corresponding to the data information, the image information, and the voice information, respectively; User age information is determined based on the first score, the second score, the third score, the first weight, the second weight, and the third weight.

8. An intelligent interactive teaching device, characterized in that: The intelligent interactive teaching device comprises: An acquisition module, used for acquiring user information and a set of functional modules of the target teaching application when the user interacts with the target teaching application, wherein the set of functional modules includes a module of at least one interactive function; A determination module, used to determine a function application solution based on the user information; An implementation module is used to select a target function module from the function module set based on the function application solution, and implement the function corresponding to the target function module on the target teaching application to achieve interactive teaching between the user and the target teaching application.

9. An intelligent interactive teaching device, characterized in that: The intelligent interactive teaching device comprises: a memory, a processor and a program stored in the memory for implementing the intelligent interactive teaching method. The memory is used to store a program for implementing an intelligent interactive teaching method; The processor is used to execute a program for implementing the intelligent interactive teaching method to implement the steps of the intelligent interactive teaching method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a program for implementing the intelligent interactive teaching method, and the program for implementing the intelligent interactive teaching method is executed by the processor to implement the steps of the intelligent interactive teaching method as described in any one of claims 1 to 7.

Images