Optical adjustment method and device, head-mounted display equipment and storage medium

Abstract

The invention discloses an optical adjustment method and device, head-mounted display equipment and a storage medium, and relates to the technical field of head-mounted display equipment. The optical adjustment method is applied to the head-mounted display device, the head-mounted display device comprises a liquid lens array and a scoring module, and the method comprises the following steps: after the curvature of the liquid lens array is adjusted based on a target optical parameter of the head-mounted display device, determining a target comfort score of a wearer through the scoring module, the target optical parameters are obtained by predicting the optical parameter prediction model based on target biological characteristic data of the wearer, and the optical parameter prediction model is obtained by taking the biological characteristic data as a sample and taking the optical parameters as label training; the curvature of the liquid lens array is calibrated based on the target comfort score. According to the invention, the VAC effect of the head-mounted display device can be reduced.

Description

Technical Field

[0001] The present application relates to the technical field of head-mounted display devices, and in particular to an optical adjustment method, device, head-mounted display device, and storage medium. Background Art

[0002] With the rapid development of head-mounted display (HMD) technology, the optimization of HMD performance and user experience has become the focus of industry research.

[0003] Traditional head-mounted displays (HMDs) rely primarily on a fixed focal length design or manual user adjustment for visual adjustment. This static adjustment mode cannot flexibly adapt to the individual biometric differences of different users, such as key parameters like pupil distance and corneal curvature. Due to the significant differences in biometric characteristics between individuals, fixed focal length or manual adjustment often makes it difficult to achieve precise matching, which in turn leads to a significant increase in visual convergence-accommodation conflict (VAC effect). The VAC (Vergence-Accommodation Conflict) effect manifests itself as the user's eyes cannot naturally converge on the same focal point when trying to focus on objects in a virtual scene, causing visual fatigue, dizziness, and other discomfort.

[0004] Therefore, how to reduce the VAC effect of head-mounted display devices has become an urgent problem to be solved by those skilled in the art.

[0005] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0006] The main purpose of this application is to provide an optical adjustment method, device, head-mounted display device and storage medium, aiming to solve the technical problem of how to reduce the VAC effect of the head-mounted display device.

[0007] To achieve the above objectives, the present application proposes an optical adjustment method, which is applied to a head-mounted display device, wherein the head-mounted display device includes a liquid lens array and a scoring module, wherein the scoring module includes at least one of an automatic scoring unit and an active scoring unit, wherein the automatic scoring unit is configured to determine a first comfort score based on a wearer's target physiological signal, and the active scoring unit is configured to receive a second comfort score input by the wearer. The method comprises: After adjusting the curvature of the liquid lens array based on target optical parameters of the head-mounted display device, determining a target comfort score for the wearer by the scoring module, wherein the target optical parameters are predicted by an optical parameter prediction model based on target biometric data of the wearer, the optical parameter prediction model being trained using biometric data as samples and optical parameters as labels, and the target comfort score is determined based on the first comfort score and / or the second comfort score; The curvature of the liquid lens array is calibrated based on the target comfort score.

[0008] In one embodiment, before the step of calibrating the curvature of the liquid lens array based on the target comfort score, the method further comprises: Determining whether the comfort score is less than a first preset score; When it is determined that the comfort score is less than the first preset score, the step of calibrating the curvature of the liquid lens array based on the target comfort score is performed.

[0009] In one embodiment, the step of calibrating the curvature of the liquid lens array based on the target comfort score includes: calibrating the target optical parameters based on the target comfort score; According to the calibrated target optical parameters, the control voltage of the liquid lens array is adjusted to adjust the curvature of the liquid lens array.

[0010] In one embodiment, the target optical parameters include a focal length compensation value, a lens curvature, and a dispersion compensation coefficient, and the step of adjusting the control voltage of the liquid lens array according to the calibrated target optical parameters includes: Calculating a curvature correction term of the liquid lens array according to the calibrated focal length compensation value and the calibrated dispersion compensation coefficient; Adding the calibrated lens curvature to the curvature correction term to obtain a target curvature of the liquid lens array; Obtaining an initial curvature of the liquid lens array, and calculating a curvature difference between the initial curvature and the target curvature; The target voltage of the liquid lens array is calculated according to the curvature difference and a preset curvature-voltage coefficient, and the control voltage of the liquid lens array is adjusted according to the target voltage.

[0011] In one embodiment, the head-mounted display device further includes an electrochromic layer. After the step of calibrating the target optical parameters based on the target comfort score, the method further includes: Calculating the target dispersion of the electrochromic layer according to the calibrated dispersion compensation coefficient; The light transmittance of the electrochromic layer is adjusted based on the target dispersion and the initial dispersion of the electrochromic layer.

[0012] In one embodiment, the head-mounted display device further includes a biometric feature acquisition module, wherein the biometric feature acquisition module includes a camera unit and an eye movement detection unit. Before the step of adjusting the curvature of the liquid lens array based on the target optical parameters of the head-mounted display device, the method further includes: Acquiring an eye image of the wearer through the camera unit; acquiring the pupil distance and corneal curvature of the wearer based on the eyeball image; Acquiring the wearer's gaze point coordinates and eye movement speed through the eye movement detection unit; Using the interpupillary distance, the corneal curvature, the gaze point coordinates, and the eye movement velocity as target biometric data of the wearer; The target biometric data is input into the optical parameter prediction model to obtain the target optical parameters of the head-mounted display device.

[0013] In one embodiment, the method further comprises: When the target comfort score is less than a first preset score, determining a loss function of the light parameter prediction model according to the target comfort score; Based on a preset gradient descent algorithm and the loss function, the trainable parameters of the optical parameter prediction model are updated.

[0014] In one embodiment, after the step of calibrating the curvature of the liquid lens array based on the target comfort score, the method further comprises: Counting the number of curvature calibrations of the liquid lens array; If the number of curvature calibrations is less than or equal to the preset number, returning to the step of determining the wearer's target comfort score by the scoring module; When the number of curvature calibration times is greater than the preset number, the method returns to the step of acquiring the wearer's eye image through the camera unit, and sets the number of curvature calibration times to zero.

[0015] In addition, to achieve the above objectives, the present application further proposes an optical adjustment device, which is provided in a head-mounted display device, wherein the head-mounted display device includes a liquid lens array and a scoring module, wherein the scoring module includes at least one of an automatic scoring unit and an active scoring unit, wherein the automatic scoring unit is used to determine a first comfort score based on a wearer's target physiological signal, and the active scoring unit is used to receive a second comfort score input by the wearer, and the device includes: a scoring module, configured to determine, via the scoring module, a target comfort score for the wearer after adjusting the curvature of the liquid lens array based on target optical parameters of the head-mounted display device, wherein the target optical parameters are predicted by an optical parameter prediction model based on target biometric data of the wearer, the optical parameter prediction model being trained using biometric data as samples and optical parameters as labels, and the target comfort score being determined based on the first comfort score and / or the second comfort score; A calibration module is configured to calibrate the curvature of the liquid lens array based on the target comfort score.

[0016] In addition, to achieve the above-mentioned purpose, the present application also proposes a head-mounted display device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the optical adjustment method described above.

[0017] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the optical adjustment method described above are implemented.

[0018] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the optical adjustment method described above are implemented.

[0019] The present invention provides an optical adjustment method, apparatus, head-mounted display (HMD) device, and storage medium, relating to the technical field of HMD devices. The optical adjustment method is applied to a HMD device, the HMD device comprising a liquid lens array and a scoring module, the scoring module comprising at least one of an automatic scoring unit and an active scoring unit, wherein the automatic scoring unit is configured to determine a first comfort score based on a target physiological signal of a wearer, and the active scoring unit is configured to receive a second comfort score input by the wearer. The method comprises: adjusting the curvature of the liquid lens array based on target optical parameters of the HMD device, and then determining the wearer's target comfort score via the scoring module, wherein the target optical parameters are predicted by an optical parameter prediction model based on target biometric data of the wearer, the optical parameter prediction model being trained using the biometric data as samples and the optical parameters as labels, and the target comfort score being determined based on the first comfort score and / or the second comfort score; and calibrating the curvature of the liquid lens array based on the target comfort score.

[0020] The present embodiment introduces a scoring module to perform real-time evaluation of the wearer's comfort and dynamically calibrates the curvature of the liquid lens array based on this evaluation result (i.e., a target comfort score), thereby effectively reducing the visual convergence-accommodation conflict (VAC effect) in the head-mounted display device and improving the user experience. Specifically, based on predicting target optical parameters based on the wearer's target biometric data and adjusting the curvature of the liquid lens array, the present embodiment further utilizes the scoring module to obtain the wearer's first comfort score (determined by an automatic scoring unit based on physiological signals such as eye movement and blink frequency) and / or second comfort score (user-input feedback), and comprehensively forms a target comfort score. Based on this score, the system performs feedback analysis on the current optical state. If it is determined that the VAC effect is still significant, the curvature of the liquid lens array is dynamically calibrated and optimized, so that the optical system better meets the user's actual visual needs. This closed-loop adaptive adjustment mechanism not only makes up for the defect that static adjustment cannot adapt to individual differences, but also improves the accuracy and personalization of optical adjustment by introducing a comfort evaluation system that combines subjective and objective factors, thereby significantly alleviating visual fatigue and dizziness caused by the VAC effect, and enhancing the immersion and comfort of the head-mounted display device. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 Schematic diagram of the optical adjustment method according to an embodiment of the present application; Figure 2 Schematic diagram of a scenario of an optical adjustment method in an embodiment of the present application; Figure 3 This is a schematic structural diagram of the optical adjustment method in an embodiment of the present application; Figure 4 This is a schematic diagram of the module structure of the optical adjustment device in an embodiment of the present application; Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the optical adjustment method in the embodiment of the present application.

[0024] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0026] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0027] With the rapid development of head-mounted display (HMD) technology, the optimization of HMD performance and user experience has become the focus of industry research.

[0028] Traditional head-mounted displays (HMDs) rely primarily on a fixed focal length design or manual user adjustment for visual adjustment. This static adjustment mode cannot flexibly adapt to the individual biometric differences of different users, such as key parameters like pupil distance and corneal curvature. Due to the significant differences in biometric characteristics between individuals, fixed focal length or manual adjustment often makes it difficult to achieve precise matching, leading to a significant increase in visual convergence accommodation conflict (VAC effect). The VAC effect occurs when the user's eyes fail to naturally converge on the same focal point when trying to focus on objects in a virtual scene, causing visual fatigue, dizziness, and other discomfort.

[0029] Therefore, how to reduce the VAC effect of head-mounted display devices has become an urgent problem to be solved by those skilled in the art.

[0030] In response to the above problems, an embodiment of the present application provides an optical adjustment method, which is applied to a head-mounted display device, wherein the head-mounted display device includes a liquid lens array and a scoring module, the scoring module including at least one of an automatic scoring unit and an active scoring unit, wherein the automatic scoring unit is used to determine a first comfort score based on the wearer's target physiological signal, and the active scoring unit is used to receive a second comfort score input by the wearer. The method includes: after adjusting the curvature of the liquid lens array based on the target optical parameters of the head-mounted display device, determining the wearer's target comfort score through the scoring module, wherein the target optical parameters are predicted by an optical parameter prediction model based on the wearer's target biometric data, the optical parameter prediction model is trained using the biometric data as samples and the optical parameters as labels, and the target comfort score is determined based on the first comfort score and / or the second comfort score; and based on the target comfort score, calibrating the curvature of the liquid lens array.

[0031] The present embodiment introduces a scoring module to perform real-time evaluation of the wearer's comfort and dynamically calibrates the curvature of the liquid lens array based on this evaluation result (i.e., a target comfort score), thereby effectively reducing the visual convergence-accommodation conflict (VAC effect) in the head-mounted display device and improving the user experience. Specifically, based on predicting target optical parameters based on the wearer's target biometric data and adjusting the curvature of the liquid lens array, the present embodiment further utilizes the scoring module to obtain the wearer's first comfort score (determined by an automatic scoring unit based on physiological signals such as eye movement and blink frequency) and / or second comfort score (user-input feedback), and comprehensively forms a target comfort score. Based on this score, the system performs feedback analysis on the current optical state. If it is determined that the VAC effect is still significant, the curvature of the liquid lens array is dynamically calibrated and optimized, so that the optical system better meets the user's actual visual needs. This closed-loop adaptive adjustment mechanism not only makes up for the defect that static adjustment cannot adapt to individual differences, but also improves the accuracy and personalization of optical adjustment by introducing a comfort evaluation system that combines subjective and objective factors, thereby significantly alleviating visual fatigue and dizziness caused by the VAC effect, and enhancing the immersion and comfort of the head-mounted display device.

[0032] The head-mounted display device in the embodiments of this application may include, but is not limited to, mixed reality (MR) devices (e.g., MR glasses or MR helmets), augmented reality (AR) devices (e.g., AR glasses or AR helmets), virtual reality (VR) devices (e.g., VR glasses or VR helmets), extended reality (XR) devices, or some combination thereof, and the like. In this embodiment, for ease of description, the following description uses the head-mounted display device as the execution subject.

[0033] Based on this, the embodiment of the present application provides an optical adjustment method, referring to Figure 1 , Figure 1 Schematic diagram of the optical adjustment method in an embodiment of the present application.

[0034] In this embodiment, an optical adjustment method is applied to a head-mounted display device, which includes a liquid lens array and a scoring module. The scoring module includes at least one of an automatic scoring unit and an active scoring unit. The automatic scoring unit is configured to determine a first comfort score based on a wearer's target physiological signal, and the active scoring unit is configured to receive a second comfort score input by the wearer. The optical adjustment method includes steps S100 to S200: Step S100, after adjusting the curvature of the liquid lens array based on the target optical parameters of the head-mounted display device, determining the wearer's target comfort score through a scoring module; Among them, the target optical parameters are predicted by the optical parameter prediction model based on the wearer's target biometric data. The optical parameter prediction model is trained with biometric data as samples and optical parameters as labels. The target comfort score is determined based on the first comfort score and / or the second comfort score.

[0035] In this embodiment, the head-mounted display device refers to a head-mounted display device used for AR (Augmented Reality), VR (Virtual Reality) or MR (Mixed Reality) experience, which provides users with an immersive visual experience through various built-in sensors and display technologies.

[0036] A liquid lens array is a special lens system whose lens shape (curvature) can be dynamically adjusted by varying the voltage applied to it. This feature allows it to adapt to different focal length requirements, thereby improving the user's visual experience and reducing visual fatigue. Furthermore, the curvature can be adjusted by adjusting the position of each micro-liquid lens in the liquid lens array.

[0037] The scoring module is a component within the headset responsible for assessing the wearer's comfort level. This scoring module includes an automatic scoring unit and / or an active scoring unit. The automatic scoring unit utilizes sensors built into the headset to collect the wearer's target physiological signals (such as blink rate and skin conductance) and calculates a primary comfort score using a preset algorithm. This process requires no direct user interaction, enabling automated monitoring of the wearer's comfort. The active scoring unit allows the wearer to enter a secondary comfort score based on their subjective experience through the device interface, allowing users to express their satisfaction with their current visual experience.

[0038] It's easy to understand that the first comfort score is automatically calculated by the automatic scoring unit based on the wearer's target physiological signals (such as blink rate and skin conductance). This scoring method does not rely on active user input, but instead indirectly reflects their visual comfort by monitoring their physical reactions. For example, if the wearer's blink rate increases significantly or their skin conductance rises during use, this may indicate that they are experiencing some degree of discomfort, resulting in a lower first comfort score.

[0039] The second comfort rating is derived from subjective feedback directly input by the wearer via the active rating unit. Wearers can express their satisfaction with their visual experience by entering a specific score or selecting options through the device's interface, based on factors such as visual clarity and the presence of vertigo. This approach allows users to directly participate in the comfort assessment process, providing valuable subjective feedback.

[0040] The target comfort score is determined based on the first comfort score and / or the second comfort score. When only the automatic scoring unit is enabled, the target comfort score can be the first comfort score, or the product of the first comfort score and the first preset weight coefficient. When only the active scoring unit is enabled, the target comfort score can be the second comfort score, or the product of the second comfort score and the second preset weight coefficient. When the automatic scoring unit and the active scoring unit are enabled at the same time, the target comfort score can be calculated by taking the arithmetic average or weighted average of the first comfort score and the second comfort score. Among them, the first preset weight coefficient and the second preset weight coefficient can be flexibly set according to the actual needs of the user or calibrated in advance according to the actual situation of the system, and this embodiment does not specifically limit this.

[0041] It's worth noting that when both the automatic and active scoring units are enabled, the target comfort score takes into account not only the objective data derived from physiological signal analysis (the first comfort score) but also the wearer's subjective feedback (the second comfort score). By combining these two different types of scores, the target comfort score can more accurately determine the wearer's actual experience quality, comprehensively reflecting the wearer's overall visual comfort in the current display state. This allows this embodiment to more precisely adjust the curvature of the liquid lens array to reduce the VAC effect and improve wearer comfort, ensuring an optimal visual experience for the wearer while minimizing visual fatigue and other discomfort symptoms caused by individual differences.

[0042] It should be noted that biometric data refers to specific physiological indicators related to the visual convergence-accommodation conflict (VAC effect). This data is crucial for reducing the VAC effect of head-mounted displays (HMDs) to reduce visual fatigue and discomfort. Specifically, biometric data includes but is not limited to the following types of information: Inter-Pupillary Distance (IPD): The distance between the centers of the pupils of each eye. This parameter is important for ensuring that virtual images are correctly focused on the user's retina.

[0043] Corneal curvature: The curvature of the cornea affects the path of light after entering the eye. Differences in corneal curvature between individuals can cause inaccurate focus or distorted vision.

[0044] Gaze point coordinates: The coordinates of the specific location on the screen where the user is looking. This helps us understand the user's gaze direction and its changes, thereby adjusting the position and clarity of displayed content.

[0045] Eye velocity: The speed at which the eyes move can reflect how the user's attention changes during browsing or interaction. Rapid eye movements may indicate that the user is experiencing some form of discomfort or trying to find a more comfortable perspective.

[0046] Optical parameters refer to those used to adjust the curvature of the liquid lens array to reduce the VAC effect and minimize visual discomfort. These parameters directly impact image clarity, color reproduction, and user visual comfort, and are crucial for mitigating the convergence-accommodation conflict (VAC effect). Specifically, optical parameters include but are not limited to the following aspects: Focus Compensation: This adjustment is made to compensate for variations in the wearer's biometrics (such as interpupillary distance and corneal curvature) that can cause actual focal length to deviate from the ideal focal length. By accurately calculating and applying this focus compensation, we ensure clear and accurate imaging, tailored to the needs of individual users.

[0047] Lens curvature: A numerical value describing the curvature of a lens surface, which determines how light is refracted and focused through the lens. Different lens curvatures affect image magnification and focus, requiring personalized adjustments based on the user's specific biometric data to achieve the optimal visual experience.

[0048] Dispersion compensation: This factor corrects chromatic aberration caused by the different refractive indices of different colored light in a lens. Proper dispersion compensation can reduce the appearance of color fringing or blurred areas, improving image color reproduction and clarity.

[0049] Other related parameters: such as luminous flux adjustment, contrast enhancement factor, etc. These parameters work together to optimize display quality, so that the virtual scene is presented to the user as naturally as possible, reducing visual fatigue and other discomfort.

[0050] In this embodiment, the optical parameter prediction model is a neural network model trained by mapping the relationship between massive amounts of biometric data (such as interpupillary distance, corneal curvature, eye movement velocity, and gaze point coordinates) and optimal optical parameters (such as focal length compensation, lens curvature, and dispersion compensation coefficient). This model extracts latent spatial associations from the biometric data and outputs optical parameters tailored to the user's current physiological state.

[0051] In this embodiment, the optical parameter prediction model predicts the optimal optical parameters (i.e., target optical parameters) that match the target biometric data based on the collected biometric data of the wearer (i.e., target biometric data). This allows this embodiment to accurately adjust the curvature of the liquid lens array based on the target optical parameters, ensuring that the head-mounted display device can provide the wearer with a more personalized wearing experience, maximize the user's visual comfort and immersion, and effectively reduce the negative impact of the VAC effect.

[0052] It should be noted that in this embodiment, the head-mounted display device has a built-in biometric data collection module. This biometric data collection module may include multiple hardware modules for collecting different types of biometric data, possessing biometric recognition capabilities and used to collect multiple key biometric data of the wearer. Upon detecting that the user is correctly wearing the head-mounted display device, this biometric data collection module can automatically activate the biometric data collection function, collect the wearer's biometric data related to the VAC effect, and output this data to the optical parameter prediction model to predict the target optical parameters required to adjust the curvature of the liquid lens array.

[0053] For example, in a feasible embodiment, the head-mounted display device further includes a biometric feature acquisition module, which includes a camera unit and an eye movement detection unit. Before adjusting the curvature of the liquid lens array based on the target optical parameters of the head-mounted display device, the optical adjustment method may further include steps S10 to S50: Step S10, obtaining an eye image of the wearer through a camera unit; It should be noted that, in this embodiment, the biometric feature acquisition module may include a camera unit and an eye movement detection unit. The camera unit may be used to capture the wearer's eye image, and the eye movement detection unit may be used to track the wearer's eye movement data.

[0054] In this embodiment, when the wearer correctly puts on the head-mounted display device, the camera unit starts working. The camera unit usually uses a high-resolution camera with automatic focus and light compensation functions to ensure that clear and accurate eye images can be obtained under different lighting conditions. During the acquisition process, the camera unit will capture the wearer's eye area in real time and obtain a series of continuous eye image frames. These image frames contain eye appearance information, such as pupil size, position, corneal morphology and other characteristics.

[0055] Step S20, obtaining the wearer's pupillary distance and corneal curvature based on the eyeball image; In this embodiment, after capturing the image of the eyeball, the image processing algorithm built into the head-mounted display device analyzes and processes the eyeball image captured by the camera unit to extract biometric data such as pupil distance and corneal curvature.

[0056] As an example, specifically, the algorithm first preprocesses the eye image, including image enhancement, edge detection and other operations to highlight the outline of the pupil. Then, it uses image recognition technology to determine the center positions of the two pupils and calculate the distance between them, which is the pupil distance.

[0057] Then, the corneal morphology information in the eyeball image is used, combined with the preset corneal model and mathematical algorithm, to calculate the corneal curvature radius. Corneal curvature is an important indicator to measure the degree of corneal curvature and is crucial for the optical design of head-mounted display devices.

[0058] Step S30, obtaining the wearer's gaze point coordinates and eye movement speed through the eye movement detection unit; In this embodiment, the eye movement detection unit calculates the coordinates of the wearer's current gaze point based on the eyeball's movement trajectory and pupil position. The gaze point coordinates reflect the wearer's visual focus. In addition to the gaze point coordinates, the eye movement detection unit can also measure the speed of the eyeball's movement, i.e., eye velocity. Changes in eye velocity can reflect information such as the wearer's level of attention and visual search efficiency.

[0059] Step S40, using the pupil distance, corneal curvature, gaze point coordinates and eye movement velocity as the wearer's target biometric data; In step S50 , the target biometric data is input into an optical parameter prediction model to obtain target optical parameters of the head-mounted display device.

[0060] In this embodiment, the optical parameter prediction model is based on a GAN (Generative Adversarial Network) model, an LSTM (Long Short Term Memory) model, a CNN (Convolutional Neural Network) model or an RNN (Recurrent Neural Network) model as a neural network model. During the model training phase, a large amount of biometric data of people of different ages, genders, etc., and a sample data set of optical parameters with the best wearing experience and the best visual comfort corresponding to the current biological signals are used. Through a deep learning algorithm, the optical parameter prediction model can learn the complex mapping relationship between biometric data and optical parameters.

[0061] In this embodiment, the head-mounted display device inputs the collected target biometric data as input data into the optical parameter prediction model. The optical parameter prediction model quickly processes and analyzes the input target biometric data, and uses the mapping relationship learned internally to predict and output target optical parameters that match the wearer's biometric data. These target optical parameters directly determine the VAC effect of the head-mounted display device.

[0062] The optical parameter prediction model can be one of a GAN (Generative Adversarial Network) model, an LSTM (Long Short Term Memory) model, a CNN (Convolutional Neural Network) model, and an RNN (Recurrent Neural Network) model, and this embodiment does not make any specific limitations on this.

[0063] As an example, the optical parameter prediction model can be a GAN (Generative Adversarial Network) model, which includes a generator and a discriminator. The generator includes an input layer (10-dimensional biological feature vector), a fully connected layer (512 nodes, Leaky ReLU), a fully connected layer (256 nodes), and an output layer (3-dimensional optical parameters: focal length compensation value f, lens curvature r, and dispersion coefficient δ).

[0064] The discriminator includes an input layer (3D optical parameters), a convolutional layer (64 filters, stride 2), a fully connected layer (128 nodes), and a binary classification output (true / generated probability). Among the multiple inference results output by the output generator, the set of data with the highest true / generated probability is selected as the final output result.

[0065] Furthermore, in a feasible implementation manner, before the above step S20, the method may further include steps A10 to A20: Step A10: if the target biometric data does not conform to the preset normal range, re-collect the target biometric data; In this embodiment, after collecting the wearer's target biometric data, the head-mounted display device performs a preliminary validity check on this data. The preset normal range is determined based on a large amount of sample data and actual application requirements, covering the range of biometric data under normal conditions for different user groups. For example, a reasonable interval is set for pupillary distance, and a corresponding normal value range is also set for corneal curvature.

[0066] When the headset determines that the collected target biometric data is not within the preset normal range, there may be a variety of reasons, such as sensor failure, interference from the collection environment, and improper wearing of the wearer. At this time, the headset will trigger the re-collection mechanism, informing the wearer through interface prompts or sound prompts to re-collect the biometric data. During the re-collection process, the biometric collection module will start again and obtain new target biometric data according to the same collection process and standards. The headset will re-verify the legitimacy of the re-collected data until the collected data is within the preset normal range, ensuring the accuracy and reliability of the data used in subsequent steps.

[0067] Taking the interpupillary distance (IPD) as an example, the normal range preset for the head-mounted display device can not only include the statistical mean ±2σ interval, but also introduce quantile corrections based on the user's age group (such as allowing ±3σ fluctuations for child users), dynamic compensation for the device wearing angle (±1mm tilt tolerance), and calibration coefficients for real-time ambient light effects (such as the IPD value may shrink by 0.5-1mm in a strong light environment).

[0068] When the head-mounted display device detects through the verification algorithm that the collected data exceeds the preset range, it will trigger a multi-dimensional abnormality diagnosis mechanism. First, the device analyzes the sensor's own status parameters (such as infrared light source intensity, camera exposure time, temperature drift, etc.), and compares them with historical benchmark values ​​to determine whether there is a hardware failure; secondly, it combines environmental sensor data (such as light intensity, humidity, and electromagnetic interference intensity) to evaluate external interference factors; finally, by analyzing the wearer's head posture (accelerometer / gyroscope data), device wearing pressure distribution (pressure sensor array data), and user interaction behavior (such as blink frequency, nystagmus pattern), it determines whether there is improper wearing (such as device slipping, light leakage, pressure on the eye socket) or user physiological abnormalities (such as fatigue, drug effects).

[0069] If an anomaly is determined to be retryable (such as a brief environmental disturbance or a minor misalignment), the headset will immediately initiate a recollection mechanism. The device will use multimodal interaction methods, including visual cues (such as pupil position calibration animations and device wearing angle diagrams), auditory cues (multilingual voice commands, ambient sound compensation), and haptic feedback (mild vibration prompts), to guide the wearer to adjust the device position, clean the collection area, or re-enter the collection state. During the recollection process, the biometric collection module (including the infrared camera array, iris scanner, eye tracker, etc.) will operate in a higher-precision mode, enable self-calibration algorithms (such as autofocus, white balance adjustment, and distortion correction), and increase data redundancy (such as taking the median after collecting three sets of data).

[0070] In step A20, the target biometric data is input into a preset convolutional network to obtain vectorized target biometric data.

[0071] In this embodiment, after the target biometric data passes the legality verification, it needs to be vectorized to facilitate subsequent processing and analysis in the GAN model. The preset convolutional network is a deep learning model designed specifically for this purpose.

[0072] Specifically, after collecting the wearer's biometric data, in order to facilitate the analysis and calculation of the subsequent model, the biometric data needs to be preprocessed. First, the abnormal values ​​in the biometric data are removed. For example, when the IPD does not meet the range of 54 to 74 mm, it is considered abnormal data and needs to be re-measured. After all the abnormal data are removed, the parameters such as IPD and corneal curvature are normalized and mapped to the interval of [0, 1]. Then, the multimodal data is synchronized through the timestamp of the collected data, and each data including the user's historical comfort score is input into the convolutional network for feature extraction, and finally a 10-dimensional feature vector is output. , where X IPD : IPD data; X cornea : corneal curvature data; X gaze : Gaze point coordinates, 10-dimensional feature vector includes: 1) interpupillary distance (IPD, 1 dimension); 2) corneal curvature (3D, extracted through iris image features); 3) gaze point coordinates (2D, x / y axis normalized values); 4) eye movement velocity (2-dimensional, horizontal / vertical components); 5) User historical comfort rating (2-dimensional, sliding average of the last 5 ratings).

[0073] It is worth mentioning that the data input to the light parameter prediction model may also include the user's historical comfort rating. Specifically, step S50 may further include step S51: Step S51, obtaining multiple historical reference scores according to a preset window; In this embodiment, in order to more comprehensively evaluate the wearer's comfort perception, the head-mounted display device will also consider the wearer's historical usage data and obtain multiple historical reference scores from the historical data according to a preset time window (such as the last 5 scores, the last month, etc.). These historical reference scores can be the comfort scores obtained by the wearer through the score acquisition module when using the head-mounted display device in the past, or they can be scores automatically calculated by the device based on other indicators (such as usage time, number of abnormal exits, etc.).

[0074] Step S52: Calculate the average of each historical reference score to obtain a historical score.

[0075] In this embodiment, after obtaining multiple historical reference scores, the head-mounted display device will average these scores to obtain a comprehensive historical score. The historical score reflects the wearer's overall comfort feeling of the head-mounted display device over the past period of time. This score can serve as an important reference for current comfort evaluation and help the device better understand the wearer's needs and preferences.

[0076] In step S53, the historical scores and the target biometric data are input into the optical parameter prediction model to obtain the target optical parameters of the head-mounted display device.

[0077] This embodiment inputs historical scores along with currently collected target biometric data into the optical parameter prediction model, enabling it to more accurately predict appropriate optical parameters for the current situation by comprehensively considering the wearer's physiological characteristics and historical usage experience. Specifically, the optical parameter prediction model not only calculates optical parameters based on the wearer's individual biometric characteristics (such as pupillary distance and corneal curvature), but also incorporates the wearer's comfort trends developed during past use, thereby achieving a transition from "static adaptation" to "dynamic personalized adaptation."

[0078] This method of integrating historical scores gives the optical parameter prediction process a certain degree of memory and adaptability: on the one hand, it can identify the wearer's long-term preference for specific optical settings and avoid repeated uncomfortable adjustment results; on the other hand, when faced with similar biometric inputs, the model can use historical scores to correct the current prediction results, making them closer to the user's actual perceptual needs and further reducing the discomfort caused by the VAC effect.

[0079] Therefore, incorporating historical scores as one of the input features into the optical parameter prediction process can help improve the responsiveness of head-mounted displays to user visual comfort in different scenarios, enhance the intelligence and personalization of optical adjustment, and ultimately achieve a more natural, stable, and comfortable immersive wearing experience.

[0080] For further examples, see Figure 2 The headset integrates an optical sensing system. Its core components include symmetrically arranged left and right infrared camera modules and left and right iris recognition camera arrays. These cameras utilize high-sensitivity sensors with low noise and high dynamic range, accurately capturing subtle features of the human eye area. The zoom module utilizes liquid lens array technology. This array consists of multiple micro-liquid lens units, each of which can independently adjust its focal length via an electric field, enabling continuous zoom with millisecond response. Focus can also be adjusted by motor-driven position adjustment. Furthermore, an electrochromic layer (a single or multiple layers of electrochromic material that undergoes reversible changes in optical properties, such as transmittance, reflectance, or absorptivity, when a voltage is applied across its terminals) precisely controls transmittance by applying varying voltages, dynamically optimizing the optical system's light throughput and contrast. The zoom module, left and right beamsplitting prisms, and high-precision optical lens arrays work together to precisely project a virtual image onto the display. Distortion is corrected via a free-form optical system, allowing the user to view a clear, distortion-free virtual image through the eyepiece.

[0081] To dynamically adjust optical parameters, the headset uses a built-in calibration algorithm to achieve real-time switching of virtual image focal length. Specifically, when the user switches from focusing on virtual image A (e.g., a nearby virtual object) to virtual image B (e.g., a distant virtual scene), the headset adjusts the focal length using the rapid response of the liquid lens array. Simultaneously, the electrochromic layer optimizes the transmittance to match the required light intensity at the new focal length. Conversely, when switching from virtual image B back to virtual image A, the headset can also complete the reverse adjustment with the same precision and speed, ensuring a consistent and comfortable visual experience.

[0082] Based on the above hardware architecture, when the head-mounted display device collects biometric data, the left and right infrared cameras work synchronously at a 60Hz sampling rate, and use the binocular stereo vision algorithm to calculate the three-dimensional coordinates of the wearer's pupil center in real time, thereby obtaining an accurate IPD value. The data is stored frame by frame in the built-in flash memory of the headset in CSV (Comma-Separated Values) format (including timestamp, left / right pupil X / Y / Z coordinates, IPD value, etc.). The iris camera captures dynamic images of the wearer's eyeballs at a high frame rate (≥30fps). The headset uses a deep learning algorithm to identify micro-deformation features of the iris surface (such as blood vessel distribution, wrinkle morphology, etc.), and combines it with a geometric optical model to invert the corneal curvature radius. The collected corneal curvature images are stored in JPEG (Joint Photographic Experts Group, a lossy compressed digital image format) format (640×480 pixels, 8-bit grayscale). The eye tracker module captures the rotation angle and micro-movement of the wearer's eyeballs at a sampling rate of 120Hz, calculates the coordinates of the gaze point, and uses the optical flow method to analyze the eye movement speed and acceleration. The detection data is stored in JSON (JavaScript Object Notation). The data is stored in JavaScript Object Notation (JavaScript Object Notation) format (including timestamp, gaze point X / Y coordinates, eye movement velocity vector, and other fields), supporting real-time gaze point heat map generation and eye movement trajectory playback.

[0083] like Figure 3 As shown in one example, the head-mounted display device is divided into two parts: the left eye area and the right eye area. The zoom module includes left and right VAC adjustment modules and left and right lenses. The VAC adjustment module includes a liquid lens array and an electrochromic layer. In this example, in addition to directly controlling the voltage of the left and right VAC adjustment modules to achieve curvature adjustment, the microcontroller unit can also control the position of each liquid lens in the liquid lens array in the left and right VAC adjustment modules through left and right motors, thereby changing the curvature of the liquid lens array.

[0084] Step S200: calibrating the curvature of the liquid lens array based on the target comfort score.

[0085] By quantifying the wearer's actual visual experience and obtaining a target comfort score, this embodiment can determine whether the current optical settings have reached the optimal state. If the target comfort score indicates that the wearer is experiencing discomfort or dissatisfaction, the system will use this score information to dynamically adjust the control voltage of the liquid lens array or the position of each liquid lens in the liquid lens array through a preset algorithm, thereby optimizing the lens curvature to ensure that it is more closely aligned with the wearer's personalized needs. This adaptive adjustment mechanism not only effectively reduces the visual convergence-accommodation conflict (VAC effect) but also significantly improves the user's visual comfort and overall user experience.

[0086] For example, in a feasible implementation, before step S200, the optical adjustment method further includes steps B10 to B20: Step B10, determining whether the comfort score is less than a first preset score; It should be noted that the first preset score refers to a baseline value or threshold set in the optical adjustment system of the head-mounted display (HMD) device, used to assess whether the wearer's visual comfort meets acceptable standards. This score is based on a series of predefined rules and standards, or an ideal comfort level derived through extensive user testing and data analysis. Specifically, the first preset score is a numerical standard that represents the minimum level of visual comfort that the wearer should achieve when using the HMD device. It is typically determined by the device manufacturer based on extensive user experience data, physiological research, and the needs of specific application scenarios. This score serves as a basis for determining whether the current optical settings need to be adjusted. If the wearer's target comfort score is lower than the first preset score, it indicates that the current optical settings do not fully meet the user's visual needs and there is room for improvement. Conversely, if the target comfort score is equal to or higher than the first preset score, it indicates that the current settings already provide a good user experience and no further adjustment is required.

[0087] By introducing the concept of a first preset score, this implementation intelligently determines when to initiate the calibration process while maintaining a positive user experience. This improves system efficiency and responsiveness, ensuring an optimal visual experience for users. This mechanism not only helps reduce unnecessary resource consumption but also significantly improves user satisfaction and overall device performance.

[0088] Step B20 , when it is determined that the comfort score is less than the first preset score, executing a step of calibrating the curvature of the liquid lens array based on the target comfort score.

[0089] In this embodiment, if the target comfort score is determined to be less than the first preset score, it means that the wearer's current visual experience is not ideal and there may be a significant VAC problem. In this case, the system automatically initiates the calibration process and proceeds to step S200 to calibrate the curvature of the liquid lens array based on the target comfort score.

[0090] This implementation adopts a judge-before-act mechanism, which not only improves the system's response efficiency and avoids unnecessary resource consumption, but also ensures that corresponding adjustments are only made when there is a real need to improve the wearer experience, helping to maintain the stability of device performance and long-term user satisfaction.

[0091] This embodiment introduces a scoring module to perform real-time evaluation of the wearer's comfort and dynamically calibrates the curvature of the liquid lens array based on this evaluation result (i.e., a target comfort score), thereby effectively reducing the visual convergence-accommodation conflict (VAC effect) in the head-mounted display device and improving the user's wearing experience. Specifically, this embodiment of the application, based on predicting target optical parameters based on the wearer's target biometric data and adjusting the curvature of the liquid lens array, further utilizes the scoring module to obtain the wearer's first comfort score (determined by an automatic scoring unit based on physiological signals such as eye movement and blink frequency) and / or second comfort score (user-input feedback), and comprehensively forms a target comfort score. Based on this score, the system performs feedback analysis on the current optical state. If it is determined that the VAC effect is still significant, the curvature of the liquid lens array is dynamically calibrated and optimized, so that the optical system better meets the user's actual visual needs. This closed-loop adaptive adjustment mechanism not only makes up for the defect that static adjustment cannot adapt to individual differences, but also improves the accuracy and personalization of optical adjustment by introducing a comfort evaluation system that combines subjective and objective factors, thereby significantly alleviating visual fatigue and dizziness caused by the VAC effect, and enhancing the immersion and comfort of the head-mounted display device.

[0092] In a feasible implementation, step S200 calibrates the curvature of the liquid lens array based on the target comfort score, and may include steps S210 to S220: Step S210, calibrating target optical parameters based on the target comfort score; In this embodiment, when it is determined that the current optical settings fail to fully meet the wearer's visual comfort needs and that a certain degree of VAC effect or other discomfort factors exist, the system can use a feedback control algorithm (such as PID control, gradient descent method, etc.) to fine-tune the original target optical parameters based on the degree of deviation between the target comfort score and the ideal score, thereby generating a set of optimized optical parameters that are more consistent with the wearer's subjective feelings and physiological state, i.e., the calibrated target optical parameters.

[0093] Step S220 , adjusting the control voltage of the liquid lens array according to the calibrated target optical parameters to adjust the curvature of the liquid lens array.

[0094] After completing the calibration of the target optical parameters, this embodiment can convert these optimized parameters (i.e., the calibrated target optical parameters) into specific control instructions and input them into the liquid lens array's driver module. Each lens unit in the liquid lens array has a variable curvature characteristic, and its curvature can be dynamically controlled by applying different voltages. Therefore, this embodiment calculates the corresponding control voltage value based on the calibrated target optical parameters and applies it to the corresponding liquid lens unit, thereby changing the curvature distribution of the lens surface.

[0095] This implementation implements a closed-loop feedback mechanism from "perceived comfort" to "physical optical adjustment": the wearer's target comfort score is converted into actual optical parameter changes, which are ultimately reflected in the physical morphology adjustment of the liquid lens array, making the virtual image more closely aligned with the user's visual focus, effectively alleviating the VAC effect, and improving display quality and user experience.

[0096] In summary, the target optical parameters are calibrated based on the comfort score in step S210, and the calibration results are applied to the actual adjustment of the liquid lens array in step S220. This embodiment constructs a dynamic adaptive optical adjustment mechanism that integrates subjective feedback and objective adjustment, significantly improving the visual adaptability and user satisfaction of the head-mounted display device in complex application scenarios.

[0097] Furthermore, in a feasible implementation manner, the target optical parameters include a focal length compensation value, a lens curvature, and a dispersion compensation coefficient, and step S220 may further include steps S221 to S224: Step S221, calculating a curvature correction term of the liquid lens array according to the calibrated focal length compensation value and the calibrated dispersion compensation coefficient; It should be noted that, in this embodiment, the focal length compensation value is used to compensate for the deviation between the actual focal length and the ideal focal length caused by differences in the wearer's biometric characteristics (such as pupillary distance and corneal curvature), so as to ensure clear and accurate imaging.

[0098] Among them, lens curvature is used to describe the degree of curvature of the lens surface. Different curvatures will affect the refraction and focusing effects of light.

[0099] In addition, the dispersion compensation coefficient is used to correct the dispersion phenomenon caused by the different refractive indices of light of different colors, reduce chromatic aberration, and improve the color reproduction and clarity of the image.

[0100] In this embodiment, the curvature correction term of the liquid lens array, ie, the curvature that needs to be compensated, can be calculated based on the focal length compensation value and the dispersion compensation coefficient.

[0101] Step S32, adding the calibrated lens curvature and the curvature correction term to obtain the target curvature of the liquid lens array; In this embodiment, after the curvature correction term is calculated, the lens curvature and the curvature correction term are added together to obtain the target curvature to which the liquid lens array needs to be adjusted.

[0102] Step S33, obtaining the initial curvature of the liquid lens array, and calculating the curvature difference between the initial curvature and the target curvature; In this embodiment, in order to calculate the control voltage that needs to be adjusted, it is also necessary to calculate the curvature difference between the initial curvature and the target curvature of the lens in the liquid lens array.

[0103] Step S34, calculating a target voltage of the liquid lens array according to the curvature difference and a preset curvature-voltage coefficient, and adjusting a control voltage of the liquid lens array according to the target voltage; In this embodiment, after the curvature difference is calculated, the target voltage to which the liquid lens array needs to be adjusted can be calculated based on the preset curvature-voltage coefficient. Then, the control voltage of the liquid lens array is adjusted to the target voltage, and the curvature of the liquid lens array can be adjusted to the target curvature.

[0104] Specifically, in one example, the radius of curvature R of the liquid lens is strictly related to the focal length f by the thin lens formula: ; in: n: refractive index of liquid lens material (e.g. PDMS, n=1.43); R fix : The radius of the fixed curvature surface (determined by the mechanical structure of the lens, such as R fix =500 μm); R: dynamically adjusted curvature radius; The relationship between the curvature radius R of the liquid lens and the driving voltage V is: ; in: R: Target curvature radius (μm), calculated from the curvature parameter in the generator output Y.

[0105] V: driving voltage (V), the target value to be solved.

[0106] k: Lens material characteristic constant (e.g., k = 0.12 μm / V2 for dielectric elastomer).

[0107] , :The vacuum dielectric constant (8.85e-12 F / m) and the relative dielectric constant of the material (such as PDMS =2.8).

[0108] d: Electrode spacing (μm, default 50μm).

[0109] R0: Zero voltage curvature radius (determined by the initial shape of the lens, usually 200μm).

[0110] In a feasible embodiment, the head-mounted display device further includes an electrochromic layer. After step S210 calibrates the target optical parameters based on the target comfort score, the optical adjustment method may further include steps S230 to S240: Step S230, calculating the target dispersion of the electrochromic layer according to the calibrated dispersion compensation coefficient; It should be noted that in this embodiment, transmittance refers to the ratio of the actual transmitted light intensity to the incident light intensity when light passes through the electrochromic layer. The transmittance directly affects the brightness, color saturation and clarity of the display screen of the head-mounted display device.

[0111] In this embodiment, the target dispersion to which the electrochromic layer currently needs to be adjusted can be calculated based on the dispersion compensation coefficient.

[0112] Step S240 : adjusting the transmittance of the electrochromic layer based on the target dispersion and the initial dispersion of the electrochromic layer.

[0113] In this embodiment, the transmittance of the electrochromic layer is adjusted according to the target dispersion to which the electrochromic layer currently needs to be adjusted and the initial dispersion of the zoom module, so that the electrochromic layer can be adjusted to the target dispersion.

[0114] Specifically, the formula for dynamically adjusting the transmittance based on the dispersion compensation coefficient is as follows:

[0115] α: material characteristic constant; T: transmittance; δ: dispersion compensation coefficient; T0: initial light transmittance.

[0116] By collecting the wearer's target biometric data and using an optical parameter prediction model to predict target optical parameters that match the target biometric data, the head-mounted display (HMD) can achieve personalized optical settings (including the curvature of the liquid lens array and / or the transmittance of the electrochromic layer), ensuring an optimal wearing experience for each wearer. Conventional HMDs, due to their fixed focal length or manual adjustment methods, often struggle to achieve precise matching, significantly increasing the visual vergence-accommodation conflict (VAC effect). The optical adjustment method of this embodiment automatically adjusts the operating parameters of the liquid lens array and / or electrochromic layer to adapt the HMD's optical parameters to the user's biometric data, effectively reducing the VAC effect and alleviating discomfort such as visual fatigue and dizziness. Furthermore, because the HMD automatically adapts to the biometric data of each user and adjusts operating parameters in real time to reduce the VAC effect, users no longer need to perform complex manual adjustments during use. This not only improves ease of use but also significantly enhances the overall user experience.

[0117] In a feasible implementation, the optical adjustment method further includes steps C10 to C20: Step C10: when the target comfort score is less than a first preset score, determining a loss function of the light parameter prediction model according to the target comfort score; Step C20: updating the trainable parameters of the optical parameter prediction model based on a preset gradient descent algorithm and loss function.

[0118] In this embodiment, after determining the wearer's target comfort score, the head-mounted display device analyzes and processes the score. If the analysis results show that the target comfort score is at a high level (i.e., greater than or equal to a first preset score), this indicates that the target optical parameters generated by the current optical parameter prediction model are highly consistent with the wearer's actual needs. Not only do they meet the user's visual expectations, but they also do not cause noticeable discomfort during extended wear. This positive feedback indicates that the model has achieved a high degree of accuracy in capturing subtle differences in the user's biometrics and predicting optimal optical parameters. Therefore, the device takes further action to store the collected biometric data (such as pupillary distance, corneal curvature, eye movement trajectory, etc.), target optical parameters (such as focal length, light field distribution, color temperature adjustment, etc.), and the second comfort score given by the user as a complete training sample in the device's database. These samples not only record the user's current physiological state and preferences, but also reflect the output performance of the optical parameter prediction model under specific conditions, providing data resources for the continuous optimization of subsequent models.

[0119] Subsequently, these newly added training samples will be incorporated into the training process of the optical parameter prediction model. Through the machine learning algorithm, the parameters and structure of the optical parameter prediction model will be continuously iterated and optimized, so that in future uses, the target optical parameters that meet the user's personalized needs can be more accurately predicted and generated. This process is an iterative and continuous improvement process aimed at continuously improving the comfort and performance of the head-mounted display device.

[0120] On the contrary, if the analysis results show that the target comfort score is low, this indicates that the current optical parameter prediction model has deviations when outputting the target optical parameters, and fails to fully consider the wearer's biometric differences or the needs of specific usage scenarios. The device will use this target comfort score as a direct feedback signal and backpropagate it to the generator part of the optical parameter prediction model. By adjusting the weight parameters of the generator, it will guide it to learn a more accurate optical parameter generation strategy that is more in line with user needs.

[0121] After adjusting the weight parameters of the optical parameter prediction model, the device will restart the optical parameter prediction process of the optical parameter prediction model, use the updated model to re-analyze the wearer's biometric data, and generate new target optical parameters. This process may be repeated multiple times until the newly generated optical parameters can achieve a higher target comfort score in subsequent user tests. Through this continuous iteration and continuous optimization approach, the head-mounted display device can gradually approach the limits of user needs and provide users with a more comfortable and personalized visual experience.

[0122] Exemplarily, the optical parameter prediction model may be a GAN (Generative Adversarial Network) model, and steps C10 to C20 may be: determining a loss function of the GAN model according to the comfort score; and updating the weight of the generator in the GAN model based on a preset gradient descent algorithm and the loss function.

[0123] In this example, the loss function of the GAN model can be obtained by weighted calculation based on the comfort score.

[0124] Specifically, the loss function L combines adversarial loss with user rating weighting: ; L adv : Adversarial Loss, which measures the probability that the generator output parameters are detected by the discriminator.

[0125] L score : User rating loss (Comfort Loss), which quantifies the degree of matching between the generated parameters and the user's comfort.

[0126] λ1, λ2: Weight coefficients used to balance adversarial training and user feedback. The default values ​​are λ1=0.7 and λ2=0.3, which need to be adjusted based on the validation set.

[0127] Furthermore, the preset gradient current price algorithm is combined with the loss function to update the weights of the generator in the GAN model, and the model is gradually adjusted to the optimal state.

[0128] Specifically, the generator weights can be updated using mini-batch gradient descent (Mini-batch SGD): ; θ G : Trainable parameters of the generator; η: Learning rate, which controls the parameter update step size. The initial value of η is set to 0.0002, and it decays exponentially with the number of training rounds: the initial learning rate η0=0.0002; ▽ θG : Gradient of the loss function with respect to the generator parameters.

[0129] S, Y: User rating and currently generated optical parameters.

[0130] It is worth noting that in this embodiment, each time the target optical parameters are generated by the optical parameter prediction model and the curvature of the liquid lens array is adjusted based on the generated target optical parameters, the scoring module determines the wearer's target comfort score under the current optical settings, and the corresponding target biometric data, target light parameters, and target comfort score are associated and stored. This associated storage can be performed by account, by wearer, or without distinction, depending on the actual design. That is, when the head-mounted display device associates and stores the target biometric data, target light parameters, and target comfort score, it can associate and store the data logged in by the same account in the same optical parameter storage space (i.e., the storage space used for associated storage of the data). Alternatively, the wearer's identity can be determined through iris authentication, and the data for the same wearer can be associated and stored in the same optical parameter storage space. Alternatively, all the data for the head-mounted display device can be associated and stored in the same optical parameter storage space without distinction.

[0131] It is understandable that the trainable parameters of the optical parameter prediction model corresponding to different optical parameter storage spaces are different, that is, the optical parameter prediction model of the head-mounted display device can have multiple different sets of trainable parameter sets, each set of trainable parameter sets corresponds to an optical parameter storage space (that is, corresponds to an account or corresponds to a wearer). Each time the head-mounted display device is used, the login account or the identity of the wearer is first detected, and the corresponding trainable parameter set is loaded into the optical parameter prediction model so that the optical parameter prediction model matches the current login account or the current wearer. Accordingly, when a change in the login account or wearer is detected, the trainable parameter set loaded by the optical parameter prediction model is switched accordingly.

[0132] For the same optical parameter storage space, each target biometric data is stored only once, that is, only the target optical parameters and target comfort score most recently associated with the target biometric data are retained.

[0133] It is not difficult to understand that for the trainable parameter set corresponding to the same optical parameter storage space, as the optical parameter prediction model is continuously updated, the predicted target optical parameters will increasingly match the wearer's target biometric data. Correspondingly, after adjusting the curvature of the liquid lens array based on this, the wearer's target comfort score will also become higher and higher. When the target comfort score associated with each target biometric data in the entire optical parameter storage space is greater than the first preset score, or the target comfort score of the data most recently associated and stored in the optical parameter storage space within a certain number of times (for example, the last 100 times) or a certain time (for example, the last month) is greater than the first preset score, it can be considered that the trainable parameter set corresponding to the optical parameter storage space has been trained and is in the optimal state, and the trainable parameter set is marked as the target state. At this point, in subsequent use, there is no need to optimize the trainable parameter set, that is, there is no need to update the optical parameter prediction model loaded with the trainable parameter set. At the same time, after collecting the wearer's target biometric data, there is no need to perform predictions by loading the optical parameter prediction model of the trainable parameter set. The target optical parameters associated with the target biometric data can be directly called from the optical parameter storage space to adjust the curvature of the liquid lens array, thereby improving the optical adjustment speed of the head-mounted display device and saving the computing resources required for model prediction.

[0134] For example, after the pupil distance, corneal curvature, gaze point coordinates, and eye movement velocity are used as target biometric data of the wearer in step S40, the optical adjustment method may further include: Determine the optical parameter storage space corresponding to the wearer, and determine whether the trainable parameter set corresponding to the optical parameter storage space is marked as a target state; When the trainable parameter set is marked as a target state, optical parameters associated with the target biometric data are queried from the optical parameter storage space, and the curvature of the liquid lens array is adjusted based on the queried optical parameters.

[0135] The trainable parameter set is marked as the target state, which means that the trainable parameter set has been trained and is in the optimal state and does not need to be updated.

[0136] It is not difficult to understand that in this example, when the optical parameter storage space is divided by account for associated storage of the above data, determining the optical parameter storage space corresponding to the wearer is essentially determining the optical parameter storage space corresponding to the currently logged-in account.

[0137] In a feasible implementation, after step S200 calibrates the curvature of the liquid lens array based on the target comfort score, the optical adjustment method may further include steps D10 to D30: Step D10, counting the number of curvature calibrations of the liquid lens array; It should be noted that the number of curvature calibrations refers to the cumulative number of times the curvature of the liquid lens array is calibrated.

[0138] In this embodiment, each time the curvature of the liquid lens array is calibrated, the number of curvature calibrations is counted, so that the number of curvature calibrations is increased by one.

[0139] Step D20: If the number of curvature calibrations is less than or equal to the preset number, returning to the step of determining the wearer's target comfort score through the scoring module; It should be noted that the preset number of attempts refers to a threshold or upper limit for the curvature calibration of the liquid lens array during the optical adjustment process of the head-mounted display. It specifies the maximum number of attempts the system can make to adjust the curvature based on the same set of biometric data. If this preset number of attempts is reached and the desired visual comfort standard is still not achieved, the system will trigger additional operations, such as re-collecting the wearer's target biometric data.

[0140] In this embodiment, if the current curvature calibration count does not exceed a preset number (for example, three), the system determines that further fine-tuning of the current target optical parameters is possible. The system then returns to step S100 and again obtains the wearer's latest target comfort score through the scoring module. This iterative mechanism allows the system to gradually approach the optimal optical settings based on the wearer's immediate feedback until the wearer's target comfort score exceeds the first preset score.

[0141] Step D30: If the number of curvature calibration times is greater than the preset number, the process returns to the step of acquiring the wearer's eye image through the camera unit, and sets the number of curvature calibration times to zero.

[0142] In this embodiment, if the number of curvature calibrations exceeds a preset number (e.g., three in the example above), indicating that despite multiple attempts, the desired comfort level has not been achieved, the system infers that the initial biometric data (e.g., pupillary distance, corneal curvature, etc.) may be inaccurate or have changed. Therefore, the system restarts the entire optical adjustment process, returning to the step of acquiring an image of the wearer's eye through the camera unit. Simultaneously, this embodiment resets the number of curvature calibrations to zero to prevent the curvature calibrations from the current round of optical adjustment from being carried over to the next round.

[0143] It is not difficult to understand that the ultimate goal of this embodiment is to ensure that the target comfort level is greater than or equal to the first preset score, thereby reducing the VAC effect when the user uses the head-mounted display device. Therefore, in actual applications, the biometric acquisition module will detect the wearer's target biometric data in real time or periodically. When a change in the target biometric data is detected, according to actual needs, the newly collected target biometric data can be directly input into the optical parameter prediction model to start a new round of optical adjustment. It can also trigger the scoring module to determine the wearer's current target comfort score. Only when the newly determined target comfort score is less than the first preset score, the newly collected target biometric data will be input into the optical parameter prediction model to start a new round of optical adjustment.

[0144] In addition, in actual applications, the scoring module can also determine the wearer's target comfort score in real time or periodically, and when the target comfort score is less than the first preset score, trigger the execution of step S200 to calibrate the curvature of the liquid lens array based on the target comfort score.

[0145] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the optical adjustment method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0146] This application also provides an optical adjustment device, please refer to Figure 4 The optical adjustment device is provided in a head-mounted display device, the head-mounted display device includes a liquid lens array and a scoring module, the scoring module includes at least one of an automatic scoring unit and an active scoring unit, wherein the automatic scoring unit is used to determine a first comfort score based on a target physiological signal of the wearer, and the active scoring unit is used to receive a second comfort score input by the wearer, the device includes: a scoring module 10 for determining, via the scoring module, a target comfort score for the wearer after adjusting the curvature of the liquid lens array based on target optical parameters of the head-mounted display device, wherein the target optical parameters are predicted by an optical parameter prediction model based on target biometric data of the wearer, the optical parameter prediction model being trained using biometric data as samples and optical parameters as labels, and the target comfort score being determined based on the first comfort score and / or the second comfort score; The calibration module 20 is configured to calibrate the curvature of the liquid lens array based on the target comfort score.

[0147] In one embodiment, the calibration module 20 is further configured to: Determining whether the comfort score is less than a first preset score; When it is determined that the comfort score is less than the first preset score, the step of calibrating the curvature of the liquid lens array based on the target comfort score is performed.

[0148] In one embodiment, the calibration module 20 is further configured to: calibrating the target optical parameters based on the target comfort score; According to the calibrated target optical parameters, the control voltage of the liquid lens array is adjusted to adjust the curvature of the liquid lens array.

[0149] In one embodiment, the target optical parameters include a focal length compensation value, a lens curvature, and a dispersion compensation coefficient, and the calibration module 20 is further configured to: Calculating a curvature correction term of the liquid lens array according to the calibrated focal length compensation value and the calibrated dispersion compensation coefficient; Adding the calibrated lens curvature to the curvature correction term to obtain a target curvature of the liquid lens array; Obtaining an initial curvature of the liquid lens array, and calculating a curvature difference between the initial curvature and the target curvature; The target voltage of the liquid lens array is calculated according to the curvature difference and a preset curvature-voltage coefficient, and the control voltage of the liquid lens array is adjusted according to the target voltage.

[0150] In one embodiment, the head-mounted display device further includes an electrochromic layer, and the calibration module 20 is further configured to: Calculating the target dispersion of the electrochromic layer according to the calibrated dispersion compensation coefficient; The light transmittance of the electrochromic layer is adjusted based on the target dispersion and the initial dispersion of the electrochromic layer.

[0151] In one embodiment, the head-mounted display device further includes a biometric feature acquisition module, which includes a camera unit and an eye movement detection unit. The device further includes a prediction module (not shown), which is configured to: Acquiring an eye image of the wearer through the camera unit; acquiring the pupil distance and corneal curvature of the wearer based on the eyeball image; Acquiring the wearer's gaze point coordinates and eye movement speed through the eye movement detection unit; Using the interpupillary distance, the corneal curvature, the gaze point coordinates, and the eye movement velocity as target biometric data of the wearer; The target biometric data is input into the optical parameter prediction model to obtain the target optical parameters of the head-mounted display device.

[0152] In one embodiment, the apparatus further includes an updating module (not shown), wherein the updating module is configured to: When the target comfort score is less than a first preset score, determining a loss function of the light parameter prediction model according to the target comfort score; Based on a preset gradient descent algorithm and the loss function, the trainable parameters of the optical parameter prediction model are updated.

[0153] In one embodiment, the calibration module 20 is further configured to: Counting the number of curvature calibrations of the liquid lens array; If the number of curvature calibrations is less than or equal to the preset number, returning to the step of determining the wearer's target comfort score by the scoring module; When the number of curvature calibration times is greater than the preset number, the method returns to the step of acquiring the wearer's eye image through the camera unit, and sets the number of curvature calibration times to zero.

[0154] The optical adjustment device provided in this application, employing the optical adjustment method described in the aforementioned embodiments, can address the technical problem of reducing the VAC effect of head-mounted displays. Compared to the prior art, the optical adjustment device provided in this application achieves the same beneficial effects as the optical adjustment method described in the aforementioned embodiments. Other technical features of the optical adjustment device are the same as those disclosed in the aforementioned embodiments and are not further elaborated here.

[0155] The present application provides a head-mounted display device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the optical adjustment method of the above-mentioned embodiment 1.

[0156] The head-mounted display device in the embodiments of the present application may include, but is not limited to, head-mounted display devices such as mixed reality (MR) devices (such as MR glasses or MR helmets), augmented reality (AR) devices (such as AR glasses or AR helmets), virtual reality (VR) devices (such as VR glasses or VR helmets), extended reality (XR) devices, or some combination thereof.

[0157] like Figure 5 As shown, the head-mounted display device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory 1002 or programs loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the head-mounted display device. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems may be connected to the input / output interface 1006: an input device 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; a storage device 1003 including, for example, a magnetic tape or hard disk; and a communication device 1009. The communication device 1009 can allow the head-mounted display device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a head-mounted display device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have alternatively.

[0158] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0159] The head-mounted display device provided in this application, employing the optical adjustment method described in the aforementioned embodiment, can address the technical problem of reducing the VAC effect of head-mounted display devices. Compared to the prior art, the head-mounted display device provided in this application achieves the same beneficial effects as the optical adjustment method described in the aforementioned embodiment. Other technical features of this head-mounted display device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0160] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0161] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0162] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the optical adjustment method in the above-mentioned embodiment.

[0163] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0164] The computer-readable storage medium may be included in the head-mounted display device, or may exist independently without being incorporated into the head-mounted display device.

[0165] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by a head-mounted display device, the head-mounted display device: after adjusting the curvature of the liquid lens array based on the target optical parameters of the head-mounted display device, determines the target comfort score of the wearer through the scoring module, wherein the target optical parameters are predicted by an optical parameter prediction model based on the wearer's target biometric data, and the optical parameter prediction model is trained using biometric data as samples and optical parameters as labels, and the target comfort score is determined based on the first comfort score and / or the second comfort score; and based on the target comfort score, the curvature of the liquid lens array is calibrated.

[0166] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0167] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0168] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0169] The computer-readable storage medium provided herein stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned optical adjustment method, thereby solving the technical problem of reducing the VAC effect of head-mounted display devices. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided herein are similar to those of the optical adjustment method provided in the aforementioned embodiments and are not further elaborated here.

[0170] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned optical adjustment method when executed by a processor.

[0171] The computer program product provided in this application can solve the technical problem of reducing the VAC effect of head-mounted display devices. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the optical adjustment method provided in the above embodiment, and will not be repeated here.

[0172] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An optical adjustment method, characterized in that: The optical adjustment method is applied to a head-mounted display device, the head-mounted display device including a liquid lens array and a scoring module, the scoring module including at least one of an automatic scoring unit and an active scoring unit, wherein the automatic scoring unit is configured to determine a first comfort score based on a target physiological signal of a wearer, and the active scoring unit is configured to receive a second comfort score input by the wearer. The method includes: After adjusting the curvature of the liquid lens array based on target optical parameters of the head-mounted display device, determining a target comfort score for the wearer by the scoring module, wherein the target optical parameters are predicted by an optical parameter prediction model based on target biometric data of the wearer, the optical parameter prediction model being trained using biometric data as samples and optical parameters as labels, and the target comfort score is determined based on the first comfort score and / or the second comfort score; The curvature of the liquid lens array is calibrated based on the target comfort score.

2. The optical adjustment method according to claim 1, wherein: Before the step of calibrating the curvature of the liquid lens array based on the target comfort score, the method further includes: Determining whether the comfort score is less than a first preset score; When it is determined that the comfort score is less than the first preset score, the step of calibrating the curvature of the liquid lens array based on the target comfort score is performed.

3. The optical adjustment method according to claim 2, wherein: The step of calibrating the curvature of the liquid lens array based on the target comfort score comprises: calibrating the target optical parameters based on the target comfort score; According to the calibrated target optical parameters, the control voltage of the liquid lens array is adjusted to adjust the curvature of the liquid lens array.

4. The optical adjustment method according to claim 3, wherein: The target optical parameters include a focal length compensation value, a lens curvature, and a dispersion compensation coefficient. The step of adjusting the control voltage of the liquid lens array according to the calibrated target optical parameters includes: Calculating a curvature correction term of the liquid lens array according to the calibrated focal length compensation value and the calibrated dispersion compensation coefficient; Adding the calibrated lens curvature to the curvature correction term to obtain a target curvature of the liquid lens array; Obtaining an initial curvature of the liquid lens array, and calculating a curvature difference between the initial curvature and the target curvature; The target voltage of the liquid lens array is calculated according to the curvature difference and a preset curvature-voltage coefficient, and the control voltage of the liquid lens array is adjusted according to the target voltage.

5. The optical adjustment method according to claim 4, wherein: The head-mounted display device further includes an electrochromic layer. After the step of calibrating the target optical parameters based on the target comfort score, the method further includes: Calculating the target dispersion of the electrochromic layer according to the calibrated dispersion compensation coefficient; The light transmittance of the electrochromic layer is adjusted based on the target dispersion and the initial dispersion of the electrochromic layer.

6. The optical adjustment method according to any one of claims 1 to 5, characterized in that: The head-mounted display device further includes a biometric feature acquisition module, which includes a camera unit and an eye movement detection unit. Before the step of adjusting the curvature of the liquid lens array based on the target optical parameters of the head-mounted display device, the method further includes: Acquiring an eye image of the wearer through the camera unit; acquiring the pupil distance and corneal curvature of the wearer based on the eyeball image; Acquiring the wearer's gaze point coordinates and eye movement speed through the eye movement detection unit; Using the interpupillary distance, the corneal curvature, the gaze point coordinates, and the eye movement velocity as target biometric data of the wearer; The target biometric data is input into the optical parameter prediction model to obtain the target optical parameters of the head-mounted display device.

7. The optical adjustment method according to claim 6, wherein: The method further comprises: When the target comfort score is less than a first preset score, determining a loss function of the light parameter prediction model according to the target comfort score; Based on a preset gradient descent algorithm and the loss function, the trainable parameters of the optical parameter prediction model are updated.

8. The optical adjustment method according to claim 7, wherein: After the step of calibrating the curvature of the liquid lens array based on the target comfort score, the method further includes: Counting the number of curvature calibrations of the liquid lens array; If the number of curvature calibrations is less than or equal to the preset number, returning to the step of determining the wearer's target comfort score by the scoring module; When the number of curvature calibration times is greater than the preset number, the method returns to the step of acquiring the wearer's eye image through the camera unit, and sets the number of curvature calibration times to zero.

9. An optical adjustment device, characterized in that: The device is provided in a head-mounted display device, the head-mounted display device including a liquid lens array and a scoring module, the scoring module including at least one of an automatic scoring unit and an active scoring unit, wherein the automatic scoring unit is configured to determine a first comfort score based on a target physiological signal of a wearer, and the active scoring unit is configured to receive a second comfort score input by the wearer, the device comprising: a scoring module, configured to determine, via the scoring module, a target comfort score for the wearer after adjusting the curvature of the liquid lens array based on target optical parameters of the head-mounted display device, wherein the target optical parameters are predicted by an optical parameter prediction model based on target biometric data of the wearer, the optical parameter prediction model being trained using biometric data as samples and optical parameters as labels, and the target comfort score being determined based on the first comfort score and / or the second comfort score; A calibration module is configured to calibrate the curvature of the liquid lens array based on the target comfort score.

10. A head-mounted display device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the optical adjustment method according to any one of claims 1 to 8.

11. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the optical adjustment method according to any one of claims 1 to 8 are implemented.

Images