Tablet computer control method and system for multiple warning and eye protection
By integrating environmental brightness and image acquisition components in the tablet computer, analyzing user pupil changes and randomness, the problem of inaccurate eye protection effects in the prior art is solved, and more accurate eye protection alertness and vision protection are achieved.
Patent Information
- Application Number
- CN202411504696.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-26
- Publication Date
- 2025-02-07
AI Technical Summary
Existing tablet eye protection technology cannot accurately perform eye protection intervention based on user pupil changes, resulting in inaccurate eye protection effects and cannot effectively prevent vision loss or relieve visual fatigue.
By configuring the environmental brightness sensing element and image acquisition element in the tablet, collecting the environmental brightness and user images, calculating the changing brightness sequence, analyzing the user's pupil changes and randomness, predicting the pupil change parameters and randomness, classifying the alert information, and performing Multiple eye protection tips and command controls.
It improves the accuracy of eye protection alertness of tablet computers, and accurately analyzes pupil changes and randomness through multiple eye protection prompt mechanisms, reduces visual fatigue and damage, and protects users' vision health.
Smart Images
Figure CN119396285A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of electronic equipment, and in particular to a tablet computer control method and system for multiple alert eye protection. Background Art
[0002] Existing tablet computer eye protection technologies mainly focus on automatic adjustment of screen brightness and blue light filtering. Through ambient light sensors, devices can adjust screen brightness according to changes in external light, reducing eye stimulation caused by overly bright or dark displays. In addition, blue light filtering technology reduces eye fatigue and potential damage to the retina when users use electronic devices for a long time by reducing blue light radiation. However, most existing technologies ignore the monitoring and analysis of changes in user pupil size.
[0003] In a dim light environment, the pupil dilates, and the size of the pupil directly affects the eye's ability to adapt to light and the degree of visual fatigue. Pupil dilation can cause accelerated eye fatigue. However, existing eye protection technology cannot accurately intervene in eye protection based on pupil changes. This lack of targeted technology can easily lead to inaccurate eye protection effects and cannot effectively prevent vision loss or relieve visual fatigue. Summary of the invention
[0004] The present invention aims to address the technical problems in the prior art that accurate eye protection intervention cannot be performed according to pupil changes, the eye protection effect is inaccurate, and vision loss cannot be effectively prevented or visual fatigue is relieved.
[0005] In a first aspect, the present invention provides a tablet computer control method for multiple alert eye protection, comprising: collecting ambient brightness through an ambient brightness sensing element configured in the tablet computer, and calculating a brightness change sequence in combination with display content of the tablet computer and the ambient brightness; According to the brightness change sequence, a pupil change analysis and a change randomness analysis of the user are performed to obtain a predicted pupil change parameter and a predicted change randomness, and the first alert information is obtained by classification; Prompting an eye protection alert according to the first alert information, monitoring the eye protection operation within a preset alert time range, and when no eye protection operation is detected, collecting user images through an image acquisition element configured in the tablet computer, performing pupil change recognition and change randomness analysis, and obtaining pupil change recognition parameters and change randomness recognition; The second alert information is obtained according to the identification of pupil change parameters and the identification of change randomness classification, and an alert eye protection prompt is given. If no eye protection operation is detected within the preset alert time range, the tablet computer is controlled to execute the eye protection instruction.
[0006] In a second aspect, the present invention provides a tablet computer control system for multiple alert eye protection, the system comprising: The variable brightness acquisition module is used to collect the ambient brightness through the ambient brightness sensing element configured in the tablet computer, and calculate and obtain the variable brightness sequence in combination with the display content of the tablet computer and the ambient brightness; A first alertness analysis module is used to perform pupil change analysis and change randomness analysis on the user according to the change brightness sequence, obtain predicted pupil change parameters and predicted change randomness, and classify and obtain first alert information; a first alert eye protection module, configured to provide an alert eye protection prompt according to the first alert information, monitor the eye protection operation within a preset alert time range, and when no eye protection operation is detected, collect user images through an image acquisition element configured in the tablet computer, perform pupil change recognition and change randomness analysis, and obtain pupil change recognition parameters and change randomness; The second alert eye protection module is used to obtain the second alert information according to the identification pupil change parameters and the identification change randomness classification, and to provide an alert eye protection prompt. If no eye protection operation is detected within the preset alert time range, the tablet computer is controlled to execute the eye protection instruction.
[0007] In a third aspect, the present invention provides an electronic device, comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing the tablet computer control method for multiple alert eye protection in the first aspect.
[0008] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer software program stored therein, and when the computer software program is executed by a processor, the tablet computer control method for multiple alert eye protection of the first aspect is implemented.
[0009] The present invention can effectively improve the accuracy of eye protection alerts of tablet computers through one or more of the above-mentioned technical solutions. The solution collects ambient light information in real time through an ambient brightness sensing element, calculates a brightness change sequence in combination with the display content of the tablet computer, and further predicts pupil change parameters and randomness through analysis of user pupil changes and randomness of changes, thereby more accurately judging the risk of visual impairment and performing the first level of alert. In addition, the method also identifies user pupil changes through an image acquisition element to obtain more accurate alert information for a second level of alert. Its multiple eye protection prompt mechanisms ensure that users obtain more accurate eye protection guidance when using the device for a long time. Compared with traditional eye protection technologies that only rely on brightness adjustment and blue light filtering, it introduces the analysis of the impact of changes in user pupil size and the analysis of randomness of changes, accurately analyzes the degree of random changes in pupils caused by random changes in brightness, performs eye protection alerts, and effectively reduces visual fatigue and damage caused by environmental changes, brightness fluctuations, or long-term pupil dilation changes, and ultimately achieves the technical effect of improving the accuracy and reliability of alert eye protection, and further protects the user's vision health. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1 A schematic flow chart of a tablet computer control method for multiple alert eye protection provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a tablet computer control system for multiple alert eye protection provided by an embodiment of the present invention; Figure 3 A functional block diagram of an electronic device provided by an embodiment of the present invention; Figure 4 A principle block diagram of the computer-readable storage medium provided by the present invention.
[0011] In the accompanying drawings, the components represented by the reference numerals are as follows: A brightness change acquisition module 11, a first alert analysis module 12, a first alert eye protection module 13, a second alert eye protection module 14, an electronic device 100, a memory 110, a processor 120, a computer program 111, and a computer-readable storage medium 200. DETAILED DESCRIPTION
[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.
[0013] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.
[0014] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.
[0015] like Figure 1 As shown, an embodiment of the present invention provides a tablet computer control method for multiple alert eye protection, including the following steps.
[0016] S10: collecting the ambient brightness through an ambient brightness sensing element configured in the tablet computer, and calculating and obtaining a brightness variation sequence in combination with display content of the tablet computer and the ambient brightness; In the embodiment of the present application, the ambient light intensity data around the device is collected in real time by configuring an ambient brightness sensing element inside the tablet computer. The ambient brightness sensing element is a sensor that can detect the intensity of ambient light, usually based on a photodiode or a photosensitive element, and its function is to accurately sense the lighting conditions of the user's environment.
[0017] Furthermore, the brightness at multiple moments currently felt by the eyes of the user using the tablet computer is obtained by combining the content currently displayed by the tablet computer, including information such as screen brightness at multiple moments, and the ambient brightness, to obtain a variable brightness sequence.
[0018] Through the above steps, the brightness felt by the user's eyes during the current use of the tablet computer can be obtained, which can serve as a basis for subsequent analysis of the impact of brightness on changes in the user's pupils.
[0019] Step S10 in the method provided in the embodiment of the present application includes: The ambient brightness is collected by configuring an ambient brightness sensing element in the tablet computer; Acquire the display content of the tablet computer, and extract a display brightness sequence; According to the environment brightness and the display brightness sequence, a changing brightness sequence is obtained by integration.
[0020] In the embodiment of the present application, firstly, the ambient brightness sensing element configured in the tablet computer is used to monitor and collect the lighting conditions of the surrounding environment in real time. The ambient brightness sensing element is a sensor integrated inside the device, usually based on photoelectric detection technology, which can accurately sense the light intensity in the current environment. For example, the current ambient brightness detected by the photoelectric detection element is 1 lux.
[0021] Furthermore, the display content of the tablet computer, that is, the data content such as images, text or video displayed on the current screen, is collected through the processing system of the tablet computer. The light intensity, that is, the brightness, emitted by the tablet computer is different under different display contents. The light intensity emitted by the tablet computer is obtained according to the display content to obtain a display brightness sequence. Exemplarily, the brightness value can be calculated according to the color of each pixel in the display content of the tablet computer. The color of each pixel includes a combination of three color channels (red R, green G, blue B), brightness = 0.2126×R+0.7152×G+0.0722×B, the brightness of each pixel is calculated, and then the brightness mean of all pixels is calculated to obtain the display brightness at a moment. Then the display brightness at multiple moments is calculated to obtain a display brightness sequence. For example, the display brightness at a certain moment is 200.
[0022] Exemplarily, when the tablet computer control method for multiple alertness eye protection is started, for example, when the method is started after 8 o'clock in the evening, the display brightness of 100 moments evenly distributed within 10 seconds is calculated each time to obtain a display brightness sequence.
[0023] Further, according to the ambient brightness and the display brightness sequence, the total brightness felt by the user's eyes at multiple moments is integrated, that is, the brightness felt by the user's eyes. Since the display content changes randomly, the total brightness at multiple moments will change, and a change brightness sequence is obtained as multiple change brightnesses. Exemplarily, the combination of the ambient brightness and the display brightness at each moment can be directly used as the change brightness at each moment.
[0024] S20: performing pupil change analysis and change randomness analysis on the user according to the change brightness sequence, obtaining predicted pupil change parameters and predicted change randomness, and classifying and obtaining first alert information; In the embodiment of the present application, the user's pupil change analysis is performed based on the brightness change sequence. Under the brightness change sequence, the pupil size changes with the changes in the ambient brightness and the screen brightness. When the light becomes stronger, the pupil shrinks; when the light becomes weaker, the pupil expands. When the pupil expands, a larger amount of blue light enters the eye, causing greater damage to vision.
[0025] Therefore, according to the brightness change sequence, the maximum pupil size information in the user's pupil change is analyzed as a parameter for predicting pupil change, reflecting the maximum damage to the user's eyesight caused by the current brightness change sequence. In addition, according to the brightness change sequence, the randomness of the user's pupil size change caused by the brightness change is analyzed as a prediction of the randomness of the change. The greater the randomness of the user's pupil change, the more frequent the eye focus changes, and the greater the damage to the eyesight.
[0026] In this way, the predicted pupil change parameter and the predicted change randomness reflect the impact of the current environment brightness and the tablet display brightness change sequence on the eye vision. Based on the predicted pupil change parameter and the predicted change randomness, the first warning information is obtained by classification and the eye protection warning is performed. Among them, the larger the predicted pupil change parameter and the predicted change randomness, the greater the warning degree of the first warning information.
[0027] Eye protection alerts are provided through analysis of the maximum degree of pupil change under a sequence of changing brightness, as well as analysis of the randomness of pupil changes. By introducing an eye protection alert method that predicts pupil changes based on brightness, the user's eye condition can be monitored more accurately, providing effective eye protection alerts.
[0028] Step S20 in the method provided in the embodiment of the present application includes: According to the pupil size test data of the user at different brightness, a sample brightness set is collected, and pupil size information at different sample brightnesses is obtained to obtain a sample predicted pupil size information set; Using the sample brightness set and the sample predicted pupil size information set, constructing a pupil size classifier; Inputting a plurality of change brightnesses in the change brightness sequence into the pupil size classifier to obtain a predicted pupil size information sequence; Extracting the maximum pupil size information in the predicted pupil size information sequence as a predicted pupil change parameter; According to the predicted pupil size information sequence, pupil change randomness analysis is performed to obtain the predicted change randomness.
[0029] In an embodiment of the present application, based on the pupil size test data of the user at different brightnesses, such as the pupil size test data at different ambient brightnesses and tablet display brightnesses, a sample brightness set is collected, and each sample brightness includes a combination of a sample ambient brightness and a display brightness. In addition, pupil size information at different sample brightnesses is obtained as sample predicted pupil size information, specifically the diameter of the pupil, so that a sample predicted pupil size information set is obtained. Exemplarily, when the sample brightness is the sample ambient brightness and the display brightness is 1lux and 200 respectively, the sample predicted pupil size information of the corresponding user is 5mm.
[0030] Furthermore, the sample brightness set and the sample predicted pupil size information set are used as training data for a pupil size classifier, which is used to predict and analyze the user's pupil size information based on input brightness (a combination of ambient brightness and display brightness).
[0031] Exemplarily, a feedforward neural network is used, and the sample brightness set and the sample predicted pupil size information set are used as supervised training data to train and construct the pupil size classifier. Wherein, based on the feedforward neural network, the pupil size classifier is constructed, including an input layer, an output layer and a hidden layer, the input layer includes two nodes for inputting the ambient brightness and the display brightness, the output layer includes 1 node for outputting the pupil size information, and one or more hidden layers can be designed, each layer is composed of multiple neurons, and these neurons convert the brightness information into a higher-dimensional feature representation through a nonlinear activation function (such as ReLU or sigmoid). The mean square error is used as the loss function of the pupil size classifier. During each training, the sample ambient brightness and the sample display brightness within the sample brightness are passed to the pupil size classifier through the input layer, and the predicted pupil size information is output after being processed by the hidden layer and the activation function. This process is called forward propagation. Next, the error between the predicted result and the true sample predicted pupil size information is calculated using the selected loss function. Then, through backward propagation, the weight and bias of each node in the network are adjusted according to the error. Gradient descent is used to gradually optimize network parameters and reduce prediction errors. The training is completed until the error of the pupil size classifier for each set of supervised training data (each set of sample brightness and sample predicted pupil size information) is less than 5%.
[0032] Based on the trained pupil size classifier, multiple changing brightnesses in the current changing brightness sequence are respectively input into the pupil size classifier, specifically the ambient brightness and display brightness in each changing brightness are input into the pupil size classifier, and the predicted pupil size information at multiple moments is output and arranged in chronological order to obtain a predicted pupil size information sequence.
[0033] Furthermore, the maximum pupil size value is extracted from the predicted pupil size information sequence and used as the predicted pupil change parameter. This value represents the maximum dilation or contraction of the user's pupil during the entire brightness change process, and can reflect the maximum impact of lighting conditions on the user's vision.
[0034] And, according to the predicted pupil size information sequence, the randomness analysis of pupil changes is performed. The greater the randomness of pupil changes, the greater the burden of eye adaptation, which may lead to more serious visual fatigue and the greater the impact on vision. Through analysis, the randomness of predicted changes is obtained. Exemplarily, the variance of multiple predicted pupil size information in the predicted pupil size information sequence can be calculated as the randomness of predicted changes. The analysis of the randomness of predicted changes can also be performed based on other methods.
[0035] In the embodiment of the present application, according to the predicted pupil size information sequence, pupil change randomness analysis is performed to obtain the predicted change randomness, including: Extracting first pupil size information from the predicted pupil size information sequence, and randomly extracting a plurality of comparative pupil size information, calculating the mean, and obtaining average comparative pupil size information; Calculate the ratio of the difference between the first pupil size information and the average comparison pupil size information and the first pupil size information to obtain a first basic prediction change randomness; Continue to extract multiple pupil size information, calculate multiple basic prediction change randomness, and calculate the mean as the prediction change randomness.
[0036] In the embodiment of the present application, the predicted pupil size information at the first moment is extracted from the predicted pupil size information sequence as the first pupil size information. Also, multiple predicted pupil size information is randomly extracted from the predicted pupil size information sequence, for example, 10 predicted pupil size information are randomly extracted as multiple comparative pupil size information, and the mean of the multiple comparative pupil size information is calculated as the average comparative pupil size information. The average comparative pupil size information can reflect the average pupil size of the user.
[0037] Further, the difference between the first pupil size information and the average comparison pupil size information is calculated, and the ratio of the difference to the first pupil size information is calculated as the first basic prediction change randomness. If the difference between the first pupil size information and the average comparison pupil size information is larger, it means that the change degree of the first pupil size information is larger and the change is more random, then the first basic prediction change randomness is larger.
[0038] Furthermore, the second pupil size information, the third pupil size information, etc. are extracted again, and the average comparison pupil size information is randomly extracted and calculated, and the multiple basic prediction change randomness of the pupil size information predicted at all multiple moments is calculated, and the mean is calculated, which can reflect the randomness of the change of the pupil size information predicted at all multiple moments as the prediction change randomness. The greater the prediction change randomness, the greater the randomness of the current user's pupil change, and the greater the impact on vision.
[0039] By randomly extracting and calculating the average comparison of pupil size information and calculating the randomness of the change, we can obtain the change amplitude of the pupil size at different times and at other times, and then calculate the randomness of the pupil change. This can reflect the impact of the pupil size change caused by the current brightness change on the user's vision, and further perform eye protection alerts, which can improve the accuracy and reliability of eye protection alerts and improve the effect of protecting eyesight.
[0040] Step S20 in the method provided in the embodiment of the present application further includes: Calculating and obtaining a predicted vision impairment parameter according to the predicted pupil change parameter and the predicted change randomness; Collecting a sample vision impairment parameter set and obtaining a sample alertness level gradient; According to the sample alertness level gradient, the sample vision impairment parameter set is divided to obtain a plurality of sample vision impairment parameter intervals; A mapping relationship between the multiple sample vision impairment parameter intervals and sample alertness level gradients is constructed to obtain an alertness classifier, and the predicted vision impairment parameters are input and classified to obtain first alert information.
[0041] In an embodiment of the present application, the first warning information for protecting the user's eyesight under the current predicted pupil size information sequence is classified and obtained based on the predicted pupil change parameter and the predicted change randomness.
[0042] First, the predicted vision impairment parameter is calculated based on the predicted pupil change parameter and the predicted change randomness. For example, the predicted pupil change parameter and the predicted change randomness are multiplied, and the product is used as the predicted vision impairment parameter. For example, if the predicted pupil change parameter is 6mm and the predicted change randomness is 0.3, the calculated predicted vision impairment parameter is 1.8. The larger the predicted vision impairment parameter is, the greater the degree of vision impairment of the user is, and the greater the degree of vigilance required.
[0043] Furthermore, according to the monitoring data of the user using the tablet computer in the historical time, based on the above steps, a sample vision impairment parameter set is calculated. Also, a sample alert level gradient is obtained, and the sample alert level gradient includes, for example, 10 alert levels from 1 to 10. The greater the alert level, the greater the corresponding vision impairment, which is used to remind the user of the current vision impairment and remind the user to rest their eyes to protect their eyesight.
[0044] According to the 10 alert levels in the sample alert level gradient, the sample vision impairment parameter set is divided. For example, the maximum sample vision impairment parameter and the minimum sample vision impairment parameter in the sample vision impairment parameter set are obtained as the range of the sample vision impairment parameter, and then evenly divided into 10 intervals of the same length to obtain multiple sample vision impairment parameter intervals. The larger the sample vision impairment parameter interval, the greater the corresponding alert level. Furthermore, a mapping relationship between multiple sample vision impairment parameter intervals and sample alertness level gradients is constructed, for example, a mapping relationship between 10 sample vision impairment parameter intervals and 10 alertness levels is constructed, and a larger sample vision impairment parameter interval corresponds to a larger alertness level. The comparison table formed by the mapping relationship is used as an alertness classifier.
[0045] Based on the constructed alert classifier, the current predicted visual impairment parameter is input, and the first alert information is output according to the alert level corresponding to the sample visual impairment parameter interval into which the predicted visual impairment parameter falls. For example, if the first alert information is level 2, the tablet computer may display an alert message of "the current visual impairment is level 2, please pay attention" to alert the user.
[0046] The above steps can provide more accurate warnings for users' intelligent eye protection by calculating vision impairment parameters and classifying alert levels, helping users to protect their eyes more effectively and prevent vision fatigue or long-term damage.
[0047] S30: providing an eye protection reminder according to the first alert information, monitoring the eye protection operation within the preset alert time range, and when no eye protection operation is detected, collecting user images through an image acquisition element configured in the tablet computer, performing pupil change recognition and change randomness analysis, and obtaining pupil change recognition parameters and change randomness recognition; In the embodiment of the present application, the tablet computer issues an eye protection reminder according to the first warning information, for example, displays or plays a warning message "The current visual impairment is level 2, please pay attention" to alert the user. And monitors the eye protection operation within the preset warning time range to protect the user's eyesight.
[0048] Exemplarily, the preset alert time range is 20S, and the eye protection operation may be turning on the eye protection mode of the tablet computer, or locking the tablet computer, to determine whether the user has made an operation to protect eyesight.
[0049] If no eye protection operation is detected within the preset alert time range, it means that the user has not performed any eye protection behavior and needs to proceed to the next level of eye protection alert. In order to improve the accuracy of the next level of eye protection alert prompt, the image acquisition component configured in the tablet computer is used to collect user images, perform pupil change recognition and change randomness analysis, obtain pupil change recognition parameters and recognition change randomness, and perform eye protection alert.
[0050] Among them, in the process of collecting user images, collection must be carried out under the premise of user consent to protect data security.
[0051] Through the above steps, when the user ignores the initial eye protection prompt, the user's eye status can be further monitored through image means, the changes in the pupil can be accurately identified, and further eye protection warnings can be taken. This multi-level eye protection mechanism can significantly improve the accuracy and effectiveness of eye protection prompts, help users maintain healthy eye habits, and reduce the potential impact of long-term use of tablet computers on vision.
[0052] Step S30 in the method provided in the embodiment of the present application includes: Capturing a user image sequence by using an image acquisition component configured in the tablet computer; Pre-training a pupil identifier, wherein a set of sample user images and a set of sample identified pupil size information in different sample user images are collected to train the pupil identifier; Using the pupil identifier, inputting and identifying a plurality of user images in the user image sequence to obtain an identification pupil size information sequence; Extracting the largest pupil size identification information in the pupil size identification information sequence as a pupil change identification parameter; According to the pupil size identification information sequence, pupil change randomness calculation is performed to obtain the identification change randomness.
[0053] In the embodiment of the present application, the image acquisition element (usually a built-in camera) configured in the tablet computer is used to acquire user images at the next multiple moments to obtain a user image sequence. For example, user images at 100 moments within 10 seconds are acquired, and 10 frames of user images are acquired per second to obtain a user image sequence.
[0054] Furthermore, a pupil recognizer is pre-trained to identify user images to obtain user pupil size information. In order to build this pupil recognizer, it is first necessary to collect a set of sample user images with different lighting conditions, different facial angles and pupil size changes. These sample user images include the user's pupil response in a variety of usage scenarios, and can be collected through methods such as user face recognition data in historical time and used with the user's consent. At the same time, for each sample user image, the user's pupil size information is extracted and marked to obtain a sample recognition pupil size information set. The process of extracting the user's pupil size information can be done by manually extracting the mark, or by extracting the mark based on other methods. Based on these data, the pupil recognition model is trained so that it can accurately identify the user's pupil size in the user image.
[0055] Exemplarily, a convolutional neural network (CNN) is used to train the pupil identifier so that the size of the user's pupil can be efficiently and accurately identified. The sample user image set can be preprocessed, such as image cropping and scaling to make it uniform. Then, a pupil identifier is constructed based on CNN, which includes an input layer, a convolution layer, a pooling layer, a fully connected layer, and an output layer. During the training process, the sample user image is input to obtain the output pupil size information. The error between the pupil size information and the corresponding real sample is used to calculate the loss, and then random gradient descent is used to adjust network weights and other parameters to reduce the loss. In this way, multiple sets of sample data are used for iterative supervised training until the loss is less than the requirement, such as less than 5%, and the training is completed to obtain the pupil identifier.
[0056] Furthermore, multiple user images in the current user image sequence are input into the pupil identifier to perform image recognition, obtain the identified pupil size information at multiple moments, and obtain the identified pupil size information sequence.
[0057] The maximum pupil size information in the pupil size information sequence is extracted as the pupil change parameter, which reflects the maximum degree of damage to the user's vision caused by the entry of blue light due to pupil dilation.
[0058] Further, according to the sequence of pupil size information, pupil change randomness is calculated to obtain the randomness of the recognition change. The calculation of the randomness of the recognition change is the same as the calculation of the randomness of the predicted change in the aforementioned content. For example, the recognition pupil size information at the first moment among multiple moments is extracted in the sequence of pupil size information as the first pupil size information. And, multiple recognition pupil size information is randomly extracted in the sequence of pupil size information, for example, 10 recognition pupil size information are randomly extracted, the mean is calculated, and then the ratio of the difference between the first pupil size information and the mean to the first pupil size information is calculated as the first basic recognition change randomness. Then continue to extract other recognition pupil size information, and randomly extract multiple recognition pupil size information to calculate the mean, and calculate other multiple basic recognition change randomness, calculate the mean of all basic recognition change randomness, and obtain the final recognition change randomness. It reflects the randomness of pupil change in the sequence of pupil size information. The larger it is, the more random the user's pupil changes, and the greater the degree of eye fatigue.
[0059] S40: Obtain second alert information according to the pupil change parameters and the random degree of the change, and issue an eye protection alert. If no eye protection operation is detected within a preset alert time range, control the tablet computer to execute the eye protection instruction.
[0060] In an embodiment of the present application, according to the pupil change identification parameters and the randomness of the identification changes obtained based on image recognition and processing, the second warning information is classified, and a second warning eye protection prompt is performed, and the eye protection operation continues to be monitored within the preset warning time range, for example, the user's eye protection operation is monitored within 20S, such as turning on the eye protection mode or locking the tablet computer. If the eye protection operation is not detected, the tablet computer is controlled to execute the eye protection instruction, such as turning on the eye protection mode or locking the tablet computer, so as to forcibly protect the user's eyesight.
[0061] By identifying pupil change parameters and randomness of changes obtained through image recognition and processing, the second warning information is classified and a second warning eye protection reminder is given, which can improve the accuracy and reliability of the eye protection alert. Through multiple eye protection alerts, the effectiveness of the eye protection alert can be improved, and when the user does not perform eye protection operations, the eye protection instructions are executed to improve the effect of vision protection.
[0062] Step S40 in the method provided in the embodiment of the present application includes: Calculate and obtain a parameter for identifying visual impairment based on the pupil change identification parameter and the degree of randomness of the identification change; The vision impairment identification parameters are input into the alertness classifier, and the second alertness information is obtained by classification.
[0063] In an embodiment of the present application, an identification parameter for visual impairment is calculated based on the identification pupil change parameter and the identification change randomness, which is the same as the method of calculating the predicted visual impairment parameter using the predicted pupil change parameter and the predicted change randomness. For example, the identification pupil change parameter is multiplied by the identification change randomness, and the product is used as the identification parameter for visual impairment.
[0064] Furthermore, the calculated vision impairment parameter is input into the alertness classifier constructed in the aforementioned content, and the sample alertness level corresponding to the sample vision impairment parameter interval into which it falls is used as the second alert information. In this way, the second alert information is obtained by classification.
[0065] The embodiments of the present application achieve the following technical effects through the above specific implementation methods: The present invention can effectively improve the accuracy of eye protection alerts of tablet computers through one or more of the above-mentioned technical solutions. The solution collects ambient light information in real time through an ambient brightness sensing element, calculates a brightness change sequence in combination with the display content of the tablet computer, and further predicts pupil change parameters and randomness through analysis of user pupil changes and randomness of changes, thereby more accurately judging the risk of visual impairment and performing the first level of alert. In addition, the method also identifies user pupil changes through an image acquisition element to obtain more accurate alert information for a second level of alert. Its multiple eye protection prompt mechanisms ensure that users obtain more accurate eye protection guidance when using the device for a long time. Compared with traditional eye protection technologies that only rely on brightness adjustment and blue light filtering, it introduces the analysis of the impact of changes in user pupil size and the analysis of randomness of changes, accurately analyzes the degree of random changes in pupils caused by random changes in brightness, performs eye protection alerts, and effectively reduces visual fatigue and damage caused by environmental changes, brightness fluctuations, or long-term pupil dilation changes, and ultimately achieves the technical effect of improving the accuracy and reliability of alert eye protection, and further protects the user's vision health.
[0066] like Figure 2 As shown, based on the same inventive concept as the tablet computer control method for multiple alert eye protection provided in Example 1, an embodiment of the present invention provides a tablet computer control system for multiple alert eye protection, the system comprising: The variable brightness acquisition module 11 is used to collect the ambient brightness through the ambient brightness sensing element configured in the tablet computer, and calculate and obtain the variable brightness sequence in combination with the display content of the tablet computer and the ambient brightness; A first alertness analysis module 12 is used to perform pupil change analysis and change randomness analysis on the user according to the change brightness sequence, obtain predicted pupil change parameters and predicted change randomness, and classify and obtain first alert information; A first alert eye protection module 13 is used to give an alert eye protection prompt according to the first alert information, monitor the eye protection operation within a preset alert time range, and when no eye protection operation is detected, collect user images through an image acquisition element configured in the tablet computer, perform pupil change recognition and change randomness analysis, and obtain recognition pupil change parameters and recognition change randomness; The second alert eye protection module 14 is used to obtain the second alert information according to the identification of pupil change parameters and the identification of change randomness classification, and to provide an alert eye protection prompt. If no eye protection operation is detected within the preset alert time range, the tablet computer is controlled to execute the eye protection instruction.
[0067] Furthermore, the brightness change acquisition module 11 is also used for: The ambient brightness is collected by configuring an ambient brightness sensing element in the tablet computer; Acquire the display content of the tablet computer, and extract a display brightness sequence; According to the environment brightness and the display brightness sequence, a variable brightness sequence is obtained by integration.
[0068] Furthermore, the first alert analysis module 12 is also used for: According to the pupil size test data of the user at different brightness, a sample brightness set is collected, and pupil size information at different sample brightnesses is obtained to obtain a sample predicted pupil size information set; Using the sample brightness set and the sample predicted pupil size information set, constructing a pupil size classifier; Inputting a plurality of change brightnesses in the change brightness sequence into the pupil size classifier to obtain a predicted pupil size information sequence; Extracting the maximum pupil size information in the predicted pupil size information sequence as a predicted pupil change parameter; According to the predicted pupil size information sequence, pupil change randomness analysis is performed to obtain the predicted change randomness.
[0069] Wherein, performing pupil change randomness analysis according to the predicted pupil size information sequence to obtain the predicted change randomness includes: Extracting first pupil size information from the predicted pupil size information sequence, and randomly extracting a plurality of comparative pupil size information, calculating the mean, and obtaining average comparative pupil size information; Calculate the ratio of the difference between the first pupil size information and the average comparison pupil size information and the first pupil size information to obtain a first basic prediction change randomness; Continue to extract multiple pupil size information, calculate multiple basic prediction change randomness, and calculate the mean as the prediction change randomness.
[0070] Among them, the first alert information obtained by classification includes: Calculating and obtaining a predicted vision impairment parameter according to the predicted pupil change parameter and the predicted change randomness; Collecting a sample vision impairment parameter set and obtaining a sample alertness level gradient; According to the sample alertness level gradient, the sample vision impairment parameter set is divided to obtain a plurality of sample vision impairment parameter intervals; A mapping relationship between the multiple sample vision impairment parameter intervals and sample alertness level gradients is constructed to obtain an alertness classifier, and the predicted vision impairment parameters are input and classified to obtain first alert information.
[0071] Furthermore, the first alert eye protection module 13 is also used for: Capturing a user image sequence by using an image acquisition component configured in the tablet computer; Pre-training a pupil identifier, wherein a set of sample user images and a set of sample identified pupil size information in different sample user images are collected to train the pupil identifier; Using the pupil identifier, inputting and identifying a plurality of user images in the user image sequence to obtain an identification pupil size information sequence; Extracting the largest pupil size identification information in the pupil size identification information sequence as a pupil change identification parameter; According to the pupil size identification information sequence, pupil change randomness calculation is performed to obtain the identification change randomness.
[0072] Furthermore, the second alert eye protection module 14 is also used for: Calculate and obtain a parameter for identifying visual impairment based on the pupil change identification parameter and the degree of randomness of the identification change; The vision impairment identification parameters are input into the alertness classifier, and the second alertness information is obtained by classification.
[0073] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 100, including a memory 110, a processor 120, and a computer program 111 stored in the memory 110 and executable on the processor 120. When the processor 120 executes the computer program 111, the steps of the method in Example 1 are implemented.
[0074] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4As shown, this embodiment provides a computer-readable storage medium 200 on which a computer program 111 is stored. When the computer program 111 is executed by a processor, the steps of the method in Embodiment 1 are implemented.
[0075] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0076] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0077] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0078] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0080] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0081] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A tablet computer control method for multiple alert eye protection, characterized in that: The method comprises: The ambient brightness is collected by an ambient brightness sensing element configured in the tablet computer, and a brightness variation sequence is calculated based on the display content of the tablet computer and the ambient brightness; According to the brightness change sequence, a pupil change analysis and a change randomness analysis of the user are performed to obtain a predicted pupil change parameter and a predicted change randomness, and the first alert information is obtained by classification; Prompting an eye protection alert according to the first alert information, monitoring the eye protection operation within a preset alert time range, and when no eye protection operation is detected, collecting user images through an image acquisition element configured in the tablet computer, performing pupil change recognition and change randomness analysis, and obtaining pupil change recognition parameters and change randomness recognition; The second alert information is obtained according to the identification of pupil change parameters and the identification of change randomness classification, and an alert eye protection prompt is given. If no eye protection operation is detected within the preset alert time range, the tablet computer is controlled to execute the eye protection instruction.
2. The tablet computer control method for multiple alert eye protection according to claim 1, characterized in that: The ambient brightness sensing element configured in the tablet computer collects the ambient brightness, and combines the display content of the tablet computer and the ambient brightness to calculate and obtain a brightness change sequence, including: The ambient brightness is collected by configuring an ambient brightness sensing element in the tablet computer; Acquire the display content of the tablet computer, and extract a display brightness sequence; According to the environment brightness and the display brightness sequence, a variable brightness sequence is obtained by integration.
3. The tablet computer control method for multiple alert eye protection according to claim 1, characterized in that: According to the change brightness sequence, the user's pupil change analysis and change randomness analysis are performed to obtain predicted pupil change parameters and predicted change randomness, including: According to the pupil size test data of the user at different brightness, a sample brightness set is collected, and pupil size information at different sample brightnesses is obtained to obtain a sample predicted pupil size information set; Using the sample brightness set and the sample predicted pupil size information set, constructing a pupil size classifier; Inputting a plurality of change brightnesses in the change brightness sequence into the pupil size classifier to obtain a predicted pupil size information sequence; Extracting the maximum pupil size information in the predicted pupil size information sequence as a predicted pupil change parameter; According to the predicted pupil size information sequence, pupil change randomness analysis is performed to obtain the predicted change randomness.
4. The tablet computer control method for multiple alert eye protection according to claim 3, characterized in that: According to the predicted pupil size information sequence, pupil change randomness analysis is performed to obtain the predicted change randomness, including: Extracting first pupil size information from the predicted pupil size information sequence, and randomly extracting a plurality of comparative pupil size information, calculating the mean, and obtaining average comparative pupil size information; Calculate the ratio of the difference between the first pupil size information and the average comparison pupil size information and the first pupil size information to obtain a first basic prediction change randomness; Continue to extract multiple pupil size information, calculate multiple basic prediction change randomness, and calculate the mean as the prediction change randomness.
5. The tablet computer control method for multiple alert eye protection according to claim 3, characterized in that: Get first alert information by category, including: Calculating and obtaining a predicted vision impairment parameter according to the predicted pupil change parameter and the predicted change randomness; Collecting a sample vision impairment parameter set and obtaining a sample alertness level gradient; According to the sample alertness level gradient, the sample vision impairment parameter set is divided to obtain a plurality of sample vision impairment parameter intervals; A mapping relationship between the multiple sample vision impairment parameter intervals and sample alertness level gradients is constructed to obtain an alertness classifier, and the predicted vision impairment parameters are input and classified to obtain first alert information.
6. The tablet computer control method for multiple alert eye protection according to claim 1, characterized in that: The image acquisition element configured in the tablet computer is used to collect user images, perform pupil change recognition and change randomness analysis, and obtain pupil change recognition parameters and change randomness, including: Capturing a user image sequence by using an image acquisition component configured in the tablet computer; Pre-training a pupil identifier, wherein a set of sample user images and a set of sample identified pupil size information in different sample user images are collected to train the pupil identifier; Using the pupil identifier, inputting and identifying a plurality of user images in the user image sequence to obtain an identification pupil size information sequence; Extracting the largest pupil size identification information in the pupil size identification information sequence as a pupil change identification parameter; According to the pupil size identification information sequence, pupil change randomness calculation is performed to obtain the identification change randomness.
7. The tablet computer control method for multiple alert eye protection according to claim 5, characterized in that: Obtaining second alert information according to the pupil change identification parameter and the change randomness classification includes: Calculate and obtain a parameter for identifying visual impairment based on the pupil change identification parameter and the degree of randomness of the identification change; The vision impairment identification parameters are input into the alertness classifier, and the second alertness information is obtained by classification.
8. A tablet computer control system for multiple alert eye protection, characterized in that: The system comprises: A variable brightness acquisition module is used to collect the ambient brightness through an ambient brightness sensing element configured in the tablet computer, and calculate and obtain a variable brightness sequence in combination with the display content of the tablet computer and the ambient brightness; A first alertness analysis module is used to perform pupil change analysis and change randomness analysis on the user according to the change brightness sequence, obtain predicted pupil change parameters and predicted change randomness, and classify and obtain first alert information; a first alert eye protection module, configured to provide an alert eye protection prompt according to the first alert information, monitor the eye protection operation within a preset alert time range, and when no eye protection operation is detected, collect user images through an image acquisition element configured in the tablet computer, perform pupil change recognition and change randomness analysis, and obtain pupil change recognition parameters and change randomness; The second alert eye protection module is used to obtain the second alert information according to the identification pupil change parameters and the identification change randomness classification, and to provide an alert eye protection prompt. If no eye protection operation is detected within the preset alert time range, the tablet computer is controlled to execute the eye protection instruction.
9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the tablet computer control method for multiple alert eye protection as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements the tablet computer control method for multiple alert eye protection as described in any one of claims 1 to 7.