Vehicle environment adjusting method and device, computer device and medium

Abstract

The embodiment of the invention discloses a vehicle environment adjusting method and device, computer equipment and a computer readable storage medium. In a specific implementation mode, the adjusting method comprises the steps that environment information of a vehicle and behavior information of a user are obtained; inputting the behavior information into a trained first recognition model so as to output behavior type information of the user by utilizing the trained first recognition model; when the behavior type information is photographing, inputting the environment information of the vehicle into a trained prediction model so as to output predicted illumination intensity by using the trained prediction model and output target illumination intensity suitable for photographing based on the predicted illumination intensity; and outputting first control information based on the target illumination intensity, so that the dimming glass adjusts the light transmittance. According to the embodiment, the vehicle environment can be intelligently adjusted through the dimming glass, and flexible and personalized driving experience is provided for drivers and passengers.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and more specifically, to a vehicle environment adjustment method, an adjustment device, a computer device, and a computer-readable storage medium. Background Art

[0002] Currently, in the vehicle industry, it is not possible to use intelligent driving systems to provide more flexible and personalized environmental adjustment solutions. Summary of the invention

[0003] The purpose of the present disclosure is to provide a vehicle environment adjustment method, an adjustment device, a computer device and a computer-readable storage medium to solve at least one of the problems existing in the prior art.

[0004] In order to achieve the above objectives, the present invention adopts the following technical solutions:

[0005] A first aspect of the present disclosure provides a method for adjusting a vehicle environment, comprising:

[0006] Obtain vehicle environment information and user behavior information;

[0007] Inputting the behavior information into the trained first recognition model to output the user's behavior type information using the trained first recognition model;

[0008] When the behavior type information is taking a photo, inputting the environmental information of the vehicle into the trained prediction model, using the trained prediction model to output a predicted light intensity and outputting a target light intensity suitable for taking a photo based on the predicted light intensity; and

[0009] The first control information is output based on the target light intensity so that the dimming glass adjusts the light transmittance.

[0010] Optionally, the user's behavior information includes: the user's coordinate information and the user's mobile phone's coordinate information,

[0011] After obtaining the vehicle's environmental information and the user's behavior information, the adjustment method further includes:

[0012] Obtaining usage information of camera apps in the user's mobile phone; and

[0013] When the usage information is the startup information, the startup information is input into the trained first recognition model as auxiliary behavior information.

[0014] Optionally, outputting the first control information based on the target light intensity so that the dimming glass adjusts the light transmittance further includes:

[0015] Outputting first control information according to the target light intensity to control the dimming glass to adjust the light transmittance, the opening and closing degree of the sunroof and / or the side windshield sunshade, and the brightness of the interior ambient light so that the vehicle environment reaches the target light intensity, and / or

[0016] Adjust the light transmittance of the smart glass based on the feedback information submitted by users on the mobile app.

[0017] Optionally, the adjustment method further includes:

[0018] Acquiring sensing information, the sensing information including eye coordinate information of a user serving as a driver and rearview mirror coordinate information of a rearview mirror;

[0019] Determine the positional relationship between the driver's sight line and the rearview mirror according to the eye coordinate information and the rearview mirror coordinate information, and when determining the positional relationship, the direction of the sight line is obtained by inputting the eye coordinate information into the trained intention recognition model;

[0020] Based on the position relationship, the position of the light-transmitting area of ​​the side dimming glass close to the rearview mirror is obtained;

[0021] The second control information is output based on the position of the light-transmitting area, so that the side dimming glass adjusts the light transmittance.

[0022] Optionally, determining the positional relationship between the driver's line of sight and the rearview mirror according to the human eye coordinate information and the rearview mirror coordinate information further includes:

[0023] Transform the coordinate information of the rearview mirror into the coordinates of the same coordinate system as the coordinate information of the human eye, wherein the coordinate information of the rearview mirror is the coordinate information of the bottom center of the rearview mirror;

[0024] A geometric model is established based on the bottom center of the rearview mirror, the position of the driver's eyes, and the origin of the coordinate system to calculate the tilt angle of the rearview mirror;

[0025] Obtaining an updated angle of the rearview mirror based on preset constraints and updating the angle of the rearview mirror;

[0026] Based on the updated angle of the rearview mirror, the positional relationship between the driver's line of sight and the surface of the rearview mirror is obtained.

[0027] Optionally, the preset constraints include: field of view information, an angle threshold range between the line of sight and the rearview mirror, and the intersection of the line of sight and the rearview mirror is within the effective observation area of ​​the rearview mirror.

[0028] Optionally, the optimal tilt angle of the rearview mirror that meets the preset constraints is obtained by a gradient descent method using the preset constraints and used as the updated angle.

[0029] Optionally, the adjustment method further includes:

[0030] Get the opening and closing information of the vehicle's rear cover;

[0031] When the opening and closing information indicates that the rear cover of the vehicle is opened, the shadow area of ​​the ground behind the vehicle is obtained;

[0032] When the shadow area meets the preset threshold range, the third control information is output to reduce the light transmittance of the dimming glass located on the rear cover of the vehicle.

[0033] Optionally, the opening and closing information includes: opening and closing state and opening time,

[0034] When the opening and closing information indicates that the rear cover of the vehicle is open, obtaining the shadow area of ​​the ground behind the vehicle further includes:

[0035] When the opening and closing information indicates that the rear cover of the vehicle is opened, and the opening time is greater than or equal to a preset time length, the shadow area of ​​the ground behind the vehicle is obtained.

[0036] Optionally, the adjustment method further includes:

[0037] Acquire the user's touch information on the dimming glass, the touch information includes: touch direction, touch start point and target point, and touch capacitance change;

[0038] Based on the touch information, a closed pattern drawn by the user on the dimming glass is recognized;

[0039] Inputting the closed pattern into the trained second recognition model to output a pattern sample having a preset texture style;

[0040] The fourth control information is output based on the pattern sample, so that the transmittance of the touch-controlled dimming glass is adjusted to display the texture style of the pattern sample.

[0041] A second aspect of the present disclosure provides a regulating device, comprising:

[0042] An acquisition unit, which acquires vehicle environment information and user behavior information;

[0043] A first recognition unit, inputting the behavior information into a trained first recognition model, so as to output the user's behavior type information using the trained first recognition model;

[0044] a prediction unit, when the behavior type information is taking a photo, inputting the environment information of the vehicle into a trained prediction model, outputting a predicted light intensity using the trained prediction model, and outputting a target light intensity suitable for taking a photo based on the predicted light intensity; and

[0045] The control unit outputs first control information based on the target light intensity so that the dimming glass adjusts the light transmittance.

[0046] A third aspect of the present disclosure provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the adjustment method described above when executing the program.

[0047] A fourth aspect of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the adjustment method described above when the program is executed by a processor.

[0048] The beneficial effects of the present disclosure are as follows:

[0049] In response to the current existing problems, this application develops a vehicle environment adjustment method, adjustment equipment, computer equipment and computer-readable storage medium, which can use dimming glass in the vehicle to intelligently adjust the vehicle environment, provide drivers and passengers with a flexible and personalized driving experience, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The specific implementation methods of the present disclosure are further described in detail below with reference to the accompanying drawings.

[0051] Figure 1 A schematic diagram showing a flow chart of a method for adjusting a vehicle environment according to an embodiment of the present disclosure;

[0052] Figure 2 A schematic diagram showing an application scenario of the method for adjusting the vehicle environment according to an embodiment of the present disclosure;

[0053] Figure 3 A schematic diagram showing a light transmission state of the switchable glass according to an embodiment of the present disclosure is shown;

[0054] Figure 4 A flow chart showing a method for adjusting a vehicle environment according to an embodiment of the present disclosure;

[0055] Figure 5 and Figure 6 A flow chart showing a method for adjusting a vehicle environment according to another embodiment of the present disclosure;

[0056] Figure 7 A schematic diagram showing a vehicle application scenario of the related technology;

[0057] Figure 8 A flow chart showing a method for adjusting a vehicle environment according to another embodiment of the present disclosure;

[0058] Fig. 9 A schematic diagram showing the opening of a rear cover of a vehicle according to another embodiment of the present disclosure is shown;

[0059] Fig.10 A flow chart showing a method for adjusting a vehicle environment according to another embodiment of the present disclosure;

[0060] Fig.11 A schematic diagram of the structure of a computer system provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0061] In order to more clearly illustrate the present disclosure, the present disclosure is further described below in conjunction with the embodiments and drawings. Similar components in the drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present disclosure.

[0062] Reference Figure 1 As shown, the embodiment of the present disclosure provides a method for adjusting a vehicle environment, comprising:

[0063] Step S1, obtaining vehicle environment information and user behavior information;

[0064] Step S2: inputting the behavior information into the trained first recognition model, so as to output the user's behavior type information using the trained first recognition model;

[0065] Step S3: when the behavior type information is taking a photo, inputting the environmental information of the vehicle into the trained prediction model, using the trained prediction model to output a predicted light intensity and outputting a target light intensity suitable for taking a photo based on the predicted light intensity; and

[0066] Step S4: outputting first control information based on the target light intensity so that the dimming glass adjusts the light transmittance.

[0067] In this embodiment, the user behavior category is identified by inputting the collected user behavior information into a trained first recognition model. When the user behavior is determined to be taking pictures, the current light intensity is predicted and the target light intensity is further predicted by inputting the collected vehicle environment information into a trained prediction model, thereby adjusting the light transmittance of the dimming glass, thereby providing ambient fill light for the driver and passengers to take pictures, thereby improving the photography effect in the cabin and enhancing the driving experience.

[0068] The vehicle environment adjustment method provided in this embodiment can be implemented by a computer device with data processing capabilities, and the computer device can usually be a central control system of the smart cockpit, also known as an electronic control unit (ECU).

[0069] In order to facilitate understanding of the technical solution of this embodiment, Figure 2 The practical scenario of the above method provided in this embodiment is described. Figure 2As shown, the scene shows a vehicle 200, which includes a central control system 201, and the central control system 201 can be used as an adjustment device for executing the vehicle environment adjustment method. In addition, the vehicle 200 also includes: an ambient light sensor 202, a camera 203, a navigation module 204, a dimming controller 205, a seat controller 206 and a rearview mirror controller 207. The ambient light sensor 202, the camera 203 and the navigation module 204 can collect various information and transmit the collected information to the central control system 201. At the same time, the central control system 201 can control their respective actions by outputting various control information to the ambient light sensor 202, the camera 203 and the navigation module 204. On the other hand, the dimming controller 205, the seat controller 206 and the rearview mirror controller 207 receive the control information from the central control system 201 and respectively perform control actions such as dimming of the dimming glass, position adjustment of the seat, angle adjustment of the rearview mirror, etc. At the same time, the dimming controller 205, the seat controller 206 and the rearview mirror controller 207 can provide information feedback to the central control system 201. Specifically, the central control system 201 may include the above-mentioned trained first recognition model and the trained prediction model. Through this setting, the user's behavior recognition and the prediction of light intensity can be performed locally in the vehicle 200, thereby avoiding the situation in the cloud where the recognition results received are inconsistent with the real-time situation of the vehicle due to the rapid movement of the vehicle, thereby improving the accuracy of status acquisition.

[0070] It should be noted that in scenarios with lower requirements for prediction accuracy, the adjustment device that executes the adjustment method can also be a combination of the vehicle's central control system and a cloud server. For example, behavior recognition and light intensity prediction occur on the cloud server. In this case, it should also be protected by the present embodiment and will not be elaborated in this article.

[0071] On the other hand, in the embodiment of the present disclosure, the windows of the vehicle 200 adopt dimming glass. Figure 3 The three light-transmitting states of dimming glass are shown. Dimming glass, also known as smart dimming glass, electrically controlled glass, privacy glass, smart glass or magic glass, is a special optoelectronic glass product. Its biggest feature is the ability to change its transparency based on the power-on status. For example, a typical dimming glass consists of two layers of glass and a liquid crystal film (PDLC film) between the two layers of glass. When the dimming glass is powered on and reaches full power, the liquid crystal molecules will be arranged neatly, so that the glass becomes transparent state A. When the power is completely cut off, the liquid crystal molecules are randomly distributed, causing light scattering, making the glass opaque or fogged state C. Dimming glass can also use electrochromic film to achieve changes in light transmittance. For example, another typical light-transmitting glass consists of two layers of glass and an electrochromic film between the two layers of glass. When the electrochromic film can change based on the amplitude of the applied voltage, it can present transparent state A, weakly transparent state B and fogged state C. Dimming glass can control the transparency state by partition, such as Figure 3 The weakly transparent state B shown can produce different light-transmitting states by controlling the state and amplitude of the applied voltage in different regions.

[0072] It should be noted that the embodiments of the present disclosure are not limited to a specific type of dimming glass, and any dimming glass that can produce different light transmission states based on voltage control is protected by the present disclosure.

[0073] Next, from the perspective of the adjustment device, a vehicle environment adjustment method provided by this embodiment is described. Figure 2 The central control system 201 of the vehicle 200 shown, Figure 4 A flow chart of a method for adjusting a vehicle environment according to an embodiment of the present disclosure is provided.

[0074] In step S1 , environmental information of the vehicle 200 and behavior information of the user are acquired.

[0075] Combination Figure 2 and Figure 4 As shown, the camera 203 may include an in-car camera. The camera 203 captures the behavior information of the user, who may be a passenger or a driver. Optionally, the image collected by the camera 203 may be processed to ensure that the behavior information of the user can be accurately obtained.

[0076] In an embodiment of the present disclosure, behavior information may include: coordinate information of the user's mobile phone and coordinate information of the user. The behavior information is used to identify the user's behavior. For example, the coordinate information of the user's mobile phone can indicate whether the mobile phone is raised, the raised position, etc. The coordinate information of the user can indicate the direction of the face, the tilt angle of the body, etc. The relationship between the coordinate information of the user's mobile phone and the coordinate information of the user can indicate the relative position relationship between the mobile phone and the user.

[0077] In the embodiments of the present disclosure, the environmental information of the vehicle may include: season information, weather information, ambient light, vehicle location, etc. Specifically, the light intensity inside and outside the vehicle can be collected by the ambient light sensor 202, and the vehicle location information can be obtained by the navigation module 204. The navigation module 204 can be, for example, a GPS module or a Beidou module. In addition, the real-time weather can be obtained through the meteorological data interface of the central control system 201. The weather can be the weather type of the vehicle location obtained by the navigation module 204 (such as sunny, cloudy, overcast, etc.). The meteorological data interface can also obtain season information, and of course the season information is also the season information of the vehicle location. The meteorological data interface can, for example, read the meteorological application data authorized by the mobile phone by interconnecting with the user's mobile phone. Of course, the user interconnected with the central control system 201 may not be the same person as the user collected by the camera 203. For example, the vehicle 200 may be in an interconnected state with the mobile phone of the main driver, and the user image collected by the camera 203 is not limited to the main driver.

[0078] Specific to Figure 4 In the example shown, the camera 203 may be a camera set in front of the main driver and the co-driver. The camera 203 captures the image of the co-driver and obtains the behavior information contained in the image. At the same time, the current environmental information obtained is: weather, sunny; light intensity, medium; location, city center of city C; time, 3 pm.

[0079] In step S2, the behavior information is input into the trained first recognition model to output the user's behavior type information using the trained first recognition model.

[0080] The trained first recognition model is, for example, a pre-trained first recognition model loaded in the central control system 201. The specific training process may include, for example: using images containing preset categories of actions and / or postures and images of other categories of actions and / or postures that are different from the preset categories of actions and / or postures to train the first recognition model. The first recognition model may be, for example, a convolutional neural network (CNN). Other machine learning models may also be used without taking up too much computing power. Optionally, in order to improve the model's ability to correctly understand and predict data when faced with new, unseen data, the diversity of the data may be increased as much as possible during training.

[0081] Specifically in this step, the central control system 201 inputs the acquired behavior information into the trained first recognition model, and the trained first recognition model outputs the user's behavior type information, which is used to indicate the user's behavior type. Optionally, the trained first recognition model can also output the user's location at the same time.

[0082] Specific to Figure 4In the example shown, the trained first recognition model recognizes that the passenger's behavior purpose is to raise the mobile phone to take a photo, that is, it recognizes the user's behavior type information as taking a photo, and recognizes that the passenger is in the front passenger seat.

[0083] Considering that users use mobile phones to take pictures, they may raise the phone to take selfies or take other pictures of the scenery outside the car window. When taking pictures of other things, there may be recognition errors because the posture of raising the phone is similar to the posture of regular mobile phone use and the face is not facing the phone.

[0084] Preferably, after step S1, the adjustment method further comprises: obtaining usage information of a camera software in the user's mobile phone; and

[0085] When the usage information is the startup information, the startup information is input into the trained first recognition model as auxiliary behavior information.

[0086] Exemplarily, the vehicle 200 can generally allow at least one user to be connected to the central control system 201 at the same time. The central control system 201 monitors the activity status of the user's mobile phone through the connection interface between the user's mobile phone and the vehicle 200, thereby determining whether there is any behavior of opening the camera application. The connection interface can be, for example, Bluetooth or Wi-Fi. When the startup information is obtained, the usage information indicating the behavior of starting the camera application is input as auxiliary behavior information into the trained first recognition model, which helps the trained first recognition model to accurately identify whether any of the occupants in the car are ready to take pictures, which will greatly improve the recognition accuracy of user behavior.

[0087] In step S3, when the behavior type information is taking a photo, the vehicle's environmental information is input into the trained prediction model to use the trained prediction model to output a predicted light intensity and output a target light intensity suitable for taking photos based on the predicted light intensity.

[0088] The trained prediction model is, for example, a pre-trained prediction model loaded in the central control system 201. The specific training process may include, for example, training the prediction model using historical data. Historical data include, for example, weather conditions, light intensity, time characteristics, etc. At the same time, in order for the prediction model to be able to predict the target light intensity suitable for photographing, during training, the optimal light intensity is calculated using the input data such as weather conditions, light intensity, time characteristics, etc. For example, considering that a stronger shading effect is required in sunny weather, in addition, the light angle in winter is different from that in summer, and the shading effect in sunny weather in winter and sunny weather in summer in the same time period should also be different.

[0089] In order to load the trained prediction model into the central control system 201 of the vehicle 200, the prediction model may adopt a regression model that saves more computing power, such as a support vector machine (SVM) or a random forest.

[0090] In step S4, first control information is output based on the target light intensity so that the dimming glass adjusts the light transmittance.

[0091] Specifically, in the storage of the vehicle 200, a lookup table of the control voltage corresponding to the target light intensity and the light transmittance of the dimming glass or the light transmittance of the dimming glass can be stored. The central control system 201 can retrieve the light transmittance of the dimming glass corresponding to the target light intensity or the control voltage corresponding to the light transmittance according to the target light intensity, and output a first control signal to the dimming controller 205. The dimming controller 205 will apply the corresponding control voltage to the dimming glass based on the received first control signal, so that the vehicle environment can reach a light intensity suitable for the user who is about to take a photo. For example, Figure 4 The medium dimming glass is capacitive glass, but this is not restrictive.

[0092] Optionally, the predicted target light intensity can be achieved in the vehicle 200 through cooperation of multiple dimmable mechanisms.

[0093] For example, the vehicle 200 may include a sunroof and a side windshield sunshade that can be intelligently controlled. Then step S4 may further include: outputting first control information according to the target light intensity to control the dimming glass to adjust the light transmittance, the opening and closing degree of the sunroof and / or the side windshield sunshade, and the brightness of the interior ambient light, so that the vehicle environment reaches the target light intensity, thereby setting the best fill light effect.

[0094] In this case, the memory of the vehicle 200 may store a lookup table corresponding to the target light intensity: the light transmittance of the dimming glass or the control voltage of the dimming glass, the opening and closing degree of the sunroof, or the light transmittance of the dimming glass or the control voltage of the dimming glass, the opening and closing degree of the side windshield sunshade, or the light transmittance of the dimming glass or the control voltage of the dimming glass, the opening and closing degree of the sunroof, and the opening and closing degree of the side windshield sunshade. At this time, the first control information may include control information for the dimming glass, and control information for the sunroof and / or the side windshield sunshade.

[0095] In addition, considering that users' experience is different, or that everyone's photography needs are different, a shading effect adjustment function is also provided in the embodiments of the present disclosure.

[0096] Optionally, step S4 further includes: adjusting the light transmittance of the switchable glass based on feedback information submitted by the user on the mobile phone application.

[0097] For example, after the user's mobile phone establishes a connection with the central control system 201, the interface based on the mobile phone application can provide real-time feedback. For example, the interface of the mobile phone application prompts the current shading effect and asks whether the user is satisfied. For the user, the feedback operation mechanism is, for example, a button in the form of an interface or a chart. The user's operation at the corresponding position is submitted to the central control system 201 as feedback information. The central control system 201 dynamically adjusts the control information output to the dimming glass in real time based on the received feedback information, thereby adjusting the light transmittance of the dimming glass.

[0098] On the other hand, whether the vehicle uses shading film or shading glass, a triangular non-shading area will be left in the rearview mirror area to allow the driver to observe the environment behind the car for safe driving. However, the biggest problem with this treatment method is that after long-term driving and sun exposure, the internal firmware corresponding to the reserved non-shading area will age and show color stratification, or the driver's hand skin temperature will continue to rise under the sun, causing sunburn for people with sensitive skin. More importantly, the central control part corresponding to the two reserved areas is generally where the airbag is located, and the aging of components will cause safety risks and hidden dangers.

[0099] In some other optional embodiments, refer to Figure 5 As shown, the adjustment method further includes the following steps S5 to S7. Figure 4 The example shown also provides Figure 5 The process of the corresponding embodiment.

[0100] In step S5 , sensing information is acquired, the sensing information including eye coordinate information of a user who is a driver and rearview mirror coordinate information of a rearview mirror.

[0101] The vehicle 200 further includes an angle sensor and a position sensor. The angle sensor may be disposed in the rearview mirror to detect an actual angle of the rearview mirror.

[0102] There may be multiple position sensors for detecting the height of the driver's seat, the driver's height and / or the driver's eye position. The driver's height can be measured, for example, by an infrared sensor or an ultrasonic sensor. As for the driver's eye position, when the eye position is obtained by using a camera to capture the driver's image, no position sensor is required. Otherwise, an infrared sensor can be used to measure the driver's eye position.

[0103] In this embodiment, the eye coordinate information of the user as the driver and the rearview mirror coordinate information of the rearview mirror may be monitored by the position sensor.

[0104] Exemplarily, taking the rearview mirror close to the driver's side and the driver as an example, mathematical modeling is performed based on the geometric relationship, and the driver's eye height is defined as h, the horizontal distance between the driver's eyes and the bottom center point of the rearview mirror is d, the driver's seat height is s, the height from the bottom center point of the rearview mirror to the ground is hm, the inclination angle between the rearview mirror and the vertical plane is α, and the angle between the rearview mirror and the horizontal plane is β.

[0105] Further, a first coordinate system is established, for example, a rectangular coordinate system is established with the center of the seat base as the origin, the X axis of the rectangular coordinate system points to the front of the vehicle, the Y axis is perpendicular to the bottom surface and points upward, and the Z axis points to the left side of the vehicle 200. Then the eye coordinate information is (0, h, 0).

[0106] In addition, if a second rectangular coordinate system is established with the projection position of the bottom center of the rearview mirror on the ground as the origin, the X axis points to the front of the vehicle, the Y axis is perpendicular to the bottom surface and points upward, and the Z axis points to the left side of the vehicle 200. The bottom center coordinate information of the rearview mirror is (0, hm, 0).

[0107] In step S6, the positional relationship between the driver's line of sight and the rearview mirror is determined based on the eye coordinate information and the rearview mirror coordinate information. When determining the positional relationship, the direction of the line of sight is obtained by inputting the eye coordinate information into a trained intention recognition model.

[0108] Preferably, the driver's behavioral intention can be identified by a trained intention recognition model, thereby obtaining the driver's line of sight direction. For example, the intention recognition model can adopt a Llama model.

[0109] Specifically, refer to Figure 6 As shown, step S6 further includes the following steps:

[0110] In step S61, coordinate transformation is performed on the rearview mirror coordinate information to convert it into the coordinate system of the human eye coordinate information. The rearview mirror coordinate information is the coordinate information of the bottom center of the rearview mirror.

[0111] Continuing with the example in the previous step, in order to facilitate the calculation of the positional relationship between the driver's line of sight and the rearview mirror, the coordinate information of the human eye and the coordinate information of the rearview mirror need to be placed in the same coordinate system. According to the mathematical modeling described above, when the coordinate information of the rearview mirror is transformed into the coordinate system of the coordinate information of the human eye, its coordinates are (d,hm+s,0).

[0112] In step S62, a geometric model is established based on the bottom center of the rearview mirror, the driver's eye position, and the origin of the coordinate system to calculate the tilt angle of the rearview mirror.

[0113] Specifically, the line connecting the driver's line of sight and the horizontal line where the bottom of the rearview mirror is located forms a triangle, and the inclination angle α between the rearview mirror and the vertical plane can be calculated using the trigonometric function relationship; at the same time, the driver's line of sight, the intersection of the driver's line of sight and the side of the rearview mirror, and the parallel line of the side of the rearview mirror form a triangle, and the angle β between the rearview mirror and the horizontal plane can be calculated using the trigonometric function relationship.

[0114] For example, assuming that the driver's eye height h = 1.5m, the height from the center point of the rearview mirror bottom to the ground hm = 1.2m, the horizontal distance from the center point of the rearview mirror bottom to the driver's eye d = 0.7m, and the seat height s = 0.5m, after the coordinate system is set, the coordinates of the driver's eye position are (0, 1.5, 0), and the coordinates of the center point of the rearview mirror bottom are (0.7, 1.7, 0). Then, the inclination angle θ between the driver's line of sight and the bottom horizontal line of the rearview mirror can be calculated to satisfy the relationship:

[0115]

[0116] Then, the inclination angle θ≈-16° (tilted downward) between the driver's line of sight and the bottom horizontal line of the rearview mirror is obtained.

[0117] It should be noted that, although the numerical relationship between the rearview mirror near the driver's side and the driver's eyes and the driver's seat is used as an example to describe the specific numerical value obtaining process, those skilled in the art should understand that for the rearview mirror near the driver's side, the mathematical modeling and geometric relationship principles are the same, and the only difference is the distance value and the positive and negative coordinates, which will not be described in detail in this article. The following steps are not different for the rearview mirrors on both sides, so there is no need to distinguish the rearview mirrors.

[0118] In step S63, the update angle of the rearview mirror is obtained based on the preset constraint condition and the angle of the rearview mirror is updated.

[0119] In the embodiments of the present disclosure, it is intended to use constraints to find the updated angle of the rearview mirror based on the current eye position of the driver, so that the rearview mirror adjusted by the updated angle can enable the driver to have the most suitable observation effect for observing the side and rear environment when looking at the rearview mirror.

[0120] Optionally, the preset constraints include: field of view information, an angle threshold range between the line of sight and the rearview mirror, and the intersection of the line of sight and the rearview mirror is within the effective observation area of ​​the rearview mirror.

[0121] Among them, the field of view range information indicates the range information that ensures that the driver can see enough rear field of view when the range information is met, for example, at least the scene within a certain distance behind the vehicle can be seen. The angle threshold range of the line of sight and the rearview mirror indicates that when the range is met, the intersection point of the line of sight and the rearview mirror is ensured to fall within the effective observation area, and at the same time, the angle cannot be too steep or flat, thereby providing constraints on observation comfort. The rearview mirror has an effective observation area and an ineffective observation area. When the intersection point of the line of sight and the rearview mirror is directly limited to be within the effective observation area of ​​the rearview mirror, the observation validity is further limited from the intersection range level relative to the angle threshold range. Exemplarily, the effective observation area of ​​the rearview mirror can be defined as a rectangle, and its boundary is determined by the size and tilt angle of the rearview mirror.

[0122] Optionally, the preset constraints may be used to obtain the optimal tilt angle of the rearview mirror that meets the preset constraints through a gradient descent method and used as the update angle.

[0123] Through the above arrangement, it can be ensured that after the height, forward leaning, backward leaning and other positions of the driver change, the position relationship between the rearview mirror and the driver is always ensured that the driver can see clearly in the rearview mirror.

[0124] Specifically, the update of the angle of the rearview mirror can be achieved by the central control system 201 sending control information to the rearview mirror controller 207, and the rearview mirror controller 207 controls the motor behind the rearview mirror based on the control information to adjust the rearview mirror to move up, down, left, and right.

[0125] In step S64, based on the updated angle of the rearview mirror, the positional relationship between the driver's line of sight and the surface of the rearview mirror is acquired.

[0126] That is to say, after the rearview mirror adjusts its angle based on the driver's eye position, under this premise, the positional relationship between the driver's line of sight and the surface of the rearview mirror is finally obtained, thereby ensuring that the range of the dimming glass in the subsequent steps is also the optimal adjustment range.

[0127] In step S7, based on the positional relationship, the position of the light-transmitting area of ​​the side dimming glass close to the rearview mirror is acquired.

[0128] Specifically, after determining the tilt angle of the rearview mirror, the intersection point on the rearview mirror can be determined, and then the visible range of the line of sight on the dimming glass, that is, the position of the light-transmitting area, can be determined.

[0129] In step S8, second control information is output based on the position of the light-transmitting area, so that the side dimming glass adjusts the light transmittance.

[0130] Based on the determined position of the light-transmitting area, the central control system 201 sends the second control information to the dimming controller 205, so that the dimming controller 205 adjusts the voltage value of each area in the side dimming glass, so that the light transmittance corresponding to the position of the light-transmitting area is 100%, and the light transmittance of other areas is the transmittance required by the driver and passengers. This transmittance is, for example, the light transmittance that meets the target light intensity for taking photos in the above embodiment. Figure 4 The GPS / Beidou / weather / season information input shown in the figure is intended to illustrate the coordination of the two transmittance adjustments.

[0131] Alternatively, further reference is made to Figure 4 As shown, the central control system 201 can also automatically adjust the seat height and backrest angle according to the driver's posture habits and posture preferences, and based on the adjustment of the seat height and backrest angle, complete the angle update of the above-mentioned rearview mirror and the position determination of the light-transmitting area, which will not be elaborated here.

[0132] Alternatively, the user acting as a driver can also submit feedback to the central control system 201 using a mobile phone application or the user interaction interface of the central control system 201, thereby giving a suggested adjustment direction. Of course, the central control system 201 can determine the position of the pass-through area after updating the rearview mirror based on the suggested adjustment direction, which will not be elaborated here.

[0133] Further optionally, considering that the driver does not observe the rearview mirror at a constant frequency, the light-transmitting area can be set only after the human eye image is captured and the human eye's intention to observe the rearview mirror is identified. Of course, the initial light-transmitting area can be set according to the minimum visible area.

[0134] On the other hand, referring to Figure 7 As shown, considering that when going on an outing or traveling, the trunk is usually used as a picnic table to build a canopy, in this case, the vehicle rear cover needs to be opened, and the open rear cover and rear area cause a large part of the canopy area to be wasted.

[0135] In other optional embodiments, the vehicle environment adjustment method provided by the present disclosure further improves the comprehensive utilization of the trunk lid.

[0136] Reference Figure 8 and Fig. 9 As shown, the adjustment aspects also include:

[0137] Step S9, obtaining the opening and closing information of the rear cover of the vehicle;

[0138] Step S10: when the opening and closing information indicates that the rear cover of the vehicle is opened, obtaining a shadow area of ​​the ground at the rear of the vehicle;

[0139] Step S11: when the shadow area meets a preset threshold range, output third control information to reduce the light transmittance of the dimming glass located on the rear cover of the vehicle.

[0140] Through this setting, when the rear cover is open, the shadow area of ​​the rear of the vehicle is detected to determine whether to build a canopy. The preset range can, for example, set the shadow area value of the rear area of ​​the vehicle when the canopy is usually built. The dimming glass of the rear cover of the vehicle can be used to enlarge the area and range of the canopy inside and outside the vehicle from the side.

[0141] Optionally, the preset threshold range may be set to be larger than the projection area of ​​the tent. In this case, the light and visible range in the tent may be increased by setting the dimming glass to a transparent state when the tent is being built.

[0142] Optionally, the opening and closing information includes: an opening and closing state and an opening time, and when the opening and closing information indicates that the rear cover of the vehicle is open, obtaining the shadow area of ​​the ground behind the vehicle further includes:

[0143] When the opening and closing information indicates that the rear cover of the vehicle is opened, and the opening time is greater than or equal to a preset time length, a shadow area of ​​the ground behind the vehicle is obtained.

[0144] Through this setting, the length of time the vehicle's rear cover is open can be combined with the shadow area as a control basis for the dimming glass, so as to avoid the problem of mistakenly judging it as a skylight scene when the vehicle stays in the shaded area for a short time.

[0145] In some other optional embodiments, the adjustment method further includes:

[0146] Acquiring the user's touch information on the dimming glass, the touch information including: touch direction, touch start point and target point, and touch capacitance change;

[0147] Based on the touch information, identifying a closed pattern drawn by the user on the dimming glass;

[0148] Inputting the closed pattern into a trained second recognition model to output a pattern sample having a preset texture style;

[0149] Fourth control information is output based on the pattern sample, so that the transmittance of the touch-controlled dimming glass is adjusted to display the texture style of the pattern sample.

[0150] Through this setting, the collection and recognition of the user's touch information on the dimming glass can be utilized to realize personalized pattern display using the dimming glass intelligence.

[0151] Specific reference Fig.10As shown, when the user touches the dimming glass, the user's touch information starts to be continuously collected, and the touch information includes: touch direction, touch start point and target point, and touch capacitance change.

[0152] When there is no pattern displayed in the touch area, it means that the touch information recognition process needs to be entered. The closed pattern drawn by the user on the dimming glass is recognized based on the touch information.

[0153] For dimming glass, interactive touch that simply forms a blinds style can be implemented using the microcontroller marquee principle, that is, the starting point and target direction form a capacitance change with a time difference. When the touch pattern is convex and the starting point and the end point overlap, it is recognized as a closed pattern.

[0154] Optionally, the burr data of the identified closed pattern is removed. The closed pattern is input into a trained second recognition model to output a pattern sample with a preset texture style. The trained second recognition model is, for example, a Llama model, a convolutional neural network model or other recognition model trained according to samples in a pattern library. The identified pattern sample with a preset pattern and texture style is the pattern in the beautified pixel data set. The central control system 201 outputs fourth control information based on the pattern sample, so that the transmittance of the touched dimming glass is adjusted to display the texture style of the pattern sample, such as circles, clouds and other patterns are reflected by the light transmittance, opacity, and light transmittance of the dimming glass.

[0155] Further optionally, in order to improve the aesthetics of the displayed pattern, the transparency control of the dimming glass can also be used to depict a smooth transition between patterns.

[0156] Specifically, the transparency change of electrochromic glass is related to the applied voltage and time. The rate of change of transparency can be described by the following formula:

[0157]

[0158] Where dD is the transparency, V is the applied voltage, V0 is the threshold voltage, and k and n are material-dependent constants.

[0159] Next, the touch coordinates are mapped and optimized. In order to improve the accuracy of touch coordinate mapping, the least square method can be used for calibration. Assume that the known touch point coordinate set is The ideal coordinates after mapping are Then we can calculate:

[0160]

[0161] Among them, a, b, c, d, e, and f are the optimal coordinate transformation parameters for the best mapping.

[0162] Furthermore, gradient and transparency calculations are performed. The smooth transition of transparency from one area to another can be calculated using polynomial interpolation. For example, for the transition area between two areas, the transparency L can be approximated using the normalization method:

[0163] L i (x) = a3x 3 +a2x 2 +a1x+a0

[0164] The calculated result can be solved by the Cardano method (it can also be solved by directly calling a third-party library through the code). The calculated result here is the optimal gradient parameters a3, a2, a1 and a0. The more equal the spacing between the parameters, the smaller the differential change, and the smoother the transition change.

[0165] Based on the same inventive concept, the embodiment of the present disclosure provides a regulating device, which can be specifically implemented as Figure 2 The central control system shown includes:

[0166] An acquisition unit, which acquires vehicle environment information and user behavior information;

[0167] A first recognition unit, inputting the behavior information into a trained first recognition model, so as to output the user's behavior type information by using the trained first recognition model;

[0168] a prediction unit, when the behavior type information is taking a photo, inputting the environment information of the vehicle into a trained prediction model, so as to output a predicted light intensity using the trained prediction model and output a target light intensity suitable for taking a photo based on the predicted light intensity; and

[0169] The control unit outputs first control information based on the target light intensity so that the dimming glass adjusts the light transmittance.

[0170] By providing adjustment equipment, dimming glass can be used in the vehicle to intelligently adjust the vehicle environment, providing drivers and passengers with a flexible and personalized driving experience.

[0171] Another embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements:

[0172] Obtain vehicle environment information and user behavior information;

[0173] Inputting the behavior information into a trained first recognition model to output the user's behavior type information using the trained first recognition model;

[0174] When the behavior type information is taking a photo, inputting the environment information of the vehicle into a trained prediction model, so as to output a predicted light intensity using the trained prediction model and output a target light intensity suitable for taking a photo based on the predicted light intensity; and

[0175] First control information is output based on the target light intensity so that the dimming glass adjusts the light transmittance.

[0176] In practical applications, the computer-readable storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more 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 suitable combination of the above. In the present embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0177] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0178] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0179] Computer program code for performing the operation of the present application can 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" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate 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 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 can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0180] like Fig.11 As shown, a structural schematic diagram of a computer device provided by another embodiment of the present application. Fig.11 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0181] like Fig.11 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0182] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0183] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0184] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 not shown, usually called a "hard drive"). Although Figure 7 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0185] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0186] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed through an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 20. Fig.11 As shown, the network adapter 20 communicates with other modules of the computer device 12 via the bus 18. It should be understood that although Figure 7 Not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0187] The processor unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing an automatic demonstration method of an application based on the Android debugging bridge for a terminal on which an application is installed, or implementing a vehicle environment adjustment method provided in an embodiment of the present application.

[0188] In the description of the present disclosure, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present disclosure and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present disclosure. Unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, and it can be the internal connection of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present disclosure can be understood according to the specific circumstances.

[0189] It should also be noted that, in the description of the present disclosure, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of further restrictions, the elements defined by the statement "comprise one..." do not exclude the presence of other identical elements in the process, method, article or equipment including the elements.

[0190] Obviously, the above embodiments of the present disclosure are merely examples for clearly illustrating the present disclosure, and are not limitations on the implementation methods of the present disclosure. For ordinary technicians in this field, other different forms of changes or modifications can be made on the basis of the above description. It is impossible to list all the implementation methods here. All obvious changes or modifications derived from the technical solution of the present disclosure are still within the protection scope of the present disclosure.

Claims

1. A method for adjusting a vehicle environment, characterized in that: include: Obtain vehicle environment information and user behavior information; Inputting the behavior information into a trained first recognition model to output the user's behavior type information using the trained first recognition model; When the behavior type information is taking a photo, inputting the environmental information of the vehicle into a trained prediction model, so as to output a predicted light intensity using the trained prediction model and output a target light intensity suitable for taking a photo based on the predicted light intensity; as well as First control information is output based on the target light intensity so that the dimming glass adjusts the light transmittance.

2. The adjustment method according to claim 1, characterized in that: The user's behavior information includes: the user's coordinate information and the coordinate information of the user's mobile phone, After obtaining the vehicle environment information and the user behavior information, the adjustment method further includes: Obtaining usage information of the camera software in the user's mobile phone; and When the usage information is startup information, the startup information is input into the trained first recognition model as auxiliary behavior information.

3. The adjustment method according to claim 1, characterized in that: The outputting the first control information based on the target light intensity so that the dimming glass adjusts the light transmittance further includes: Outputting the first control information according to the target light intensity to control the dimming glass to adjust the light transmittance, the opening and closing degree of the sunroof and / or the side windshield sunshade, and the brightness of the interior ambient light so that the vehicle environment reaches the target light intensity, and / or Based on the feedback information submitted by the user on the mobile phone application, the light transmittance of the dimming glass is adjusted.

4. The adjustment method according to claim 1, characterized in that: Also includes: Acquiring sensing information, wherein the sensing information includes eye coordinate information of a user serving as a driver and rearview mirror coordinate information of a rearview mirror; Determining the positional relationship between the driver's line of sight and the rearview mirror according to the eye coordinate information and the rearview mirror coordinate information, wherein the direction of the line of sight when determining the positional relationship is obtained by inputting the eye coordinate information into a trained intention recognition model; Based on the positional relationship, obtaining the position of the light-transmitting area of ​​the side dimming glass close to the rearview mirror; as well as The second control information is output based on the position of the light-transmitting area, so that the side dimming glass adjusts the light transmittance.

5. The adjustment method according to claim 4, characterized in that: The determining the positional relationship between the driver's line of sight and the rearview mirror according to the human eye coordinate information and the rearview mirror coordinate information further comprises: Transforming the rearview mirror coordinate information into coordinates of the coordinate system of the human eye coordinate information, wherein the rearview mirror coordinate information is the coordinate information of the bottom center of the rearview mirror; Establishing a geometric model based on the bottom center of the rearview mirror, the eye position of the driver, and the origin of the coordinate system to calculate the inclination angle between the driver's line of sight and the bottom horizontal line of the rearview mirror; Obtaining an updated angle of the rearview mirror based on a preset constraint condition and updating the angle of the rearview mirror; Based on the updated angle of the rearview mirror, a positional relationship between the driver's line of sight and the surface of the rearview mirror is obtained.

6. The adjustment method according to claim 5, characterized in that: The preset constraint conditions include: field of view information, an angle threshold range between the line of sight and the rearview mirror, and an intersection point between the line of sight and the rearview mirror being within an effective observation area of ​​the rearview mirror.

7. The adjustment method according to claim 5, characterized in that: The preset constraints are used to obtain the optimal tilt angle of the rearview mirror that meets the preset constraints through a gradient descent method and used as the update angle.

8. The adjustment method according to claim 1, characterized in that: Also includes: Get the opening and closing information of the vehicle's rear cover; When the opening and closing information indicates that the rear cover of the vehicle is open, obtaining a shadow area of ​​the ground behind the vehicle; as well as When the shadow area meets a preset threshold range, third control information is output to reduce the light transmittance of the dimming glass located on the rear cover of the vehicle.

9. The adjustment method according to claim 8, characterized in that: The opening and closing information includes: opening and closing state and opening time, When the opening and closing information indicates that the rear cover of the vehicle is open, obtaining the shadow area of ​​the ground behind the vehicle further includes: When the opening and closing information indicates that the rear cover of the vehicle is opened, and the opening time is greater than or equal to a preset time length, a shadow area of ​​the ground behind the vehicle is obtained.

10. The adjustment method according to claim 1, characterized in that: Also includes: Acquiring the user's touch information on the dimming glass, the touch information including: touch direction, touch start point and target point, and touch capacitance change; Based on the touch information, identifying a closed pattern drawn by the user on the dimming glass; Inputting the closed pattern into a trained second recognition model to output a pattern sample having a preset texture style; and Fourth control information is output based on the pattern sample, so that the transmittance of the touch-controlled dimming glass is adjusted to display the texture style of the pattern sample.

11. A regulating device, characterized in that: include: An acquisition unit, which acquires vehicle environment information and user behavior information; A first recognition unit, inputting the behavior information into a trained first recognition model, so as to output the user's behavior type information by using the trained first recognition model; a prediction unit, when the behavior type information is taking a photo, inputting the environmental information of the vehicle into a trained prediction model, so as to output a predicted light intensity using the trained prediction model and output a target light intensity suitable for taking a photo based on the predicted light intensity; as well as The control unit outputs first control information based on the target light intensity so that the dimming glass adjusts the light transmittance.

12. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the adjustment method according to any one of claims 1 to 10 is implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the adjustment method according to any one of claims 1 to 10 is implemented.

Images