AI emotion recognition and training system, method, medium and equipment

Abstract

The invention discloses an AI emotion recognition and training system and method, a medium and equipment, and the system comprises an emotion training module which is used for training different emotions of a trained child; the display module is used for displaying standard level expressions of the trained children so as to guide the trained children to make corresponding facial expressions, and is also used for displaying just shot facial photos of the trained children; the central control module is connected with the emotion training module and the display module and is used for controlling each module to work normally; the audio output module is connected with the central control module and is used for outputting prompt tones and assisting in indicating pictures to guide the trained children to make corresponding facial expressions; and the AI module is used for shooting facial expressions of the trained children and also used for generating standard level expressions of the trained children. According to the system, facial expressions of trained children are shot through the AI module, standard level expressions of the trained children are generated, and the problems of inattention, psychological conflict and the like of the children are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of autism rehabilitation training, and in particular to an AI emotion recognition and training system, method, medium and device. BACKGROUND

[0002] Autism spectrum disorder (ASD) is a neurodevelopmental disease, and the global incidence rate has reached 1 / 36. In China, there are more than 2 million children aged 0-14 with ASD, and the number of new cases increases by 160,000 each year. Clinical studies have shown that 85% of autistic children have difficulty in recognizing and expressing facial expressions, which directly leads to their social interaction disorders, and the specific manifestations are: they cannot accurately understand the emotional intentions of others, they have difficulty in conveying their own emotions through facial expressions, and they have eye avoidance phenomena when interacting with others. Existing research has shown that when autistic children observe their own facial expression models, they can reduce their anxiety, and the activation intensity of their brain mirror neuron system is 2.3 times higher than that of observing other people's faces. Self-referential stimulation is more likely to trigger the neural resonance of the premotor cortex and the superior temporal sulcus, and to rebuild the damaged "observation-mimicry" neural pathway.

[0003] At present, there are many systems and methods for emotional recognition intervention for autistic children, but they all have some defects. Traditional training methods rely on manual observation and feedback, which has the disadvantages of low efficiency, strong subjectivity, and lack of immediate technical support. In the existing technology, although some electronic training tools can provide basic expression demonstrations, they cannot dynamically adjust the difficulty according to individual differences, lack precise analysis and feedback of children's actual expression movements, have poor generalization ability, and have poor long-term maintenance effect. Most of the existing expression libraries use western adult templates, such as IBT, which points out that China lacks localized expression data, and autistic children have a high resistance rate of 68% to non-personal expression. Most training uses static picture teaching, uses standardized expression pictures, lacks dynamic emotion recognition training, and cannot be personalized, while real-time face-to-face intervention training can cause children to avoid eye contact, and autistic children have a resistance rate of 68% to other people's face templates. In addition, some emerging technology training systems, such as AR and VR, have high hardware costs and certain barriers to operation and use, and children being trained are likely to resist the equipment, resulting in poor concentration and low learning interest. SUMMARY

[0004] The AI emotion recognition and training system, method, medium and device provided by the embodiments of the present application solve the technical problem that the existing underwater wireless power supply system does not have feasibility in complex marine environments.

[0005] In order to achieve the above object, the embodiment of the present application provides an AI emotion recognition and training system, which comprises an emotion training module, a display module, a central control module, an audio output module and an AI module, wherein the emotion training module is used for training a trainee child with different emotions, the display module is used for displaying standard level expressions of the trainee child to guide the trainee child to make corresponding facial expressions, and is also used for displaying a photo of the trainee child's face just taken, the central control module is connected with the emotion training module and the display module, and is used for controlling the normal work of each module, the audio output module is connected with the central control module, and is used for outputting a prompt tone and an auxiliary indication picture to guide the trainee child to make corresponding facial expressions, and the AI module is used for taking photos of the trainee child's facial expressions, and is also used for generating standard level expressions of the trainee child.

[0006] Optionally, the emotion training module comprises a happy emotion training module, an angry emotion training module, a sad emotion training module and a surprised emotion training module, wherein the happy emotion training module is used for training the trainee child with a happy emotion, the angry emotion training module is used for training the trainee child with an angry emotion, the sad emotion training module is used for training the trainee child with a sad emotion, and the surprised emotion training module is used for training the trainee child with a surprised emotion.

[0007] Optionally, the AI emotion recognition and training system further comprises a level operation area and a control button area, the level operation area is located at the right side of the desktop, and the level operation area is provided with a level 1 button and a level 2 button; the control button area is located below the desktop, and the control button area is provided with a start button and an end button.

[0008] Optionally, the AI module is provided with a "taking" button and an "AI making" button, the "taking" button is used for controlling the AI module to start taking photos of the trainee child's facial expressions, and the "AI making" button is used for controlling the AI module to start generating standard level expressions of the trainee child.

[0009] In addition, in order to achieve the above object, the embodiment of the present application further provides an AI emotion recognition and training method, which applies the AI emotion recognition and training system of any of the above embodiments, and the method comprises the following steps: based on the AI module, taking a photo of a trainee child's face; based on the result of the photo, generating a plurality of standard level expressions of the trainee child; based on the standard level expressions of the trainee child, dividing different levels of expression training to train the trainee child with different emotions; obtaining a first level expression training result; comparing the training result with the standard level expressions of the trainee child to obtain a similarity score; based on the similarity score, carrying out next level expression training or re-carrying out first level training.

[0010] Optionally, the AI-based module captures a happy face of the child to be trained to obtain a neutral expression of the child to be trained.

[0011] Optionally, the AI-based module captures a happy face of the child to be trained to obtain a neutral expression of the child to be trained.

[0012] Optionally, the AI-based module captures a happy face of the child to be trained to obtain a neutral expression of the child to be trained.

[0013] In addition, to achieve the above object, the embodiment of the present application further provides a computer readable storage medium, which includes instructions, when the instructions are run on a computer, the computer executes the AI emotion recognition and training method described in any embodiment of the present application.

[0014] In addition, to achieve the above object, the embodiment of the present application further provides a computer device, which includes at least one processor, a memory and an input and output unit; wherein the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the AI emotion recognition and training method described in any embodiment of the present application.

[0015] The one or more technical solutions provided in the embodiment of the present application have at least the following technical effects or advantages:

[0016] In the embodiment of the present application, the AI module is used to take pictures of the facial expressions of the trained children, and generate standard checkpoint expressions of the trained children, and the emotion training module is used to train the trained children with different emotions. The training method uses the children's own faces as the imitation object, overcomes the problems of children's lack of concentration and psychological resistance, and improves the sense of immersion. By dividing different levels of expression training, the trained children can start training from low to high levels. This easy-to-difficult training method makes it easier for children to accept, cultivates the emotion recognition ability of autistic children, and improves the generalization ability of autistic children to different emotional expressions in different scenes and social situations. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application, the drawings needed in the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0018] Figure 1 The module schematic diagram of the AI emotion recognition and training system provided in the embodiment of the present application;

[0019] Figure 2 The structure schematic diagram of the AI emotion recognition and training system provided in the embodiment of the present application;

[0020] Figure 3 The side view of the AI emotion recognition and training system provided in the embodiment of the present application;

[0021] Figure 4 The front view of the AI emotion recognition and training system provided in the embodiment of the present application;

[0022] Figure 5 The stm learning table learning module distribution schematic diagram in the present application;

[0023] Figure 6 The flowchart of the AI emotion recognition and training method provided in the embodiment of the present application;

[0024] Figure 7 The AI intelligent capture and material generation schematic diagram provided in the embodiment of the present application;

[0025] Figure 8 The training interface schematic diagram of four kinds of primary emotion training provided in the embodiment of the present application;

[0026] Figure 9 The training interface schematic diagram of four kinds of secondary emotion training provided in the embodiment of the present application;

[0027] Figure 10 The structure schematic diagram of the medium provided in the embodiment of the present application;

[0028] Figure 11 A structural schematic diagram of a computing device provided by an embodiment of the present application.

[0029] In the figure, 6, switch; 8, control button area; 10, screen data line; 11, level operation area; 12, desktop; 13, base; 14, support shaft; 15, adjusting rod; 16, stm screen; 17, stm camera; 18, mounting slot; 19, first USB interface; 20, second USB interface; 21, first wireless communication interface; 22, second wireless communication interface. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0031] In the related description of the embodiments, the terms "include, contain, have" and the like are open terms, which are generally preferred to be understood as including but not limited to; the term "at least one" is generally preferred to be understood as one or more, wherein "more" refers to two or more; the term "at least one of the following" or similar expressions refers to any combination of these items, including any combination of single item or multiple items, for example, "at least one of a, b or c", or "at least one of a, b and c", which can represent a, b, c, a-b (i.e. a and b), a-c, b-c, or a-b-c, wherein a, b, and c can be single or multiple; the symbol "A / B" is used to describe the selection relationship of the associated object, which generally represents the relationship of "or".

[0032] In the following description of the embodiments of the present application, the terms used in the embodiments of the present application are only for the purpose of describing the specific embodiments, and are not intended to limit the present application. The singular forms "a" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0033] Those skilled in the art should understand that in the following description of the embodiments of the present application, the order of the serial numbers does not mean the order of execution, and some or all steps can be executed in parallel or in sequence, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0034] Those skilled in the art should understand that the numerical ranges in the embodiments of the present application should be understood as also specifically disclosing each intermediate value between the upper limit and the lower limit of the range. Each smaller range between any stated value or stated range of values and any other stated value or stated range of values is also included within the present application. The upper and lower limits of these smaller ranges can be independently included or excluded from the range.

[0035] Unless otherwise defined, technical / scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. Although preferred methods and materials are described herein, any methods and materials similar or equivalent to those described herein can be used in the practice or testing of the present application. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods and / or materials in connection with the documents. In the case of conflict, the content of this specification will control.

[0036] To solve the above technical problems, with reference to Figures 1-5 The embodiments of the present application provide an AI emotion recognition and training system, which comprises:

[0037] An emotion training module is configured to train a child trainee in different emotions.

[0038] A display module is configured to display a standard checkpoint expression of the child trainee to guide the child trainee to make a corresponding facial expression, and to display a photo of the child trainee just taken.

[0039] A central control module is connected with the emotion training module and the display module, and is configured to control the normal work of the modules.

[0040] An audio output module is connected with the central control module, and is configured to output a prompt tone to assist the indication picture to guide the child trainee to make a corresponding facial expression.

[0041] An AI module is configured to take a photo of the facial expression of the child trainee, and to generate the standard checkpoint expression of the child trainee.

[0042] Specifically, with reference to Figure 2 and Figure 3 The system further comprises an stm learning table and an stm camera 17, and the stm camera 17 is connected with the display module 120 through a wireless transmission module, which is a first wireless communication interface 21 and a second wireless communication interface 22. The first wireless communication interface 21 and the second wireless communication interface 22 are respectively located in the interior of the stm camera 17 and the display module 120, and are configured to wirelessly connect the two devices.

[0043] The stm learning table comprises a table top 12 connected with a central control module, a supporting shaft 14 arranged at the bottom of the table top 12, and an adjusting rod 15 arranged on the supporting shaft 14 and capable of freely adjusting the height of the table top 12 to adapt to children of different heights.

[0044] Further, the table top 12 is provided with a mounting slot 18 for connecting the display module and the table top 12, a first USB interface 19 and a second USB interface 20, the first USB interface 19 is connected with a screen data line 10, and the second USB interface 20 is used for connecting external equipment (such as a U disk).

[0045] The display module is an stm screen 16 connected with an stm camera 17 through a magnetic interface.

[0046] In addition, the lower end of the supporting shaft 14 is provided with a base 13, which can stably place the stm learning table on the ground.

[0047] In the example embodiment, the AI emotion recognition and training system further comprises:

[0048] A level operation area 11 is arranged at the right side of the table top 12 and provided with a first-level button and a second-level button.

[0049] A control button area 8 is arranged below the table top 12 and provided with a start button and an end button.

[0050] Reference Figure 5 In the example embodiment, the emotion training module comprises:

[0051] A happy emotion training module is used for training the happy emotion of the trainee children.

[0052] An angry emotion training module is used for training the angry emotion of the trainee children.

[0053] A sad emotion training module is used for training the sad emotion of the trainee children.

[0054] A surprised emotion training module is used for training the surprised emotion of the trainee children.

[0055] Specifically, the happy emotion training module is provided with an icon button a, the button is pressed to start the happy emotion training; the angry emotion training module is provided with an icon button b, the button is pressed to start the happy emotion training; the sad emotion training module is provided with an icon button c, the button is pressed to start the happy emotion training; and the surprised emotion training module is provided with an icon button d, the button is pressed to start the happy emotion training.

[0056] In the example embodiment, the AI module is provided with a "shooting" button and an "AI making" button, the "shooting" button is used to control the AI module to start shooting the facial expressions of the trained children, and the "AI making" button is used to control the AI module to start generating the standard level expressions of the trained children.

[0057] In the embodiment of the application, the facial expressions of the trained children are shot by the AI module, and the standard level expressions of the trained children are generated, and the trained children are trained by the emotion training module to have different emotions. The training method uses the child's own face as the imitation object, overcomes the problems of children's lack of concentration and psychological resistance, and also improves the sense of substitution. By dividing different levels of expression training, the trained children can start training from low to high level. This easy-to-difficult training method makes it easier for children to accept, cultivates the emotion recognition ability of autistic children, and improves the generalization ability of autistic children to different emotional expressions in different scenes and social conditions.

[0058] On the basis of the above embodiment, with reference to Figure 6 and Figure 7 The embodiment of the application also provides an AI emotion recognition and training method, which applies the AI emotion recognition and training system of any one of claims 1-4. The method can include the following steps:

[0059] S10, capturing and shooting the face of the trained child based on the AI module.

[0060] In the example embodiment, step S10 can include the following steps:

[0061] S110, capturing and shooting the happy face of the trained child based on the AI module to obtain the neutral expression of the trained child.

[0062] In the example embodiment, before step S10, preparation work needs to be done first, as follows:

[0063] First, connect the screen data line 10 to the first USB interface 20, turn on the switch, and have the trained child sit facing the stm camera 17. Then, the instructor presses the "shooting" icon button, and the relevant information of the button is transmitted to the central control module. The central control module transmits the processed data to the stm screen.

[0064] After the preparation work is completed, the instructor guides the trained child to start shooting, and after the shooting is completed, the stm screen 15 will display the shooting result.

[0065] S20, generating a plurality of standard level expressions of the trained children based on the results of the face capturing and shooting.

[0066] In the example embodiment, step S20 can include the following steps:

[0067] S210, generating a happy standard checkpoint expression of the trained child based on the neutral expression of the trained child;

[0068] S220, generating an angry standard checkpoint expression of the trained child based on the neutral expression of the trained child;

[0069] S230, generating a sad standard checkpoint expression of the trained child based on the neutral expression of the trained child;

[0070] S240, generating a surprised standard checkpoint expression of the trained child based on the neutral expression of the trained child.

[0071] S30, referring to Figure 8 and Figure 9 , generating different levels of expression training based on the standard checkpoint expressions of the trained child, and training the trained child with different emotions.

[0072] In the example embodiment, step S30 can include the following steps:

[0073] S310, generating a first level of expression training based on the standard checkpoint expressions of the trained child;

[0074] S320, adding environmental factors based on the first level of expression training to generate a second level of expression training;

[0075] S330, conducting two levels of happy expression training from low to high for the trained child;

[0076] S340, conducting two levels of angry expression training from low to high for the trained child;

[0077] S350, conducting two levels of sad expression training from low to high for the trained child;

[0078] S360, conducting two levels of surprised expression training from low to high for the trained child.

[0079] In the example embodiment, the instructor presses the "start" button of the control button area 8, at which time the upper right corner of the stm screen displays the time, which is limited to 30 seconds. The trained child needs to complete the imitation within 30 seconds according to the voice provided by the image and audio output module 6, and the instructor will give assistance if necessary. The stm camera 16 will record the whole process of imitation.

[0080] S40, obtaining the first level of expression training results.

[0081] Specifically, after the trained child completes the imitation, the instructor presses the "end" button of the control button area 8, and then exports the imitation process video, that is, the first-level expression training result. S50, the training result is compared with the standard level expression of the trained child, and a similarity score is obtained.

[0082] S60, based on the similarity score, the next level of expression training is performed, or the first level of training is performed again.

[0083] Specifically, a threshold of the similarity score needs to be preset before starting the training. If the similarity score is lower than the preset threshold, the first level of training is performed again. If the similarity score is greater than or equal to the preset threshold, the next level (i.e., the second level) of expression training is performed.

[0084] Next, taking the second level of happy mood training as an example, the second level of expression training is described:

[0085] The instructor presses the 2-level button of the level operation area 11 and the "AI making" button of the AI module. At this time, the stm screen will display the happy training level icon, the level mark, and the standard level expression of the happy trained child with content, voice, and environment (as shown in Figure 9 After preparation, the instructor presses the "start" button of the control button area 8. At this time, the corresponding specific voice will be played from the audio output module 6. At this time, the upper right corner will display the time, which is limited to 60 seconds. The trained child needs to complete the imitation according to the image and voice within the specified time, and the instructor will assist if necessary. At the same time, the stm camera 16 will record the whole process of imitation. After completing the imitation, the instructor presses the "end" button of the control button area 8, and then exports the imitation process video and performs similarity evaluation. After reaching the standard, the next expression module (such as sad, angry) training can be performed.

[0086] It can be understood that the processes of sad mood training 2, angry mood training 2, and surprise mood training 2 are the same as above.

[0087] The present application can well solve this problem by capturing the neutral expression of the trained child through the stm camera, and then generating the standardized expression of the four emotion modules based on the face of the trained child through the AI intelligence. Then, the child is allowed to imitate his own expression for training, so that the trained child is interested in his own facial expression, has more sense of identification, does not have a resistance psychology, and can effectively improve the emotion recognition ability and imitation ability of the trained personnel.

[0088] On the basis of the above embodiment, the present application further provides a computer readable storage medium, which is referred to Figure 10The illustrated computer readable storage medium is an optical disc 50, and a computer program (i.e., a program product) is stored on the optical disc 50. When the computer program is run by a processor, each step described in the above method embodiments is implemented, for example, based on the AI module, a face of a child to be trained is captured; based on a result of the face capturing, a plurality of standard checkpoint expressions of the child to be trained are generated; based on the standard checkpoint expressions of the child to be trained, different levels of expression training are divided to train the child to be trained to different emotions; a first level of expression training result is obtained; the training result is compared with the standard checkpoint expressions of the child to be trained to obtain a similarity score; based on the similarity score, the next level of expression training is performed, or the first level of training is performed again. The specific implementation of each step is not repeated here.

[0089] It should be noted that examples of the computer readable storage medium can also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other optical, magnetic storage medium, which will not be repeated here.

[0090] In addition, on the basis of the above-mentioned embodiments, the embodiments of the present application also provide a computing device, Figure 11 A block diagram of an exemplary computing device 602 suitable for implementing the embodiments of the present application is shown, and the computing device 60 can be a computer system or a server. Figure 11 The displayed computing device 60 is only an example, and should not bring any limitation to the function and use range of the embodiments of the present application.

[0091] As Figure 11As shown, computer device 602 can include one or more processors 604, such as one or more central processing units (CPUs), each of which can implement one or more hardware threads. Computer device 602 can also include any memory 606 for storing any kind of information such as code, settings, data, etc. Without limitation, for example, memory 606 can include any one or combination of: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, etc. More generally, any memory can use any technology for storing information. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of computer device 602. In one case, computer device 602 can perform any operation of the associated instructions when processor 604 executes the associated instructions stored in any memory or combination of memories. Computer device 602 also includes one or more drive mechanisms 6011 such as a hard drive mechanism, an optical disk drive mechanism, etc. for interacting with any memory.

[0092] Computer device 602 can also include an input / output module 610 (I / O) for receiving various inputs (via input devices 612) and for providing various outputs (via output devices 614). One particular output mechanism can include a presentation device 616 and an associated graphical user interface (GUI) 6111. In other embodiments, input / output module 610 (I / O), input devices 612, and output devices 614 can also not be included, just as a computer device in a network. Computer device 602 can also include one or more network interfaces 620 for exchanging data with other devices via one or more communication links 622. One or more communication buses 624 couple the above-described components together.

[0093] Communication links 622 can be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. Communication links 622 can include any combination of hardwired links, wireless links, routers, gateway functionality, name servers, etc., governed by any protocol or combination of protocols.

[0094] In the description of the present application, it should be explained that the terms "first", "second", "third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0095] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0096] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. The described device embodiments are merely illustrative. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, or a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0097] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to the actual needs to achieve the purposes of the embodiments of the present application.

[0098] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit.

[0099] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium of a processor. Based on such understanding, the technical solutions of the present application essentially or the part that makes a contribution to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various other media that can store program codes.

[0100] Finally, it should be noted that the above examples are merely specific embodiments of the present application, and are used to illustrate the technical solutions of the present application, but not to limit the same. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that, within the technical scope disclosed by the present application, any person skilled in the art can still modify or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features. Such modifications, changes or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0101] In addition, although the operations of the methods of the present application are described in a particular order in the drawings, this does not require or imply that the operations must be performed in that particular order, or that all of the illustrated operations must be performed to achieve desirable results. Additionally or alternatively, certain steps can be omitted, combined, performed simultaneously, or performed in a different order.

Claims

1. An AI emotion recognition and training system, characterized in that, The AI emotion recognition and training system comprises: an emotion training module for training a child to express different emotions; a display module for displaying standard level expressions of the child to guide the child to make corresponding facial expressions, and for displaying a photo of the child's face just taken; a central control module connected with the emotion training module and the display module, for controlling the normal operation of the modules; an audio output module connected with the central control module, for outputting prompt sounds to assist the display module in guiding the child to make corresponding facial expressions; an AI module for taking photos of the child's facial expressions and for generating standard level expressions of the child. 2.The AI emotion recognition and training system of claim 1, wherein, The emotion training module comprises: a happy emotion training module for training the child to express happy emotion; an angry emotion training module for training the child to express angry emotion; a sad emotion training module for training the child to express sad emotion; a surprised emotion training module for training the child to express surprised emotion. 3.The AI emotion recognition and training system of claim 1, wherein, The AI emotion recognition and training system further comprises: a level operation area located at the right side of the table and provided with a level 1 button and a level 2 button; a control button area located below the table and provided with a start button and an end button. 4.The AI emotion recognition and training system of claim 1, wherein, The AI module is provided with a "take photo" button and an "AI make" button, the "take photo" button being used to control the AI module to start taking photos of the child's facial expressions, and the "AI make" button being used to control the AI module to start generating standard level expressions of the child.

5. An AI emotion recognition and training method, applying the AI emotion recognition and training system of any one of claims 1-4, characterized in that, The method comprises the following steps: capturing the face of the child based on the AI module; generating a plurality of standard level expressions of the child based on the result of the face capturing; dividing different level expression training based on the standard level expressions of the child, to train the child to express different emotions; obtaining the result of the first level expression training; comparing the training result with the standard level expressions of the child to obtain a similarity score; based on the similarity score, carrying out the next level expression training or re-carrying out the first level training. 6.The AI emotion recognition and training method of claim 5, wherein, The capturing of the face of the child based on the AI module comprises the following steps: capturing the face of the child based on the AI module to obtain a neutral expression of the child. 7.The AI emotion recognition and training method of claim 6, wherein, The generating of a plurality of standard level expressions of the child based on the result of the face capturing comprises the following steps: generating a happy standard level expression of the child based on the neutral expression of the child; generating an angry standard level expression of the child based on the neutral expression of the child; generating a sad standard level expression of the child based on the neutral expression of the child; generating a surprised standard level expression of the child based on the neutral expression of the child. 8.The AI emotion recognition and training method of claim 5, wherein, The generating of different level expression training based on the standard level expressions of the child to train the child to express different emotions comprises the following steps: generating first level expression training based on the standard level expressions of the child. Based on the first level of facial expression training, environmental factors are added to generate a second level of facial expression training; Two levels of happy facial expression training are performed on the children from low to high; Two levels of angry facial expression training are performed on the children from low to high; Two levels of sad facial expression training are performed on the children from low to high; Two levels of surprised facial expression training are performed on the children from low to high.

9. A computer-readable storage medium, characterized in that, It comprises instructions which, when run on a computer, cause the computer to perform the AI emotion recognition and training method of any one of claims 5-8.

10. A computing device, comprising: The computing device comprises: at least one processor, a memory and an input-output unit; wherein the memory is configured to store a computer program, and the processor is configured to invoke the computer program stored in the memory to execute the AI emotion recognition and training method of any one of claims 5-8.

Images