Welding machine screen display brightness control method and system

Abstract

The invention relates to the technical field of brightness control, in particular to a welding machine screen display brightness control method and system. The method comprises the following steps: acquiring a welding machine screen image, environment perception data and a user face image; performing illumination intensity calculation on the environment perception data to generate environment illumination intensity data; performing glare analysis on the environment perception data through the environment illumination intensity data to generate environment glare influence data; performing environment perception brightness adjustment on the welding machine screen image based on the environment glare influence data to generate environment perception brightness adjustment data; performing visual perception feature analysis on the user face image based on the environmental perception brightness adjustment data to generate user visual perception feature data; and performing eyeball tracking on the user face image by using a computer vision technology to generate user eyeball tracking data. According to the invention, efficient and accurate brightness control is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of brightness control, and particularly to a method and system for controlling the display brightness of a welding machine screen. Background Art

[0002] In the application of welding machines, the control of the display brightness of the screen is an important technology, which has a direct impact on the visual comfort and work efficiency of welding operators. Traditional methods for controlling the display brightness of welding machine screens mainly rely on manual adjustment or fixed brightness settings, which can lead to the brightness not adapting to environmental changes and causing visual fatigue for operators. There are problems of low efficiency and inaccuracy in brightness control. With the improvement of industrial automation and intelligence levels, an intelligent method and system for controlling the display brightness of welding machine screens are needed to meet the requirements of precise control and adaptive adjustment of display brightness in modern welding machine applications. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention proposes a method and system for controlling the display brightness of a welding machine screen to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a method for controlling the display brightness of a welding machine screen, including the following steps:

[0005] Step S1: Obtain the welding machine screen image, environmental perception data, and user face image; calculate the light intensity of the environmental perception data to generate environmental light intensity data; perform glare analysis on the environmental perception data through the environmental light intensity data to generate environmental glare impact data;

[0006] Step S2: Perform environmental perception brightness adjustment on the welding machine screen image based on the environmental glare impact data to generate environmental perception brightness adjustment data; perform visual perception feature analysis on the user face image based on the environmental perception brightness adjustment data to generate user visual perception feature data;

[0007] Step S3: Use computer vision technology to perform eye tracking on the user face image to generate user eye tracking data; calculate the blink frequency of the user eye tracking data to generate blink frequency data; perform pupil constriction analysis on the user eye tracking data based on the blink frequency data to generate pupil deformation data;

[0008] Step S4: Perform pupil deformation - brightness correlation analysis on the user visual perception feature data based on the pupil deformation data to construct a pupil deformation - brightness response curve; perform adaptive brightness adjustment processing on the environmental perception brightness adjustment data using a brightness - visual response model to generate visual perception brightness adjustment data; calculate the visual fatigue of the user face image based on the blink frequency data and the pupil deformation data to generate a user visual fatigue index;

[0009] Step S5: Identify the eye fixation points from the user's eye tracking data to generate the eye fixation point position data; perform fixation frequency analysis on the welder screen image based on the eye fixation point position data to generate the user fixation frequency data; perform fixation area segmentation on the welder screen image based on the eye fixation point position data and the user fixation frequency data to generate the user fixation area segmented image;

[0010] Step S6: Conduct regional brightness dynamic adjustment analysis on the user fixation area segmented image according to the user visual fatigue index to generate the regional brightness dynamic adjustment data; optimize the vision of the welder screen image using the regional brightness dynamic adjustment data to generate the vision optimization dynamic brightness adjustment data; perform brightness control decision-making analysis using the vision optimization dynamic brightness adjustment data and the visual perception brightness adjustment data, and construct a brightness control decision engine to execute the brightness control operation.

[0011] The present invention uses environmental perception data and user facial images: By acquiring the welding machine screen image, the system can obtain the content displayed on the screen. At the same time, acquiring environmental perception data includes information such as environmental light intensity for analyzing the lighting conditions. Acquiring the user facial image can be used for subsequent eye tracking and visual fatigue calculation. By calculating the light intensity in the environmental perception data, the system can understand the brightness level of the current environment, providing a benchmark for subsequent brightness adjustment. Through comprehensive analysis of the environmental perception data and light intensity data, the system can evaluate the glare situation in the environment, that is, the degree of interference of light reflection or strong flashes on vision. According to the environmental glare impact data, the system can dynamically adjust the brightness of the welding machine screen to offset the impact of environmental glare and ensure that the content on the screen is clearly visible. By analyzing the welding machine screen image after environmental perception brightness adjustment for the user facial image, the system can understand the user's perception characteristics of the screen brightness, such as brightness and contrast. Through computer vision technology, the system can perform eye tracking on the user facial image, that is, real-time monitor and record the movement trajectory and fixation point position of the user's eyes. Based on the eye tracking data, the system can calculate the frequency of the user's blinking to evaluate the user's visual attention and fatigue level. By analyzing the eye tracking data, the system can detect and quantify the degree of pupil constriction in different fixation regions to provide more detailed visual fatigue indicators. Pupil deformation-brightness correlation analysis: Based on the pupil deformation data and user visual perception characteristic data, the system can establish a correlation model between pupil deformation and brightness to understand the impact of pupil deformation on visual perception. Using the pupil deformation-brightness correlation model and the brightness-visual response model, the system can automatically adjust the brightness of the welding machine screen to adapt to the user's visual needs and environmental changes, providing the best visual experience. By analyzing the user's eye tracking data, the system can identify and determine the fixation point position of the user's eyes. It can accurately capture the user's fixation point on the welding machine screen, that is, the position where the user focuses attention during welding machine operation. Using the eye fixation point position data, the system can calculate the number and frequency of the user's continuous fixation points on the welding machine screen, that is, the user's behavior pattern of looking at the welding machine screen. Analyze and evaluate the user's attention level and work efficiency on the content of the welding machine screen. According to the eye fixation point position data and user fixation frequency data, the system can perform fixation region segmentation on the welding machine screen image, divide the welding machine screen into different regions, and generate corresponding user fixation region segmentation images. According to the user's visual fatigue index, the system performs regional brightness dynamic adjustment analysis on the user fixation region segmentation image.By analyzing the fatigue level of the user's gaze area, the system can determine which areas need to adjust the brightness to reduce the user's visual fatigue. Based on the user's gaze area and visual fatigue situation, it generates the optimal brightness adjustment data for each area to optimize the visual effects of different areas on the welding machine screen, provides automated brightness control, ensures that the content on the welding machine screen is clearly visible in different areas, reduces the user's eye burden, and improves work efficiency and comfort.

[0012] Preferably, step S1 includes the following steps:

[0013] Step S11: Obtain the welding machine screen image, environmental perception data, and user face image;

[0014] Step S12: Perform optical path tracing on the environmental perception data to generate optical path tracing data;

[0015] Step S13: Analyze the environmental light distribution of the environmental perception data according to the optical path tracing data to generate environmental light distribution data;

[0016] Step S14: Calculate the illumination intensity of the environmental light distribution data to generate environmental illumination intensity data;

[0017] Step S15: Perform wavelength chromatic aberration analysis on the environmental illumination intensity data to generate illumination wavelength chromatic aberration data;

[0018] Step S16: Perform glare analysis on the environmental perception data through the illumination wavelength chromatic aberration data to generate environmental glare impact data.

[0019] The present invention obtains data related to the brightness control of the welding machine screen. The welding machine screen image provides the display content on the current screen, the environmental perception data provides information about the surrounding environment, and the user face image can be used to analyze the user's visual perception and comfort, providing information about the propagation path of light in the environment. By performing optical path tracing on the environmental perception data, the processes of light reflection, refraction, scattering, etc. in the environment can be simulated, so as to more accurately understand the light distribution on the welding machine screen. By analyzing the optical path tracing data, the environmental light distribution around the welding machine screen can be understood, including information such as the intensity, direction, and scattering of light. By calculating the environmental light distribution data, the environmental illumination intensity received by the welding machine screen can be determined, that is, the light energy density in the environment, which is very important for subsequent brightness control. By performing wavelength chromatic aberration analysis on the environmental illumination intensity data, the intensity distribution of light of different wavelengths can be determined. By analyzing the illumination wavelength chromatic aberration data, the glare situation on the welding machine screen can be evaluated, including the degree of interference of light intensity, reflection, refraction, etc. on the user's vision. This helps to determine an appropriate screen brightness control strategy to reduce the adverse effects of glare on the user experience.

[0020] Preferably, the specific steps of step S2 are as follows:

[0021] Step S21: Compare the environmental glare impact data based on a preset environmental glare threshold index. When the preset environmental glare threshold index is less than the environmental glare impact data, perform a brightness increase process on the welder screen image to generate environmental perception brightness adjustment data;

[0022] Step S22: When the preset environmental glare threshold index is greater than the environmental glare impact data, perform a brightness decrease process on the welder screen image to generate environmental perception brightness adjustment data;

[0023] Step S23: Detect the line-of-sight deviation of the user's facial image to generate line-of-sight deviation data;

[0024] Step S24: Perform a visual perception feature analysis on the line-of-sight deviation data based on the environmental perception brightness adjustment data to generate user visual perception feature data.

[0025] The present invention evaluates the environmental glare impact data according to a preset environmental glare threshold index. If the environmental glare impact data exceeds the preset threshold index, it indicates that the glare in the environment is strong. At this time, a brightness increase process needs to be performed on the welder screen image. By increasing the screen brightness, the impact of glare can be offset, improving the visibility and recognition of the content displayed on the screen for the welder operator. Evaluate the environmental glare impact data according to a preset environmental glare threshold index. If the environmental glare impact data is lower than the preset threshold index, it indicates that the glare in the environment is weak. At this time, a brightness decrease process can be performed on the welder screen image. By reducing the screen brightness, the reflection and glare of the screen can be reduced, improving the visibility and recognition of the content displayed on the screen for the welder operator. By analyzing the user's facial image, the line-of-sight direction and position of the welder operator can be determined. The line-of-sight deviation data can be used for subsequent brightness adjustment and user visual perception feature analysis. By performing a correlation analysis on the environmental perception brightness adjustment data and the line-of-sight deviation data, the visual perception features of the welder operator under different brightness conditions can be understood. This includes information such as the visibility of the welder screen and the degree of concentration on the welding process. By analyzing these features, the welder screen brightness control strategy can be further optimized to provide a better user experience and working effect.

[0026] Preferably, the specific steps of step S3 are as follows:

[0027] Step S31: Use computer vision technology to perform eye positioning on the user's facial image to generate user eye positioning point data;

[0028] Step S32: Perform continuous inter-frame phase matching on the user's facial image based on the user's eye positioning point data to generate eye inter-frame matching data;

[0029] Step S33: Reconstruct the viewing point movement trajectory for the eye inter-frame matching data to generate an eye movement trajectory curve;

[0030] Step S34: Perform eye tracking on the user's facial image according to the eye movement trajectory curve to generate user eye tracking data;

[0031] Step S35: Calculate the blink frequency for the user's eye tracking data to generate blink frequency data;

[0032] Step S36: Perform pupil constriction analysis on the user's eye tracking data based on the blink frequency data to generate pupil deformation data.

[0033] The present invention accurately detects and locates the eye position of the welder operator through computer vision technology. By using the feature points or feature regions in the facial image, the position and direction of the eyes in the image can be determined. The eye positioning point data provides information about the fixation point of the welder operator, which helps with subsequent eye tracking and welder screen brightness control. The continuous inter-frame phase matching technology is used to analyze the movement of the user's eyes between different frames. By comparing the changes in the eye positioning points in consecutive frames, the movement direction and speed of the eyes can be determined. The eye inter-frame matching data provides information about the dynamic changes in the user's fixation point, which helps with subsequent eye movement trajectory reconstruction and eye tracking. The movement trajectory of the user's eyes is reconstructed based on the eye inter-frame matching data. Through the matching data between consecutive frames, the movement path of the welder operator's fixation point can be inferred. The eye movement trajectory curve provides the trajectory information of the user's fixation point, which helps with subsequent eye tracking and welder screen brightness control. The eyes of the welder operator are tracked according to the eye movement trajectory curve. By associating the eye movement trajectory with the facial image, the fixation point of the welder operator can be tracked in real time. The user eye tracking data provides information about the eye position and gaze direction of the welder operator, which helps with subsequent blink frequency calculation and pupil deformation analysis. The blink frequency of the welder operator is calculated by analyzing the user's eye tracking data. By detecting the change in the opening and closing state of the eyes, the number of blinks and the blink frequency of the welder operator can be determined. The blink frequency data provides an indicator of the welder operator's attention and visual fatigue level, which helps with subsequent pupil deformation analysis and welder screen brightness control. The pupil constriction of the welder operator is analyzed according to the blink frequency data. By detecting the changes in the pupil during blinking, the attention and concentration level of the welder operator can be inferred. The pupil deformation data provides an indicator of the welder operator's attention and visual fatigue level, which helps to further optimize the welder screen brightness control strategy to provide a better user experience and working effect.

[0034] Preferably, the specific steps of step S36 are as follows:

[0035] Step S361: Perform an analysis of the light intensity response on the user's eye tracking data based on the blink frequency data to generate eye light intensity response data;

[0036] Step S362: Perform an analysis of the pupil contraction rate on the user's eye tracking data according to the eye light intensity response data to generate pupil contraction rate data;

[0037] Step S363: Perform an analysis of the contraction time on the pupil contraction rate data to generate pupil contraction time data;

[0038] Step S364: Perform a dynamic contraction change analysis on the user's eye tracking data based on the pupil contraction time data to generate pupil dynamic contraction data;

[0039] Step S365: Calculate the contraction amplitude of the pupil dynamic contraction data to generate pupil deformation data.

[0040] The present invention infers the light intensity response of the eyeball by analyzing the correlation between the blink frequency data and the eye tracking data of the welder operator. By observing the light intensity change of the eyeball during blinking, the reaction of the welder operator to light when blinking can be determined. The eyeball light intensity response data provides the relationship between the blink of the welder operator and visual attention, which is helpful for subsequent pupil contraction rate analysis and welder screen brightness control. Analyze the pupil contraction rate of the welder operator based on the eyeball light intensity response data. By observing the size change of the pupil under the change of eyeball light intensity, the pupil contraction rate of the welder operator can be calculated. The pupil contraction rate data provides the sensitivity of the welder operator to light change, which is helpful for subsequent pupil contraction time analysis and welder screen brightness control. Calculate the pupil contraction time of the welder operator by analyzing the pupil contraction rate data. By observing the time required for the pupil to change from the initial state to the maximum contraction state, the response speed of the welder operator to light change can be determined. The pupil contraction time data provides the adaptability and adjustment ability of the welder operator to light change, which is helpful for subsequent analysis of pupil dynamic contraction data and welder screen brightness control. Analyze the dynamic contraction change in the eye tracking data of the welder operator according to the pupil contraction time data. By observing the contraction process of the pupil at different fixation points, the attention and visual sensitivity of the welder operator to different regions can be inferred. The pupil dynamic contraction data provides the attention degree and visual attention distribution of the welder operator to different regions, which is helpful for subsequent calculation of pupil deformation data and welder screen brightness control. Calculate the degree of pupil deformation in the eye tracking data of the welder operator according to the pupil dynamic contraction data. By measuring the contraction amplitude of the pupil at different fixation points, the interest degree and visual attention distribution of the welder operator to different regions can be determined. The pupil deformation data provides a quantitative index for the visual sensitivity and attention distribution of the welder operator to different regions, which is helpful for precisely controlling the welder screen brightness to provide the best visual experience and operating environment.

[0041] Preferably, the specific steps of step S4 are as follows:

[0042] Step S41: Perform pupil deformation-brightness correlation analysis on the user's visual perception feature data based on the pupil deformation data to generate pupil deformation-brightness response data;

[0043] Step S42: Fit the correlation curve of the pupil deformation-brightness response data to construct a pupil deformation-brightness response curve;

[0044] Step S43: Perform adaptive brightness adjustment processing on the environmental perception brightness adjustment data using a brightness-visual response model to generate visual perception brightness adjustment data;

[0045] Step S44: Perform blink interval difference analysis on the user's facial image according to the blink frequency data to generate blink interval difference data;

[0046] Step S45: Analyze the contraction efficiency of the pupil deformation data to generate user pupil contraction sensitivity data;

[0047] Step S46: Use the user visual fatigue calculation formula to calculate the visual fatigue of the user pupil contraction sensitivity data based on the blink interval difference data, and generate a user visual fatigue index.

[0048] Through observing the degree of pupil deformation and its changes under different brightness conditions, the present invention can establish a correlation model between pupil deformation and brightness. The pupil deformation - brightness response data provides the visual perception characteristics of the welding machine operator under different brightness conditions, which helps with subsequent brightness adjustment control. By performing curve fitting on the pupil deformation - brightness response data, a correlation curve between pupil deformation and brightness is established. Through the fitting curve, the relationship between pupil deformation and brightness can be more accurately described, and a mathematical model for brightness adjustment can be provided. The pupil deformation - brightness response curve provides a basis and reference for subsequent brightness adjustment. According to the visual perception characteristics of the welding machine operator and the pupil deformation - brightness response curve, the brightness can be adjusted accordingly according to the brightness of the current environment. The visual perception brightness adjustment data provides information for automatically adjusting the brightness of the welding machine screen according to the visual perception characteristics of the welding machine operator. Based on the blink frequency data of the welding machine operator, the difference in blink intervals in the user's facial image is analyzed. By observing the change in the time interval of the welding machine operator's blinks, the degree of visual fatigue and attention level of the welding machine operator can be inferred. The blink interval difference data provides a quantitative index of the visual fatigue state of the welding machine operator, which helps with subsequent visual fatigue calculation and brightness adjustment control. By measuring the degree of deformation of the pupil from the initial state to the maximum contraction state, the sensitivity of the welding machine operator to light changes can be evaluated. The pupil contraction sensitivity data provides information on the welding machine operator's ability to perceive light changes and adaptive brightness adjustment. According to the blink interval difference data and the visual fatigue calculation formula, the visual fatigue of the user's pupil contraction sensitivity data is calculated. By analyzing the change in the blink interval of the welding machine operator and combining the pupil contraction sensitivity data, the degree of visual fatigue of the welding machine operator can be evaluated. The user visual fatigue index provides a quantitative assessment of the degree of visual fatigue of the welding machine operator, which helps identify potential fatigue risks and take corresponding measures.

[0049] Preferably, the user visual fatigue calculation formula in step S46 is specifically:

[0050]

[0051] Among them, V is the user's visual fatigue index, T is the user's device usage time, t is the screen resolution, D is the complexity of the viewing point movement trajectory, L is the screen illumination intensity, I is the user's blink frequency, F is the pupil constriction efficiency, C is the user's pupil deformation response rate, A is the user's pupil constriction amplitude, P is the viewing point movement speed, H is the difference value of the pupil sizes of the left and right eyes, R is the pupil size change rate, and S is the number of head movements.

[0052] The present invention passes through It represents the ratio of the user's device usage time to the screen resolution divided by the complexity of the viewing point movement trajectory. This ratio can reflect the degree to which the user browses and observes the information on the screen within a specific time. A higher ratio means that the user uses the device more attentively, considering the user's attention level. It represents the ratio between the natural logarithm of the screen illumination intensity and the natural logarithm of the user's blink frequency. This ratio can measure the degree to which the screen brightness affects the user's blink frequency. A higher ratio means that the screen brightness has a greater impact on the user's blink frequency. It represents the limit value of the pupil constriction efficiency. The pupil constriction efficiency reflects the pupil's ability to adjust to light. The limit value represents the maximum constriction ability of the pupil under absolute illumination conditions, which is the product of the user's pupil constriction amplitude and the viewing point movement speed. Both the pupil constriction amplitude and the viewing point movement speed are related to the change in the user's attention. A larger value means that the pupil constriction amplitude is larger when the user moves the viewing point. It represents the cube root of the difference value of the pupil sizes of the left and right eyes and the pupil size change rate. The difference value of the pupil sizes of the left and right eyes and the pupil size change rate reflect the user's eye's ability to adapt to light and adjust. Both the number of head movements and the viewing point movement distance are related to the user's way of browsing the screen information. A higher ratio means that the user frequently moves the head to observe the information on the screen. The formula comprehensively considers the user's attention level, the impact of screen brightness on eye fatigue, pupil adjustment ability, attention change, eye adaptation ability, and head movement situation through multiple parameters and calculation steps to help evaluate the user's visual fatigue degree during device use.

[0053] Preferably, the specific steps of step S5 are as follows:

[0054] Step S51: Perform visual focus convergence processing on the user's eye tracking data to generate visual focus area data;

[0055] Step S52: Identify the eye fixation points for the visual focus area data to generate eye fixation point position data;

[0056] Step S53: Perform fixation frequency analysis on the welder screen image through the eye fixation point position data to generate user fixation frequency data;

[0057] Step S54: Construct a fixation heat map for the eye fixation point position data based on the user's fixation frequency data to construct an eye fixation heat map.

[0058] Step S55: Divide the welding machine screen image into fixation regions based on the eye fixation heat map to generate a user fixation region segmented image.

[0059] The present invention can determine the region where the visual focus of the welding machine operator is located on the welding machine screen by analyzing the eye movement trajectory and fixation points of the welding machine operator. The visual focus region data provides the main attention regions of the welding machine operator on the screen, which helps with subsequent fixation analysis and brightness control. By analyzing the fixation points of the welding machine operator within the focus region, the fixation position of the operator's eyes on the welding machine screen can be determined. The eye fixation point position data provides the specific fixation positions of the welding machine operator on the screen, which helps with subsequent fixation frequency analysis and fixation region segmentation. By counting the number of fixation points and the time in different regions of the welding machine operator, the fixation frequency of the welding machine screen can be calculated, that is, the degree of concentrated attention of the welding machine operator in different regions. The user fixation frequency data provides the attention distribution of the welding machine operator in different regions, which helps with subsequent fixation heat map construction and fixation region segmentation. By visualizing the distribution of fixation points as a heat map, the main fixation regions and hotspots of the welding machine operator on the welding machine screen can be intuitively displayed. The eye fixation heat map provides visual information on the attention distribution of the welding machine operator on the screen, which helps to understand the visual attention pattern of the welding machine operator. According to the distribution of fixation points of the welding machine operator within the focus region, the welding machine screen image can be divided into different region blocks, and each region block represents the fixation region of the welding machine operator. The user fixation region segmented image provides a visual representation of the visual attention region of the welding machine operator on the welding machine screen, which helps with subsequent brightness control and display optimization. By visual focus convergence processing, eye fixation point recognition, and fixation frequency analysis, the fixation region and attention distribution of the welding machine operator can be determined. By constructing the fixation heat map and the fixation region segmented image, the visual attention pattern and fixation region of the welding machine operator can be intuitively displayed. This information can be used to optimize the brightness control of the welding machine screen to ensure sufficient visibility and a comfortable visual experience for the welding machine operator in key regions.

[0060] Preferably, the specific steps of step S6 are as follows:

[0061] Step S61: Segment the non-fixation regions of the welding machine screen image based on the user fixation region segmented image to generate a fixation region image and a non-fixation region image.

[0062] Step S62: Compare the user's visual fatigue index based on a preset user visual fatigue threshold index. When the preset user visual fatigue threshold index is less than or equal to the user's visual fatigue index, perform region brightness enhancement processing on the fixation area image to generate fixation area brightness adjustment data;

[0063] Step S63: Perform region brightness reduction processing on the non-fixation area image to generate non-fixation area brightness adjustment data;

[0064] Step S64: Perform region brightness dynamic adjustment analysis on the fixation area brightness adjustment data and the non-fixation area brightness adjustment data according to the user's visual fatigue index to generate region brightness dynamic adjustment data;

[0065] Step S65: Use the region brightness dynamic adjustment data to perform color temperature optimization analysis on the welder screen image to generate color temperature optimization data;

[0066] Step S66: Use the color temperature optimization data to perform visual optimization on the region brightness dynamic adjustment data to generate visually optimized dynamic brightness adjustment data;

[0067] Step S67: Perform brightness control decision analysis using the visually optimized dynamic brightness adjustment data and the visually perceived brightness adjustment data, and construct a brightness control decision engine to execute the brightness control operation.

[0068] By separating the gaze area and non-gaze area of the welder operator in the welder screen image, the present invention can extract the areas that the welder operator mainly focuses on and other unimportant areas, providing a basis for subsequent brightness control and visual optimization. Based on the user's visual fatigue index, it is judged whether the degree of the user's visual fatigue exceeds a preset threshold. If the user's visual fatigue index exceeds or equals the threshold, it indicates that the user may be fatigued and brightness adjustment is required to reduce the visual burden. Therefore, the brightness of the gaze area image is increased to make the area on the welder screen that the user gazes at brighter, so as to improve visibility and slow down visual fatigue. Since the attention of the welder operator is mainly concentrated on the gaze area, the brightness of the non-gaze area can be correspondingly reduced to reduce energy consumption and interference. By reducing the brightness of the non-gaze area, the power consumption and visual comfort of the welder screen can be optimized. Based on the user's visual fatigue index, dynamic adjustment analysis is performed on the brightness adjustment data of the gaze area and the brightness adjustment data of the non-gaze area. According to the degree of the user's visual fatigue, the brightness adjustment degree of the gaze area and the non-gaze area is adjusted to achieve dynamic brightness adjustment of the welder screen. By dynamically adjusting the brightness, a more suitable display effect can be provided according to the degree of the user's fatigue, improving the visual comfort and work efficiency of the welder operator. By adjusting the color temperature of the welder screen according to the brightness adjustment degree of different areas, a more suitable color performance for the welder operator can be provided. The optimization of the color temperature can improve the color reproduction ability and visual comfort of the image, enhancing the welder operator's ability to observe and judge the weld seam and the welding process. By combining color temperature adjustment and area brightness adjustment, the visual effect of the welder screen image can be further optimized, enabling the welder operator to observe the weld seam and the welding process more clearly. The visual optimization dynamic brightness adjustment data provides more refined and personalized brightness adjustment to meet the needs of different welding environments and welder operators. Using the visual optimization dynamic brightness adjustment data and the visual perception brightness adjustment data for brightness control decision analysis, and constructing a brightness control decision engine. According to these data, the system can automatically adjust the brightness of the welder screen according to the real-time welder operation environment and the needs of the welder operator. The brightness control decision engine can achieve intelligent brightness control according to different input parameters and algorithms to provide the best visual experience and working environment.

[0069] In this specification, a welder screen display brightness control system is also provided for executing the welder screen display brightness control method as described above, including:

[0070] An ambient light module, configured to obtain a welder screen image, ambient perception data, and a user's facial image; calculate the light intensity of the ambient perception data to generate ambient light intensity data; perform glare analysis on the ambient perception data through the ambient light intensity data to generate ambient glare impact data;

[0071] A visual perception module, which is used to perform ambient perception brightness adjustment on the welder screen image based on the ambient glare impact data to generate ambient perception brightness adjustment data; perform visual perception feature analysis on the user's facial image based on the ambient perception brightness adjustment data to generate user visual perception feature data;

[0072] A pupil deformation module, which is used to perform eye tracking on the user's facial image using computer vision technology to generate user eye tracking data; calculate the blink frequency of the user's eye tracking data to generate blink frequency data; perform pupil constriction analysis on the user's eye tracking data based on the blink frequency data to generate pupil deformation data;

[0073] A visual fatigue module, which is used to perform pupil deformation - brightness correlation analysis on the user's visual perception feature data based on the pupil deformation data to construct a pupil deformation - brightness response curve; perform adaptive brightness adjustment processing on the ambient perception brightness adjustment data using a brightness - visual response model to generate visually perceived brightness adjustment data; calculate the visual fatigue of the user's facial image based on the blink frequency data and the pupil deformation data to generate a user visual fatigue index;

[0074] A fixation area segmentation module, which is used to identify the eye fixation points of the user's eye tracking data to generate eye fixation point position data; perform fixation frequency analysis on the welder screen image through the eye fixation point position data to generate user fixation frequency data; segment the welder screen image into fixation areas through the eye fixation point position data and the user fixation frequency data to generate a user fixation area segmented image;

[0075] A regional brightness dynamic adjustment module, which is used to perform regional brightness dynamic adjustment analysis on the user's fixation area segmented image according to the user visual fatigue index to generate regional brightness dynamic adjustment data; perform visual optimization on the welder screen image using the regional brightness dynamic adjustment data to generate visually optimized dynamic brightness adjustment data; perform brightness control decision - making analysis using the visually optimized dynamic brightness adjustment data and the visually perceived brightness adjustment data to construct a brightness control decision - making engine to execute brightness control operations.

[0076] The present invention obtains the welding machine screen image, environmental perception data, and user facial image: By obtaining this data, the system can understand the current environmental conditions and user status. By calculating the light intensity of the environmental perception data, the system can obtain the light intensity information of the current environment. By performing glare analysis on the environmental perception data using the light intensity data, the system can understand the glare situation in the environment. According to the environmental glare impact data, the environmental perception brightness of the welding machine screen image is adjusted to improve the visibility and comfort of the screen in the case of glare. By performing visual perception feature analysis on the user facial image based on the environmental perception brightness adjustment data, the system can understand the visual perception characteristics of the user under different lighting conditions. Using computer vision technology to perform eye tracking on the user facial image, the system can obtain the position and movement information of the user's eyes. By analyzing the eye tracking data, the system can calculate the user's blink frequency, which is an indicator for evaluating the degree of user visual fatigue. Based on the blink frequency data, the system can further analyze the pupil constriction situation in the user's eye tracking data to understand the user's attention and fatigue level. By performing correlation analysis on the user's visual perception feature data and pupil deformation data, the system can construct a pupil deformation-brightness response curve to help understand the pupil deformation situation of the user under different brightness conditions. According to the brightness-visual response model and the environmental perception brightness adjustment data, the system can perform adaptive brightness adjustment processing to provide a screen brightness suitable for the user's current visual state. According to the blink frequency data and pupil deformation data, the system can calculate the user's visual fatigue index, which is used to evaluate the degree of user fatigue and attention level. By processing the user's eye tracking data, the system can identify the position of the eye fixation point to understand the area of interest of the user on the welding machine screen. By performing fixation frequency analysis on the welding machine screen image using the eye fixation point position data, the system can understand the fixation frequency of the user in different areas, which helps to understand the focus points on the welding machine screen. According to the eye fixation point position data and the user fixation frequency data, the system can perform fixation area segmentation on the welding machine screen image, dividing the welding machine screen into different areas for subsequent dynamic adjustment of the area brightness. According to the user's visual fatigue index, by performing dynamic adjustment analysis of the area brightness on the user's fixation area segmented image, the system can adjust the brightness of different areas of the welding machine screen according to the degree of user visual fatigue to provide a more comfortable visual experience. Using the area brightness dynamic adjustment data, the system can perform visual optimization on the welding machine screen image to improve the visibility and comfort of different areas of the welding machine screen. Combining the visual optimization dynamic brightness adjustment data and the visual perception brightness adjustment data, the system can perform brightness control decision analysis to determine the final brightness adjustment strategy. Brief Description of the Drawings

[0077] Figure 1 It is a schematic flow chart of the steps of the welding machine screen display brightness control method of the present invention;

[0078] Figure 2 is a schematic diagram of the detailed implementation steps of step S1;

[0079] Figure 3 is a schematic diagram of the detailed implementation steps of step S2;

[0080] Figure 4 is a schematic diagram of the detailed implementation steps of step S3. Specific implementation manners

[0081] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0082] The embodiments of the present application provide a method and a system for controlling the display brightness of a welding machine screen. The execution subjects of the method and system for controlling the display brightness of the welding machine screen include, but are not limited to, the following general computing nodes that carry this system: mechanical equipment, data processing platforms, cloud server nodes, network uploading devices, etc. The data processing platform includes, but is not limited to, at least one of an audio and image management system, an information management system, and a cloud data management system.

[0083] Please refer to Figures 1 to 4 , the present invention provides a method for controlling the display brightness of a welding machine screen, and the method for controlling the display brightness of the welding machine screen includes the following steps:

[0084] Step S1: Obtain the welding machine screen image, environmental perception data, and user facial image; calculate the light intensity of the environmental perception data to generate environmental light intensity data; perform glare analysis on the environmental perception data through the environmental light intensity data to generate environmental glare influence data;

[0085] Step S2: Perform environmental perception brightness adjustment on the welding machine screen image based on the environmental glare influence data to generate environmental perception brightness adjustment data; perform visual perception feature analysis on the user facial image based on the environmental perception brightness adjustment data to generate user visual perception feature data;

[0086] Step S3: Use computer vision technology to perform eye tracking on the user facial image to generate user eye tracking data; calculate the blink frequency of the user eye tracking data to generate blink frequency data; perform pupil constriction analysis on the user eye tracking data based on the blink frequency data to generate pupil deformation data;

[0087] Step S4: Perform pupil deformation - brightness correlation analysis on the user's visual perception feature data based on the pupil deformation data to construct a pupil deformation - brightness response curve; perform adaptive brightness adjustment processing on the ambient perception brightness adjustment data using a brightness - visual response model to generate visually perceived brightness adjustment data; calculate the visual fatigue of the user's facial image based on the blink frequency data and the pupil deformation data to generate a user visual fatigue index;

[0088] Step S5: Identify the eye fixation points for the user's eye tracking data to generate eye fixation point position data; perform fixation frequency analysis on the welder's screen image through the eye fixation point position data to generate user fixation frequency data; perform fixation area segmentation on the welder's screen image through the eye fixation point position data and the user fixation frequency data to generate a user fixation area segmented image;

[0089] Step S6: Perform regional brightness dynamic adjustment analysis on the user's fixation area segmented image according to the user visual fatigue index to generate regional brightness dynamic adjustment data; perform visual optimization on the welder's screen image using the regional brightness dynamic adjustment data to generate visually optimized dynamic brightness adjustment data; perform brightness control decision - making analysis using the visually optimized dynamic brightness adjustment data and the visually perceived brightness adjustment data to construct a brightness control decision - making engine to execute the brightness control operation.

[0090] The present invention is based on environmental perception data and user facial images: By acquiring the welding machine screen image, the system can obtain the content displayed on the screen. At the same time, acquiring environmental perception data includes information such as environmental light intensity for analyzing the lighting conditions. Acquiring the user facial image can be used for subsequent eye tracking and visual fatigue calculation. By calculating the light intensity in the environmental perception data, the system can understand the brightness level of the current environment, providing a benchmark for subsequent brightness adjustment. Through comprehensive analysis of the environmental perception data and light intensity data, the system can evaluate the glare situation in the environment, that is, the degree of interference of light reflection or strong flashes on vision. According to the environmental glare impact data, the system can dynamically adjust the brightness of the welding machine screen to offset the impact of environmental glare and ensure that the content on the screen is clearly visible. By analyzing the welding machine screen image after environmental perception brightness adjustment for the user facial image, the system can understand the user's perception characteristics of the screen brightness, such as brightness and contrast. Through computer vision technology, the system can perform eye tracking on the user facial image, that is, real-time monitor and record the movement trajectory and fixation point position of the user's eyes. Based on the eye tracking data, the system can calculate the frequency of the user's blinks to evaluate the user's visual attention and fatigue level. By analyzing the eye tracking data, the system can detect and quantify the degree of pupil constriction in different fixation areas to provide more detailed visual fatigue indicators. Pupil deformation - brightness correlation analysis: Based on the pupil deformation data and user visual perception characteristic data, the system can establish a correlation model between pupil deformation and brightness to understand the impact of pupil deformation on visual perception. Using the pupil deformation - brightness correlation model and brightness - visual response model, the system can automatically adjust the brightness of the welding machine screen to adapt to the user's visual needs and environmental changes, providing the best visual experience. By analyzing the user's eye tracking data, the system can identify and determine the fixation point position of the user's eyes. It can accurately capture the fixation point of the user on the welding machine screen, that is, the position where the user focuses during welding machine operation. Using the eye fixation point position data, the system can calculate the number and frequency of the user's continuous fixation points on the welding machine screen, that is, the user's behavior pattern of looking at the welding machine screen. Analyze and evaluate the user's attention level and work efficiency to the content on the welding machine screen. According to the eye fixation point position data and user fixation frequency data, the system can perform fixation area segmentation on the welding machine screen image, divide the welding machine screen into different areas, and generate corresponding user fixation area segmentation images. According to the user's visual fatigue index, the system performs regional brightness dynamic adjustment analysis on the user fixation area segmentation image.By analyzing the fatigue level of the user's gaze area, the system can determine which areas need to adjust the brightness to reduce the user's visual fatigue. Based on the user's gaze area and visual fatigue situation, it generates the optimal brightness adjustment data for each area to optimize the visual effects of different areas on the welding machine screen, provides automated brightness control, ensures that the content on the welding machine screen is clearly visible in different areas, reduces the user's eye burden, and improves work efficiency and comfort.

[0091] In the embodiment of the present invention, refer to Figure 1 As described, it is a schematic flowchart of the steps of a method for controlling the display brightness of a welding machine screen according to the present invention. In this example, the steps of the method for controlling the display brightness of the welding machine screen include:

[0092] Step S1: Obtain the welding machine screen image, environmental perception data, and user face image; calculate the light intensity of the environmental perception data to generate environmental light intensity data; perform glare analysis on the environmental perception data through the environmental light intensity data to generate environmental glare impact data.

[0093] In this embodiment, a suitable image acquisition device (such as a camera or sensor) is used to obtain the image of the welding machine screen. The image acquisition device can be installed at an appropriate position and angle to obtain a clear image of the welding machine screen. An environmental perception device (such as a light sensor, temperature sensor, etc.) is used to obtain data related to the welding machine usage environment. These data can include environmental parameters such as light intensity, temperature, and humidity. The light intensity of the environment is calculated using the data obtained from the environmental perception device. This can involve the processing and analysis of light sensor data to obtain the light level in the environment. Using the environmental light intensity data and the welding machine screen image, glare analysis is performed on the environmental perception data. This can involve image processing and computer vision techniques to detect and analyze the glare situation in the image. Based on the results of the glare analysis, environmental glare impact data is generated. These data can include information such as glare intensity, the position and size of the glare area.

[0094] Step S2: Perform environmental perception brightness adjustment on the welding machine screen image based on the environmental glare impact data to generate environmental perception brightness adjustment data; perform visual perception feature analysis on the user face image based on the environmental perception brightness adjustment data to generate user visual perception feature data.

[0095] In this embodiment, environmental glare impact data is used to calculate the brightness adjustment required for the welder screen image based on the glare intensity and position information. Different brightness adjustment strategies can be adopted according to the magnitude of the glare intensity, such as reducing the screen brightness or adjusting the contrast, to mitigate the impact of glare. The brightness adjustment algorithm is applied to convert the environmental glare impact data into actual screen brightness adjustment values to generate environmental perception brightness adjustment data. Using the obtained user facial image and combining it with the environmental perception brightness adjustment data, visual perception feature analysis is performed. Computer vision techniques and image processing algorithms can be used to detect features related to visual perception such as facial expressions, pupil size, and signs of eye fatigue. These features in the facial image are analyzed to understand the changes in the user's visual perception under different brightness adjustment conditions. According to the results of the visual perception feature analysis, user visual perception feature data is generated, including facial expression analysis results, pupil size data, and degree of eye fatigue. These data can be used to evaluate the visual comfort and fatigue level of the user under different environmental brightness conditions.

[0096] Step S3: Use computer vision technology to perform eye tracking on the user's facial image to generate user eye tracking data; calculate the blink frequency of the user eye tracking data to generate blink frequency data; perform pupil constriction analysis on the user eye tracking data based on the blink frequency data to generate pupil deformation data;

[0097] In this embodiment, an eye tracking algorithm and computer vision technology are used to perform eye tracking on the user's facial image. This may involve using a specific face detection algorithm to locate the eye region and using an eye tracking algorithm to track the position of the eyes in the image. According to the output of the eye tracking algorithm, user eye tracking data is generated, including information such as the position coordinates and movement trajectory of the eyes. These data can be used to analyze the focus points and changes in fixation points of the user during the use of the welder. Using the eye tracking data, the degree of eye fatigue is evaluated by calculating the blink frequency of the user. Computer vision technology and blink detection algorithms can be used to detect the opening and closing state of the eyes and then calculate the blink frequency. Using the blink frequency data, pupil constriction analysis is performed on the user eye tracking data. This may involve analyzing the relationship between blinking and pupil constriction to understand the pupil deformation during the use of the welder. According to the results of the pupil constriction analysis, pupil deformation data is generated, indicating the changes in the pupil of the user during the use of the welder. These data can be used to evaluate the impact of welder use on the user's eye fatigue and visual burden.

[0098] Step S4: Based on the pupil deformation data, perform pupil deformation-brightness correlation analysis on the user's visual perception feature data to construct a pupil deformation-brightness response curve; use the brightness-visual response model to perform adaptive brightness adjustment processing on the ambient perception brightness adjustment data to generate visual perception brightness adjustment data; calculate the visual fatigue of the user's facial image according to the blink frequency data and the pupil deformation data to generate the user's visual fatigue index;

[0099] In this embodiment, the pupil deformation data and the user's visual perception feature data are used to perform pupil deformation-brightness correlation analysis, which may involve statistical analysis methods. By comparing the relationship between pupil deformation and brightness adjustment data, a pupil deformation-brightness response curve is constructed. The response curve can reflect the correlation degree between pupil deformation and brightness adjustment, providing a basis for subsequent adaptive brightness adjustment. Based on the constructed pupil deformation-brightness response curve, a brightness-visual response model is established. Using this model, adaptive brightness adjustment processing is performed on the ambient perception brightness adjustment data, and according to the output of the model, visual perception brightness adjustment data is generated. These data can better adapt to the user's visual perception and provide a more comfortable brightness adjustment. Using the blink frequency data and the pupil deformation data, the visual fatigue of the user's facial image is calculated, which may involve statistical analysis methods, combining the information of blink frequency and pupil deformation to evaluate the user's visual fatigue degree. This may involve setting corresponding visual fatigue indicators according to the change degree of blink frequency and pupil deformation, such as the visual fatigue index.

[0100] Step S5: Identify the eye fixation points for the user's eye tracking data to generate eye fixation point position data; perform fixation frequency analysis on the welder screen image through the eye fixation point position data to generate the user's fixation frequency data; perform fixation area segmentation on the welder screen image through the eye fixation point position data and the user's fixation frequency data to generate the user's fixation area segmented image;

[0101] In this embodiment, an eye tracking algorithm and computer vision technology are used to identify the eye fixation points of the user from the eye tracking data. This may involve using a specific fixation point recognition algorithm to determine the position of the user's eye fixation points based on the eye tracking data and fixation point characteristics. The fixation point position data can represent the specific position on the welding machine screen where the user is looking. The fixation frequency analysis may involve calculating the proportion of time that the user's fixation points stay on the welding machine screen continuously to determine the degree of attention of the user to different regions. By analyzing the fixation frequencies of different regions, user fixation frequency data can be generated, which represents the degree of attention of the user to each region on the welding machine screen. The welding machine screen image is divided into multiple regions according to the fixation point position data, and each region corresponds to the position of the user's fixation point. According to the user fixation frequency data, each region can be weighted to identify the regions with high user attention, and finally a user fixation region segmented image is generated for visualizing the regions on the welding machine screen where the user is looking.

[0102] Step S6: Perform regional brightness dynamic adjustment analysis on the user fixation region segmented image according to the user visual fatigue index to generate regional brightness dynamic adjustment data; use the regional brightness dynamic adjustment data to perform visual optimization on the welding machine screen image to generate visual optimization dynamic brightness adjustment data; use the visual optimization dynamic brightness adjustment data and visual perception brightness adjustment data to perform brightness control decision analysis, and construct a brightness control decision engine to execute the brightness control operation.

[0103] In this embodiment, based on the user's visual fatigue index, regional brightness dynamic adjustment analysis is performed on the user fixation region segmented image. This may involve setting corresponding brightness adjustment strategies according to the visual fatigue index to adjust the brightness of different regions on the welding machine screen. By analyzing the brightness requirements of each fixation region, regional brightness dynamic adjustment data is generated for subsequent visual optimization and brightness control decision-making. According to the regional brightness dynamic adjustment data, the brightness of different regions of the image is adjusted to improve the user's visual experience. Through visual optimization, visual optimization dynamic brightness adjustment data is generated for subsequent brightness control decision analysis. Based on the visual optimization dynamic brightness adjustment data and visual perception brightness adjustment data, brightness control decision analysis is performed. This may involve formulating a brightness control strategy according to the trade-off between the two data to achieve the best brightness adjustment effect, and constructing a brightness control decision engine to execute the brightness control operation according to the analysis results and adjust the brightness settings of the welding machine screen.

[0104] In this embodiment, referring to Figure 2 as described, it is a schematic diagram of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0105] Step S11: Obtain the welding machine screen image, environmental perception data, and user facial image;

[0106] Step S12: Perform optical path tracing on the environmental perception data to generate optical path tracing data;

[0107] Step S13: Analyze the environmental light distribution of the environmental perception data according to the optical path tracing data to generate environmental light distribution data;

[0108] Step S14: Calculate the illumination intensity of the environmental light distribution data to generate environmental illumination intensity data;

[0109] Step S15: Perform wavelength color difference analysis on the environmental illumination intensity data to generate illumination wavelength color difference data;

[0110] Step S16: Perform glare analysis on the environmental perception data through the illumination wavelength color difference data to generate environmental glare impact data.

[0111] The present invention obtains data related to the brightness control of the welding machine screen. The welding machine screen image provides the display content on the current screen, the environmental perception data provides information about the surrounding environment, and the user's facial image can be used to analyze the user's visual perception and comfort, providing information about the propagation path of light in the environment. By performing optical path tracing on the environmental perception data, the processes of reflection, refraction, scattering, etc. of light in the environment can be simulated, so as to more accurately understand the distribution of light on the welding machine screen. By analyzing the optical path tracing data, the environmental light distribution around the welding machine screen can be understood, including information such as the intensity, direction, and scattering of light. By calculating the environmental light distribution data, the environmental illumination intensity received by the welding machine screen can be determined, that is, the light energy density in the environment, which is very important for subsequent brightness control. By performing wavelength color difference analysis on the environmental illumination intensity data, the intensity distribution of light of different wavelengths can be determined. By analyzing the illumination wavelength color difference data, the glare situation on the welding machine screen can be evaluated, including the degree of interference of the intensity, reflection, refraction, etc. of light on the user's vision. This helps to determine an appropriate screen brightness control strategy to reduce the adverse impact of glare on the user experience.

[0112] In this embodiment, image data on the welding machine screen is obtained through corresponding sensors or imaging devices, which may include real-time images during the welding process or stored images. Relevant data in the environment is obtained using environmental perception sensors (such as light sensors), which may include information such as light intensity, light color temperature, and ambient temperature. A facial image of the user is obtained through an imaging device or sensor, which can be used for subsequent facial expression analysis or calculation of the visual fatigue index. The light in the environment is simulated and traced using a ray tracing algorithm, which can calculate the interaction information between the light and objects by simulating the propagation path of the light in the environment. According to the results of the ray path tracing algorithm, ray path tracing data is generated, which may include information such as the incident angle, reflectivity, and transmittance of the light, for subsequent analysis of the environmental light distribution. Using the ray path tracing data, the light distribution in the environment is analyzed, which may include determining information such as the intensity, direction, and color distribution of the light. According to the results of the environmental light distribution analysis, environmental light distribution data is generated, which can describe the light intensity, color, etc. at different positions in the environment, for subsequent calculation of the light intensity. Using the environmental light distribution data, the light intensity at different positions in the environment is calculated, which can be calculated based on information such as the intensity, direction, and color of the light. According to the results of the light intensity calculation, environmental light intensity data is generated, which can describe the light intensity levels at different positions in the environment, for subsequent analysis of the color difference of the light wavelengths. Based on the environmental light intensity data, a color difference analysis of light with different wavelengths is performed, which may involve comparing the relative intensity or color distribution of light with different wavelengths. According to the results of the wavelength color difference analysis, light wavelength color difference data is generated, which can describe the intensity difference or color difference of light with different wavelengths in the environment, for subsequent analysis of environmental glare. Using the light wavelength color difference data, a glare analysis of the environmental perception data is performed, which may involve detecting strong light irradiation in the environment and its impact on the welding machine screen image and the user. According to the results of the glare analysis, environmental glare impact data is generated, which can describe the glare situation that appears in the environment and the degree of its impact on the welding machine screen image and the user's vision.

[0113] In this embodiment, referring to Figure 3 as described, it is a schematic diagram of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0114] Step S21: Compare the environmental glare impact data based on a preset environmental glare threshold index. When the preset environmental glare threshold index is less than the environmental glare impact data, the brightness of the welding machine screen image is increased to generate environmental perception brightness adjustment data;

[0115] Step S22: If the preset environmental glare threshold index is greater than the environmental glare impact data, perform brightness reduction processing on the welder screen image to generate environmental perception brightness adjustment data;

[0116] Step S23: Detect the line-of-sight deviation of the user's facial image to generate line-of-sight deviation data;

[0117] Step S24: Analyze the visual perception feature of the line-of-sight deviation data based on the environmental perception brightness adjustment data to generate user visual perception feature data.

[0118] The present invention evaluates the environmental glare impact data according to the preset environmental glare threshold index. If the environmental glare impact data exceeds the preset threshold index, it indicates that the glare in the environment is strong. At this time, brightness increase processing needs to be performed on the welder screen image. By increasing the screen brightness, the impact of glare can be offset, and the visibility and recognition of the content displayed on the screen by the welder operator can be improved. The environmental glare impact data is evaluated according to the preset environmental glare threshold index. If the environmental glare impact data is lower than the preset threshold index, it indicates that the glare in the environment is weak. At this time, brightness reduction processing can be performed on the welder screen image. By reducing the screen brightness, the reflection and glare of the screen can be reduced, and the visibility and recognition of the content displayed on the screen by the welder operator can be improved. By analyzing the user's facial image, the line-of-sight direction and position of the welder operator can be determined. The line-of-sight deviation data can be used for subsequent brightness adjustment and user visual perception feature analysis. By performing correlation analysis on the environmental perception brightness adjustment data and the line-of-sight deviation data, the visual perception features of the welder operator under different brightness conditions can be understood. This includes information such as the visibility of the welder screen and the degree of attention to the welding process. By analyzing these features, the welder screen brightness control strategy can be further optimized to provide a better user experience and working effect.

[0119] In this embodiment, according to system requirements and user needs, an environmental glare threshold index is preset in advance. This threshold index can represent the tolerance degree of the system to environmental glare. Compare the environmental glare impact data with the preset environmental glare threshold index. If the environmental glare impact data exceeds the threshold, perform brightness increase processing, adjust the brightness of the welder screen image, and increase the brightness level of the screen. This can be achieved by increasing the intensity of light on the image or adjusting the brightness curve. Compare the environmental glare impact data with the preset environmental glare threshold index. If the environmental glare impact data is lower than the threshold, perform brightness decrease processing, adjust the brightness of the welder screen image, and lower the brightness level of the screen. This can be achieved by reducing the intensity of light or adjusting the brightness curve. Through image processing technology or face recognition algorithm, detect the eye position and line-of-sight direction in the user's facial image. This can be used to determine whether the user's line of sight deviates from the welder screen. According to the result of the line-of-sight deviation detection, generate line-of-sight deviation data. These data can describe the user's eye position and line-of-sight direction for subsequent analysis and processing. Utilize the environmental perception brightness adjustment data and line-of-sight deviation data to analyze the user's visual perception characteristics. This can involve the perception characteristics of the user regarding the brightness, contrast, line-of-sight concentration, etc. of the welder screen image. According to the environmental perception brightness adjustment data and line-of-sight deviation data, combined with the preset environmental glare threshold index, analyze the user's visual perception of the welder screen image under different environmental lighting conditions. According to the result of the analysis of the visual perception characteristics, generate the user's visual perception characteristic data. These data can describe the user's perception characteristics regarding comfort, visibility, and visual fatigue degree, etc. of the welder screen image under different environmental conditions.

[0120] In this embodiment, referring to Figure 4 as described, it is a schematic diagram of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0121] Step S31: Use computer vision technology to perform eye positioning on the user's facial image to generate user eye positioning point data;

[0122] Step S32: Perform continuous inter-frame phase matching on the user's facial image based on the user eye positioning point data to generate eye inter-frame matching data;

[0123] Step S33: Reconstruct the viewpoint movement trajectory of the eye inter-frame matching data to generate an eye movement trajectory curve;

[0124] Step S34: Perform eye tracking on the user's facial image according to the eye movement trajectory curve to generate user eye tracking data;

[0125] Step S35: Calculate the blink frequency of the user eye tracking data to generate blink frequency data;

[0126] Step S36: Perform pupil constriction analysis on the user's eye tracking data based on the blink frequency data to generate pupil deformation data.

[0127] The present invention accurately detects and locates the eye position of the welder operator through computer vision technology. By using the feature points or feature regions in the facial image, the position and direction of the eyes in the image can be determined. The eye position point data provides information about the fixation focus of the welder operator, which is helpful for subsequent eye tracking and welder screen brightness control. Analyze the movement of the user's eyes between different frames through the continuous frame - to - frame phase matching technology. By comparing the changes of the eye position points in consecutive frames, the movement direction and speed of the eyes can be determined. The eye frame - to - frame matching data provides information about the dynamic changes of the user's fixation focus, which is helpful for subsequent eye movement trajectory reconstruction and eye tracking. Reconstruct the movement trajectory of the user's eyes based on the eye frame - to - frame matching data. Through the matching data between consecutive frames, the movement path of the welder operator's fixation focus can be inferred. The eye movement trajectory curve provides the trajectory information of the user's fixation focus, which is helpful for subsequent eye tracking and welder screen brightness control. Track the welder operator's eyes according to the eye movement trajectory curve. By associating the eye movement trajectory with the facial image, the fixation focus of the welder operator can be tracked in real time. The user's eye tracking data provides information about the eye position and gaze direction of the welder operator, which is helpful for subsequent blink frequency calculation and pupil deformation analysis. Calculate the blink frequency of the welder operator by analyzing the user's eye tracking data. By detecting the change in the open - closed state of the eyes, the number of blinks and the blink frequency of the welder operator can be determined. The blink frequency data provides an index of the welder operator's attention and visual fatigue level, which is helpful for subsequent pupil deformation analysis and welder screen brightness control. Analyze the pupil constriction of the welder operator according to the blink frequency data. By detecting the change in the pupil during blinking, the attention and concentration level of the welder operator can be inferred. The pupil deformation data provides an index of the welder operator's attention and visual fatigue level, which is helpful for further optimizing the welder screen brightness control strategy to provide a better user experience and working effect.

[0128] In this embodiment, computer vision technology is applied to process the user's facial image using an eye localization algorithm to determine the position and bounding box of the eyes. According to the results of the eye localization algorithm, the center point coordinates of the eyes are extracted and output as eye localization point data. Using the user's eye localization point data, an inter-frame phase matching algorithm is applied to process consecutive facial image frames. This algorithm can identify the displacement and rotation of the eyes between different frames. According to the results of the inter-frame phase matching algorithm, the displacement and rotation information of the eyes are extracted and output as eye inter-frame matching data. Using the eye inter-frame matching data, a gaze movement trajectory reconstruction algorithm is applied to reconstruct the movement trajectory of the eyes. This algorithm can estimate the movement trajectory of the eyes in space. According to the results of the gaze movement trajectory reconstruction algorithm, curve data describing the movement trajectory of the eyes is generated. These data can be used for subsequent analysis and processing. Using the eye movement trajectory curve data, an eye tracking algorithm is applied to process the user's facial image to determine the position and bounding box of the eyes in the image. According to the results of the eye tracking algorithm, the center point coordinates and bounding box information of the eyes are extracted and output as eye tracking data. Using the user's eye tracking data, a blink detection algorithm is applied to analyze the state of the eyes to detect blink events. According to the results of the blink detection algorithm, the occurrence frequency of blink events is counted and output as blink frequency data. Using the blink frequency data and the user's eye tracking data, a pupil constriction analysis algorithm is applied. According to the results of the pupil constriction analysis algorithm, the deformation information of the pupils is extracted and output as pupil deformation data.

[0129] In this embodiment, the specific steps of step S36 are as follows:

[0130] Step S361: Perform an intensity response analysis on the user's eye tracking data based on the blink frequency data to generate eye intensity response data;

[0131] Step S362: Perform a pupil constriction rate analysis on the user's eye tracking data according to the eye intensity response data to generate pupil constriction rate data;

[0132] Step S363: Perform a constriction time analysis on the pupil constriction rate data to generate pupil constriction time data;

[0133] Step S364: Perform a dynamic constriction change analysis on the user's eye tracking data based on the pupil constriction time data to generate pupil dynamic constriction data;

[0134] Step S365: Calculate the constriction amplitude of the pupil dynamic constriction data to generate pupil deformation data.

[0135] The present invention infers the light intensity response of the eyeball by analyzing the correlation between the blink frequency data and the eye tracking data of the welding machine operator. By observing the light intensity change of the eyeball during blinking, the reaction of the welding machine operator to light during blinking can be determined. The eyeball light intensity response data provides the relationship between the blink of the welding machine operator and visual attention, which helps with subsequent pupil contraction rate analysis and welding machine screen brightness control. Analyze the pupil contraction rate of the welding machine operator based on the eyeball light intensity response data. By observing the size change of the pupil under the change of eyeball light intensity, the pupil contraction rate of the welding machine operator can be calculated. The pupil contraction rate data provides the sensitivity of the welding machine operator to light changes, which helps with subsequent pupil contraction time analysis and welding machine screen brightness control. Calculate the pupil contraction time of the welding machine operator by analyzing the pupil contraction rate data. By observing the time required for the pupil to change from the initial state to the maximum contraction state, the response speed of the welding machine operator to light changes can be determined. The pupil contraction time data provides the adaptability and adjustment ability of the welding machine operator to light changes, which helps with subsequent pupil dynamic contraction data analysis and welding machine screen brightness control. Analyze the dynamic contraction changes in the eye tracking data of the welding machine operator according to the pupil contraction time data. By observing the contraction process of the pupil at different fixation points, the attention and visual sensitivity of the welding machine operator to different regions can be inferred. The pupil dynamic contraction data provides the degree of attention of the welding machine operator to different regions and the distribution of visual attention, which helps with subsequent pupil deformation data calculation and welding machine screen brightness control. Calculate the degree of pupil deformation in the eye tracking data of the welding machine operator according to the pupil dynamic contraction data. By measuring the contraction amplitude of the pupil at different fixation points, the degree of interest of the welding machine operator in different regions and the distribution of visual attention can be determined. The pupil deformation data provides a quantitative index of the visual sensitivity and attention distribution of the welding machine operator to different regions, which helps to accurately control the brightness of the welding machine screen to provide the best visual experience and operating environment.

[0136] In this embodiment, for the extracted eye image region, light intensity calculation can be performed. Image processing techniques such as grayscale transformation or color space conversion can be used to obtain the light intensity information of pixel values. According to the result of the light intensity calculation, the light intensity response data of the eye is associated with the blink frequency data, and the eye light intensity response data is generated. For the pupil region, light intensity calculation is performed to obtain the light intensity information of the pixels within the pupil region. According to the light intensity information of the pupil region and in combination with the blink frequency data, the pupil contraction rate is calculated. The pupil contraction rate can be determined by comparing the pupil size or light intensity changes at different time points. Using the pupil contraction rate data, the occurrence of pupil contraction events is detected. Thresholds or other detection algorithms can be used to determine the start and end of the contraction events. For the detected pupil contraction events, the duration is calculated, that is, the time from the start of pupil contraction to the recovery of the normal size. Using the pupil contraction time data and the eye tracking data, a dynamic contraction change analysis algorithm is applied to analyze the dynamic changes of the pupil. This algorithm can detect and describe the dynamic contraction changes of the pupil in different time periods. According to the result of the dynamic contraction change analysis algorithm, the dynamic contraction information of the pupil is extracted and output as the pupil dynamic contraction data. Using the pupil dynamic contraction data, the contraction amplitude of the pupil in each contraction event is calculated. This can be determined by comparing the size or light intensity changes of the pupil during contraction with its reference value during non - contraction. The contraction amplitude of the pupil is associated with the eye tracking data, and pupil deformation data is generated. These data can represent the degree of pupil deformation at different time points and reflect the dynamic characteristics of the user's eye tracking.

[0137] In this embodiment, the specific steps of step S4 are as follows:

[0138] Step S41: Based on the pupil deformation data, perform pupil deformation - brightness correlation analysis on the user's visual perception feature data to generate pupil deformation - brightness response data;

[0139] Step S42: Perform correlation curve fitting on the pupil deformation - brightness response data to construct a pupil deformation - brightness response curve;

[0140] Step S43: Use the brightness - visual response model to perform adaptive brightness adjustment processing on the ambient perception brightness adjustment data to generate visual perception brightness adjustment data;

[0141] Step S44: According to the blink frequency data, perform blink interval difference analysis on the user's facial image to generate blink interval difference data;

[0142] Step S45: Perform contraction efficiency analysis on the pupil deformation data to generate user pupil contraction sensitivity data;

[0143] Step S46: Based on the blink interval difference data, use the user visual fatigue calculation formula to calculate the visual fatigue of the user's pupil contraction sensitivity data, and generate the user visual fatigue index.

[0144] The present invention can establish an association model between pupil deformation and brightness by observing the degree of pupil deformation and its changes under different brightness conditions. The pupil deformation - brightness response data provides the visual perception characteristics of the welding machine operator under different brightness conditions, which helps with subsequent brightness adjustment control. By performing curve fitting on the pupil deformation - brightness response data, an association curve between pupil deformation and brightness is established. Through the fitted curve, the relationship between pupil deformation and brightness can be more accurately described, and a mathematical model for brightness adjustment can be provided. The pupil deformation - brightness response curve provides a basis and reference for subsequent brightness adjustment. According to the visual perception characteristics of the welding machine operator and the pupil deformation - brightness response curve, the brightness can be adjusted accordingly based on the brightness of the current environment. The visual perception brightness adjustment data provides information for automatically adjusting the brightness of the welding machine screen according to the visual perception characteristics of the welding machine operator. Based on the blink frequency data of the welding machine operator, analyze the blink interval difference in the user's facial image. By observing the change in the time interval of the welding machine operator's blinks, the degree of visual fatigue and attention level of the welding machine operator can be inferred. The blink interval difference data provides a quantitative index of the visual fatigue state of the welding machine operator, which helps with subsequent visual fatigue calculation and brightness adjustment control. By measuring the degree of deformation of the pupil from the initial state to the maximum contraction state, the sensitivity of the welding machine operator to light changes can be evaluated. The pupil contraction sensitivity data provides information on the welding machine operator's perception ability of light changes and adaptive brightness adjustment. According to the blink interval difference data and the visual fatigue calculation formula, calculate the visual fatigue of the user's pupil contraction sensitivity data. By analyzing the change in the blink interval of the welding machine operator and combining with the pupil contraction sensitivity data, the degree of visual fatigue of the welding machine operator can be evaluated. The user visual fatigue index provides a quantitative assessment of the degree of visual fatigue of the welding machine operator, which helps to identify potential fatigue risks and take corresponding measures.

[0145] In this embodiment, for the visual perception characteristics under different brightness conditions, relevant data such as visual comfort and clarity can be collected through methods such as subjective user evaluation or objective measurement. By correlating the pupil deformation data with the corresponding visual perception characteristic data, statistical methods, correlation analysis and other technical means can be used to determine the relationship between pupil deformation and brightness. According to the correlation analysis results between pupil deformation and brightness, the pupil deformation is associated with the corresponding brightness value, and pupil deformation-brightness response data is generated for subsequent analysis and processing. Using mathematical or statistical methods, curve fitting of the pupil deformation-brightness response data is carried out. Common fitting methods include linear regression, polynomial regression, exponential function fitting, etc. According to the fitting results, a pupil deformation-brightness response curve is generated, which describes the relationship between pupil deformation and brightness and can be used for subsequent brightness adjustment processing and visual fatigue analysis. Based on the existing research results of brightness-visual response, a model between brightness and visual perception is established. This model can be an empirical model, a neural network model, etc., and is used to describe the impact of brightness on visual perception. Using the established brightness-visual response model, the environmental perceived brightness adjustment data is processed, and the environmental brightness is adjusted according to the visual perception effect predicted by the model to provide a visual experience that better meets the user's needs. According to the blink frequency data, the time interval between the user's blinks is calculated. The blink interval refers to the time interval between two consecutive blinks. The blink interval data is analyzed to explore the differences in the user's blink intervals. Statistical methods, data visualization and other means can be used to compare the blink interval differences under different conditions, such as the blink interval differences between the fatigued state and the non-fatigued state. According to the pupil deformation data, the contraction efficiency of the user's pupils under different stimuli is calculated. The contraction efficiency can be defined as the change amplitude of the pupil deformation relative to the stimulus. The pupil contraction efficiency data is analyzed to explore the contraction sensitivity of the user's pupils. The contraction efficiency differences under different stimulus conditions, such as brightness change, light source color change, etc., can be compared. According to the results of the contraction efficiency analysis, the pupil contraction sensitivity data of the user is generated for subsequent visual fatigue calculation and analysis. A suitable visual fatigue calculation formula is selected, which can estimate the user's visual fatigue degree based on the blink interval difference data and the pupil contraction sensitivity data. According to the selected visual fatigue calculation formula, the blink interval difference data and the pupil contraction sensitivity data are used for calculation to obtain the user's visual fatigue index.

[0146] In this embodiment, the specific formula for calculating the user's visual fatigue in step S46 is as follows:

[0147]

[0148] Wherein, V is the user's visual fatigue index, T is the user's device usage time, t is the screen resolution, D is the complexity of the viewing point movement trajectory, L is the screen illumination intensity, I is the user's blink frequency, F is the pupil contraction efficiency, C is the user's pupil deformation response rate, A is the user's pupil contraction amplitude, P is the viewing point movement speed, H is the difference value of the pupil sizes of the left and right eyes, R is the pupil size change rate, and S is the number of head movements.

[0149] In the present invention, represents the ratio of the user's device usage time to the screen resolution divided by the complexity of the viewing point movement trajectory. This ratio can reflect the degree to which the user browses and observes the information on the screen within a specific time. A higher ratio means that the user uses the device more attentively, considering the user's attention level. represents the ratio between the natural logarithm of the screen illumination intensity and the natural logarithm of the user's blink frequency. This ratio can measure the degree to which the screen brightness affects the user's blink frequency. A higher ratio means that the screen brightness has a greater impact on the user's blink frequency. represents the limit value of the pupil contraction efficiency. The pupil contraction efficiency reflects the ability of the pupil to adjust to light. The limit value represents the maximum contraction ability of the pupil under absolute illumination conditions, which is the product of the user's pupil contraction amplitude and the viewing point movement speed. Both the pupil contraction amplitude and the viewing point movement speed are related to the change in the user's attention. A larger value means that the pupil contraction amplitude is larger when the user moves the viewing point. represents the cube root of the difference value of the pupil sizes of the left and right eyes and the pupil size change rate. The difference value of the pupil sizes of the left and right eyes and the pupil size change rate reflect the user's eye's ability to adapt to and adjust to light. Both the number of head movements and the viewing point movement distance are related to the user's way of browsing the information on the screen. A higher ratio means that the user frequently moves the head to observe the information on the screen. The formula comprehensively considers the user's attention level, the impact of screen brightness on eye fatigue, pupil adjustment ability, attention change, eye adaptation ability, and head movement situation through multiple parameters and calculation steps to help evaluate the degree of visual fatigue of the user during device use.

[0150] In this embodiment, the specific steps of step S5 are as follows:

[0151] Step S51: Perform visual focus convergence processing on the user's eye tracking data to generate visual focus area data;

[0152] Step S52: Identify the eye fixation points for the visual focus area data to generate eye fixation point position data;

[0153] Step S53: Perform fixation frequency analysis on the welding machine screen image through the eye fixation point position data to generate user fixation frequency data;

[0154] Step S54: Construct a fixation heat map for the eye fixation point position data based on the user's fixation frequency data to construct an eye fixation heat map.

[0155] Step S55: Divide the welding machine screen image into fixation regions based on the eye fixation heat map to generate a user fixation region segmented image.

[0156] The present invention can determine the region where the visual focus of the welding machine operator is located on the welding machine screen by analyzing the eye movement trajectory and fixation points of the welding machine operator. The visual focus region data provides the main attention regions of the welding machine operator on the screen, which helps subsequent fixation analysis and brightness control. By analyzing the fixation points of the welding machine operator within the focus region, the fixation position of the operator's eyes on the welding machine screen can be determined. The eye fixation point position data provides the specific fixation positions of the welding machine operator on the screen, which helps subsequent fixation frequency analysis and fixation region segmentation. By counting the number and duration of fixation points of the welding machine operator in different regions, the fixation frequency of the welding machine screen can be calculated, that is, the degree of concentrated attention of the welding machine operator in different regions. The user fixation frequency data provides the attention distribution of the welding machine operator in different regions, which helps subsequent fixation heat map construction and fixation region segmentation. By visualizing the distribution of fixation points as a heat map, the main fixation regions and hot spots of the welding machine operator on the welding machine screen can be intuitively displayed. The eye fixation heat map provides visual information on the attention distribution of the welding machine operator on the screen, which helps to understand the visual attention pattern of the welding machine operator. According to the distribution of fixation points of the welding machine operator within the focus region, the welding machine screen image can be divided into different region blocks, and each region block represents the fixation region of the welding machine operator. The user fixation region segmented image provides a visual representation of the visual attention regions of the welding machine operator on the welding machine screen, which helps subsequent brightness control and display optimization. By visual focus convergence processing, eye fixation point recognition, and fixation frequency analysis, the fixation region and attention distribution of the welding machine operator can be determined. By constructing the fixation heat map and the fixation region segmented image, the visual attention pattern and fixation region of the welding machine operator can be intuitively demonstrated. This information can be used to optimize the brightness control of the welding machine screen to ensure sufficient visibility and a comfortable visual experience for the welding machine operator in key regions.

[0157] In this embodiment, the eye tracking data is processed to identify the user's visual focus convergence area, which can be determined by analyzing information such as the trajectory of eye movement and fixation duration. According to the result of the visual focus convergence processing, visual focus area data is generated, which represents the main attention areas of the user when observing the welder screen. Using computer vision or image processing techniques, the visual focus area data is analyzed and processed to determine the position of the eye fixation point, which can be achieved by detecting feature points, edges and other information in the visual focus area. According to the result of the eye fixation point recognition, eye fixation point position data is generated, which represents the fixation position of the user's eyes on the welder screen. Using the eye fixation point position data and the welder screen image data, the viewing frequency of the user in different areas is analyzed, and the viewing frequency can be calculated by counting the number of times or the duration of the eye fixation points appearing in different areas. Using the user viewing frequency data and the eye fixation point position data, an eye fixation heat map is constructed. Image processing techniques can be used to mark the areas with high viewing frequency as hot spots to form a heat map. Using the eye fixation heat map, the welder screen image is divided into multiple areas. According to the position and intensity of the hot spots, the image is divided into different blocks, and each block represents a user fixation area. According to the result of the fixation area segmentation, the corresponding welder screen image area is extracted to generate a user fixation area segmented image, which shows the user's fixation areas on the welder screen and can be used for further analysis and understanding of the user's attention distribution.

[0158] In this embodiment, the specific steps of step S6 are as follows:

[0159] Step S61: Segment the non-fixation area of the welder screen image through the user fixation area segmented image to generate a fixation area image and a non-fixation area image;

[0160] Step S62: Compare the user visual fatigue index based on a preset user visual fatigue threshold index. When the preset user visual fatigue threshold index is less than or equal to the user visual fatigue index, perform a region brightness increase process on the fixation area image to generate fixation area brightness adjustment data;

[0161] Step S63: Perform a region brightness decrease process on the non-fixation area image to generate non-fixation area brightness adjustment data;

[0162] Step S64: Perform a region brightness dynamic adjustment analysis on the fixation area brightness adjustment data and the non-fixation area brightness adjustment data according to the user visual fatigue index to generate region brightness dynamic adjustment data;

[0163] Step S65: Perform a color temperature optimization analysis on the welder screen image using the region brightness dynamic adjustment data to generate color temperature optimization data;

[0164] Step S66: Visually optimize the regional brightness dynamic adjustment data using the color temperature optimization data to generate visually optimized dynamic brightness adjustment data;

[0165] Step S67: Conduct brightness control decision analysis using the visually optimized dynamic brightness adjustment data and visually perceived brightness adjustment data, and construct a brightness control decision engine to execute the brightness control operation.

[0166] In the present invention, by separating the gazed area and the non-gazed area of the welder's screen image, the areas that the welder mainly focuses on and other unimportant areas can be extracted, providing a basis for subsequent brightness control and visual optimization. Based on the user's visual fatigue index, it is determined whether the user's visual fatigue degree exceeds a preset threshold. If the user's visual fatigue index exceeds or equals the threshold, it indicates that the user may be fatigued and brightness adjustment is required to reduce the visual burden. Therefore, the brightness of the gazed area image is increased, making the area gazed by the user on the welder's screen brighter to improve visibility and slow down visual fatigue. Since the welder's attention is mainly concentrated on the gazed area, the brightness of the non-gazed area can be correspondingly reduced to lower energy consumption and reduce interference. By reducing the brightness of the non-gazed area, the power consumption and visual comfort of the welder's screen can be optimized. Based on the user's visual fatigue index, dynamic adjustment analysis is performed on the gazed area brightness adjustment data and the non-gazed area brightness adjustment data. According to the user's visual fatigue degree, the brightness adjustment degrees of the gazed area and the non-gazed area are adjusted to achieve dynamic brightness adjustment of the welder's screen. By dynamically adjusting the brightness, a more suitable display effect can be provided according to the user's fatigue degree, improving the visual comfort and work efficiency of the welder. By adjusting the color temperature of the welder's screen according to the brightness adjustment degrees of different areas, a color performance more suitable for the welder can be provided. The optimization of the color temperature can improve the color reproduction ability and visual comfort of the image, enhancing the welder's observation and judgment abilities of the weld and the welding process. By combining color temperature adjustment and regional brightness adjustment, the visual effect of the welder's screen image can be further optimized, enabling the welder to observe the weld and the welding process more clearly. The visually optimized dynamic brightness adjustment data provides more refined and personalized brightness adjustment to meet the needs of different welding environments and welders. Brightness control decision analysis is conducted using the visually optimized dynamic brightness adjustment data and the visually perceived brightness adjustment data, and a brightness control decision engine is constructed. Based on these data, the system can automatically adjust the brightness of the welder's screen according to the real-time welder operation environment and the welder's needs. The brightness control decision engine can achieve intelligent brightness control according to different input parameters and algorithms to provide the best visual experience and working environment.

[0167] In this embodiment, by using the user's gaze area segmented image, the welding machine screen image is segmented into a gaze area image and a non-gaze area image. According to the position information of each block in the gaze area segmented image, the corresponding area of the welding machine screen image is extracted as the gaze area image, and the non-gaze area image is the remaining area. The preset user visual fatigue threshold index is compared with the user's visual fatigue index. If the preset threshold index is less than or equal to the user's fatigue index, the brightness of the gaze area image is adjusted to increase the brightness of the gaze area, which can be achieved by increasing the brightness, adjusting the contrast, or applying other image processing techniques. The brightness of the non-gaze area image is adjusted to decrease the brightness of the non-gaze area, which can be achieved by reducing the brightness, adjusting the contrast, or applying other image processing techniques. According to the user's visual fatigue index, by integrating the gaze area brightness adjustment data and the non-gaze area brightness adjustment data, dynamic adjustment analysis of the regional brightness is carried out, which may involve adjusting the amplitude and method of brightness increase or decrease according to the user's fatigue level and the importance of the gaze area. According to the analysis results, dynamic adjustment data of the regional brightness is generated, and the brightness adjustment parameters or transformations of different regions are recorded. The color temperature optimization analysis of the welding machine screen image is carried out, which may involve adjusting the color temperature of the corresponding region according to the brightness adjustment parameters or transformations of different regions to optimize the image display effect, and recording the parameters or transformations for color temperature optimization of the welding machine screen image to generate color temperature optimization data. The visual optimization of the dynamic adjustment data of the regional brightness is carried out, which may involve adjusting the dynamic adjustment data of the regional brightness according to the color temperature optimization parameters or transformations to obtain a better visual effect, and recording the parameters or transformations for visual optimization of the dynamic adjustment data of the regional brightness to generate visually optimized dynamic brightness adjustment data. By integrating the visually optimized dynamic brightness adjustment data and the visually perceived brightness adjustment data, brightness control decision analysis is carried out, which may involve determining the final brightness control strategy according to the brightness adjustment parameters of different regions, the visually perceived brightness, and the visual optimization results. According to the results of the brightness control decision analysis, a brightness control decision engine is constructed, which can automatically perform corresponding brightness control operations according to the real-time user visual fatigue index and the welding machine screen image, including adjusting the brightness of the gaze area and the non-gaze area, so as to provide a better user experience.

[0168] In this embodiment, a welding machine screen display brightness control system is also provided for performing the welding machine screen display brightness control as described above, including:

[0169] An ambient light module for obtaining the welding machine screen image, ambient perception data, and the user's face image; calculating the light intensity of the ambient perception data to generate ambient light intensity data; and performing glare analysis on the ambient perception data through the ambient light intensity data to generate ambient glare impact data;

[0170] A visual perception module, which is used to perform ambient perception brightness adjustment on the welder screen image based on the environmental glare impact data to generate ambient perception brightness adjustment data; perform visual perception feature analysis on the user's facial image based on the ambient perception brightness adjustment data to generate user visual perception feature data;

[0171] A pupil deformation module, which is used to perform eye tracking on the user's facial image using computer vision technology to generate user eye tracking data; calculate the blink frequency of the user's eye tracking data to generate blink frequency data; perform pupil constriction analysis on the user's eye tracking data based on the blink frequency data to generate pupil deformation data;

[0172] A visual fatigue module, which is used to perform pupil deformation - brightness correlation analysis on the user's visual perception feature data based on the pupil deformation data to construct a pupil deformation - brightness response curve; perform adaptive brightness adjustment processing on the ambient perception brightness adjustment data using a brightness - visual response model to generate visual perception brightness adjustment data; calculate the visual fatigue of the user's facial image based on the blink frequency data and the pupil deformation data to generate a user visual fatigue index;

[0173] A fixation area segmentation module, which is used to identify the eye fixation points of the user's eye tracking data to generate eye fixation point position data; perform fixation frequency analysis on the welder screen image through the eye fixation point position data to generate user fixation frequency data; segment the welder screen image into fixation areas through the eye fixation point position data and the user fixation frequency data to generate a user fixation area segmented image;

[0174] A regional brightness dynamic adjustment module, which is used to perform regional brightness dynamic adjustment analysis on the user's fixation area segmented image according to the user visual fatigue index to generate regional brightness dynamic adjustment data; perform visual optimization on the welder screen image using the regional brightness dynamic adjustment data to generate visual optimization dynamic brightness adjustment data; perform brightness control decision - making analysis using the visual optimization dynamic brightness adjustment data and the visual perception brightness adjustment data to construct a brightness control decision - making engine to execute brightness control operations.

[0175] The present invention obtains the welder screen image, environmental perception data, and user facial image: By obtaining this data, the system can understand the current environmental conditions and user status. By calculating the light intensity of the environmental perception data, the system can obtain the light intensity information of the current environment. By performing glare analysis on the environmental perception data based on the light intensity data, the system can understand the glare situation in the environment. According to the environmental glare impact data, the system adjusts the environmental perception brightness of the welder screen image to improve the visibility and comfort of the screen in the case of glare. By performing visual perception feature analysis on the user facial image based on the environmental perception brightness adjustment data, the system can understand the visual perception features of the user under different lighting conditions. Using computer vision technology to perform eye tracking on the user facial image, the system can obtain the position and movement information of the user's eyes. By analyzing the eye tracking data, the system can calculate the user's blink frequency, which is an indicator for evaluating the degree of the user's visual fatigue. Based on the blink frequency data, the system can further analyze the pupil constriction situation in the user's eye tracking data to understand the user's attention and fatigue degree. By performing correlation analysis on the user's visual perception feature data and pupil deformation data, the system can construct a pupil deformation - brightness response curve to help understand the pupil deformation situation of the user under different brightness conditions. According to the brightness - visual response model and the environmental perception brightness adjustment data, the system can perform adaptive brightness adjustment processing to provide a screen brightness suitable for the user's current visual state. According to the blink frequency data and pupil deformation data, the system can calculate the user's visual fatigue index, which is used to evaluate the user's fatigue degree and attention level. By processing the user's eye tracking data, the system can identify the position of the eye fixation point to understand the area of interest of the user on the welder screen. By performing fixation frequency analysis on the welder screen image based on the eye fixation point position data, the system can understand the fixation frequency of the user in different areas, which helps to understand the focus points on the welder screen. According to the eye fixation point position data and the user fixation frequency data, the system can perform fixation area segmentation on the welder screen image, dividing the welder screen into different areas for subsequent dynamic adjustment of the area brightness. According to the user's visual fatigue index, the system can perform dynamic adjustment analysis of the area brightness of the user's fixation area segmented image, and adjust the brightness of different areas of the welder screen according to the user's visual fatigue degree to provide a more comfortable visual experience. Using the area brightness dynamic adjustment data, the system can perform visual optimization on the welder screen image to improve the visibility and comfort of different areas of the welder screen. Combining the visual optimization dynamic brightness adjustment data and the visual perception brightness adjustment data, the system can perform brightness control decision - making analysis to determine the final brightness adjustment strategy.

[0176] Therefore, in all aspects, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Accordingly, all changes that fall within the meaning and scope of the equivalent elements of the application documents are intended to be embraced within the present invention.

[0177] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly, the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed related items.

[0178] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A method for controlling the display brightness of a welding machine screen, characterized in that Including the following steps: Step S1: Obtain the welding machine screen image, environmental perception data, and user facial image; calculate the light intensity of the environmental perception data to generate environmental light intensity data; perform glare analysis on the environmental perception data through the environmental light intensity data to generate environmental glare impact data; Step S2: Perform environmental perception brightness adjustment on the welding machine screen image based on the environmental glare impact data to generate environmental perception brightness adjustment data; perform visual perception feature analysis on the user facial image based on the environmental perception brightness adjustment data to generate user visual perception feature data; Step S3: Use computer vision technology to perform eye tracking on the user facial image to generate user eye tracking data; Calculate the blink frequency of the user eye tracking data to generate blink frequency data; perform pupil constriction analysis on the user eye tracking data based on the blink frequency data to generate pupil deformation data; Step S4: Perform pupil deformation-brightness correlation analysis on the user visual perception feature data based on the pupil deformation data to construct a pupil deformation-brightness response curve; Perform adaptive brightness adjustment processing on the environmental perception brightness adjustment data using a brightness-visual response model to generate visually perceived brightness adjustment data; Calculate the visual fatigue of the user facial image based on the blink frequency data and pupil deformation data to generate a user visual fatigue index; Step S5: Identify the eye fixation points of the user eye tracking data to generate eye fixation point position data; Perform fixation frequency analysis on the welding machine screen image through the eye fixation point position data to generate user fixation frequency data; Perform fixation area segmentation on the welding machine screen image through the eye fixation point position data and user fixation frequency data to generate a user fixation area segmented image; Step S6: Perform regional brightness dynamic adjustment analysis on the user fixation area segmented image according to the user visual fatigue index to generate regional brightness dynamic adjustment data; Perform visual optimization on the welding machine screen image using the regional brightness dynamic adjustment data to generate visually optimized dynamic brightness adjustment data; Perform brightness control decision analysis using the visually optimized dynamic brightness adjustment data and visually perceived brightness adjustment data, construct a brightness control decision engine, and execute brightness control operations.

2. The method for controlling the display brightness of the welder screen according to claim 1, wherein The specific steps of Step S1 are: Step S11: Obtain the welding machine screen image, environmental perception data, and user facial image; Step S12: Perform light path tracing on the environmental perception data to generate light path tracing data; Step S13: Perform environmental light distribution analysis on the environmental perception data according to the light path tracing data to generate environmental light distribution data; Step S14: Calculate the light intensity of the environmental light distribution data to generate environmental light intensity data; Step S15: Perform wavelength color difference analysis on the environmental light intensity data to generate light wavelength color difference data; Step S16: Perform glare analysis on the environmental perception data through the light wavelength color difference data to generate environmental glare impact data.

3. The method for controlling the display brightness of the welding machine screen according to claim 1, wherein, The specific steps of Step S2 are: Step S21: Compare the environmental glare impact data based on a preset environmental glare threshold index. When the preset environmental glare threshold index is less than the environmental glare impact data, perform brightness enhancement processing on the welder screen image to generate environmental perception brightness adjustment data; Step S22: When the preset environmental glare threshold index is greater than the environmental glare impact data, perform brightness reduction processing on the welder screen image to generate environmental perception brightness adjustment data; Step S23: Detect the line-of-sight deviation of the user's facial image to generate line-of-sight deviation data; Step S24: Analyze the visual perception characteristic of the line-of-sight deviation data based on the environmental perception brightness adjustment data to generate user visual perception characteristic data.

4. The method for controlling the display brightness of the welder screen according to claim 1, characterized in that, The specific steps of Step S3 are as follows: Step S31: Use computer vision technology to perform eye positioning on the user's facial image to generate user eye positioning point data; Step S32: Perform continuous inter-frame phase matching on the user's facial image based on the user eye positioning point data to generate eye inter-frame matching data; Step S33: Reconstruct the viewpoint movement trajectory of the eye inter-frame matching data to generate an eye movement trajectory curve; Step S34: Perform eye tracking on the user's facial image according to the eye movement trajectory curve to generate user eye tracking data; Step S35: Calculate the blink frequency of the user eye tracking data to generate blink frequency data; Step S36: Analyze the pupil constriction of the user eye tracking data based on the blink frequency data to generate pupil deformation data.

5. The method for controlling the display brightness of the welder screen according to claim 4, wherein, The specific steps of Step S36 are as follows: Step S361: Analyze the light intensity response of the user eye tracking data based on the blink frequency data to generate eye light intensity response data; Step S362: Analyze the pupil constriction rate of the user eye tracking data according to the eye light intensity response data to generate pupil constriction rate data; Step S363: Analyze the constriction time of the pupil constriction rate data to generate pupil constriction time data; Step S364: Analyze the dynamic constriction change of the user eye tracking data based on the pupil constriction time data to generate pupil dynamic constriction data; Step S365: Calculate the constriction amplitude of the pupil dynamic constriction data to generate pupil deformation data.

6. The method for controlling the display brightness of the welder screen according to claim 1, wherein The specific steps of Step S4 are as follows: Step S41: Analyze the pupil deformation-brightness correlation of the user visual perception characteristic data based on the pupil deformation data to generate pupil deformation-brightness response data; Step S42: Fit the correlation curve of the pupil deformation-brightness response data to construct a pupil deformation-brightness response curve; Step S43: Use the brightness-visual response model to perform adaptive brightness adjustment processing on the environmental perception brightness adjustment data to generate visual perception brightness adjustment data; Step S44: Analyze the blink interval difference of the user's facial image according to the blink frequency data to generate blink interval difference data; Step S45: Analyze the constriction efficiency of the pupil deformation data to generate user pupil constriction sensitivity data; Step S46: Calculate the visual fatigue of the user's pupil contraction sensitivity data using the user visual fatigue calculation formula based on the blink interval difference data, and generate the user visual fatigue index.

7. The method for controlling the display brightness of the welder screen according to claim 6, characterized in that, The specific user visual fatigue calculation formula in Step S46 is as follows: Where, V is the user visual fatigue index, T is the user device usage time, t is the screen resolution, D is the complexity of the viewing point movement trajectory, L is the screen illumination intensity, I is the user blink frequency, F is the pupil contraction efficiency, C is the user pupil deformation response rate, A is the user pupil contraction amplitude, P is the viewing point movement speed, H is the difference value of the pupil sizes of the left and right eyes, R is the pupil size change rate, and S is the number of head movements.

8. The method for controlling the display brightness of the welding machine screen according to claim 1, wherein, The specific steps of Step S5 are as follows: Step S51: Perform visual focus convergence processing on the user's eye tracking data to generate visual focus area data; Step S52: Identify the eye fixation points from the visual focus area data to generate eye fixation point position data; Step S53: Analyze the fixation frequency of the welding machine screen image based on the eye fixation point position data to generate the user fixation frequency data; Step S54: Construct an eye fixation heat map for the eye fixation point position data based on the user fixation frequency data to construct an eye fixation heat map; Step S55: Divide the welding machine screen image into fixation areas based on the eye fixation heat map to generate the user fixation area segmented image.

9. The method for controlling the display brightness of the welder screen according to claim 1, characterized in that, The specific steps of Step S6 are as follows: Step S61: Segment the non-fixation area of the welding machine screen image based on the user fixation area segmented image to generate a fixation area image and a non-fixation area image; Step S62: Compare the user visual fatigue index with a preset user visual fatigue threshold index. When the preset user visual fatigue threshold index is less than or equal to the user visual fatigue index, perform a region brightness increase process on the fixation area image to generate fixation area brightness adjustment data; Step S63: Perform a region brightness decrease process on the non-fixation area image to generate non-fixation area brightness adjustment data; Step S64: Perform a region brightness dynamic adjustment analysis on the fixation area brightness adjustment data and the non-fixation area brightness adjustment data based on the user visual fatigue index to generate region brightness dynamic adjustment data; Step S65: Perform a color temperature optimization analysis on the welding machine screen image using the region brightness dynamic adjustment data to generate color temperature optimization data; Step S66: Perform a visual optimization on the region brightness dynamic adjustment data using the color temperature optimization data to generate visual optimization dynamic brightness adjustment data; Step S67: Perform a brightness control decision analysis using the visual optimization dynamic brightness adjustment data and the visual perception brightness adjustment data, construct a brightness control decision engine, and execute the brightness control operation.

10. A welding machine screen display brightness control system, characterized in that, For implementing the welding machine screen display brightness control method as described in claim 1, it includes: An ambient light module, configured to obtain the welding machine screen image, ambient perception data, and the user's facial image; calculate the illumination intensity of the ambient perception data to generate ambient illumination intensity data; perform glare analysis on the ambient perception data based on the ambient illumination intensity data to generate ambient glare impact data; A visual perception module, which is used to perform ambient perception brightness adjustment on the welder screen image based on the ambient glare impact data to generate ambient perception brightness adjustment data; perform visual perception feature analysis on the user's facial image based on the ambient perception brightness adjustment data to generate user visual perception feature data; A pupil deformation module, which is used to perform eye tracking on the user's facial image using computer vision technology to generate user eye tracking data; calculate the blink frequency of the user's eye tracking data to generate blink frequency data; perform pupil constriction analysis on the user's eye tracking data based on the blink frequency data to generate pupil deformation data; A visual fatigue module, which is used to perform pupil deformation-brightness correlation analysis on the user's visual perception feature data based on the pupil deformation data to construct a pupil deformation-brightness response curve; perform adaptive brightness adjustment processing on the ambient perception brightness adjustment data using a brightness-visual response model to generate visual perception brightness adjustment data; calculate the visual fatigue of the user's facial image based on the blink frequency data and the pupil deformation data to generate a user visual fatigue index; A fixation area segmentation module, which is used to identify the eye fixation points of the user's eye tracking data to generate eye fixation point position data; perform fixation frequency analysis on the welder screen image through the eye fixation point position data to generate user fixation frequency data; segment the welder screen image into fixation areas through the eye fixation point position data and the user fixation frequency data to generate a user fixation area segmented image; A regional brightness dynamic adjustment module, which is used to perform regional brightness dynamic adjustment analysis on the user fixation area segmented image according to the user visual fatigue index to generate regional brightness dynamic adjustment data; perform visual optimization on the welder screen image using the regional brightness dynamic adjustment data to generate visual optimization dynamic brightness adjustment data; perform brightness control decision analysis using the visual optimization dynamic brightness adjustment data and the visual perception brightness adjustment data to construct a brightness control decision engine to execute brightness control operations.

Images