Zoom glasses regulation and control method and equipment based on artificial intelligence

Abstract

The invention belongs to the technical field of zoom glasses, and provides a zoom glasses regulation and control method and equipment based on artificial intelligence. The method comprises the following steps: when the current time reaches a training period in preset work and rest information, controlling a range finder on zoom glasses to measure obstacles in a front preset range, and obtaining a group of fed-back first distance data; analyzing according to first distance data measured by the range finder to obtain a head posture of the user, and determining the zoom glasses as target zoom glasses when judging that the head posture accords with a preset posture; and obtaining dynamic training data corresponding to the user associated with each piece of target zoom glasses, and respectively sending the dynamic training data to the corresponding target zoom glasses to enable the target zoom glasses to start a training mode, namely, dynamically adjusting the focal length of the glasses according to the dynamic training data. According to the invention, at least remote and overall rapid switching of the zoom mode of the zoom glasses can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of zoom glasses, and more specifically, to a method and device for adjusting a zoom glass based on artificial intelligence. Background Art

[0002] In the field of glasses technology, as people's demands for vision correction and visual experience continue to increase, traditional single-focus and bifocal lenses are no longer able to meet the increasingly diverse needs. Against this background, zoom glasses have emerged as an important innovation in the field of glasses technology.

[0003] As Figure 1 shown, the basic principle of zoom glasses lies in their adoption of advanced optical technology and adaptive lens materials. These lenses can automatically adjust the diopter according to the change of the wearer's eye focus, thereby achieving continuous change of the focal length. Specifically, zoom glasses usually consist of two groups of free-form lenses, which can move back and forth under the drive of a motor. When both lenses are negative diopters, they will be superimposed to produce a high negative diopter, which is suitable for near vision needs; when one is positive and the other is negative, the diopters will cancel each other out, which is suitable for far vision needs. Through this design, the diopter of the zoom glasses can vary within a continuous range, with the diopter range from +3.00D to -3.00D, or even higher, so as to meet the visual needs at different distances.

[0004] Zoom glasses can be configured with a normal mode and a training mode. In the normal mode, the zoom range of the zoom glasses will be relatively small to support the daily use of users, such as reading, etc.; while in the dynamic mode, the zoom range of the zoom glasses will be much larger, so that the eyes of users can be trained with a higher intensity to improve hyperopia and myopia conditions.

[0005] However, the current mode switching of zoom glasses requires manual operation by users (such as button operation, voice operation, etc.), and the usability is not good; moreover, in usage scenarios where there are many users wearing zoom glasses, such as in classrooms, it is impossible to switch the modes of the zoom glasses of multiple users in the usage scenario more quickly and uniformly. Therefore, how to improve the convenience of mode switching of zoom glasses in usage scenarios where there are many users wearing zoom glasses, such as in classrooms, is a technical problem that urgently needs to be solved at present. Summary of the Invention

[0006] In view of this, the present invention provides a method, device, electronic device, computer storage medium and computer program product for adjusting a zoom glass based on artificial intelligence to solve at least one of the above technical problems.

[0007] The present invention provides an artificial intelligence-based zoom glasses control method, which is applied to a remote management terminal and includes the following method steps: When the current time reaches the training period in the preset work and rest information, control the rangefinder on the zoom glasses to measure obstacles in a preset range in front, and obtain a set of first distance data fed back; Analyze the first distance data measured by the rangefinder to obtain the head posture of the user. When it is determined that the head posture conforms to the preset posture, determine the zoom glasses as the target zoom glasses; Obtain the dynamic training data corresponding to the users associated with each of the target zoom glasses, and send the dynamic training data to the corresponding target zoom glasses respectively, so that the target zoom glasses can turn on the training mode, that is, perform dynamic adjustment of the glasses focal length according to the dynamic training data.

[0008] As an example, the control of the rangefinder on the zoom glasses to measure obstacles in a preset range in front includes: Obtain another set of second distance data measured by the rangefinder in the normal mode, and calculate the width of the material that the user is looking at according to the second distance data; Wherein, the width refers to the dimension of the material from the end close to the user's body to the end away from the user's body; Determine the preset range according to the width, and control the rangefinder on the zoom glasses to measure obstacles in the preset range in front; Wherein, the preset range is positively correlated with the width.

[0009] As an example, the analysis of the first distance data measured by the rangefinder to obtain the head posture of the user includes: Divide the preset range into a lower area and an upper area, and separately separate the third distance data corresponding to the lower area and the fourth distance data corresponding to the upper area from the first distance data; Determine the size data of the material according to the third distance data, and calculate the equivalent distance according to the fourth distance data. The equivalent distance is the average value or the mode value of each distance in the fourth distance data; Evaluate the head downward tilt angle of the user according to the size data and the equivalent distance, and this head downward tilt angle is the head posture.

[0010] As an example, the evaluation of the head downward tilt angle of the user according to the size data and the equivalent distance includes: Retrieve the upper body size of the user and the surface layer height of the table and chair to form basic data; Input the basic data, the size data and the equivalent distance into an evaluation model based on Transformer, and the evaluation model outputs the evaluated head downward tilt angle of the user.

[0011] As an example, the evaluation model includes a convolutional network, a first encoder, a second encoder, and a decoder. The output end of the convolutional network is respectively connected to the input ends of the first encoder and the second encoder, and the output ends of the first encoder and the second encoder are respectively connected to the decoder.

[0012] The present invention also provides an artificial intelligence-based zoom glasses control device, which is applied to a remote management terminal. The device includes an acquisition and sending module and a determination module. The acquisition and sending module is configured to, when the current time reaches the training period in the preset work and rest information, control a rangefinder on the zoom glasses to measure obstacles in a preset range in front and obtain a set of first distance data as feedback. The determination module is configured to analyze the first distance data measured by the rangefinder to obtain the user's head posture, and when it is determined that the head posture conforms to the preset posture, determine the zoom glasses as the target zoom glasses. The acquisition and sending module is further configured to acquire dynamic training data corresponding to the users associated with each of the target zoom glasses, and send the dynamic training data to the corresponding target zoom glasses respectively, so that the target zoom glasses turn on the training mode, that is, perform dynamic adjustment of the glasses focal length according to the dynamic training data.

[0013] As an example, the acquisition and sending module is specifically configured to: acquire another set of second distance data measured by the rangefinder in the normal mode, and calculate the width of the material that the user is looking at according to the second distance data; wherein, the width refers to the dimension of the material in the direction from the end close to the user's body to the end far from the user's body; determine the preset range according to the width, and control the rangefinder on the zoom glasses to measure obstacles in the preset range in front; wherein, the preset range is positively correlated with the width.

[0014] As an example, the determination module is specifically configured to: divide the preset range into a lower region and an upper region, and separately separate from the first distance data the third distance data corresponding to the lower region and the fourth distance data corresponding to the upper region; determine the size data of the material according to the third distance data, calculate the equivalent distance according to the fourth distance data, and the equivalent distance is the average value or the mode value of each distance in the fourth distance data; evaluate the user's head downward tilt angle according to the size data and the equivalent distance, and this head downward tilt angle is the head posture.

[0015] As an example, the determination module is specifically configured to: retrieve the upper body size of the user and the surface layer height of the table and chair to form basic data; input the basic data, the size data, and the equivalent distance into an evaluation model based on Transformer, and the evaluation model outputs the evaluated head downward tilt angle of the user.

[0016] As an example, the evaluation model includes a convolutional network, a first encoder, a second encoder, and a decoder. The output end of the convolutional network is respectively connected to the input ends of the first encoder and the second encoder, and the output ends of the first encoder and the second encoder are respectively connected to the decoder.

[0017] The present invention also provides an electronic device, which is characterized in that: the electronic device includes at least one processor, a memory, and a computer program stored in the memory and operable on the at least one processor. When the computer program is executed by the processor, the method described in any one of the foregoing items is implemented.

[0018] The present invention also provides a computer storage medium, which stores a computer program that can be executed by a processor to implement the method described in any one of the foregoing items.

[0019] The present invention also provides a computer program product, which includes a computer program that can be executed by a processor to implement the method described in any one of the foregoing items.

[0020] The beneficial effects of the present invention are as follows: on the one hand, the solution of the present invention can centrally control the zoom modes of the zoom glasses of multiple users in scenarios such as classrooms by a remote management terminal, without the need for users to manually adjust the zoom mode, greatly improving the convenience of use. On the other hand, the present invention first analyzes whether the user's head posture is suitable for starting the training mode, and only when the head posture is suitable for starting the training mode, personalized dynamic training data is sent to the zoom glasses for execution, so as to avoid large-scale zoom training when the user is in a situation such as lowering the head, thereby improving the zoom training effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a schematic diagram of the basic zoom principle of the zoom glasses.

[0023] Figure 2 It is a schematic flowchart of a method for controlling a zoom glass based on artificial intelligence disclosed in an embodiment of the present invention.

[0024] Figure 3 It is a schematic structural diagram of a device for controlling a zoom glass based on artificial intelligence disclosed in an embodiment of the present invention. Detailed implementation manners

[0025] The following specific embodiments illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0026] In addition, the technical features involved in different implementation manners of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0027] As Figure 1 shown, an embodiment of the present invention discloses a method for controlling a zoom glasses based on artificial intelligence, which is applied to a remote management terminal and includes the following method steps: when the current time reaches the training period in the preset work and rest information, controlling a rangefinder on the zoom glasses to measure obstacles in a preset range in front, and obtaining a set of first distance data fed back; analyzing the first distance data measured by the rangefinder to obtain the head posture of the user, and when it is determined that the head posture conforms to a preset posture, determining the zoom glasses as target zoom glasses; obtaining dynamic training data corresponding to the users associated with each of the target zoom glasses, and sending the dynamic training data to the corresponding target zoom glasses respectively, so that the target zoom glasses turn on the training mode, that is, dynamically adjust the focal length of the glasses according to the dynamic training data.

[0028] The solution of the present invention is applied to scenarios with multiple users wearing zoom glasses, such as classrooms, glasses rehabilitation / correction centers, etc. In these scenarios, normal teaching / self-study activities can be carried out for users, and there are training periods (such as rest periods or specially set eye training periods) during the breaks of teaching / self-study activities, and the corresponding preset work and rest information is specifically compiled. During the teaching / self-study period, the remote management terminal uniformly sends control instructions to each zoom glasses in the scenario to switch its zoom mode to the normal mode; and when the current time reaches the training period in the preset work and rest information, the remote management terminal uniformly sends control instructions to each zoom glasses in the scenario to switch its zoom mode from the normal mode to the training mode.

[0029] In addition, before switching the zoom mode from the normal mode to the training mode, it is further necessary to determine whether the corresponding user is ready for training, that is, whether the head posture reaches a preset posture. For example, the preset posture is that the head is vertically facing forward. In the training mode, the user needs to stop the bowed head posture when reading or studying, but raise the head and keep facing forward, so that the user's eye vision is wider and will keep a farther distance from obstacles (such as textbooks). At this time, a higher-intensity zoom action is performed to train the eyes.

[0030] Specifically, when the current time reaches the training period in the preset work and rest information, the rangefinder on the zoom glasses is controlled to measure obstacles in a preset range in front. The rangefinder feeds back a set of first distance data it measures to the remote management terminal. The remote management terminal analyzes the head posture of the user based on this set of first distance data. When it is determined that the head posture conforms to the preset posture, the corresponding zoom glasses are determined as the target zoom glasses. Then, the dynamic training data corresponding to each target zoom glasses is retrieved from the database and sent to the target zoom glasses for execution, that is, the training mode is enabled, so as to realize the personalized training of the user's eyes.

[0031] Therefore, on the one hand, the solution of the present invention can centrally control the zoom modes of the zoom glasses of multiple users in scenarios such as classrooms by the remote management terminal, without the need for users to manually adjust the zoom mode, and the usability is greatly improved. On the other hand, the present invention also first analyzes whether the head posture of the user is suitable for enabling the training mode, and only when the head posture is suitable for enabling the training mode, the personalized dynamic training data is sent to the zoom glasses for execution, so as to avoid large-amplitude zoom training when the user is in a bowed head or other situations, thereby improving the zoom training effect.

[0032] As an example, the controlling the rangefinder on the zoom glasses to measure obstacles in a preset range in front includes: obtaining another set of second distance data measured by the rangefinder in the normal mode, and calculating the width of the material that the user is looking at according to the second distance data; wherein, the width refers to the dimension of the material from the end close to the user's body to the end away from the user's body; determining the preset range according to the width, and controlling the rangefinder on the zoom glasses to measure obstacles in the preset range in front; wherein, the preset range is positively correlated with the width.

[0033] In this embodiment, in the normal mode, the user looks down at the learning materials placed on the desk, such as textbooks, etc. In the training mode, the user switches from the head-down posture to the head-up and straight-ahead posture to adapt to the stronger change in the focal length of the varifocal glasses. However, when the user switches from the head-down posture to the head-up posture, it may not necessarily conform to the preset posture. For example, although the user raises the head to a certain extent, the head-up amplitude is insufficient, and at this time, the user's eyes are still looking down at the learning materials on the desk (i.e., "peeking"). Moreover, the wider the learning materials are, the easier it is for the user to obtain a better viewing effect by tilting the learning materials.

[0034] Based on the above actual situation, the present invention first analyzes the width of the learning materials that the user is looking at in the normal mode, and then determines the size of the preset range for the distance measuring instrument to scan the obstacle distance according to the width. Among them, the wider the learning materials are, the greater the probability that the user's head posture conforms to the preset posture but obtains a better viewing effect by tilting the learning materials. At this time, a larger preset range is set, which is beneficial to scanning the learning materials placed obliquely. If the learning materials are scanned, it indicates that there is a high probability that the user is not looking straight ahead at this time, that is, the condition for switching to the training mode is not met; on the contrary, the smaller the probability that the user's head posture conforms to the preset posture but obtains a better viewing effect by tilting the learning materials, and at this time, a smaller preset range is set.

[0035] In addition, in the normal mode of the varifocal glasses, the distance measuring instrument periodically measures the obstacle distance information in the directly-ahead area measured by the varifocal glasses, that is, the above-mentioned another set of second distance data. Based on the second distance data, the outline of the learning materials that the user is looking at can be determined, and thus its width can be evaluated.

[0036] As an example, analyzing the user's head posture based on the first distance data measured by the distance measuring instrument includes: dividing the preset range into a lower area and an upper area, and separately separating the third distance data corresponding to the lower area and the fourth distance data corresponding to the upper area from the first distance data; determining the size data of the material according to the third distance data, and calculating the equivalent distance according to the fourth distance data, where the equivalent distance is the average value or the mode value of each distance in the fourth distance data; evaluating the head-down angle of the user according to the size data and the equivalent distance, and the head-down angle is the head posture.

[0037] In this embodiment, after the user switches from looking down to looking up, the rangefinder is controlled to detect the distance to obstacles within a preset range in front. The preset range can be divided into a lower region and an upper region, and accordingly, the first distance data is correspondingly divided into third distance data and fourth distance data. Among them, the third distance data is used to analyze whether the rangefinder scans the learning material that the user previously looked at, and the fourth distance data is used to analyze whether the obstacles in front are "relatively far" as a whole. For example, when there is a wall within 30 cm in front of a user, it is not appropriate to perform high-intensity zoom training at this time, while if there is a podium 5 m in front of a user, it is appropriate to perform high-intensity zoom training at this time.

[0038] Therefore, based on the third distance data and the fourth distance data, the size data (such as width, area, etc.) of the material placed on the desktop and the equivalent distance of the front scene (the equivalent distance is the average value or the mode value of each distance in the fourth distance data) can be determined respectively. Based on this, the head tilt angle of the user at this time (compared with the vertical direction, the larger the head tilt angle, the greater the corresponding head-down amplitude) can be evaluated, that is, the head pose of the user is obtained.

[0039] As an example, the evaluation of the user's head tilt angle according to the size data and the equivalent distance includes: retrieving the upper body size of the user and the surface height of the desk and chair to form basic data; inputting the basic data, the size data, and the equivalent distance into an evaluation model based on Transformer, and the evaluation model outputs the evaluated head tilt angle of the user.

[0040] In this embodiment, the present invention constructs an evaluation model based on Transformer. This evaluation model can comprehensively analyze the size data and the equivalent distance analyzed from the first distance data measured by the rangefinder mentioned above to evaluate the head tilt angle of the user at this time. In addition, since the upper body size of the user and the surface height of the desk and chair (i.e., the height of the desktop and the chair surface) will also directly affect the size of the learning material scanned in the lower region, the present invention also inputs these data into the evaluation model to improve the accuracy of the evaluated head tilt angle of the user.

[0041] As an example, the evaluation model includes a convolutional network, a first encoder, a second encoder, and a decoder. The output end of the convolutional network is respectively connected to the input ends of the first encoder and the second encoder, and the output ends of the first encoder and the second encoder are respectively connected to the decoder.

[0042] In this embodiment, the evaluation model of the present invention integrates a convolutional network. The convolutional network extracts feature data from the input data, and then the dual encoders perform encoding processing on the feature data respectively. After the analysis results of the dual encoders are weighted and fused, for example, the decoder performs decoding processing to obtain the head tilt angle of the evaluated user.

[0043] As an example, the remote management terminal is further configured to send individual control parameters to the zoom glasses, and the individual control parameters are used to implement independent training of the left and right eyes.

[0044] In this embodiment, both the left and right eyes of myopic users may have refractive errors such as myopia, hyperopia, or astigmatism (for example, different myopia degrees in the left and right eyes). However, in existing zoom glasses, the left and right eyes are controlled by a single motor, and the left and right eyes cannot be trained independently. To solve this technical problem, the present invention sets the remote management terminal to formulate corresponding zoom control parameters according to the myopia conditions of the left and right eyes of a specific myopic user, integrates the two zoom control parameters into individual control parameters, and sends them to the corresponding zoom glasses. The zoom glasses can then perform independent and personalized training on the left and right eyes according to the two zoom control parameters. Among them, the zoom glasses are correspondingly provided with two motors on the left and right. The solution of the present invention is suitable for training in different scenarios, such as reading, watching TV, and looking into the distance, and precise training can be carried out in these scenarios.

[0045] It should be noted that when the user's reading training posture is incorrect or the user is too close to the book, the zoom glasses can also detect these bad behaviors based on the built-in sensors (such as the aforementioned rangefinder, but it can also be a gyroscope, etc.), and then issue a sound reminder.

[0046] As Figure 3 shown, the present invention also provides an artificial intelligence-based zoom glasses control device applied to the remote management terminal. The device includes an acquisition and sending module and a determination module. The acquisition and sending module is configured to control the rangefinder on the zoom glasses to measure obstacles in a preset range in front when the current time reaches the training period in the preset work and rest information, and obtain a set of first distance data as feedback. The determination module is configured to analyze the user's head posture based on the first distance data measured by the rangefinder, and determine the zoom glasses as the target zoom glasses when it is determined that the head posture conforms to the preset posture. The acquisition and sending module is further configured to obtain the dynamic training data corresponding to the users associated with each of the target zoom glasses, and send the dynamic training data to the corresponding target zoom glasses respectively, so that the target zoom glasses can turn on the training mode, that is, perform dynamic adjustment of the glasses focal length according to the dynamic training data.

[0047] As an example, the obtaining and sending module is specifically configured to: obtain another set of second distance data measured by the rangefinder in the normal mode, and calculate the width of the material being gazed at by the user according to the second distance data; wherein, the width refers to the dimension of the material in the direction from the end close to the user's body to the end far from the user's body; determine the preset range according to the width, and control the rangefinder on the zoom glasses to measure obstacles within the preset range in front; wherein, the preset range is positively correlated with the width.

[0048] As an example, the determining module is specifically configured to: divide the preset range into a lower region and an upper region, and separately separate from the first distance data the third distance data corresponding to the lower region and the fourth distance data corresponding to the upper region; determine the size data of the material according to the third distance data, and calculate the equivalent distance according to the fourth distance data, where the equivalent distance is the average value or the mode value of the distances in the fourth distance data; evaluate the head downward tilt angle of the user according to the size data and the equivalent distance, and this head downward tilt angle is the head posture.

[0049] As an example, the determining module is specifically configured to: retrieve the upper body size of the user and the surface height of the table and chair to form basic data; input the basic data, the size data, and the equivalent distance into an evaluation model based on Transformer, and the evaluation model outputs the evaluated head downward tilt angle of the user.

[0050] As an example, the evaluation model includes a convolutional network, a first encoder, a second encoder, and a decoder. The output end of the convolutional network is respectively connected to the input ends of the first encoder and the second encoder, and the output ends of the first encoder and the second encoder are respectively connected to the decoder.

[0051] The present invention also discloses an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. When the computer program is executed by the processor, it implements the method steps as described in any one of the foregoing items.

[0052] The present invention also discloses a computer storage medium, which stores a computer program that can be executed by a processor to implement the method as described in any one of the foregoing items.

[0053] The present invention also discloses a computer program product, which includes a computer program that can be executed by a processor to implement the method as described in any one of the foregoing items.

[0054] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more integrated available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as digital video discs (DVDs)), or semiconductor media (such as solid state disks (SSDs)), etc.

[0055] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0056] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0057] In addition, in each embodiment of the present invention, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0058] As mentioned above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A zoom glasses control method based on artificial intelligence, applied to a remote management terminal, characterized in that: It includes the following method steps: when the current time reaches the training period in the preset work and rest information, control the rangefinder on the zoom glasses to measure obstacles in a preset range in front, and obtain a set of first distance data as feedback; Analyze the head posture of the user based on the first distance data measured by the rangefinder. When it is determined that the head posture conforms to the preset posture, determine the zoom glasses as the target zoom glasses; Obtain the dynamic training data corresponding to the user associated with each of the target zoom glasses, and send the dynamic training data to the corresponding target zoom glasses respectively, so that the target zoom glasses can turn on the training mode, that is, perform dynamic adjustment of the lens focal length according to the dynamic training data.

2. The zoom glasses control method based on artificial intelligence according to claim 1, characterized in that: The control of the rangefinder on the zoom glasses to measure obstacles in a preset range in front includes: obtaining another set of second distance data measured by the rangefinder in the normal mode, and calculating the width of the material that the user is looking at according to the second distance data; where the width refers to the dimension of the material from the end close to the user's body to the end away from the user's body; determine the preset range according to the width, and control the rangefinder on the zoom glasses to measure obstacles in the preset range in front; where the preset range is positively correlated with the width.

3. The zoom glasses control method based on artificial intelligence according to claim 2, characterized in that: Analyzing the head posture of the user based on the first distance data measured by the rangefinder includes: dividing the preset range into a lower region and an upper region, and separately separating from the first distance data the third distance data corresponding to the lower region and the fourth distance data corresponding to the upper region; determining the size data of the material according to the third distance data, and calculating the equivalent distance according to the fourth distance data, where the equivalent distance is the average value or the mode value of the distances in the fourth distance data; evaluating the head downward tilt angle of the user according to the size data and the equivalent distance, and this head downward tilt angle is the head posture.

4. The zoom glasses control method based on artificial intelligence according to claim 3, wherein: The evaluation of the head downward tilt angle of the user according to the size data and the equivalent distance includes: retrieving the upper body size of the user and the surface height of the table and chair to form basic data; inputting the basic data, the size data and the equivalent distance into an evaluation model based on Transformer, and the evaluation model outputs the evaluated head downward tilt angle of the user.

5. The zoom glasses control method based on artificial intelligence according to claim 4, characterized in that: The evaluation model includes a convolutional network, a first encoder, a second encoder and a decoder. The output end of the convolutional network is respectively connected to the input ends of the first encoder and the second encoder, and the output ends of the first encoder and the second encoder are respectively connected to the decoder.

6. A zoom glasses control device based on artificial intelligence, applied to a remote management terminal, characterized in that: The device includes an acquisition and sending module and a determination module; the acquisition and sending module is used to control the rangefinder on the zoom glasses to measure obstacles in a preset range in front when the current time reaches the training period in the preset work and rest information, and obtain a set of first distance data as feedback; The determining module is configured to analyze the first distance data measured by the rangefinder to obtain the user's head posture, and determine the zoom glasses as the target zoom glasses when it is determined that the head posture conforms to the preset posture; the obtaining and sending module is further configured to obtain the dynamic training data corresponding to the users associated with each of the target zoom glasses, and send the dynamic training data to the corresponding target zoom glasses respectively, so that the target zoom glasses enter the training mode, that is, perform dynamic adjustment of the lens focal length according to the dynamic training data.

7. The zoom glasses control device based on artificial intelligence according to claim 6, characterized in that: The obtaining and sending module is specifically configured to: obtain another set of second distance data measured by the rangefinder in the normal mode, and calculate the width of the material that the user is looking at according to the second distance data; wherein, the width refers to the dimension of the material in the direction from the end close to the user's body to the end away from the user's body; determine the preset range according to the width, and control the rangefinder on the zoom glasses to measure obstacles in the front preset range; wherein, the preset range is positively correlated with the width.

8. An electronic device, characterized in that: The electronic device includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, and the computer program, when executed by the processor, implements the method as described in any one of claims 1-5.

9. A computer storage medium, characterized in that: The computer storage medium stores a computer program that can be executed by a processor to implement the method as described in any one of claims 1-5.

10. A computer program product, characterized in that: The computer program product includes a computer program that can be executed by a processor to implement the method as described in any one of claims 1-5.

Images