Visual field rehabilitation training method, device, system, storage medium and program product

Abstract

The application relates to the technical field of healthcare information, and provides a visual field rehabilitation training method, device and system, a storage medium and a program product, which can improve visual neglect of a target object. According to an eye movement heat map of the target object, a visual low-attention area of the target object is determined; a virtual scene is created, and a virtual object matching the virtual scene is generated in the visual low-attention area; the virtual object is used for visual search training of the target object; according to an upper limit value of a direction integration angle corresponding to the visual low-attention area, an evaluation baseline corresponding to the visual low-attention area is determined; the higher the upper limit value of the direction integration angle, the higher the evaluation baseline; according to the evaluation baseline, visual search training of the target object on the virtual object in the visual low-attention area is evaluated to obtain an evaluation result; and the virtual object is adjusted according to the evaluation result to perform the next visual search training.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of healthcare information, in particular to a visual field rehabilitation training method and device, a visual field rehabilitation training system, a storage medium and a computer program product. BACKGROUND

[0002] Visual rehabilitation training can be used for visually impaired subjects, which can be through visual stimulation and tasks to promote the recovery and improvement of visual function. Traditional visual rehabilitation training programs aim to help visually impaired subjects improve spatial orientation, movement and navigation ability, but it is difficult to improve the visual neglect of visually impaired subjects. SUMMARY

[0003] Therefore, it is necessary to provide a visual field rehabilitation training method, device, system, storage medium and computer program product to solve the above technical problems.

[0004] The present application provides a visual field rehabilitation training method, which comprises:

[0005] According to the eye movement heat map of the target subject, the visual low attention area of the target subject is determined;

[0006] A virtual scene is created, and a virtual object matching the virtual scene is generated in the visual low attention area; the virtual object is used for the target subject to perform visual search training;

[0007] According to the upper limit value of the direction integration angle corresponding to the visual low attention area, the evaluation baseline corresponding to the visual low attention area is determined; the higher the upper limit value of the direction integration angle, the higher the evaluation baseline;

[0008] According to the evaluation baseline, the visual search training of the target subject for the virtual object in the visual low attention area is evaluated to obtain an evaluation result;

[0009] According to the evaluation result, the virtual object is adjusted for the next visual search training.

[0010] In one embodiment, the method further comprises:

[0011] A view window is sequentially created for each region in the visual field of the target subject;

[0012] For any region, gradually increase the direction integration angle, and each increase of the direction integration angle, each point in the control point array moves in any direction within the window of the region, and the direction integration angle does not exceed the direction integration angle, according to whether the actual overall movement direction of the point array and the overall movement direction identified by the target object are consistent, determine whether to continue to increase the direction integration angle, if the direction integration angle is stopped to continue to increase, the direction integration angle obtained by this time is determined as the upper limit value of the direction integration angle corresponding to the region;

[0013] According to the upper limit value of the direction integration angle corresponding to the region belonging to the visual low attention area, the upper limit value of the direction integration angle corresponding to the visual low attention area is obtained.

[0014] In one embodiment, according to whether the actual overall movement direction of the point array and the overall movement direction identified by the target object are consistent, it is determined whether to continue to increase the direction integration angle, comprising:

[0015] If the actual overall movement direction of the point array and the overall movement direction identified by the target object are consistent, it is determined to continue to increase the direction integration angle;

[0016] If the actual overall movement direction of the point array and the overall movement direction identified by the target object are not consistent, stop to continue to increase the direction integration angle.

[0017] In one embodiment, according to the evaluation result, the virtual object is adjusted, comprising:

[0018] If the evaluation result represents that the visual search training situation of the target object for the virtual object in the visual low attention area reaches the evaluation baseline, the appearance position of the virtual object is adjusted, so that the adjusted appearance position is deeper in the field of view than the unadjusted appearance position;

[0019] If the evaluation result represents that the visual search training situation of the target object for the virtual object in the visual low attention area does not reach the evaluation baseline, the appearance position of the virtual object is adjusted, so that the unadjusted appearance position is deeper in the field of view than the adjusted appearance position.

[0020] In one embodiment, before the evaluation baseline is used to evaluate the visual search training situation of the target object for the virtual object in the visual low attention area, the method further comprises:

[0021] Determine the search duration, saccade times and sliding direction evaluation accuracy of the target object for the virtual object;

[0022] The visual search training index value is obtained according to at least one of the search duration, the saccade number and the slide direction evaluation accuracy, and is used to represent the visual search training situation of the target object for the virtual object in the visual low attention area of the target object.

[0023] In one embodiment, the visual low attention area of the target object is determined according to the eye movement heat map of the target object, including:

[0024] The attention degree of the target object for each region of the visual field is obtained according to the eye movement heat map of the target object.

[0025] The region with low attention degree is determined as the visual low attention area of the target object.

[0026] The present application provides a visual field rehabilitation training device, the device includes:

[0027] The low attention area determination module is used to determine the visual low attention area of the target object according to the eye movement heat map of the target object.

[0028] The virtual processing module is used to create a virtual scene, and generate a virtual object matched with the virtual scene in the visual low attention area; the virtual object is used for the target object to perform visual search training.

[0029] The baseline determination module is used to determine the evaluation baseline corresponding to the visual low attention area according to the upper limit value of the direction integration angle corresponding to the visual low attention area; the higher the upper limit value of the direction integration angle, the higher the evaluation baseline.

[0030] The evaluation module is used to evaluate the visual search training situation of the target object for the virtual object in the visual low attention area according to the evaluation baseline, and obtain an evaluation result.

[0031] The adjustment module is used to adjust the virtual object according to the evaluation result, so as to perform the next visual search training.

[0032] The present application provides a visual field rehabilitation training system, including a memory and a processor, the memory stores a computer program, and the processor executes the above method.

[0033] The present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to execute the above method.

[0034] The present application provides a computer program product, which stores a computer program, and the computer program is executed by a processor to execute the above method.

[0035] The field of view rehabilitation training method, device, system, storage medium and computer program product can determine the visual low attention area of the target object according to the eye movement heat map of the target object, create a virtual scene, and generate a virtual object matching the virtual scene in the visual low attention area, so as to train the target object to search visually. The visual low attention area of the target object can be trained specifically, and the visual neglect of the target object can be improved to a certain extent. Moreover, the evaluation baseline corresponding to the visual low attention area can be determined according to the upper limit value of the direction integration angle corresponding to the visual low attention area. The higher the upper limit value of the direction integration angle, the higher the evaluation baseline. According to the evaluation baseline, the visual search training of the target object on the virtual object in the visual low attention area can be evaluated specifically, and a more accurate evaluation result can be obtained. Based on the evaluation result, the virtual object can be adjusted for the next visual search training, and the closed-loop training process of 'visual search training-adjustment-visual search training again' for the visual low attention area can be realized, so that the visual neglect of the target object can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0037] Figure 1 A flowchart of a field of view rehabilitation training method in an embodiment;

[0038] Figure 2 A flowchart of determining a visual search training index value in an embodiment;

[0039] Figure 3 Another flowchart of a field of view rehabilitation training method in an embodiment;

[0040] Figure 4 A structural block diagram of a field of view rehabilitation training device in an embodiment;

[0041] Figure 5 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0043] It should be noted that the terms "first", "second", etc. used in the present application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "include" and "have" and any variations thereof used in the present application are intended to cover non-exclusive inclusion. The term "a plurality of" used in the present application means two or more. The term "and / or" used in the present application means one of the options or any combination of the options.

[0044] The field of view rehabilitation training method provided by the present application includes steps that can be executed by devices with operation processing capabilities, such as head-mounted devices. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, a mixed reality (MR) device, smart glasses, etc. The method can include Figure 1 The steps shown.

[0045] Step S101, according to the eye movement heat map of the target object, determining the visual low attention area of the target object.

[0046] The eye movement heat map of the target object can be read in real time by the eye movement target engine. After obtaining the eye movement heat map, the area ignored or rarely noticed by the target object can be determined according to the eye movement heat map, which can be referred to as a visual low attention area.

[0047] Step S102, creating a virtual scene, and generating a virtual item matching the virtual scene in the visual low attention area.

[0048] The virtual scene can include but is not limited to a life-like virtual scene, such as a living room, a kitchen, a subway, a bedroom, a park, an office, etc. Various virtual scenes have corresponding virtual items, for example, the virtual items corresponding to the living room virtual scene can be a milk box, a key, a mobile phone, etc. The virtual items corresponding to the kitchen virtual scene can be a spatula, etc. The virtual items corresponding to the subway virtual scene can be an umbrella. The virtual items corresponding to the bedroom virtual scene can be a remote control. The virtual items corresponding to the park virtual scene can be a frisbee. The virtual items corresponding to the office virtual scene can be a U disk. Through the life-like virtual scene and the corresponding virtual items, the real environment in which the target object is located can be simulated, the effectiveness of the target object when facing daily challenges can be improved, and the laboratory indicators can be seamlessly migrated to complex environments such as daily traffic, vehicle flow, and shelf, so that the field of view rehabilitation is applied to life ability.

[0049] The virtual scene can be created using VR or MR technology, and the virtual item matching the virtual scene in the visual low attention area can be generated. In this way, the target object performs visual search training based on the virtual item.

[0050] Step S103: Determine the evaluation baseline corresponding to the visual low attention area based on the upper limit of the directional integration angle corresponding to the visual low attention area.

[0051] The orientation integration (CDDI) of the target object can be determined by a noisy dot matrix in the visual low attention area of ​​the target object.

[0052] Step S104: Based on the evaluation baseline, evaluate the visual search training of the target object for virtual objects in the low visual attention area, and obtain the evaluation result.

[0053] The aforementioned steps can generate virtual objects in the low visual attention area to enable the target object to undergo visual search training. Then, based on the evaluation baseline of the low visual attention area, the visual search training can be evaluated to obtain the evaluation result. The evaluation result can be used to describe whether the target object's visual search training has reached the evaluation baseline.

[0054] Step S105: Adjust the virtual items based on the evaluation results for the next visual search training.

[0055] If the evaluation results indicate that the visual search training of the target object does not reach the evaluation baseline, it means that the training is too difficult for the target object. The virtual items appearing in the low visual attention area can be adjusted to reduce the training difficulty. After the adjustment, the target object can conduct the next visual search training and repeat the above steps. The visual search training will be evaluated according to the evaluation baseline of the low visual attention area to obtain the corresponding evaluation results.

[0056] If the evaluation results indicate that the visual search training of the target object has reached the evaluation baseline, it means that the training is not too difficult for the target object. The virtual items appearing in the low visual attention area can be adjusted to increase the training difficulty. After the adjustment, the target object can conduct the next visual search training and repeat the above steps. The visual search training situation is evaluated according to the evaluation baseline of the low visual attention area to obtain the corresponding evaluation results.

[0057] According to the eye movement heat map of the target object, the visual low attention area of the target object is determined, a virtual scene is created, and a virtual object matching the virtual scene is generated in the visual low attention area, so that the target object can perform visual search training. The visual low attention area of the target object can be trained specifically, and the visual neglect of the target object can be improved to a certain extent. Moreover, the upper limit value of the direction integration angle corresponding to the visual low attention area can be determined according to the upper limit value of the direction integration angle corresponding to the visual low attention area. The higher the upper limit value of the direction integration angle, the higher the evaluation baseline. According to the evaluation baseline, the visual search training of the target object on the virtual object in the visual low attention area can be evaluated specifically, and a more accurate evaluation result can be obtained. Based on the evaluation result, the virtual object can be adjusted for the next visual search training, and a closed-loop training process of “visual search training-adjustment-visual search training again” for the visual low attention area can be realized, so that the visual neglect of the target object can be improved.

[0058] In one embodiment, the method provided by the present application further comprises:

[0059] A view window is created for each region in the field of view of the target object in sequence. For any region, the direction integration angle is gradually increased. Each time the direction integration angle is increased, each point in the point array moves in any direction in the view window of the region without exceeding the direction integration angle. Whether to continue to increase the direction integration angle is determined according to whether the actual overall movement direction of the point array and the overall movement direction recognized by the target object are consistent. If the increase of the direction integration angle is stopped, the direction integration angle obtained by the increase is determined as the upper limit value of the direction integration angle corresponding to the region. The upper limit value of the direction integration angle corresponding to the visual low attention area is obtained according to the upper limit value of the direction integration angle corresponding to the region belonging to the visual low attention area.

[0060] The field of view of the target object can be divided into multiple regions, and a corresponding view window can be created for each region.

[0061] Taking one of the regions as an example, after the corresponding view window is created for the region, the direction integration angle can be gradually increased. Each time the direction integration angle is increased, the point array can be displayed in the view window, and each point in the point array can move in any direction in the view window without exceeding the direction integration angle (such as 135°). The target object can recognize the overall movement direction of the point array in the view window. Whether to continue to increase the direction integration angle is determined according to whether the overall movement direction recognized by the target object and the actual overall movement direction of the point array are consistent. If the increase of the direction integration angle is stopped, it means that the maximum direction integration capability of the target object has been evaluated. At this time, the direction integration angle can be taken as the upper limit value of the direction integration angle corresponding to the region.

[0062] By the above manner, the upper limit value of the direction integration angle corresponding to each region can be determined. Some of the regions are in the visual low attention area, and the upper limit value of the direction integration angle corresponding to the regions can be processed comprehensively (such as averaging) to obtain the upper limit value of the direction integration angle corresponding to the visual low attention area.

[0063] In the process of processing the upper limit value of the direction integration angle corresponding to the regions in the visual low attention area comprehensively, the regions in the visual low attention area can be clustered according to the distance between the regions to obtain multiple clusters, and it is determined whether the upper limit value of the direction integration angle corresponding to the regions in each cluster is close; if so, the upper limit value of the direction integration angle corresponding to the regions in the cluster is processed by averaging, and the entire region composed of the regions in the cluster is taken as a single visual low attention area, and the average result is taken as the upper limit value of the direction integration angle corresponding to the visual low attention area; if not, it can be indicated that the upper limit value of the direction integration angle corresponding to the regions in the cluster is quite different, and at this time, the regions in the cluster can be taken as visual low attention areas respectively, and the upper limit value of the direction integration angle corresponding to each region is taken as the upper limit value of the direction integration angle corresponding to the corresponding visual low attention area.

[0064] The embodiment can accurately position the limit of the direction integration capability of each region by independently testing the upper limit value of the corresponding direction integration angle for each region of the field of view, so that the upper limit value of the direction integration angle corresponding to the visual low attention area can be obtained more accurately.

[0065] In one embodiment, whether to continue to increase the direction integration angle is determined according to whether the actual overall movement direction of the dot matrix and the overall movement direction recognized by the target object are consistent, including:

[0066] If the actual overall movement direction of the dot matrix and the overall movement direction recognized by the target object are consistent, it is determined to continue to increase the direction integration angle; if the actual overall movement direction of the dot matrix and the overall movement direction recognized by the target object are inconsistent, the direction integration angle is stopped from being continued to increase.

[0067] Taking one of the regions as an example, after the corresponding view window is created for the region, the direction integration angle can be gradually increased; each time the direction integration angle is increased, the dot matrix in the view window can be displayed, and each point in the dot matrix can move in any direction in the view window without exceeding the direction integration angle (such as not exceeding 135°). The target object can recognize the overall movement direction of the dot matrix in the view window.

[0068] If the overall movement direction recognized by the target object is consistent with the actual overall movement direction of the dot matrix, it can be indicated that the limit of the direction integration capability of the target object for the region has not been tested, and at this time, it can be determined to continue to increase the direction integration angle.

[0069] If the overall movement direction recognized by the target object is inconsistent with the actual overall movement direction of the dot matrix, it can be indicated that the limit of the direction integration capability of the target object for the region has been tested, and at this time, it can be determined to stop continuing to increase the direction integration angle.

[0070] In the embodiment, by comparing the overall movement direction recognized by the target object with the actual overall movement direction of the dot matrix, the limit of the direction integration capability of the target object for each region can be reliably tested, and a more accurate upper limit of the direction integration angle can be obtained.

[0071] In one embodiment, the virtual item is adjusted according to the evaluation result, including:

[0072] If the evaluation result represents that the visual search training of the target object for the virtual item in the visual low attention area reaches the evaluation baseline, the appearance position of the virtual item is adjusted so that the adjusted appearance position is deeper in the field of view than the unadjusted appearance position; if the evaluation result represents that the visual search training of the target object for the virtual item in the visual low attention area does not reach the evaluation baseline, the appearance position of the virtual item is adjusted so that the unadjusted appearance position is deeper in the field of view than the adjusted appearance position.

[0073] The virtual item can be generated in the visual low attention area to make the target object perform visual search training; then, according to the evaluation baseline of the visual low attention area, the visual search training can be evaluated to obtain an evaluation result, which can be used to describe whether the visual search training of the target object reaches the evaluation baseline.

[0074] If the evaluation result represents that the visual search training of the target object reaches the evaluation baseline, it can be indicated that the difficulty of this training for the target object is not too high, and the virtual item appearing in the visual low attention area can be adjusted in the direction of increasing the training difficulty, specifically, the appearance position of the virtual item can be adjusted so that the virtual item is deeper in the field of view at the adjusted appearance position than at the unadjusted appearance position, so that the target object can perform the next visual search training, and the above steps can be repeated to evaluate the next visual search training according to the evaluation baseline of the visual low attention area to obtain a corresponding evaluation result.

[0075] If the evaluation result indicates that the visual search training of the target object does not reach the evaluation baseline, it can be concluded that the training is too difficult for the target object, and the virtual object appearing in the visual low attention area can be adjusted in the direction of reducing the training difficulty. Specifically, the appearance position of the virtual object can be adjusted, so that the appearance position of the virtual object before adjustment is deeper in the field of view than the appearance position after adjustment, so that the target object can perform the next visual search training, and the above steps are repeated to evaluate the next visual search training according to the evaluation baseline of the visual low attention area, and the corresponding evaluation result is obtained.

[0076] In the embodiment, when the visual search training of the target object meets the standard, the training difficulty can be automatically increased by moving the virtual object to a deeper position in the field of view, which can continuously challenge the limit of the visual search ability of the target object; when the visual search training of the target object does not meet the standard, the difficulty can be appropriately reduced by moving the virtual object to a shallower position in the field of view, so that the training difficulty can be matched with the visual ability of the target object.

[0077] In one embodiment, before evaluating the visual search training of the target object for the virtual object in the visual low attention area according to the evaluation baseline, the method provided by the application further comprises Figure 2 The steps are shown as follows:

[0078] In step S201, the search duration, saccade times and sliding direction evaluation accuracy of the target object for the virtual object are determined; in step S202, at least one of the search duration, saccade times and sliding direction evaluation accuracy is used to obtain a visual search training index value; the visual search training index value is used to represent the visual search training of the target object for the virtual object in the visual low attention area.

[0079] The virtual object can slide in the visual low attention area. For example, in a virtual scene of a subway rush hour, a crowd can be displayed in a window in the visual low attention area, the speed of the crowd can be 1.2 meters per second, and the direction of the crowd can be switched every 15 seconds. The virtual object (such as an umbrella) can drift with the crowd, and the main search task of the target object can be to lock and virtually grab the virtual object within a set time. In addition, a direction task can also be embedded, the virtual object (such as an umbrella) can slide at a direction of 10°, and the target object needs to identify and report the sliding direction of the virtual object.

[0080] The search duration can be the duration from the appearance of the virtual object in the visual low attention area to the target object locking the virtual object with the eyes; the shorter the search duration, the higher the efficiency of the target object searching for the virtual object in the visual low attention area.

[0081] The number of saccades can be the number of times of rapid and jumping movements of the eyeball of the target object in the process of searching for the virtual item; the fewer the number of saccades, the more efficient the visual path planning of the target object.

[0082] The accuracy rate of the evaluation of the sliding direction can be the percentage of the number of times that the target object correctly identifies the sliding direction of the virtual item in the total number of times; the higher the accuracy rate of the evaluation of the sliding direction, the stronger the attention allocation and the detail resolution of the target object when completing the main search task.

[0083] The visual search training of the target object can be scored according to the search duration, and the obtained score value can be referred to as a first score value; the visual search training of the target object can be scored according to the number of saccades, and the obtained score value can be referred to as a second score value; the visual search training of the target object can be scored according to the accuracy rate of the evaluation of the sliding direction, and the obtained score value can be referred to as a third score value.

[0084] The visual search training index value can be obtained according to at least one of the first score value, the second score value and the third score value. Exemplarily, the first score value, the second score value and the third score value can be weighted and summed, and the visual search training index value can be obtained according to the result of the weighted sum. The visual search training index value can be used to represent the visual search training situation of the target object for the virtual item in the visual low-attention area.

[0085] If the visual search training index value exceeds the evaluation baseline of the visual low-attention area, it can be indicated that the visual search training situation of the target object meets the standard; if the visual search training index value does not exceed the evaluation baseline of the visual low-attention area, it can be indicated that the visual search training situation of the target object does not meet the standard.

[0086] In this embodiment, the visual search training index value is obtained according to at least one of the search duration, the number of saccades and the accuracy rate of the evaluation of the sliding direction, the relatively complex and abstract visual search capability can be converted into a relatively stable and reliable quantitative index value, and a relatively accurate basis can be provided for subsequent adjustment of the training difficulty.

[0087] In one embodiment, the visual low-attention area of the target object is determined according to the eye movement heat map of the target object, comprising:

[0088] According to the eye movement heat map of the target object, the attention degree of the target object to each region of the field of view is obtained; the region with low attention degree is determined as the visual low-attention area of the target object.

[0089] The eye movement heat map can be obtained by superimposing and visualizing the fixation points and the fixation duration of each fixation point by color. The attention degree of the target object to each region of the field of view can be determined through the color distribution on the eye movement heat map.

[0090] The regions can be sorted in order of attention from low to high, and the regions sorted in the front can be determined as the low-attention regions, so that the visual low-attention area of the target object can be obtained. Alternatively, the regions with attention lower than the attention threshold can be determined as the low-attention regions, so that the visual low-attention area of the target object can be obtained.

[0091] The embodiment can convert the subjective and difficult-to-quantify visual inattention problem into objective data measurement of the attention of each region in the visual field by analyzing the eye movement heat map, and can effectively exclude the deviation caused by subjective description.

[0092] In an exemplary embodiment, as shown in Figure 3 A visual field rehabilitation training method is also provided, which can include the following steps:

[0093] In step S301, the attention of each region of the target object to the visual field is obtained according to the eye movement heat map of the target object, and the low-attention region is determined as the visual low-attention area of the target object.

[0094] Specifically, the eye movement target engine can be used to read the eye movement heat map of the target object in real time, and the color distribution on the eye movement heat map can be used to determine the attention of each region of the target object to the visual field, and the low-attention region is determined as the visual low-attention area of the target object.

[0095] In step S302, the upper limit value of the direction integration angle corresponding to the visual low-attention area is determined.

[0096] Specifically, a view window can be created for each region in the visual field of the target object in sequence. For any region, the direction integration angle is gradually increased, and each point in the point array moves in any direction within the view window of the region without exceeding the direction integration angle. If the actual overall movement direction of the point array and the overall movement direction recognized by the target object are consistent, the direction integration angle is determined to continue to increase. If the actual overall movement direction of the point array and the overall movement direction recognized by the target object are inconsistent, the direction integration angle is stopped from continuing to increase, and the direction integration angle obtained by this increase is determined as the upper limit value of the direction integration angle corresponding to the region. The upper limit value of the direction integration angle corresponding to the visual low-attention area is obtained according to the upper limit value of the direction integration angle corresponding to the region belonging to the visual low-attention area.

[0097] In step S303, a virtual scene is created, and a virtual object matching the virtual scene is generated in the visual low-attention area.

[0098] Specifically, a virtual scene can be created using VR or MR technology, and a virtual item matching the virtual scene can be generated in the visual low-attention area. In this way, the target object is trained for visual search based on the virtual item.

[0099] In step S304, the evaluation baseline corresponding to the visual low-attention area is determined according to the upper limit of the direction integration angle corresponding to the direction of the visual low-attention area.

[0100] Specifically, the direction integration ability of the target object can be determined in the visual low-attention area of the target object by using a noise dot array. The direction integration ability can be evaluated by using the upper limit of the direction integration angle. The higher the upper limit of the direction integration angle, the higher the direction integration ability. Accordingly, the evaluation baseline of the visual low-attention area can be higher. That is, the upper limit of the direction integration angle and the evaluation baseline of the same visual low-attention area can have a positive correlation.

[0101] In step S305, at least one of the search duration, the saccade number, and the slide direction evaluation accuracy of the target object for the virtual item is obtained to obtain a visual search training index value.

[0102] Specifically, the visual search training of the target object can be scored according to the search duration, and the obtained score value can be referred to as a first score value. The visual search training of the target object can be scored according to the saccade number, and the obtained score value can be referred to as a second score value. The visual search training of the target object can be scored according to the slide direction evaluation accuracy, and the obtained score value can be referred to as a third score value. The visual search training index value can be obtained according to at least one of the first score value, the second score value, and the third score value.

[0103] In step S306, an evaluation result is obtained according to whether the visual search training index value exceeds the evaluation baseline.

[0104] Specifically, if the visual search training index value exceeds the evaluation baseline of the visual low-attention area, it can be indicated that the visual search training of the target object meets the standard. If the visual search training index value does not exceed the evaluation baseline of the visual low-attention area, it can be indicated that the visual search training of the target object does not meet the standard.

[0105] In step S307, if the evaluation result indicates that the visual search training of the target object for the virtual item in the visual low-attention area meets the evaluation baseline, the appearance position of the virtual item is adjusted so that the adjusted appearance position is deeper in the visual field than the unadjusted appearance position, so as to perform the next visual search training.

[0106] Specifically, if the evaluation result indicates that the visual search training of the target object does not reach the evaluation baseline, it can be explained that the difficulty of this training is too high for the target object, and the appearance position of the virtual object can be adjusted so that the appearance position before adjustment is deeper in the field of view than the appearance position after adjustment, so that the target object can perform the next visual search training, and the above steps are repeated to evaluate the next visual search training according to the evaluation baseline of the visual low attention area, and the corresponding evaluation result is obtained.

[0107] Step S308, if the evaluation result indicates that the visual search training of the target object for the virtual object in the visual low attention area does not reach the evaluation baseline, the appearance position of the virtual object is adjusted so that the appearance position before adjustment is deeper in the field of view than the appearance position after adjustment, to perform the next visual search training.

[0108] Specifically, if the evaluation result indicates that the visual search training of the target object does not reach the evaluation baseline, it can be explained that the difficulty of this training is too high for the target object, and the appearance position of the virtual object can be adjusted so that the appearance position before adjustment is deeper in the field of view than the appearance position after adjustment, so that the target object can perform the next visual search training, and the above steps are repeated to evaluate the next visual search training according to the evaluation baseline of the visual low attention area, and the corresponding evaluation result is obtained.

[0109] The scheme of the embodiment can be applied to the visual field rehabilitation training of the target object (such as a visually impaired object), and a new visual field rehabilitation training method can be provided for the target object by fusing VR / MR technology, visual field tracking, intelligent algorithm and personalized rehabilitation plan. The intelligent algorithm can analyze the progress of the target object so as to adjust the rehabilitation plan, so that the rehabilitation effect is maximized; through the virtual scene of visual simulation, the training unit and the real-time feedback mechanism, personalized visual field rehabilitation training can be performed according to the specific needs and progress of the target object, so as to accelerate the rehabilitation process of the target object, and also help the target object to better adapt to the visual challenges in daily life.

[0110] The embodiment can use a dual-engine architecture for visual field rehabilitation training. Specifically:

[0111] (1) Static foundation: through the diagnostic partition engine, the mask of blind area-transition area-normal area is automatically generated from the fundus / visual field meter data, and age and gender can also be introduced, so that the partition has the adaptive ability of age and gender; the ripple animation of the blind area and the transient bright spot of the transition area convert "whether to see" into quantifiable "motion perception threshold" and "dynamic light sensitivity curve", laying a precise baseline for subsequent training.

[0112] (2) Dynamic transition: In the same window (which can be black curtain based), first train the direction discrimination (FDD, Fine Direction Discrimination) ability with moving dot array, and then switch to the direction integration ability with noise dot array. The angle / noise range can be tightened or widened in real time, so that the "local direction discrimination" can be smoothly transitioned to "global integration", and the real motion such as traffic flow and crowd can be simulated to complete the leap from static threshold to dynamic ability.

[0113] (3) Real scene landing: Through the eye movement target engine, the eye movement heat map can be read in real time, and the virtual objects (such as milk boxes, umbrellas, and mobile phones) matched with the virtual scene can be refreshed at the edge of the blind area in a life-like dynamic virtual scene (such as subway peak, supermarket shelf, and street corner).

[0114] Among them, the virtual object can be instantaneously moved with the eyeball rotation, so that the target object needs to search and saccade optimization for positioning; the search duration, saccade frequency, and confirmation delay can be recorded in real time and compared with the personal baseline, and the virtual object can be automatically moved to the deep or outer edge of the blind area, so as to maintain the "optimal challenge area"; the crowd obstruction and direction drift can be continuously changed, so that the FDD / CDDI ability can be seamlessly embedded in the daily action of "finding earphones and avoiding pedestrians", and the transition from laboratory index to life application can be realized.

[0115] The visual field rehabilitation training of the embodiment can realize the three-level progression of "static partitioning → dynamic direction → real scene", and change "can see" to "can see how far, can find how fast, and can avoid how accurately", so that the target object can go from "can see" to "can quickly, accurately and safely find the required objects in a complex environment", and the target object can quickly adapt to daily life.

[0116] In the treatment area and blind area positioning of the embodiment, a double-engine closed-loop architecture can be used, the partition mask (such as blind area, transition area and normal area) can be automatically generated from the fundus image / visual field data through the diagnostic partitioning engine, and can be adaptively adjusted according to the age and gender of the target object. The eye movement heat map can be read in real time through the eye movement target engine, and the movable virtual objects can be dynamically placed at the edge of the visual low attention area.

[0117] In the dynamic animation stimulation of the static blind area of the embodiment, a continuous periodic animation (such as ripple / drift dot array) can be generated inside any connected blind area, the animation can be randomly frozen for a set time (such as 2 seconds), the target object can feed back "whether the change is perceived" through the handle / voice in the frozen window, and then the perception accuracy can be calculated in real time, so that the speed, direction range and freezing probability of the next animation can be dynamically adjusted, and the "motion perception threshold" can be accurately quantified. The embodiment quantifies the motion perception in the blind area into a traceable index.

[0118] In the transient bright spot stimulation in the static transition zone, a transient bright spot with a set duration (such as 200 milliseconds) can be placed in the transition zone, and the target object can press the button to confirm within 1.5±0.5s. The position, size, and contrast of the transient bright spot can be updated in real time according to the “correctness x reaction time” of the previous reaction. The embodiment can change the traditional “static threshold” to a “dynamic threshold curve”, so that the light sensitivity training is always in the optimal challenge interval of the target object.

[0119] The embodiment provides direction discrimination micro-task training, which can be placed after static blind area animation stimulation, as an upgrade of dynamic direction perception, a simple window can be opened in the center of the blind area, and a cluster of dot matrix can move along four basic directions, and the target object can point out “up, down, left, right”. According to the correctness of the target object feedback result, the offset angle can be tightened or relaxed, and the direction sensitivity of the blind area can be quantified to degree, so as to lay the foundation for the direction accuracy of the subsequent integration task.

[0120] The embodiment provides direction integration macro-task training, hundreds of dot matrix in the same window can be mixed with different directions, the target object can distinguish “whether the whole is left or right”, the direction noise can be continuously enlarged or reduced, and the noise range can be adjusted in real time by ladder method. The larger the noise range is, the higher the difficulty of direction integration is, so that the difficulty of direction integration can be matched with the current ability of the target object; the determined upper limit value of the direction integration angle can map the global motion integration ability of the target object, so as to complete the leap from “local micro-discrimination” to “global integration”, and simulate complex motion scenes such as daily traffic and crowds.

[0121] The embodiment provides eye movement thermodynamic diagram to find stationary object training, the eye movement target engine is used to read the eye movement thermodynamic diagram of the target object in real time; VR or MR technology can be used to create a virtual scene, and virtual objects can be daily real objects matched with the virtual scene, such as milk cartons, keys, mobile phones, etc.; the visual low attention area can be determined through the eye movement thermodynamic diagram, and the virtual object can be generated at the edge or inside of the visual low attention area, and the rest of the area can be arranged with interference objects with similar shapes. The search duration (i.e. the time consumption of the first fixation to the target object) and the number of saccades of the target object during training can be recorded. If the search duration or the number of saccades is less than 20% of the individual baseline, the virtual object can automatically move 0.5° to the deep part of the visual low attention area. If the search duration or the number of saccades is higher than 20% of the individual baseline, the virtual object can automatically move outward and reduce the density of interference objects, while increasing the tactile / auditory prompts.

[0122] The embodiment provides a visual field thermal map dynamic complex scene comprehensive training, a dynamic virtual scene can be created, virtual objects conforming to the virtual scene are brushed out near a visual low attention area, the virtual objects can be dynamically moved with the virtual scene, an eye of a target object can be turned to search, a search duration is recorded, a change rate of the virtual scene is dynamically adjusted, and the training result can be uploaded to a server.

[0123] Take a living living room virtual scene as an example for introduction, visual field rehabilitation training based on the living room virtual scene can include the following contents.

[0124] (1) Days 1 to 7: Living room static perception;

[0125] The scene can be that the target object wears MR glasses and sits in the living room.

[0126] The task can include:

[0127] Blind area ripple: a water ripple animation can appear in the blind area above the tea table, frozen for 2 seconds, the target object can answer "see / not see" through voice; the ripple amplitude can be reduced by 10% each time.

[0128] Transition zone bright spot: a 200 millisecond transient bright spot can appear in the transition zone of the sofa armrest, and the target object can confirm by pressing a key; the brightness of the transient bright spot can be adjusted in real time according to "correctness x reaction time". The brightness can be adjusted downward when the correctness is high, and the brightness can be adjusted downward when the reaction time is short.

[0129] The target can include: establishing a personal blind area / transition zone baseline, and completing static perception threshold quantification.

[0130] (2) Days 8 to 14: Living room direction advancement;

[0131] The scene can be that the curtains are pulled down to keep simple.

[0132] The task can include:

[0133] Direction discrimination training: in a 5° circular view window in the central visual low attention area, a bundle of blue dot arrays can move 2° to 15°, and the target object can point out "up, down, left, right"; the offset angle can be gradually tightened.

[0134] Direction integration training: the dot arrays in the view window can drift left / right as a whole, and the target object can point out "overall direction"; the noise range can be gradually enlarged.

[0135] The target can include: upgrading "whether the direction can be distinguished" to "degree threshold" and "global integration angle".

[0136] (3) Days 15 to 21: Kitchen find still objects;

[0137] The scene can be a one-to-one VR kitchen.

[0138] The task can include:

[0139] A red spatula is displayed at the edge of the visual low-focus zone; the rest of the area is placed with the same black spatula as interference. Record the search duration and saccade times; if the search duration or saccade times are less than 20% of the individual baseline, the red spatula can automatically move 1° deeper into the visual low-focus zone, and if the search duration or saccade times are more than 20% of the individual baseline, the red spatula can automatically move outward and reduce the density of interference objects, while increasing tactile / auditory cues.

[0140] The goal can include: migrating the directional ability to the "find objects" static scene.

[0141] (4) 22 to 30 days: dynamic object search in subway morning peak;

[0142] The scene can be a simulated morning peak platform through MR technology, in which the crowd can move at 1.2 m / s, and the direction can be changed every 15 seconds.

[0143] The task can include:

[0144] A blue umbrella is brushed at the edge of the visual low-focus zone; the blue umbrella can drift with the crowd, and the target object needs to lock and "virtually grab" within 60 seconds. At the same time, embed the direction task, the blue umbrella handle can slide at an angle of 10°, and the target object can point out the sliding direction. According to the three indicators of search time, saccade times, and sliding direction accuracy, adjust the speed of the crowd and the depth of the appearance of the blue umbrella in real time.

[0145] The goal can include: verifying and solidifying training results, and realizing the life migration from the living room to the subway.

[0146] The present embodiment can also be applicable to other scenes, which can include but are not limited to:

[0147] Scene 1: "Find remote control" at home at night;

[0148] Static perception: 150 milliseconds of micro-light flashes in the blind area under the bedroom light.

[0149] Real scene: after turning off the light, the room is left with only the TV backlight, and the remote control is randomly dropped in the blind area. The target object needs to find and press the power button within 30 seconds.

[0150] Difficulty knob: light brightness and remote control color change in real time according to performance.

[0151] Scene 2: "Chase frisbee" while walking in the park;

[0152] Static perception: flashing frisbee shadow appears in the blind area of the lawn.

[0153] Real scene: frisbee is thrown by VR technology, along the parabolic trajectory through the blind area; the target object needs to rotate the eyeball tracking and "catch".

[0154] Difficulty knob: frisbee speed, trajectory curvature adjusts with performance.

[0155] Scene 3: office "find U disk";

[0156] Static perception: 100 milliseconds of metal reflection flashes in the blind area of the office table.

[0157] Real scene: the gap of the drawer, bookshelf, keyboard is full of interference U disk; the target object needs to lock the target and "pull out" within 45 seconds.

[0158] Difficulty knob: the number of interference, the intensity of reflection changes in real time.

[0159] The embodiment can realize the synchronous growth of training difficulty and demand through double-engine closed loop, motion perception threshold, light-sensitive dynamic threshold, FDD micro-training task, CDDI macro-training task, and static / dynamic life scene driven by eye movement heat map, can seamlessly migrate laboratory indicators to complex environments such as daily people flow, vehicle flow, and shelves, and can better make the visual field rehabilitation result land to the life ability.

[0160] It should be understood that although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps. It can be understood that the steps in different embodiments can be freely combined as needed, and various non-contradictory schemes formed by the combination are within the scope of protection of the present application.

[0161] Based on the same inventive concept, the embodiment of the present application also provides a visual field rehabilitation training device for implementing the visual field rehabilitation training method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more visual field rehabilitation training device embodiments provided below can refer to the limitations of the visual field rehabilitation training method in the above text, which will not be repeated here.

[0162] In one embodiment, asFigure 4 As shown, a visual field rehabilitation training device is provided, comprising:

[0163] A low attention area determination module 401 is configured to determine a visual low attention area of a target object according to an eye movement heat map of the target object.

[0164] A virtual processing module 402 is configured to create a virtual scene and generate a virtual object matching the virtual scene in the visual low attention area; the virtual object is used for visual search training of the target object.

[0165] A baseline determination module 403 is configured to determine an evaluation baseline corresponding to the visual low attention area according to an upper limit value of a direction integration angle corresponding to the visual low attention area; the higher the upper limit value of the direction integration angle, the higher the evaluation baseline.

[0166] An evaluation module 404 is configured to evaluate a visual search training situation of the target object for the virtual object in the visual low attention area according to the evaluation baseline, to obtain an evaluation result.

[0167] An adjustment module 405 is configured to adjust the virtual object according to the evaluation result, to perform a next visual search training.

[0168] In an embodiment, the device further comprises a direction integration evaluation module configured to:

[0169] create a view window for each region in the visual field of the target object in sequence; for any region, gradually increase a direction integration angle, and each time the direction integration angle is increased, move each point in a control point array in the view window of the region in any direction not exceeding the direction integration angle, and determine whether to continue to increase the direction integration angle according to whether an actual overall movement direction of the point array and an overall movement direction recognized by the target object are consistent, and if the increase of the direction integration angle is stopped, determine the direction integration angle obtained by the increase as an upper limit value of the direction integration angle corresponding to the region; and obtain the upper limit value of the direction integration angle corresponding to the visual low attention area according to the upper limit values of the direction integration angles corresponding to the regions belonging to the visual low attention area.

[0170] In an embodiment, the direction integration evaluation module is configured to:

[0171] if the actual overall movement direction of the point array and the overall movement direction recognized by the target object are consistent, determine to continue to increase the direction integration angle; and if the actual overall movement direction of the point array and the overall movement direction recognized by the target object are not consistent, stop to continue to increase the direction integration angle.

[0172] In an embodiment, the adjustment module 405 is configured to:

[0173] If the evaluation result represents that the visual search training situation of the target object for the virtual item in the visual low-attention area reaches the evaluation baseline, the appearance position of the virtual item is adjusted so that the adjusted appearance position is deeper in the visual field than the unadjusted appearance position; if the evaluation result represents that the visual search training situation of the target object for the virtual item in the visual low-attention area does not reach the evaluation baseline, the appearance position of the virtual item is adjusted so that the unadjusted appearance position is deeper in the visual field than the adjusted appearance position.

[0174] In an embodiment, the device further comprises a training indicator value determination module for:

[0175] determining an evaluation accuracy of search duration, saccade times and slide direction of the target object for the virtual item; obtaining a visual search training indicator value according to at least one of the evaluation accuracy of search duration, saccade times and slide direction; the visual search training indicator value is used to represent the visual search training situation of the target object for the virtual item in the visual low-attention area.

[0176] In an embodiment, the low-attention area determination module 401 is configured to:

[0177] obtain the attention degree of the target object for each region of the visual field according to the eye movement heat map of the target object; determine the region with low attention degree as the visual low-attention area of the target object.

[0178] Each module in the visual field rehabilitation training device described above can be realized by software, hardware and their combinations in whole or in part. Each module described above can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operation corresponding to each module.

[0179] In an exemplary embodiment, a computer device is provided, which can be used as a visual field rehabilitation training system. The internal structure diagram of the computer device can be as shown in Figure 5As shown in the figure. The computer device includes a processor, a memory, an Input / Output (I / O) interface, and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the data involved in the above method. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a visual field rehabilitation training method.

[0180] Those skilled in the art can understand that, Figure 5 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0181] In one embodiment, a visual field rehabilitation training system is provided, including a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps in each of the above method embodiments.

[0182] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by the processor to implement the steps in each of the above method embodiments.

[0183] In one embodiment, a computer program product is provided, which stores a computer program, and the computer program is executed by the processor to implement the steps in each of the above method embodiments.

[0184] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0185] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0186] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0187] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A visual field rehabilitation training device, characterized by, The device comprises: a low attention area determination module configured to determine a visual low attention area of a target object according to an eye movement heat map of the target object; a virtual processing module configured to create a virtual scene and generate a virtual object matching the virtual scene in the visual low attention area; the virtual object is used for visual search training of the target object; a baseline determination module configured to determine an evaluation baseline corresponding to the visual low attention area according to an upper limit value of a direction integration angle corresponding to the visual low attention area; the higher the upper limit value of the direction integration angle, the higher the evaluation baseline; an evaluation module configured to evaluate a visual search training situation of the target object for the virtual object in the visual low attention area according to the evaluation baseline to obtain an evaluation result; an adjustment module configured to adjust the virtual object according to the evaluation result for the next visual search training; wherein the device further comprises a direction integration evaluation module configured to create a view window for each area in a field of view of the target object in sequence; for any area, gradually increase a direction integration angle, and each time the direction integration angle is increased, each point in a control point array moves in any direction in the view window of the area within the direction integration angle, and whether to continue to increase the direction integration angle is determined according to whether the actual overall movement direction of the point array and the overall movement direction recognized by the target object are consistent; if the increase of the direction integration angle is stopped, the direction integration angle obtained by the increase is determined as an upper limit value of the direction integration angle corresponding to the area; and the upper limit value of the direction integration angle corresponding to the visual low attention area is obtained according to the upper limit value of the direction integration angle corresponding to the area belonging to the visual low attention area.

2. The apparatus of claim 1, wherein, The direction integration evaluation module is configured to: if the actual overall movement direction of the point array and the overall movement direction recognized by the target object are consistent, it is determined to continue to increase the direction integration angle; if the actual overall movement direction of the point array and the overall movement direction recognized by the target object are inconsistent, it is determined to stop increasing the direction integration angle.

3. The apparatus of claim 1, wherein, The adjustment module is configured to: if the evaluation result represents that the visual search training situation of the target object for the virtual object in the visual low attention area reaches the evaluation baseline, adjust the appearance position of the virtual object so that the adjusted appearance position is deeper in the field of view than the unadjusted appearance position; if the evaluation result represents that the visual search training situation of the target object for the virtual object in the visual low attention area does not reach the evaluation baseline, adjust the appearance position of the virtual object so that the unadjusted appearance position is deeper in the field of view than the adjusted appearance position.

4. The apparatus of claim 1, wherein, The device further comprises a training index value determination module configured to: determine a search duration, a saccade frequency and a sliding direction evaluation accuracy of the target object for the virtual object; The visual search training index value is obtained according to at least one of the search duration, the saccade number and the slide direction evaluation accuracy; and the visual search training index value is used to represent the visual search training situation of the target object for the virtual object in the visual low-attention area.

5. The apparatus of claim 4, wherein, The training index value determination module is configured to: score the visual search training of the target object according to the search duration, and obtain a first score value; score the visual search training of the target object according to the saccade number, and obtain a second score value; score the visual search training of the target object according to the slide direction evaluation accuracy, and obtain a third score value; obtain a visual search training index value according to at least one of the first score value, the second score value and the third score value.

6. The apparatus of claim 1, wherein, The virtual scene includes a life-like virtual scene.

7. The device of any one of claims 1 to 6, wherein, The low-attention area determination module is configured to: obtain the attention degree of each area of the field of view of the target object according to the eye movement heat map of the target object; and determine a low-attention area of the target object as the area with low attention degree.

8. A visual field rehabilitation training system comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the following steps: determine a visual low-attention area of the target object according to the eye movement heat map of the target object; create a virtual scene, and generate a virtual object matching the virtual scene in the visual low-attention area; the virtual object is used for visual search training of the target object; determine an evaluation baseline corresponding to the visual low-attention area according to a direction integration angle upper limit value corresponding to the visual low-attention area; the higher the direction integration angle upper limit value, the higher the evaluation baseline; evaluate the visual search training situation of the target object for the virtual object in the visual low-attention area according to the evaluation baseline, and obtain an evaluation result; adjust the virtual object according to the evaluation result, so as to perform the next visual search training; The step of obtaining the direction integration angle upper limit value corresponding to the visual low-attention area includes: creating a view window for each area in the field of view of the target object in sequence; for any area, gradually increasing the direction integration angle, and moving each point in a control point array in any direction in the view window of the area within the direction integration angle, determining whether to continue to increase the direction integration angle according to whether the actual overall movement direction of the point array and the overall movement direction recognized by the target object are consistent, and determining the direction integration angle upper limit value corresponding to the area if the direction integration angle is stopped from being continuously increased; and obtaining the direction integration angle upper limit value corresponding to the visual low-attention area according to the direction integration angle upper limit values corresponding to the areas belonging to the visual low-attention area.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the following steps: determine a visual low-attention area of the target object according to the eye movement heat map of the target object; create a virtual scene, and generate a virtual object matching the virtual scene in the visual low-attention area; the virtual object is used for visual search training of the target object; determine an evaluation baseline corresponding to the visual low-attention zone according to a direction integration angle upper limit value corresponding to the visual low-attention zone; the higher the direction integration angle upper limit value, the higher the evaluation baseline; evaluate a visual search training situation of the target object with respect to the virtual object in the visual low-attention zone according to the evaluation baseline, and obtain an evaluation result; adjust the virtual object according to the evaluation result, so as to perform a next visual search training; wherein the step of obtaining the direction integration angle upper limit value corresponding to the visual low-attention zone comprises: creating a view window for each region in a field of view of the target object in sequence; for any region, gradually increasing a direction integration angle, and each time the direction integration angle is increased, each point in a control point array moves in any direction within the view window of the region and does not exceed the direction integration angle, and whether to continue to increase the direction integration angle is determined according to whether the actual overall movement direction of the point array and the overall movement direction recognized by the target object are consistent, and if the direction integration angle is stopped from being continuously increased, the direction integration angle obtained by this time of increasing is determined as the direction integration angle upper limit value corresponding to the region; and the direction integration angle upper limit value corresponding to the visual low-attention zone is obtained according to the direction integration angle upper limit values corresponding to the regions belonging to the visual low-attention zone.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by a processor to implement the following steps: determine a visual low-attention zone of a target object according to an eye movement heat map of the target object; create a virtual scene, and generate a virtual object matching the virtual scene in the visual low-attention zone; the virtual object is used for the target object to perform visual search training; determine an evaluation baseline corresponding to the visual low-attention zone according to a direction integration angle upper limit value corresponding to the visual low-attention zone; the higher the direction integration angle upper limit value, the higher the evaluation baseline; evaluate a visual search training situation of the target object with respect to the virtual object in the visual low-attention zone according to the evaluation baseline, and obtain an evaluation result; adjust the virtual object according to the evaluation result, so as to perform a next visual search training; wherein the step of obtaining the direction integration angle upper limit value corresponding to the visual low-attention zone comprises: creating a view window for each region in a field of view of the target object in sequence; for any region, gradually increasing a direction integration angle, and each time the direction integration angle is increased, each point in a control point array moves in any direction within the view window of the region and does not exceed the direction integration angle, and whether to continue to increase the direction integration angle is determined according to whether the actual overall movement direction of the point array and the overall movement direction recognized by the target object are consistent, and if the direction integration angle is stopped from being continuously increased, the direction integration angle obtained by this time of increasing is determined as the direction integration angle upper limit value corresponding to the region; and the direction integration angle upper limit value corresponding to the visual low-attention zone is obtained according to the direction integration angle upper limit values corresponding to the regions belonging to the visual low-attention zone.

Images