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

Abstract

The application discloses an optical adjustment method, a head-mounted device and a storage medium, relates to the technical field of head-mounted devices, and the optical adjustment method is applied to the head-mounted device. The head-mounted device comprises a biological feature acquisition module and a liquid lens array. The method comprises the following steps: collecting target biological feature data of a wearer through the biological feature acquisition module; inputting the target biological feature data into a preset optical parameter prediction neural network model to obtain target optical parameters, wherein the optical parameter prediction neural network model is trained by taking biological feature data as samples, and the optical parameters are labels; and adjusting the control voltage of the liquid lens array based on the target optical parameters to adjust the target curvature of the lenses in the liquid lens array. The application enables the head-mounted device to adapt to the biological feature data of different users, automatically adjusts the focal length of the head-mounted device, and reduces the VAC effect of the head-mounted device.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of head-mounted display devices, and particularly relates to an optical adjustment method, a head-mounted display device and a storage medium. BACKGROUND

[0002] With the rapid development of head-mounted display device (hereinafter referred to as "head-mounted display device") technology, the optimization of the performance and user experience of the head-mounted display device has become the focus of industry research.

[0003] The traditional head-mounted display device mainly relies on fixed focal length design or user manual adjustment in the visual adjustment mechanism. This static adjustment mode cannot flexibly adapt to the individualized biological feature differences of different users, such as interpupillary distance, corneal curvature and other key parameters. Due to the significant differences in biological features among individuals, fixed focal length or manual adjustment often cannot achieve accurate matching, thereby significantly increasing the visual vergence accommodation conflict (VAC effect). The VAC (Vergence-Accommodation Conflict) effect is that when the user tries to focus on the object in the virtual scene, the visual lines of the two eyes cannot naturally converge at the same focal point, causing visual fatigue, dizziness and other discomfort.

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

[0005] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

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

[0007] To achieve the above purpose, the present application provides an optical adjustment method, which is applied to a head-mounted display device, the head-mounted display device comprising a biological feature acquisition module and a liquid lens array; the method comprising:

[0008] acquiring target biological feature data of a wearer through the biological feature acquisition module;

[0009] inputting the target biological feature data into a preset optical parameter prediction neural network model to predict target optical parameters, wherein the optical parameter prediction neural network model is trained with biological feature data as samples and optical parameters as labels;

[0010] adjusting the control voltage of the liquid lens array based on the target optical parameters to adjust the curvature of the lenses in the liquid lens array.

[0011] In an embodiment, the target optical parameter comprises a focal length compensation value, a lens curvature, and a dispersion compensation coefficient.

[0012] The step of adjusting the control voltage of the liquid lens array based on the target optical parameter comprises:

[0013] calculating a curvature correction term according to the focal length compensation value and the dispersion compensation coefficient;

[0014] adding the lens curvature and the curvature correction term to obtain a target curvature of the liquid lens array;

[0015] calculating a curvature difference value between an initial curvature of the liquid lens array and the target curvature;

[0016] calculating a target voltage according to the curvature difference value and a preset curvature-voltage coefficient;

[0017] adjusting the control voltage according to the target voltage.

[0018] In an embodiment, before the step of inputting the target biological feature data into the preset optical parameter prediction neural network model, the method further comprises:

[0019] recollecting the target biological feature data if the target biological feature data does not conform to a preset normal range;

[0020] inputting the target biological feature data into a preset convolutional network to obtain vectorized target biological feature data.

[0021] In an embodiment, the head-mounted device further comprises a score obtaining module.

[0022] After the step of adjusting the control voltage of the liquid lens array based on the target optical parameter, the method further comprises:

[0023] obtaining a comfort score through the score obtaining module;

[0024] updating the optical parameter prediction neural network model based on the comfort score, and returning to the step of collecting target biological feature data of the wearer through the biological feature collection module.

[0025] In an embodiment, the score obtaining module comprises a physiological signal collection unit.

[0026] The step of obtaining a comfort score through the score obtaining module comprises:

[0027] collecting target physiological signals of the wearer through the physiological signal collection unit;

[0028] determine a comfort score corresponding to the target physiological signal according to a preset mapping relationship.

[0029] In an embodiment, the target physiological signal comprises: a blink frequency and a skin conductance.

[0030] The step of determining the comfort score corresponding to the target physiological signal according to a preset mapping relationship comprises:

[0031] determining a first comfort score corresponding to the blink frequency and a second comfort score corresponding to the skin conductance according to a preset mapping relationship, wherein the blink frequency is negatively correlated with the first comfort score, and the skin conductance is negatively correlated with the second comfort score.

[0032] performing weighted calculation on the first comfort score and the second comfort score according to a preset weight to obtain the comfort score.

[0033] In an embodiment, the optical parameter prediction neural network model is a GAN model, and the step of updating the optical parameter prediction neural network model based on the comfort score comprises:

[0034] determining a loss function of the GAN model according to the comfort score;

[0035] updating a weight of a generator in the GAN model based on a preset gradient descent algorithm and the loss function.

[0036] In an embodiment, the biological feature acquisition module comprises: a camera unit and an eye movement detection unit; and the target biological feature data comprises: an interpupillary distance, a corneal curvature, a gaze point coordinate and an eye movement speed.

[0037] The step of acquiring target biological feature data of a wearer by the biological feature acquisition module comprises:

[0038] acquiring an eyeball image of the wearer by the camera unit;

[0039] acquiring an interpupillary distance and a corneal curvature of the wearer based on the eyeball image;

[0040] acquiring a gaze point coordinate and an eye movement speed of the wearer by the eye movement detection unit.

[0041] In addition, to achieve the above-mentioned purposes, the present application also provides a head-mounted device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the optical adjustment method as described above.

[0042] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the optical adjustment method described above.

[0043] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the optical adjustment method described above.

[0044] This application provides an optical adjustment method. The method involves collecting target biometric data of the wearer through a biometric acquisition module mounted on a head-mounted display device. The target biometric data is then input into an optical parameter prediction neural network model that has been trained using the biometric data as samples and the optical parameters as labels. After obtaining the target optical parameters output by the optical parameter prediction neural network model, the control voltage of the liquid lens array of the head-mounted display device is adjusted based on the target optical parameters to adjust the target curvature of the lenses in the head-mounted display device, thereby reducing the VAC effect of the head-mounted display device.

[0045] In summary, this application uses a pre-trained optical parameter prediction neural network model to predict optical parameters adapted to the user's biometric data based on the collected target biometric data of the wearer. Then, based on the optical parameters, it adjusts the control voltage of the liquid lens array in the head-mounted display device to adjust the target curvature of the lens in the head-mounted display device. Compared with a fixed focal length or a method where the user manually adjusts the focal length, this application enables the head-mounted display device to adapt to the biometric data of different users, automatically adjust the focal length of the head-mounted display device, and reduce the VAC effect of the head-mounted display device. Attached Figure Description

[0046] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0047] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a schematic flowchart of an embodiment of the optical adjustment method of this application;

[0049] Figure 2 This is a schematic diagram of the head-mounted display device structure involved in the embodiment of the optical adjustment method of this application;

[0050] Figure 3 The feedback flowchart provided for the second embodiment of the optical adjustment method of the present application is shown in the figure;

[0051] Figure 4 The flowchart provided for the second embodiment of the optical adjustment method of the present application is shown in the figure;

[0052] Figure 5 The device structure diagram of the hardware running environment involved in the optical adjustment method in the embodiments of the present application is shown in the figure.

[0053] The purpose implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and do not limit the present application.

[0055] In order to better understand the technical solutions of the present application, the specific embodiments will be described in detail below with reference to the drawings in the specification.

[0056] The main solution of the embodiments of the present application is: collecting target biological feature data of the wearer through the biological feature acquisition module; inputting the target biological feature data into a preset optical parameter prediction neural network model to predict target optical parameters, wherein the optical parameter prediction neural network model is trained with biological feature data as samples and optical parameters as labels; adjusting the control voltage of the liquid lens array based on the target optical parameters to adjust the target curvature of the lenses in the liquid lens array.

[0057] With the rapid development of head-mounted display device (referred to as "head-mounted device") technology, the optimization of performance and user experience of head-mounted devices has become the focus of industry research.

[0058] The traditional head-mounted device mainly relies on fixed focal length design or user manual adjustment in visual adjustment mechanism. This static adjustment mode cannot flexibly adapt to the individualized biological feature differences of different users, such as interpupillary distance, corneal curvature and other key parameters. Due to the significant differences in biological features among individuals, fixed focal length or manual adjustment often cannot achieve accurate matching, which in turn leads to a significant increase in visual vergence accommodation conflict (VAC effect). VAC (Vergence-Accommodation Conflict) effect refers to the phenomenon that when the user tries to focus on the objects in the virtual scene, the lines of sight of the two eyes cannot naturally converge at the same focal point, causing visual fatigue, dizziness and other discomfort.

[0059] Therefore, how to reduce the VAC effect of the head-mounted device has become a problem to be solved by those skilled in the art.

[0060] To solve the above problems, the optical adjustment method provided in the present application collects target biological feature data of the wearer through the biological feature acquisition module carried by the head-mounted device, inputs the target biological feature data into an optical parameter prediction neural network model trained in advance with biological feature data as samples and optical parameters as labels, obtains target optical parameters output by the optical parameter prediction neural network model, and adjusts the control voltage of the liquid lens array of the head-mounted device based on the target optical parameters to adjust the target curvature of the lens in the head-mounted device, thereby reducing the VAC effect of the head-mounted device.

[0061] In summary, the optical parameter prediction neural network model trained in advance is used to predict the optical parameters suitable for the biological feature data of the user based on the target biological feature data of the wearer collected, and then the control voltage of the liquid lens array of the head-mounted device is adjusted based on the optical parameters to adjust the target curvature of the lens in the head-mounted device. Compared with the fixed focal length or manual adjustment of the focal length by the user, the head-mounted device can adapt to the biological feature data of different users and automatically adjust the focal length of the head-mounted device, thereby reducing the VAC effect of the head-mounted device.

[0062] The head-mounted device in the embodiment of the present application can include but is not limited to a head-mounted display device such as a Mixed Reality (MR) device (e.g., MR glasses or MR helmet), an Augmented Reality (AR) device (e.g., AR glasses or AR helmet), a Virtual Reality (VR) device (e.g., VR glasses or VR helmet), an Extended Reality (XR) device or some combination thereof. In the present embodiment, the head-mounted device is taken as the execution subject for the convenience of description.

[0063] Based on this, the optical adjustment method provided in the present application embodiment is a method for adjusting the optical parameters of a head-mounted device, and the head-mounted device includes a biological feature acquisition module and a liquid lens array. Figure 1 , Figure 1 The flowchart of the first embodiment of the optical adjustment method of the present application is shown in the figure.

[0064] In the present embodiment, the optical adjustment method is applied to a head-mounted device, and the head-mounted device includes a biological feature acquisition module and a liquid lens array. The optical adjustment method includes steps S10-S30:

[0065] Step S10: Collect target biological feature data of the wearer through the biological feature acquisition module;

[0066] It should be noted that in this embodiment, the head-mounted device (i.e. head-mounted display device) mainly applies AR (Augmented Reality) technology, VR (Virtual Reality) technology and MR (Mixed Reality) technology, based on which the user can display virtual content in a real scene through various sensors, cameras or optical components in the device when wearing the head-mounted device.

[0067] It should be noted that in this embodiment, the biological collection module can include a plurality of hardware modules for collecting different types of biological feature data, has biological feature recognition capability, and is used to collect a plurality of key biological feature data of the wearer.

[0068] In this embodiment, the biological feature collection module built-in the head-mounted device automatically starts the biological feature data collection function after detecting that the user correctly wears the head-mounted device, and collects the biological feature data of the wearer related to the VAC effect, including but not limited to inter-pupillary distance (IPD), corneal curvature, iris texture, etc.

[0069] In a feasible implementation, the setting position of the liquid lens array can also be adjusted based on the collected IPD.

[0070] In this embodiment, the liquid lens array can be arranged in a set of mechanical structures that can adjust the position respectively, and after the IPD of the wearer is collected, the setting position of the liquid lens array is adjusted according to the IPD, so that the visual center of the liquid lens array matches the IPD, and further adapts to the physiological data of the user.

[0071] Further, in a feasible implementation, the biological feature collection module includes a camera unit and an eye movement detection unit; the target biological feature data includes inter-pupillary distance, corneal curvature, gaze point coordinates and eye movement speed; and the step S10 can include steps S11-S15.

[0072] Step S11, acquiring the eye image of the wearer through the camera unit;

[0073] It should be noted that in this embodiment, the biological feature collection module can include a camera unit and an eye movement detection unit, the camera unit can be used to collect the eye image of the wearer, and the eye movement detection unit can be used to track the eye movement data of the wearer.

[0074] In this embodiment, when the wearer correctly wears the head-mounted device, the camera unit starts to work. The camera unit usually adopts a high-resolution camera and has automatic focusing and light compensation functions to ensure that clear and accurate eye images can be obtained under different lighting conditions. During the collection process, the camera unit will capture the eye region of the wearer in real time and obtain a series of continuous eye image frames. These image frames contain appearance information of the eye, such as pupil size, position, corneal shape, and other characteristics.

[0075] Step S12, obtaining the interpupillary distance and corneal curvature of the wearer based on the eye image;

[0076] In this embodiment, after the eye image is collected, the image processing algorithm built in the head-mounted device analyzes and processes the eye image collected by the camera unit to extract biometric data such as interpupillary distance and corneal curvature.

[0077] As an example, specifically, the algorithm first pre-processes the eye image, including image enhancement, edge detection, and other operations to highlight the outline of the pupil. Then, the center positions of the two pupils are determined through image recognition technology, and the distance between them is calculated, which is the interpupillary distance.

[0078] Then, the corneal shape information in the eye image is used to calculate the radius of curvature of the cornea in combination with a pre-set corneal model and mathematical algorithm. Corneal curvature is an important indicator to measure the degree of curvature of the cornea and is crucial for the optical design of the head-mounted device.

[0079] Step S13, obtaining the gaze point coordinates and eye movement speed of the wearer through the eye movement detection unit;

[0080] In this embodiment, the eye movement detection unit calculates the coordinates of the current gaze point of the wearer according to the movement trajectory of the eye and the position information of the pupil. The gaze point coordinates reflect the visual focus position of the wearer. In addition to the gaze point coordinates, the eye movement detection unit can also measure the movement speed of the eye, i.e., the eye movement speed. Changes in eye movement speed can reflect the degree of concentration of the wearer's attention and the efficiency of visual search.

[0081] In addition, the historical comfort ratings of the user can also be included in the input model data, specifically including:

[0082] Step S14, obtaining a plurality of historical reference ratings according to a pre-set window;

[0083] In this embodiment, in order to more comprehensively evaluate the comfort feeling of the wearer, the head-mounted device will also consider the historical use data of the wearer, obtain a plurality of historical reference scores from the historical data according to a preset time window (such as the last 5 scores, the last month, etc.), which can be the comfort scores obtained by the wearer through the score acquisition module when using the head-mounted device in the past, or scores automatically calculated by the device according to other indicators (such as use time, number of abnormal exits, etc.).

[0084] Step S15, the average of each historical reference score is calculated to obtain a historical score.

[0085] In this embodiment, after obtaining a plurality of historical reference scores, the head-mounted device will average these scores to obtain a comprehensive historical score, which reflects the overall comfort feeling of the wearer to the head-mounted device in the past period of time. This score can be an important reference for current comfort evaluation, helping the device better understand the needs and preferences of the wearer.

[0086] In a further example, please refer to Figure 2 The head-mounted device is internally integrated with an optical perception system, the core components of which include left and right symmetrical infrared camera modules and left and right iris recognition camera arrays. These cameras use high-sensitivity sensors with low noise and high dynamic range characteristics, and can accurately capture the subtle features of the eye area. In the zoom control module, a liquid lens array technology is used, which is composed of multiple micro liquid lens units. Each unit can be independently adjusted in focus by electric field driving, realizing continuous zoom function with millisecond-level response. At the same time, cooperating with the electrochromic layer, the light transmittance is accurately controlled by applying different voltages, so as to dynamically optimize the light flux and contrast of the optical system. After the cooperation of the zoom module, left and right light splitting prisms and high-precision optical lens groups, the virtual image is accurately projected to the display screen, and the distortion is corrected through the free-form optical system, so that the user can observe the clear and distortion-free virtual image through the eyepiece.

[0087] For dynamic adjustment of optical parameters, the head-mounted device can realize real-time switching of virtual image focal length through the built-in calibration algorithm. Specifically, when the user needs to switch from focusing on virtual image A (such as a close-range virtual object) to virtual image B (such as a long-range virtual scene), the head-mounted device can complete the focal length adjustment through the fast response characteristics of the liquid lens array, and the electrochromic layer synchronously optimizes the light transmittance to match the light intensity requirement under the new focal length. Conversely, when returning from virtual image B to virtual image A, the head-mounted device can also complete the reverse adjustment with the same accuracy and speed, ensuring the coherence and comfort of the user's visual experience.

[0088] Based on the above hardware architecture, when the head-mounted device collects biological feature data, the left and right infrared cameras work synchronously at a sampling rate of 60 Hz, and the three-dimensional coordinates of the pupil center of the wearer are calculated in real time through a binocular stereo vision algorithm, and then the accurate IPD value is obtained. The data is stored in the CSV format (including timestamp, left / right pupil X / Y / Z coordinates, IPD value, etc.) in frames in the flash memory built-in the head-mounted device, the iris camera collects dynamic images of the wearer's eyeball at a high frame rate (≥30 fps), the head-mounted device uses deep learning algorithm to identify the micro-deformation features (such as blood vessel distribution, wrinkle shape, etc.) on the surface of the iris, and combines with the geometric optical model to inverse the corneal curvature radius, the collected corneal curvature image is stored in JPEG format (640×480 pixels, 8-bit grayscale), the eye tracker module captures the rotation angle and micro-movement of the wearer's eyeball at a sampling rate of 120 Hz, calculates the gaze point coordinates, and analyzes the eye movement speed and acceleration using the optical flow method, and the detection data is stored in JSON format (including timestamp, gaze point X / Y coordinates, eye movement speed vector, etc.) to support real-time gaze point heat map generation and eye movement trajectory playback function.

[0089] In step S20, the target biological feature data is input into a preset optical parameter prediction neural network model to predict the target optical parameter, wherein the optical parameter prediction neural network model is trained based on biological feature data as samples and optical parameters as labels.

[0090] It should be noted that in the present embodiment, 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 are integrated in the head-mounted device as a basic neural network model, and the optical parameter prediction neural network model is obtained through a large amount of training. In the model training stage, a large amount of biological feature data of different age, gender and other population, and sample data set of corresponding optical parameters with best wearing experience and best visual comfort degree of current biological signal are used, and through deep learning algorithm, the optical parameter prediction neural network model can learn the complex mapping relationship between biological feature data and optical parameters.

[0091] In the embodiment, the head-mounted device inputs the collected target biological feature data as input data into a preset optical parameter prediction neural network model, the optical parameter prediction neural network model performs rapid processing and analysis on the input target biological feature data, predicts and outputs target optical parameters matched with the wearer biological feature data by using the mapping relationship learned in the optical parameter prediction neural network model, and the target optical parameters directly determine the VAC effect of the head-mounted device.

[0092] The optical parameter prediction neural network model can be 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, and the embodiment is not limited in this regard.

[0093] As an example, the optical parameter prediction neural network model can be a GAN (Generative Adversarial Network) model, the GAN model including a generator and a discriminator, the generator (Generator) including an input layer (a 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).

[0094] The discriminator (Discriminator) includes an input layer (3-dimensional optical parameters), a convolutional layer (64 filters, step 2), a fully connected layer (128 nodes), and a binary output (real / generated probability). Among the multiple inference results output by the generator, the group of data with the highest real / generated probability is selected as the final output result.

[0095] Further, in a feasible implementation, before the step S20, the method can further include steps A10-A20:

[0096] Step A10, in the case where the target biological feature data does not conform to the preset normal range, re-collecting the target biological feature data;

[0097] In this embodiment, after the target biological feature data of the wearer is collected, the head-mounted device performs preliminary legality verification on the data. The preset normal range is determined according to a large amount of sample data and actual application requirements, and covers the biological feature data range of different user groups in the normal state. For example, a reasonable interval range is set for interpupillary distance, and there is also a corresponding normal value range for corneal curvature.

[0098] When the head-mounted device determines that the collected target biological feature data is not within the preset normal range, there can be many reasons, such as sensor failure, collection environment interference, non-standard wearing of the wearer, etc. At this time, the head-mounted device triggers a re-collection mechanism, and informs the wearer to re-collect biological feature data through interface prompts or voice prompts. During the re-collection process, the biological feature collection module is started again, and new target biological feature data is obtained according to the same collection process and standard. The head-mounted device performs legality verification on the re-collected data again, until the collected data meets the preset normal range, to ensure that the data used in the subsequent steps is accurate and reliable.

[0099] Taking interpupillary distance (IPD) as an example, the preset normal range of the head-mounted device can not only include the statistical mean ± 2σ interval, but also introduce quantile correction based on user age group (such as allowing ± 3σ fluctuation for child users), dynamic compensation of device wearing angle (± 1mm tilt tolerance), and calibration coefficient of real-time environmental light influence (such as IPD value may shrink 0.5-1mm in strong light environment).

[0100] When the head-mounted device detects that the collected data exceeds the preset range through the verification algorithm, a multi-dimensional abnormality diagnosis mechanism is triggered. First, the device analyzes the state parameters of the sensor itself (such as infrared light source intensity, camera exposure time, temperature drift, etc.), compares the historical baseline value to determine whether there is a hardware failure; second, combined with environmental sensor data (such as light intensity, humidity, electromagnetic interference intensity) to evaluate external interference factors; finally, by analyzing the head posture of the wearer (accelerometer / gyroscope data), device wearing pressure distribution (pressure sensor array data), and user interaction behavior (such as blink frequency, eye tremor pattern), to determine whether there is non-standard wearing (such as device sliding, light leakage, orbital compression) or user physiological abnormalities (such as fatigue, drug effects) and the like.

[0101] If it is determined that the abnormality is retryable (such as a temporary environmental disturbance or a slight wearing deviation), the head-mounted device will immediately start the re-collection mechanism. The device will guide the wearer to adjust the device position, clean the collection area, or re-enter the collection state through multi-modal interaction modes such as visual prompts (such as pupil position calibration animation, device wearing angle diagram), auditory prompts (multilingual voice instructions, environmental sound effect compensation), and tactile feedback (slight vibration prompt). During the re-collection process, the biometric feature collection module (including infrared camera array, iris scanner, eye tracker, etc.) will operate in a higher precision mode, enable self-calibration algorithms (such as auto-focus, white balance adjustment, distortion correction), and increase data redundancy (such as collecting 3 sets of data and taking the median).

[0102] Step A20, input the target biometric feature data into the preset convolutional network to obtain the vectorized target biometric feature data.

[0103] In this embodiment, after the target biometric feature data passes the legality check, it needs to be vectorized for subsequent processing and analysis in the optical parameter prediction neural network model. The preset convolutional network is a deep learning model specially designed for this purpose.

[0104] Specifically, after collecting the wearer's biometric feature data, the biometric feature data also needs to be preprocessed for subsequent model analysis and calculation. First, the abnormal values in the biometric feature data are removed, for example, when the IPD does not meet the range of 54 to 74 mm, it is considered as abnormal data and needs to be re-measured. After removing the abnormal data, the IPD, corneal curvature and other parameters are normalized to the interval [0, 1], then the timestamp of the collected data is synchronized with the multi-modal data, and finally the 10-dimensional feature vector is output by inputting the collected data including the user's historical comfort score into the convolutional network for feature extraction. wherein X IPD : IPD data; X cornea : corneal curvature data; X gaze : gaze point coordinates, the 10-dimensional feature vector includes:

[0105] 1) interpupillary distance (IPD, 1 dimension);

[0106] 2) corneal curvature (3 dimensions, extracted from iris image features);

[0107] 3) gaze point coordinates (2 dimensions, x / y axis normalized values);

[0108] 4) eye movement speed (2 dimensions, horizontal / vertical components);

[0109] 5) user's historical comfort score (2 dimensions, sliding average of the last 5 scores).

[0110] Step S30, adjusting the control voltage of the liquid lens array based on the target optical parameter to adjust the target curvature of the lens in the liquid lens array.

[0111] In this embodiment, after the head-mounted device receives the target optical parameter output by the optical parameter prediction neural network model, the control voltage adjustment program of the liquid lens array is immediately started. The liquid lens array is a key component in the head-mounted device for realizing optical zoom and aberration correction, and the accuracy of its working parameters directly affects the VAC effect of the head-mounted device.

[0112] In this embodiment, the head-mounted device adjusts the control voltage of the liquid lens array in real time through electronic control means according to the received target optical parameter. Through the electro-deformation material, the change of the control voltage can cause the lens material to deform in a specific way to adjust the curvature of the lens.

[0113] Further, in a possible implementation, the target optical parameter includes a focal length compensation value, a lens curvature, and a dispersion compensation coefficient; and the step S30 can further include steps S31-S35.

[0114] Step S31, calculating a curvature correction term according to the focal length compensation value and the dispersion compensation coefficient;

[0115] 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 the differences in biological characteristics of the wearer (such as different interpupillary distances and corneal curvatures), to ensure clear and accurate imaging.

[0116] The lens curvature is used to describe the degree of curvature of the lens surface, and different curvatures will affect the refraction and focusing effect of light.

[0117] The dispersion compensation coefficient is used to correct the dispersion phenomenon caused by the different refractive indices of different color light, reduce chromatic aberration, and improve the color restoration and clarity of the image.

[0118] In this embodiment, the curvature correction term, i.e., the curvature that needs to be compensated, can be calculated according to the focal length compensation value and the dispersion compensation coefficient.

[0119] Step S32, adding the lens curvature and the curvature correction term to obtain the target curvature of the liquid lens array;

[0120] In this embodiment, after the curvature correction term is calculated, the target curvature of the liquid lens array to be adjusted can be obtained by adding the lens curvature and the curvature correction term.

[0121] Step S33, calculating the curvature difference between the initial curvature and the target curvature of the liquid lens array;

[0122] 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 lenses in the liquid lens array.

[0123] Step S34: Calculate the target voltage based on the curvature difference and the preset curvature-voltage coefficient;

[0124] In this embodiment, after calculating the curvature difference, MagicK calculates the target voltage based on the preset curvature-voltage coefficient.

[0125] Step S35: Adjust the control voltage according to the target voltage.

[0126] In this embodiment, after obtaining the target voltage, adjusting the control voltage to the target voltage can adjust the lens curvature of the liquid lens array.

[0127] Specifically, in one example, the radius of curvature R of the liquid lens is strictly related to the focal length f via the thin lens formula:

[0128] ;

[0129] in:

[0130] n: Refractive index of the liquid lens material (e.g., PDMS, n=1.43);

[0131] R fix The radius of the fixed curvature surface (determined by the lens's mechanical structure, such as R) fix =500μm);

[0132] R: Dynamically adjustable radius of curvature;

[0133] The relationship between the radius of curvature R of a liquid lens and the driving voltage V is as follows:

[0134] ;

[0135] in:

[0136] R: Target radius of curvature (μm), calculated from the curvature parameter in the generator output Y.

[0137] V: Driving voltage (V), the target value to be calculated.

[0138] k: Lens material property constant (e.g., for dielectric elastomers, k = 0.12 μm / V²).

[0139] , Vacuum permittivity (8.85e-12 F / m) and relative permittivity of materials (e.g., PDMS) = 2.8).

[0140] d: electrode spacing (pm, default 50 pm).

[0141] R0: zero voltage curvature radius (determined by the initial shape of the lens, usually 200 pm).

[0142] By collecting the target biological feature data of the wearer and using the optical parameter prediction neural network model to predict the optical parameters that adapt to the user's biological feature data, the head-mounted device can achieve personalized optical adaptation, which ensures that each user can obtain the best wearing experience regardless of their biological feature data. Traditional head-mounted devices often have difficulty achieving precise matching due to the use of fixed focal length or manual adjustment methods, resulting in a significant increase in visual accommodation convergence adjustment conflict (VAC effect), while the optical adjustment method of the present application automatically adjusts the working parameters of the liquid lens array, enabling the optical parameters of the head-mounted device to adapt to the user's biological feature data, thereby effectively reducing the VAC effect and reducing visual fatigue and dizziness and other discomfort. In addition, since the head-mounted device can automatically adapt to the biological feature data of different users and adjust the working parameters in real time to reduce the VAC effect, users do not need to perform complex manual adjustment operations during use, which not only improves the convenience of use, but also significantly improves the overall experience of users.

[0143] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as the above embodiment one can refer to the above introduction, and the following will not be repeated. On this basis, please refer to Figure 3 , Figure 3 is a flowchart of the second embodiment of the optical adjustment method of the present application.

[0144] In this embodiment, the head-mounted device further comprises a score acquisition module; after the above step S30, the optical adjustment method can further comprise steps S40-S50:

[0145] Step S40, obtaining the comfort score by the score acquisition module;

[0146] In this embodiment, after the head-mounted device adjusts the working parameters of the liquid lens array based on the target optical parameters, the built-in score acquisition module of the device is used to monitor and evaluate the comfort feeling of the wearer in real time. Specifically, the score acquisition module can obtain the comfort score in various ways, for example:

[0147] Physiological index monitoring: using the built-in sensor to monitor the heart rate, skin electrical response and other physiological indexes of the wearer, which can reflect the tension and comfort state of the wearer.

[0148] Visual feedback collection: through the built-in camera or eye tracking technology of the head-mounted device, the wearer's blinking frequency, eye movement and other visual behaviors are observed to infer their visual comfort.

[0149] User-initiated feedback: provide comfort rating options on the user interface of the head-mounted device, allowing the wearer to rate according to their subjective feelings.

[0150] The scoring acquisition module integrates the above information and calculates the current comfort score through a preset algorithm. This score reflects the wearer's satisfaction and comfort feeling for the current optical parameters of the head-mounted device.

[0151] Further, in a feasible implementation, the scoring acquisition module includes a physiological signal acquisition unit, and the step S40 can include steps S41-S42:

[0152] Step S41, acquiring the target physiological signal of the wearer through the physiological signal acquisition unit;

[0153] In this embodiment, when feedback detection is performed, the physiological signal acquisition unit acquires the target physiological signal of the wearer.

[0154] Step S42, determining the comfort score corresponding to the target physiological signal according to the preset mapping relationship.

[0155] In this embodiment, in the head-mounted device, the mapping relationship between the physiological signal and the comfort score is pre-stored, and according to this mapping relationship, the comfort score corresponding to the target physiological signal can be determined.

[0156] Specifically, when evaluating the comfort of the head-mounted device user, the entire evaluation process integrates interactive technology, biological signal detection technology and data analysis algorithm. Specifically, in the process of obtaining the comfort score, the head-mounted device first displays the interactive interface in the form of a graphical user interface (GUI) through its built-in display module, guiding the user to complete a series of preset operation tasks or evaluation processes. At the same time, in order to enhance the diversity and convenience of interaction, the device is also equipped with a speaker system that can output voice prompts to guide the user on how to submit their subjective ratings of the current use experience through voice commands, touch clicks or other preset interaction methods (such as gesture recognition, eye tracking triggering, etc.).

[0157] While the user is interacting with the device, the head-mounted device collects the user's physiological data in a non-intrusive manner. On the one hand, the device measures the changes in the skin conductivity around the user's eyes through bioelectricity detection sensors integrated around the eyes or the frame. Skin conductivity is a sensitive indicator of sympathetic nervous system activity, and its changes are closely related to the individual's emotional state, cognitive load, and physiological stress response. When the user experiences discomfort such as visual fatigue, motion sickness, or accommodation conflict during the use of the head-mounted device, the excitability of the sympathetic nervous system will significantly increase, prompting the sweat glands to secrete more, thereby causing the skin conductivity to rise. On the other hand, in a comfortable use state, the parasympathetic nervous system dominates, and the skin conductivity tends to be stable or decrease. Therefore, by continuously monitoring the changes in skin conductivity, the user's comfort level can be objectively reflected.

[0158] On the other hand, the head-mounted device also uses the built-in camera or a special eye tracking sensor to monitor the user's blinking behavior in real time. Blinking frequency and eye closure time are another important indicator of user physiological state and cognitive load, and their changes can also reveal the user's comfort level. Specifically, when the user feels uncomfortable or tired, the blinking frequency often increases, and the eye closure time may also be extended, which are natural reactions of the body to alleviate discomfort by reducing visual stimulation.

[0159] Based on the above-mentioned user biological signals obtained from skin conductivity and blinking behavior, the head-mounted device can use algorithmic models for comprehensive analysis to objectively and accurately evaluate the user's comfort level. To further improve the accuracy and reliability of the evaluation, the device will also collect scoring data from multiple data sources, multiple different time points, or different use scenarios, and use a weighted average method to integrate and process these data, ultimately obtaining a comprehensive and objective comfort score.

[0160] Further, in a possible implementation, please refer to Figure 4 The target physiological signals include: blinking frequency and skin conductivity; and the step S42 can include steps S421-S422.

[0161] The step S421 determines a first comfort score corresponding to the blinking frequency and a second comfort score corresponding to the skin conductivity according to a preset mapping relationship, wherein the blinking frequency is negatively correlated with the first comfort score, and the skin conductivity is negatively correlated with the second comfort score.

[0162] It should be noted that, under normal circumstances, the blinking frequency of a person in a relaxed and comfortable state is relatively stable and natural. When the head-mounted device is uncomfortable, such as visual fatigue, dry eyes, etc., the wearer will unconsciously increase the blinking frequency in an attempt to alleviate the discomfort. Therefore, the higher the blinking frequency, the lower the comfort level of the wearer, and the lower the first comfort score. Similarly, the skin conductance reflects the electrical properties of the skin. When the human body is in a state of tension, anxiety or discomfort, the sweat glands of the skin will increase secretion, causing the skin conductance to rise. When wearing a head-mounted device, if discomfort occurs, the wearer's mood may be affected, causing changes in skin conductance. Therefore, the higher the skin conductance, the lower the comfort level of the wearer, and the lower the second comfort score.

[0163] In this embodiment, through a large amount of experimental data collection and analysis, a mapping relationship between the blinking frequency and the first comfort score can be established. For example, different blinking frequency intervals are set to correspond to different first comfort scores. When the blinking frequency is in a lower interval, the first comfort score is higher. As the blinking frequency increases, the first comfort score gradually decreases. Similarly, based on experimental data, a mapping relationship between the skin conductance and the second comfort score is established. Different skin conductance thresholds or ranges are set to correspond to different second comfort scores. The lower the skin conductance value, the higher the second comfort score. The higher the skin conductance value, the lower the second comfort score.

[0164] Step S422, the first comfort score and the second comfort score are weighted and calculated according to the preset weight to obtain the comfort score.

[0165] In this embodiment, the first comfort score and the second comfort score are weighted and calculated according to the preset weight, so as to obtain the final comfort score. The preset weight is determined according to the importance of blinking frequency and skin conductance in reflecting the comfort level of the wearer.

[0166] By comprehensively considering the blinking frequency and the skin conductance, two physiological signals, and determining their corresponding comfort scores respectively, and then performing weighted calculation, the comfort state of the wearer can be more comprehensively and accurately evaluated. Compared with the single physiological signal evaluation method, this method can reduce the error caused by individual differences and signal fluctuations, and improve the reliability of the comfort score.

[0167] Step S50, updating the optical parameter prediction neural network model based on the comfort score, and returning to the step of collecting the target biological feature data of the wearer through the biological feature collection module.

[0168] In this embodiment, after obtaining the comfort score, the head-mounted device analyzes and processes the score. If the analysis result shows that the comfort score is at a high level, it indicates that the target optical parameters generated by the current optical parameter prediction neural network model are highly matched with the actual needs of the wearer. Not only does it meet the user's expectations in terms of visual effect, but it also does not cause significant discomfort during long-term wear. This positive feedback indicates that the model has high accuracy in capturing subtle differences in user biological characteristics and predicting optimal optical parameters. Therefore, the device further takes action to store the biological characteristic data collected this time (such as interpupillary distance, corneal curvature, eye movement trajectory, etc.), target optical parameters (such as focal length, light field distribution, color temperature adjustment, etc.), and user-provided comfort score 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 neural network model under specific conditions, providing data resources for the continuous optimization of subsequent models.

[0169] Subsequently, these newly added training samples will be included in the training process of the optical parameter prediction neural network model. Through machine learning algorithms, the parameters and structure of the optical parameter prediction neural network model are continuously iteratively optimized, so that in future use, it can more accurately predict and generate target optical parameters that meet the user's individual needs. This process is a cycle of continuous improvement, aiming to continuously improve the comfort and performance of the head-mounted device.

[0170] On the contrary, if the analysis result shows a low comfort score, it indicates that the current optical parameter prediction neural network model has deviations in outputting target optical parameters, failing to fully consider the biological feature differences of the wearer or the needs in specific use scenarios. The device will use this comfort score as direct feedback signal, back-propagating to each layer of neural network of the optical parameter prediction neural network model, adjusting the weight parameters of each layer of neural network, and guiding it to learn more accurate and user demand-oriented optical parameter generation strategies.

[0171] After adjusting the weight parameters of the optical parameter prediction neural network model, the device will re-collect the target biological characteristic data of the wearer and input it into the updated and adjusted optical parameter prediction neural network model, thereby generating new target optical parameters. This process may be repeated multiple times until the newly generated optical parameters can obtain a high comfort score in subsequent user tests. Through this continuous iteration and continuous optimization, the head-mounted device can gradually approach the limit of user needs, providing users with a more comfortable and more personalized visual experience.

[0172] Further, in an available embodiment, the optical parameter prediction neural network model is a GAN model, and the step of updating the GAN model based on the comfort score in step S50 comprises steps S51-S52:

[0173] In step S51, the loss function of the GAN model is determined according to the comfort score.

[0174] In this embodiment, the loss function of the GAN model can be obtained by weighted calculation according to the comfort score.

[0175] Specifically, the loss function L combines the adversarial loss and the user score weighting:

[0176] ;

[0177] L adv : Adversarial Loss, measures the probability that the generator output parameters are recognized by the discriminator.

[0178] L score : Comfort Loss, quantifies the matching degree of the generated parameters and the user comfort.

[0179] λ1, λ2: weight coefficients, used to balance the adversarial training and user feedback. The default values are λ1=0.7, λ2=0.3, which need to be adjusted according to the validation set.

[0180] In step S52, the weights of the generator in the GAN model are updated based on the preset gradient descent algorithm and the loss function.

[0181] In this embodiment, further, the weights of the generator in the GAN model are updated using the preset gradient descent algorithm combined with the loss function, gradually adjusting the model to the optimal state.

[0182] Specifically, the Mini-batch SGD can be used to update the weights of the generator:

[0183] ;

[0184] θ G : trainable parameters of the generator;

[0185] η: Learning Rate, controls the step size of parameter update. The initial value of η is set to 0.0002, which is exponentially decayed with the training round: the initial learning rate η0=0.0002;

[0186] ▽ θG : the gradient of the loss function with respect to the generator parameters.

[0187] S, Y: user score and the current generated optical parameters.

[0188] In one possible implementation, before the step S50, the optical adjustment method further comprises steps B10-B20:

[0189] Step B10, determining whether the comfort score is less than a first preset score.

[0190] It should be noted that the first preset score refers to a reference value or threshold value set in the optical adjustment system of the head-mounted device, which is used to evaluate whether the visual comfort of the wearer has reached an acceptable standard. This score is based on a series of pre-defined rules, standards or ideal comfort levels obtained through extensive user testing and data analysis. Specifically, the first preset score is a numerical standard representing the minimum level of visual comfort that the wearer should achieve when using the head-mounted device, which is usually determined by the device manufacturer based on a large amount of user experience data, physiological research and the needs of specific application scenarios. This score serves as a basis for judgment to help the system decide whether to update the optical parameter prediction neural network model. If the target comfort score of the wearer is less than the first preset score, it indicates that the current optical settings have not fully met the user's visual needs, and there is room for improvement in the optical parameter prediction neural network model; otherwise, if the target comfort score is equal to or higher than the first preset score, it means that the current settings can already provide a good user experience, and there is no need to further update the optical parameter prediction neural network model.

[0191] By introducing the concept of the first preset score, this embodiment can intelligently determine when to start the update process of the optical parameter prediction neural network model while ensuring user experience, thereby improving the prediction accuracy of the optical parameter prediction neural network model and ensuring the best visual experience for users. This mechanism not only helps to reduce unnecessary resource consumption, but also significantly improves user satisfaction and overall performance of the device.

[0192] Step B20, in the case where the target comfort score is determined to be less than the first preset score, performing the step of updating the optical parameter prediction neural network model based on the comfort score.

[0193] In this embodiment, once it is determined that the comfort score is less than the first preset score, it means that the current visual experience of the wearer has not reached an ideal state, and there may be a more obvious VAC problem. At this time, the system will automatically start the update process and enter step S50 to update the optical parameter prediction neural network model based on the comfort score.

[0194] The embodiment adopts a mechanism of judging first and then acting, which not only improves the response efficiency of the system, avoids unnecessary resource consumption, but also ensures that the model is updated only when the wearer's experience needs to be improved, thereby helping to maintain the stability of the device performance and the long-term satisfaction of the user.

[0195] The embodiment realizes personalized prediction of the target optical parameter by introducing a scoring module to evaluate the comfort of the wearer in real time and dynamically updating the optical parameter prediction neural network model based on the evaluation result (i.e., the comfort score), so that the target optical parameter predicted by the optical parameter prediction neural network model is more matched with the target biological feature data of the wearer, thereby effectively reducing the visual accommodation convergence adjustment conflict (VAC effect) in the head-mounted device and improving the user wearing experience.

[0196] Further, in a possible implementation, after the step B10, the optical adjustment method further includes steps B30-B40:

[0197] Step B30, calibrating the target optical parameter based on the comfort score;

[0198] In the embodiment, when it is determined that the current optical setting fails to fully meet the visual comfort needs of the wearer, there is a certain degree of VAC effect or other discomfort factors, the system can use a feedback control algorithm (such as PID control, gradient descent method, etc.) to fine-tune the original target optical parameter according to the deviation between the comfort score and the ideal score, to generate a set of optimized optical parameters that are more in line with the subjective feelings and physiological state of the wearer, i.e., the calibrated target optical parameter.

[0199] Step B40, adjusting the control voltage of the liquid lens array according to the calibrated target optical parameter to adjust the curvature of the liquid lens array.

[0200] After the calibration of the target optical parameter is completed, the embodiment can convert these optimized parameters (i.e., the calibrated target optical parameter) into specific control instructions and input them to the driving module of the liquid lens array. Each lens unit in the liquid lens array has variable curvature characteristics, and the curvature can be dynamically regulated by applying different voltages. Therefore, the embodiment calculates the corresponding control voltage value according to the calibrated target optical parameter and loads it to the corresponding liquid lens unit, thereby changing the curvature distribution of the lens surface.

[0201] The embodiment realizes a closed-loop feedback mechanism from "perceived comfort" to "physical optical adjustment": the comfort score of the wearer is converted into actual changes in optical parameters, and ultimately embodied in the physical form adjustment of the liquid lens array, so that the virtual image is more in line with the visual focus of the user, effectively alleviating the VAC effect and improving the display quality and user experience.

[0202] In summary, by performing the comfort score-based calibration on the target optical parameters through step B30 and applying the calibration results to the actual adjustment of the liquid lens array through step B40, the embodiment constructs a dynamic adaptive optical adjustment mechanism that integrates score feedback and physical adjustment, thereby significantly improving the visual adaptation capability and user satisfaction of the head-mounted device in complex application scenarios.

[0203] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the optical adjustment method of the present application. Further simple transformations based on this technical concept are within the protection scope of the present application.

[0204] The present application provides a head-mounted device, which comprises at least one processor and a memory connected in communication with 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 in Embodiment I.

[0205] Reference will be made to the accompanying drawings Figure 5 which shows a structural schematic diagram of a head-mounted device suitable for implementing the embodiments of the present application. The head-mounted device in the embodiments of the present application can include, but is not limited to, a head-mounted display device such as a Mixed Reality (MR) device (e.g., MR glasses or MR helmet), an Augmented Reality (AR) device (e.g., AR glasses or AR helmet), a Virtual Reality (VR) device (e.g., VR glasses or VR helmet), an Extended Reality (XR) device, or some combination thereof.

[0206] As Figure 5As shown, the head-mounted device can include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for the operation of the head-mounted device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the head-mounted device to communicate with other devices wirelessly or by wire to exchange data. Although the head-mounted device with various systems is shown in the figure, it should be understood that all the shown systems are not required to be implemented or possessed. More or fewer systems can be alternatively implemented or possessed.

[0207] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of embodiments of the present disclosure are performed.

[0208] The head-mounted device provided by the present application adopts the optical adjustment method in the above-mentioned embodiments, which can solve the technical problem of how to reduce the VAC effect of the head-mounted device. Compared with the prior art, the head-mounted device provided by the present application has the same beneficial effects as the optical adjustment method provided by the above-mentioned embodiments, and the other technical features in the head-mounted device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0209] It should be understood that various aspects of the disclosure can be implemented in 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 appropriate manner in any one or more embodiments or examples.

[0210] The above description is merely illustrative of the application and is not intended to limit the scope of the application. Any modifications or equivalents of the application should be construed as falling within the scope of the application. The scope of the application should be determined by the appended claims.

[0211] The application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e., a computer program) for performing the optical adjustment method in the above embodiments.

[0212] The computer readable storage medium provided by the application may, for example, be a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system or device, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electric connection having one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read only memory (ROM), an erasable programmable read only memory (EPROM or flash memory), an optical fiber, a portable compact disk read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination thereof. In the present embodiment, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, a system, or a device. The program code contained on the computer readable storage medium can be transmitted by any appropriate medium, including but not limited to an electric wire, an optical cable, an RF (Radio Frequency), or the like, or any appropriate combination thereof.

[0213] The above computer readable storage medium can be contained in a head-mounted device, or can exist separately and not be assembled into a head-mounted device.

[0214] The computer readable storage medium described above carries one or more programs, when the one or more programs are executed by the head-mounted device, the head-mounted device is caused to: acquire target biological feature data of a wearer through a biological feature acquisition module; input the target biological feature data into a preset optical parameter prediction neural network model to predict target optical parameters, wherein the optical parameter prediction neural network model is trained by taking biological feature data as samples and taking optical parameters as labels; and adjust a control voltage of a liquid lens array based on the target optical parameters to adjust a target curvature of the liquid lens array.

[0215] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0216] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0217] The modules involved in the embodiments of the present application can be implemented in a software manner or in a hardware manner. In some cases, the name of the module does not constitute a limitation on the module itself.

[0218] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e. computer program) for executing the optical adjustment method described above, and can solve the technical problem of how to reduce the VAC effect of the head-mounted device. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the optical adjustment method provided by the above-mentioned embodiments, which will not be repeated here.

[0219] The present application also provides a computer program product comprising a computer program, which, when executed by a processor, implements the steps of the optical adjustment method as described above.

[0220] The computer program product provided by the present application can solve the technical problem of how to reduce the VAC effect of the head-mounted device. Compared with the prior art, the computer program product provided by the present application has the same beneficial effects as the optical adjustment method provided by the above-mentioned embodiments, which will not be repeated here.

[0221] The above only describes some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation, direct / indirect application in other related technical fields based on the technical concept of the present application, and the contents of the specification and drawings are included in the patent protection scope of the present application.

Claims

1. A method of optical adjustment, characterized by, The optical adjustment method is applied to a head-mounted device, and the head-mounted device comprises a biological feature acquisition module and a liquid lens array; the method comprises: acquiring target biological feature data of a wearer through the biological feature acquisition module; inputting the target biological feature data into a preset optical parameter prediction neural network model to predict target optical parameters, wherein the optical parameter prediction neural network model is trained by taking biological feature data as samples and optical parameters as labels; adjusting a control voltage of the liquid lens array based on the target optical parameters to adjust the curvature of the liquid lens array; wherein the biological feature acquisition module comprises a camera unit and an eye movement detection unit; the target biological feature data comprises interpupillary distance, corneal curvature, gaze point coordinates, eye movement speed and historical scores; the biological feature acquisition module is further used for: obtaining an eyeball image of the wearer through the camera unit; obtaining the interpupillary distance and corneal curvature of the wearer based on the eyeball image; obtaining the gaze point coordinates and eye movement speed of the wearer through the eye movement detection unit; obtaining a plurality of historical reference scores according to a preset window, wherein the historical reference scores are historical comfort scores; calculating the average of each historical reference score to obtain a historical score.

2. The method of optical adjustment of claim 1, wherein, The target optical parameters comprise focal length compensation values, lens curvatures and dispersion compensation coefficients; The step of adjusting the control voltage of the liquid lens array based on the target optical parameters comprises: calculating a curvature correction term according to the focal length compensation value and the dispersion compensation coefficient; adding the lens curvature and the curvature correction term to obtain the target curvature of the liquid lens array; calculating the curvature difference between the initial curvature of the liquid lens array and the target curvature; calculating the target voltage according to the curvature difference and a preset curvature-voltage coefficient; adjusting the control voltage according to the target voltage.

3. The method of optical adjustment of claim 1, wherein, Before the step of inputting the target biological feature data into the preset optical parameter prediction neural network model, the method further comprises: if the target biological feature data does not match a preset normal range, reacquiring the target biological feature data; inputting the target biological feature data into a preset convolutional network to obtain vectorized target biological feature data.

4. The method of optical adjustment of claim 1, wherein, The head-mounted device further comprises a score acquisition module; After the step of adjusting the control voltage of the liquid lens array based on the target optical parameters, the method further comprises: obtaining a comfort score through the score acquisition module; updating the optical parameter prediction neural network model based on the comfort score, and returning to the step of acquiring target biological feature data of a wearer through the biological feature acquisition module.

5. The method of optical adjustment of claim 4, wherein, The score acquisition module comprises a physiological signal acquisition unit; The step of obtaining a comfort score through the score acquisition module comprises: acquiring target physiological signals of the wearer through the physiological signal acquisition unit; determining the comfort score corresponding to the target physiological signals according to a preset mapping relationship.

6. The method of optical adjustment of claim 5, wherein, The target physiological signals comprise blink frequency and skin conductance. The step of determining the comfort score corresponding to the target physiological signal according to the preset mapping relationship comprises: determining a first comfort score corresponding to the blink frequency and a second comfort score corresponding to the skin conductance according to a preset mapping relationship, wherein the blink frequency is negatively correlated with the first comfort score, and the skin conductance is negatively correlated with the second comfort score; weighting the first comfort score and the second comfort score according to a preset weight to obtain the comfort score.

7. The method of optical adjustment of claim 4, wherein, The optical parameter prediction neural network model is a GAN model, and the step of updating the optical parameter prediction neural network model based on the comfort score comprises: determining a loss function of the GAN model according to the comfort score; updating the weight of the generator in the GAN model based on a preset gradient descent algorithm and the loss function.

8. A head-mounted device, comprising: The device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the optical adjustment method according to any one of claims 1 to 7.

9. A storage medium, characterized by The storage medium is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the optical adjustment method according to any one of claims 1 to 7.

Images