Training system for improving concentration of autistic children

Abstract

The invention provides a training system for improving concentration of autistic children, and belongs to the technical field of medical rehabilitation, and the training system comprises a patient wearable VR device and a supervision guide terminal; the supervision guide terminal is used for generating a training difficulty indication instruction; the patient wearable VR equipment is used for responding to the training difficulty indication instruction to generate an eye movement tracking training scheme, and guiding the patient to train based on the eye movement tracking training scheme; the supervision and guidance terminal is further used for synchronously displaying a first-person view angle scene of the patient in the training process, and when the first-person view angle scene is not matched with the ideal sight gazing scene, the first-person view angle scene is adjusted by taking the patient as the center; the first-person viewing angle scene is a watching scene under the viewing angle of the patient. According to the monitoring and guiding terminal, the first person view scene of the patient in the training process is synchronously displayed, the watching scene of the patient in the training process is monitored and adjusted, and the accuracy of screening, diagnosis and prognosis analysis results is effectively improved.

Description

Technical Field

[0001] This invention relates to the field of medical rehabilitation technology, specifically to a training system for improving the concentration of children with autism. Background Technology

[0002] Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder with a high incidence and disability rate, severely impacting the developmental abilities and mental and physical health of children and adolescents. Among the early behavioral manifestations of children with ASD, impaired eye communication is particularly prominent; abnormal eye fixation is one of the clinical symptoms of ASD and also an early behavioral marker. Eye tracking (ET), as a non-invasive and highly real-time detection method, tracks changes in visual pathways by measuring infrared light reflected from the pupil and cornea. It measures and studies movement trajectories by the eye's fixation point or relative head movement position, providing a direct and accurate reflection of the degree and distribution characteristics of visual attention. ET possesses high objectivity, accuracy, and sensitivity, and is widely used in research areas such as social attention and limited interests in children with ASD.

[0003] In recent years, electrophysiological intervention (ET) has been used for early screening, identification, diagnosis, and prognostic analysis of children with ASD. For example, analyzing the general gaze characteristics, gaze duration, and distribution of children with ASD can improve the disease identification rate; its combined application with scales can improve diagnostic accuracy. However, the current specific method of using ET technology involves creating virtual training scenarios based on virtual reality such as VR, where patients train and obtain training results. These results are then used for early screening, identification, diagnosis, and prognostic analysis of ASD. But once patients enter the training phase, doctors cannot intervene in the training process. That is, doctors can only know the patient's training results, but not the information from the training process itself. This can lead to invalid training results, adversely affecting the accuracy of screening, diagnosis, and prognostic analysis.

[0004] Therefore, there is an urgent need to provide a training system to improve the attention of children with autism, enabling doctors to obtain process information during the training process and intervene in the training process based on the process information, so as to improve the accuracy of screening, diagnosis and prognosis analysis results. Summary of the Invention

[0005] In view of this, it is necessary to provide a training system to improve the attention of children with autism, in order to solve the technical problem that doctors can only know the patient's training results, but cannot know the information of the patient's training process, which may lead to invalid training results and thus low accuracy of screening, diagnosis and prognosis analysis results.

[0006] To address the aforementioned technical problems, this invention provides a training system for improving the attention span of children with autism, comprising: a wearable VR device for the patient and a monitoring and guidance terminal; The supervisory guidance terminal is used to generate training difficulty indication instructions; The patient's wearable VR device is used to generate an eye-tracking training plan in response to the training difficulty instruction, and to guide the patient to train based on the eye-tracking training plan; The supervision and guidance terminal is also used to synchronously display the patient's first-person perspective scene during the training process. When the first-person perspective scene does not match the ideal gaze scene, the first-person perspective scene is adjusted with the patient as the center. The first-person perspective scene is the gaze scene from the patient's perspective.

[0007] In one possible implementation, the supervision and guidance terminal is also used to synchronously display the patient's third-person perspective scene during the training process. When the deviation between the patient's position in the third-person perspective scene and the center position of the third-person perspective scene is greater than a preset deviation, the patient's position in the third-person perspective scene is adjusted with the patient as the center. The third-person perspective scene is the panoramic scene of the patient's wearable VR device.

[0008] In one possible implementation, the supervision and guidance terminal includes a viewpoint switching button, and the supervision and guidance terminal responds to the click command of the viewpoint switching button to switch the line of sight between the first-person view scene and the third-person view scene.

[0009] In one possible implementation, the patient-wearable VR device includes a training plan generation module, a training plan display module, and a training module; The training scheme generation module is used to call the eye-tracking training scheme from the preset scheme database in response to the training difficulty indication command; the eye-tracking training scheme includes a dynamic object display scheme and a dynamic object tracking gaze scheme; The training scheme display module is used to display the dynamic object on the display interface based on the dynamic object display scheme; The training module is used to determine the patient's effective fixation time based on the dynamic object tracking fixation scheme.

[0010] In one possible implementation, the effective fixation time is the fixation time during which the patient does not fixate on the dynamic object for a period of less than a preset time.

[0011] In one possible implementation, the dynamic object display scheme includes the movement path, movement speed, and initial size of the dynamic object; The dynamic object includes multiple levels of dynamic size from small to large, and the dynamic object tracking gaze scheme includes the correlation between the multiple levels of dynamic size and the effective gaze time; The correlation is as follows: when the effective fixation time of the patient on the dynamic object is greater than the set fixation time, the dynamic object is increased by one level.

[0012] In one possible implementation, the dynamic object tracking gaze scheme further includes: When the patient does not gaze at the dynamic object for a period longer than the set non-gazing duration, the dynamic object gradually decays back to its initial size.

[0013] In one possible implementation, the dynamic object tracking gaze scheme further includes: When the dynamic size of the dynamic object is the set maximum size, the dynamic object is controlled to move to the patient so that the patient can touch it with a virtual hand. When the dynamic object is touched, a preset animation is generated.

[0014] In one possible implementation, the supervised guidance terminal includes a data acquisition module, a data analysis module, and a training intervention module; The data acquisition module is used to acquire the patient's eye-tracking training data during the training process; The data analysis module is used to determine the training evaluation index value based on the eye-tracking training data and the preset training evaluation index. The training intervention module is used to generate training difficulty adjustment instructions based on the training evaluation index value, and to adjust the eye-tracking training scheme.

[0015] In one possible implementation, the eye-tracking training data includes the patient's actual fixation time and total fixation time on a dynamic object during training, as well as the patient's standard fixation time during training. The training evaluation metrics include attention focus and attention stability; The attention focus level is defined as: actual fixation time / total fixation time; The attentional stability is defined as: standard fixation time / total actual fixation time.

[0016] The beneficial effects of this invention are as follows: The training system for improving the attention of children with autism provided by this invention, by setting up a supervision and guidance terminal to synchronously display the patient's first-person perspective scene during the training process, can determine whether the first-person perspective scene matches the ideal gaze scene. When they do not match, the first-person perspective scene is adjusted with the patient as the center, realizing the monitoring and adjustment of the patient's gaze scene during the training process. That is, it realizes the monitoring and intervention of the training process, avoiding the technical problem of obtaining a large number of invalid training results when the first-person perspective scene does not match the ideal gaze scene, resulting in low accuracy of screening, diagnosis and prognosis analysis results. This effectively improves the accuracy of screening, diagnosis and prognosis analysis results.

[0017] Furthermore, by setting up a supervision and guidance terminal to generate training difficulty instructions, the present invention can realize the change and adjustment of training difficulty, improve the adaptability of the training process to the individual patient, and thus further improve the effect of rehabilitation training. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A schematic diagram of an embodiment of the training system for improving the attention span of children with autism provided by the present invention; Figure 2 A schematic diagram of an embodiment of the supervision and guidance terminal provided by the present invention; Figure 3 This is a schematic diagram of an embodiment of the wearable VR device for patients provided by the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0021] It should be understood that the illustrative drawings are not drawn to scale. The flowcharts used in this invention illustrate operations implemented according to some embodiments of the invention. It should be understood that the operations in the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed or performed simultaneously. Furthermore, those skilled in the art, guided by the content of this invention, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor systems and / or microcontroller systems.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] This invention addresses the following problems existing in current training systems for autistic children's attention: autistic children cannot independently discover and adjust their gaze scene, and when the gaze scene deviates from the gaze scene boundary (referring to the scene boundary of the patient's wearable VR device), i.e., when the patient's position deviates from the center of the gaze scene, resulting in an invalid gaze scene, a large amount of invalid data is obtained, interfering with the doctor's judgment, leading to low accuracy in screening, diagnosis, and prognosis analysis results.

[0024] In view of the above-mentioned technical problems existing in the prior art, the present invention provides a training system for improving the concentration of children with autism, which will be described in detail below.

[0025] Figure 1 A schematic diagram of an embodiment of the training system for improving the attention span of children with autism provided by the present invention is shown below. Figure 1 As shown, the training system 10 for improving the attention of children with autism includes: a wearable VR device 100 and a supervision and guidance terminal 200; The supervisory guidance terminal 200 is used to generate training difficulty indication instructions; The patient wearable VR device 100 is used to generate an eye-tracking training program in response to training difficulty instructions, and guide the patient to train based on the eye-tracking training program; The supervision and guidance terminal 200 is also used to synchronously display the patient's first-person perspective scene during the training process. When the first-person perspective scene does not match the ideal gaze scene, the first-person perspective scene is adjusted with the patient as the center. The first-person perspective scene is the gaze scene from the patient's perspective.

[0026] It should be understood that if the patient is a first-time visitor, the training difficulty is the initial training difficulty. If the patient is not a first-time visitor, the training difficulty matching the patient can be determined through the previous visit log recorded in the supervision and guidance terminal 200.

[0027] In a specific embodiment of the present invention, the patient wearable VR device 100 is a head-mounted VR device.

[0028] The supervision and guidance terminal 200 can be a desktop computer or a portable mobile terminal such as a mobile phone, tablet computer, or laptop computer. To improve its portability, in a preferred embodiment of the present invention, the supervision and guidance terminal 200 is a tablet computer.

[0029] It should be noted that the first-person perspective scene is the patient's first-person gaze scene, that is, whatever the patient sees is the same scene displayed in the supervision and guidance terminal 200, in order to ensure the synchronization between the content displayed on the patient's wearable VR device 100 and the supervision and guidance terminal 200.

[0030] The eye-tracking training program is displayed in a virtual scene. The ideal gaze scene refers to the scene that includes the eye-tracking training program. When the first-person perspective scene does not match the ideal gaze scene, it means that the patient is not paying attention to the eye-tracking program and is instead focusing their gaze on other ineffective areas.

[0031] It should be noted that the mismatch between the first-person perspective scene and the ideal gaze scene is often caused by the inconsistency between the patient's position in reality and their position in the virtual scene. Therefore, the specific method to adjust the first-person perspective scene is as follows: First, an external person, such as a doctor, guides the patient to the center of the real scene. Then, the software repositioning function is used to calibrate the virtual and real scene positions with the patient's head-mounted display as the center and the patient's height (height of the head-mounted display from the ground) as the parameter. This eliminates the problem of mismatch between the first-person perspective scene and the ideal gaze scene.

[0032] For example, if the virtual scene is 3m×3m, when the patient's gaze falls outside the virtual scene, it means that the first-person perspective scene does not match the ideal gaze scene. When the patient's gaze falls within the 3m×3m virtual scene, it means that the first-person perspective scene matches the ideal gaze scene. In this case, there is no need to adjust the first-person perspective scene.

[0033] In practical applications, there may be discrepancies between the patient's actual line of sight to the object and the line of sight displayed in the software. In such cases, the repositioning function must also be used. Specifically, the doctor guides the patient to the center of the real scene and uses the software's repositioning function to calibrate the virtual and displayed scene positions with the patient's head-mounted display as the center and the patient's height (height of the head-mounted display from the ground) as the parameter.

[0034] Compared with existing technologies, the training system 10 for improving the attention of children with autism provided in this embodiment of the invention, by setting up a supervision and guidance terminal 200 to synchronously display the patient's first-person perspective scene during the training process, can determine whether the first-person perspective scene matches the ideal gaze scene. When they do not match, the first-person perspective scene is adjusted with the patient as the center, realizing the monitoring and adjustment of the patient's gaze scene during the training process. That is, it realizes the monitoring and intervention of the training process, avoiding the technical problem of obtaining a large number of invalid training results when the first-person perspective scene does not match the ideal gaze scene, resulting in low accuracy of screening, diagnosis and prognosis analysis results, and effectively improving the accuracy of screening, diagnosis and prognosis analysis results.

[0035] Furthermore, by setting the supervision and guidance terminal 200 to generate training difficulty indication instructions, the training difficulty can be changed and adjusted, improving the adaptability of the training process to the individual patient, and thus further improving the effect of rehabilitation training.

[0036] Since the training system 10 is usually used in a room where the patient is located, and the room includes walls, if the patient is close to the wall, although the technical problems of the eye-tracking scheme can be improved to some extent by adjusting the first-person perspective scene, the following technical problems exist: when the patient is close to the wall, the patient is likely to touch the wall and be startled or injured when making any movement, which affects the training results and the training experience.

[0037] To solve the above-mentioned technical problems, in some embodiments of the present invention, the supervision and guidance terminal 200 is also used to synchronously display the patient's third-person perspective scene during the training process. When the deviation between the patient's position in the third-person perspective scene and the center position of the third-person perspective scene is greater than a preset deviation, the patient's position in the third-person perspective scene is adjusted with the patient as the center. Among them, the third-person perspective scene is the panoramic scene of the patient's wearable VR device 100.

[0038] It should be understood that a third-person perspective scene is a global perspective, equivalent to a global map of a virtual scene.

[0039] This invention ensures that the patient is centered in the third-person perspective scene by adjusting the patient's position, thus ensuring the patient's safety during training and providing space for subsequent position adjustments.

[0040] Specifically, if the virtual scene is 3m×3m, then the patient's location after adjustment will be (1.5m, 1.5m).

[0041] It should be noted that the supervision and guidance terminal 200 includes a perspective switching button. By clicking this perspective switching button, the first-person perspective scene and the third-person perspective scene can be switched.

[0042] In a specific embodiment of the present invention, adjusting the patient's position in the third-person perspective scene involves the doctor dragging the patient to adjust the patient's position. Furthermore, after adjusting the patient's position, a repositioning function is needed to reposition the patient to ensure the matching degree between the virtual and real scenes.

[0043] In some embodiments of the present invention, such as Figure 2 As shown, the patient wearable VR device 100 includes a training plan generation module 110, a training plan display module 120, and a training module 130; The training scheme generation module 110 is used to call eye-tracking training schemes from the preset scheme database in response to the training difficulty indication command; the eye-tracking training schemes include dynamic object display schemes and dynamic object tracking gaze schemes.

[0044] The scheme database may include different eye-tracking training schemes corresponding to different training difficulties in advance. Based on this, the target training difficulty can be obtained by parsing the training difficulty instruction, and the scheme database can be traversed and matched based on the target training difficulty to obtain the corresponding eye-tracking training scheme.

[0045] The training scheme display module 120 is used to display dynamic objects in the display interface based on the dynamic object display scheme.

[0046] The dynamic object display scheme may include various display parameters such as the shape of the dynamic object to be displayed, and the dynamic object is displayed on the display interface according to these display parameters.

[0047] It should be understood that the display interface is a virtual interface, that is, a virtual interface constructed in the actual space through virtual reality technology.

[0048] Training module 130 is used to determine the patient’s effective fixation time based on a dynamic object tracking fixation scheme.

[0049] It should be noted that the dynamic object tracking fixation scheme defines the criteria for determining effective fixation time. By collecting the patient's fixation time, the time that meets the criteria for effective fixation time is taken as the effective fixation time.

[0050] In a specific embodiment of the present invention, the effective fixation time is the fixation time during which the patient does not fixate on a dynamic object for a period of time less than a preset time.

[0051] For example, if a dynamic object tracking fixation scheme limits the preset time to 10 seconds, then when a patient fixates on a dynamic object for 5 seconds, if their gaze leaves the dynamic object for more than 10 seconds, the aforementioned 5 seconds of fixation is not considered valid fixation time. If the gaze leaves the dynamic object for less than 10 seconds, and then the patient subsequently fixates on the dynamic object for another 3 seconds, then the valid fixation time is 5 seconds + 3 seconds = 8 seconds.

[0052] This invention, by determining the effective fixation time, differs from the prior art in that all time a patient spends looking at a dynamic object is considered the effective fixation time. This avoids misjudging the fixation time as the effective fixation time when the patient is squinting aimlessly. However, aimless squinting is not for training purposes, thus avoiding interference of this fixation time with the training results and further improving the accuracy of screening, diagnosis, and prognosis analysis results.

[0053] In some embodiments of the present invention, the dynamic object display scheme includes the movement path, movement speed, and initial size of the dynamic object.

[0054] It should be understood that the greater the training difficulty, the more complex the movement path, the faster the movement speed, and the smaller the initial size.

[0055] It should be noted that the dynamic object display scheme can also include the number of dynamic objects; the greater the training difficulty, the more dynamic objects are used. When multiple dynamic objects are set, one round of training refers to training all dynamic objects according to the dynamic object tracking gaze scheme once.

[0056] In some embodiments of the present invention, the dynamic object includes a multi-level dynamic size from small to large, and the dynamic object tracking gaze scheme includes the correlation between the multi-level dynamic size and the effective gaze time. The correlation is as follows: when the patient's effective fixation time on a dynamic object exceeds the set fixation time, the dynamic object is incremented by one level.

[0057] It should be understood that the greater the training difficulty, the more levels of dynamic range there are.

[0058] For example, when the dynamic size includes two levels and the gaze duration is set to 6 seconds, the dynamic object tracking gaze scheme is as follows: When the effective fixation time of the patient is less than or equal to 6 seconds, the size of the dynamic object remains unchanged; when the effective fixation time is greater than 6 seconds, the size of the dynamic object increases from the initial size to the first level size. When the effective fixation time for a dynamic object of first-order size is less than or equal to 6 seconds, the size of the dynamic object remains unchanged. When the effective fixation time is greater than 6 seconds, the size of the dynamic object increases from first-order size to second-order size.

[0059] This invention, through the subtly prompting and encouraging patients to continuously focus on dynamic objects by changing their size, intervenes in the patient's attention.

[0060] Furthermore, since the larger the size of a moving object, the easier it is for a patient to fixate on it, if a patient does not fixate on a previously fixed moving object for a long time, and the size of the moving object remains unchanged, it will increase the probability of the patient fixing on that moving object subsequently. To eliminate this technical problem, in some embodiments of the present invention, the moving object tracking fixation scheme further includes: When the patient's non-focusing time on a moving object exceeds the set non-focusing time, the moving object gradually decays to its initial size.

[0061] This invention, by setting the dynamic object to gradually decay to its initial size when the patient's non-fixation time exceeds a set non-fixation time, ensures that the effective fixation time counted each time is the fixation time for the dynamic object of the initial size, thus ensuring the reliability and accuracy of the counted effective fixation time.

[0062] To further train the patient's perceptual abilities, in some embodiments of the present invention, the dynamic object tracking gaze scheme further includes: When the dynamic size of the dynamic object is the set maximum size, control the dynamic object to move to the patient so that the patient can touch it with a virtual hand. When the dynamic object is touched, a preset animation is generated.

[0063] It should be noted that: maximum size refers to the size of the dynamic object at the highest level in the dynamic object tracking gaze scheme.

[0064] If the size of a dynamic object includes three levels, then the maximum size set is the size of the third level dynamic object.

[0065] The movement path of the dynamic object can be planned based on the built-in path planning algorithm, starting from the current location of the dynamic object and ending at the patient's location. The planned path is then obtained, and the dynamic object is controlled to move along the planned path to the patient.

[0066] This invention, by setting up an interactive operation that requires the patient to use their touch hand, can guide the patient to perceive nearby dynamic objects, improve their object perception ability, and enhance the rehabilitation effect.

[0067] In a specific embodiment of the present invention, the dynamic object is a bubble. When the patient touches it, the bubble will burst, and at the same time, the animal model inside the bubble will play a preset animation, which will enhance the fun of the training process and increase the patient's enthusiasm.

[0068] The preset animations can feature different small animals running around the patient.

[0069] To further enhance the training of patients' perceptual abilities, in some embodiments of the present invention, the dynamic objects are multiple bubbles of different colors, each containing a different small animal. The animation of the small animal differs when the bubbles of different colors burst. For example, when a yellow bubble bursts, the preset animation is a rabbit hopping around, and when a blue bubble bursts, the preset animation is a panda running away. This enhances the patient's perception of different animal species and further improves their rehabilitation effect.

[0070] As the eye-tracking training program progresses, the training difficulty needs to be adjusted accordingly. To improve the accuracy and reliability of this adjustment, in some embodiments of the present invention, such as... Figure 3 As shown, the supervision and guidance terminal 200 includes a data acquisition module 210, a data analysis module 220, and a training intervention module 230; The data acquisition module 210 is used to acquire eye-tracking training data of patients during the training process.

[0071] The eye-tracking training data includes the patient's actual fixation time and total fixation time on a dynamic object during training, as well as the patient's standard fixation time during training.

[0072] It should be understood that the actual fixation time for a dynamic object refers to the total time spent fixating on the dynamic object. The total fixation time includes the fixation time on the dynamic object and the fixation time on other spaces / areas of non-dynamic objects. The standard fixation time refers to the theoretical time when the patient continuously fixates on the bubble until the bubble reaches its maximum size.

[0073] For example, if a patient fixates on a moving object for 5 seconds, does not fixate for 11 seconds, and then fixates for another 15 seconds until the bubble reaches its maximum size, the actual fixation time is 20 seconds, and the total fixation time is 31 seconds. When the fixation time is set to 5 seconds and the level is three, the standard fixation time is 15 seconds.

[0074] The data analysis module 220 is used to determine the training evaluation index value based on eye-tracking training data and preset training evaluation indexes.

[0075] In a specific embodiment of the present invention, the training evaluation index values ​​include attention focus and attention stability; Attention span is defined as: actual fixation time / total fixation time; Attentional stability is defined as: standard fixation time / total actual fixation time.

[0076] Among them, attention focus refers to the proportion of time a patient spends fixing their gaze on a bubble during training on a dynamic object, reflecting the patient's focus during training. Attention stability is used to observe the proportion of the patient's effective fixation time in the total fixation time on the bubble, and together with attention focus, it reflects the patient's final fixation concentration.

[0077] The training intervention module 230 is used to generate training difficulty adjustment instructions based on training evaluation index values ​​to adjust the eye-tracking training program.

[0078] The training evaluation index can be a weighted sum of the above-mentioned attention focus and attention stability.

[0079] This invention improves the accuracy and reliability of training difficulty adjustment by judging whether the training difficulty needs to be adjusted from two dimensions: attention focus and attention stability.

[0080] In summary, the training system for improving the attention span of children with autism provided in this invention: 1. Combines eye-tracking with virtual reality technology, guiding children with ASD to continuously focus on a specific target, effectively training their attention and concentration, and enhancing fun and participation. It can serve as a novel tool for adjunctive therapy, providing a more effective method for ASD treatment and offering greater possibilities for the rehabilitation of children with ASD. 2. By setting up a monitoring and guidance terminal to synchronously display the patient's first-person and third-person perspective scenes during training, the entire training process can be controlled and monitored by the doctor using a tablet, allowing for intervention in the training process and improving rehabilitation outcomes.

[0081] The above provides a detailed description of a training system for improving the concentration of children with autism. Specific examples have been used to illustrate the principles and implementation methods of the invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the invention. Therefore, the content of this specification should not be construed as a limitation of the invention.

Claims

1. A training system for improving the attention span of children with autism, characterized in that, include: Wearable VR devices and monitoring and guidance terminals for patients; The supervisory guidance terminal is used to generate training difficulty indication instructions; The patient's wearable VR device is used to generate an eye-tracking training plan in response to the training difficulty instruction, and to guide the patient to train based on the eye-tracking training plan; The supervision and guidance terminal is also used to synchronously display the patient's first-person perspective scene during the training process. When the first-person perspective scene does not match the ideal gaze scene, the first-person perspective scene is adjusted with the patient as the center. The first-person perspective scene is the gaze scene from the patient's perspective.

2. The training system for improving the concentration of children with autism according to claim 1, characterized in that, The supervision and guidance terminal is also used to synchronously display the patient's third-person perspective scene during the training process. When the deviation between the patient's position in the third-person perspective scene and the center position of the third-person perspective scene is greater than a preset deviation, the patient's position in the third-person perspective scene is adjusted with the patient as the center. The third-person perspective scene is the panoramic scene of the patient's wearable VR device.

3. The training system for improving the concentration of children with autism according to claim 2, characterized in that, The monitoring and guidance terminal includes a perspective switching button. When the monitoring and guidance terminal responds to the click command of the perspective switching button, the line of sight switches between the first-person perspective scene and the third-person perspective scene.

4. The training system for improving the attention span of children with autism according to claim 1, characterized in that, The patient-wearable VR device includes a training plan generation module, a training plan display module, and a training module. The training scheme generation module is used to call the eye-tracking training scheme from the preset scheme database in response to the training difficulty indication instruction; The eye-tracking training scheme includes a dynamic object display scheme and a dynamic object tracking gaze scheme. The training scheme display module is used to display dynamic objects on the display interface based on the dynamic object display scheme; The training module is used to determine the patient's effective fixation time based on the dynamic object tracking fixation scheme.

5. The training system for improving the concentration of children with autism according to claim 4, characterized in that, The effective fixation time is the fixation time during which the patient does not fixate on the dynamic object for a period of time less than a preset time.

6. The training system for improving the concentration of children with autism according to claim 4, characterized in that, The dynamic object display scheme includes the movement path, movement speed, and initial size of the dynamic object; The dynamic object includes multiple levels of dynamic size from small to large, and the dynamic object tracking gaze scheme includes the correlation between the multiple levels of dynamic size and the effective gaze time; The correlation is as follows: when the effective fixation time of the patient on the dynamic object is greater than the set fixation time, the dynamic object is increased by one level.

7. The training system for improving the attention span of children with autism according to claim 6, characterized in that, The dynamic object tracking gaze scheme also includes: When the patient does not gaze at the dynamic object for a period longer than the set non-gazing duration, the dynamic object gradually decays back to its initial size.

8. The training system for improving the attention span of children with autism according to claim 6, characterized in that, The dynamic object tracking gaze scheme also includes: When the dynamic size of the dynamic object is the set maximum size, the dynamic object is controlled to move to the patient so that the patient can touch it with a virtual hand. When the dynamic object is touched, a preset animation is generated.

9. The training system for improving the concentration of children with autism according to claim 4, characterized in that, The supervision and guidance terminal includes a data acquisition module, a data analysis module, and a training intervention module; The data acquisition module is used to acquire the patient's eye-tracking training data during the training process; The data analysis module is used to determine the training evaluation index value based on the eye-tracking training data and the preset training evaluation index. The training intervention module is used to generate training difficulty adjustment instructions based on the training evaluation index value, and to adjust the eye-tracking training scheme.

10. The training system for improving the attention span of children with autism according to claim 9, characterized in that, The eye-tracking training data includes the patient's actual fixation time and total fixation time on a dynamic object during training, as well as the patient's standard fixation time during training. The training evaluation metrics include attention focus and attention stability; The attention focus level is defined as: actual fixation time / total fixation time; The attentional stability is defined as: standard fixation time / total actual fixation time.

Images