Screen adjusting method and device, medium and product

Abstract

The invention discloses a screen adjustment method and device, a medium and a product, and relates to the technical field of vehicle-mounted screens, and the method comprises the steps: obtaining a face image of at least one screen viewer by responding to a preset precondition; and determining a target adjustment parameter according to the face image of the at least one screen viewer based on a preset visual identification model, adjusting the vehicle-mounted screen according to the target adjustment parameter, and obtaining the face image of the at least one screen viewer in time under the condition that a preset precondition is met, so as to improve the adjustment accuracy of the vehicle-mounted screen. Therefore, the target adjustment parameter is determined according to the face image of the at least one screen viewer through the visual recognition model, a user does not need to manually adjust the vehicle-mounted screen, automatic adjustment of the vehicle-mounted screen is achieved, the intelligent degree of adjustment of the vehicle-mounted screen is improved, and then the use experience of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle-mounted screen technology, and in particular to a screen adjustment method, device, medium and product. Background Art

[0002] When using the in-car screen, due to the differences in height and sitting posture of different passengers, the appropriate screen viewing angles also vary. Once the screen viewing angle does not match the passenger, it will significantly affect the passenger's viewing effect.

[0003] At present, in order to improve the viewing effect, passengers are usually required to make manual adjustments multiple times and judge the viewing effect subjectively, that is, the degree of intelligence is insufficient, which easily affects the user experience.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a screen adjustment method, device, medium and product, aiming to improve the intelligence level of vehicle-mounted screen adjustment to enhance the user experience.

[0006] To achieve the above object, the present application provides a screen adjustment method, the method comprising:

[0007] In response to satisfying a preset precondition, acquiring a facial image of at least one screen viewer;

[0008] Based on a preset visual recognition model, target adjustment parameters are determined according to the facial image of the at least one screen viewer, and the vehicle-mounted screen is adjusted according to the target adjustment parameters.

[0009] In one embodiment, in response to satisfying a preset precondition, before the step of acquiring a facial image of at least one screen viewer, the step further includes:

[0010] In response to identifying data change information of the first sensor, determining whether a seat is occupied according to the data change information;

[0011] If there is a seat occupancy, identifying whether the vehicle screen is in an unfolded state;

[0012] If the vehicle-mounted screen is not in the unfolded state, generating a first prompt message for the user to confirm whether to unfold the vehicle-mounted screen;

[0013] If the vehicle-mounted screen is in the unfolded state, it is determined that the preset precondition is met.

[0014] In one embodiment, the vehicle-mounted screen is connected to a screen carrier, and the method further comprises:

[0015] When the vehicle-mounted screen is in an unfolded state, obtaining current position information and previous position information of the screen carrier;

[0016] Determining a position change value of the screen carrier according to current position information and previous position information of the screen carrier;

[0017] If the position change value is greater than or equal to a preset position change threshold, it is determined that the preset precondition is met.

[0018] In one embodiment, before the step of acquiring the facial image of at least one screen viewer, the step further includes:

[0019] Collecting the image of the interior space of the vehicle by means of a second sensor;

[0020] At least one of facial recognition, gesture recognition, and interactive behavior recognition is performed on the in-vehicle space image to determine at least one screen viewer in the in-vehicle space image.

[0021] In one embodiment, the step of determining the target adjustment parameter according to the facial image of the at least one screen viewer based on a preset visual recognition model comprises:

[0022] identifying the number of screen viewers corresponding to the facial image of the at least one screen viewer;

[0023] If the facial image of the at least one screen viewer corresponds to a screen viewer, performing key point recognition on the facial image by using the visual recognition model to determine the eye position of the screen viewer;

[0024] Determine the binocular center coordinates of the screen viewer according to the eye positions, and determine the sitting height of the screen viewer according to the binocular center coordinates;

[0025] Select or determine the target adjustment parameter corresponding to the seat height.

[0026] In one embodiment, after the step of identifying the number of screen viewers corresponding to the facial image of the at least one screen viewer, the step further includes:

[0027] If the facial image of the at least one screen viewer corresponds to multiple screen viewers, performing key point recognition on the facial image by using the visual recognition model, respectively determining eye positions of the multiple screen viewers, and selecting or determining weights corresponding to the multiple screen viewers;

[0028] Determine the binocular center coordinates of the multiple screen viewers respectively according to the eye positions of the multiple screen viewers, and determine the sitting heights of the multiple screen viewers according to the binocular center coordinates;

[0029] The target adjustment parameter is determined according to the sitting heights of the multiple screen viewers and in combination with the weights corresponding to the multiple screen viewers.

[0030] In one embodiment, before or after the step of acquiring the facial image of at least one screen viewer, the step further includes:

[0031] Get driving status information;

[0032] Predicting a user's posture change according to the driving state information to obtain a posture change prediction result;

[0033] A screen adaptation adjustment parameter is determined according to the posture change prediction result, and the vehicle-mounted screen is adjusted according to the screen adaptation adjustment parameter.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a screen adjustment device, which includes:

[0035] A response module, configured to obtain a facial image of at least one screen viewer in response to satisfying a preset precondition;

[0036] The adjustment module is used to determine target adjustment parameters according to the facial image of the at least one screen viewer based on a preset visual recognition model, and adjust the vehicle-mounted screen according to the target adjustment parameters.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a screen adjustment device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the screen adjustment method described above.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the screen adjustment method described above are implemented.

[0039] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, wherein the computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the screen adjustment method described above are implemented.

[0040] One or more technical solutions proposed in this application have at least the following technical effects:

[0041] In response to meeting preset preconditions, a facial image of at least one screen viewer is obtained; based on a preset visual recognition model, a target adjustment parameter is determined according to the facial image of the at least one screen viewer, and the vehicle-mounted screen is adjusted according to the target adjustment parameter. When the preset preconditions are met, the facial image of at least one screen viewer is obtained in time, and then the target adjustment parameter is determined according to the facial image of the at least one screen viewer through the visual recognition model. There is no need for the user to manually adjust the vehicle-mounted screen, and automatic adjustment of the vehicle-mounted screen is achieved, thereby improving the intelligence level of the vehicle-mounted screen adjustment and thus enhancing the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 A schematic diagram of a flow chart provided for the first embodiment of the screen adjustment method of the present application;

[0045] Figure 2 A schematic diagram of a flow chart provided for the second embodiment of the screen adjustment method of the present application;

[0046] Figure 3 A schematic diagram of a flow chart provided for Embodiment 3 of the screen adjustment method of the present application;

[0047] Figure 4 A flowchart of the fourth embodiment of the screen adjustment method of the present application is provided;

[0048] Figure 5 This is a schematic diagram of the module structure of the screen adjustment device according to an embodiment of the present application;

[0049] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the screen adjustment method in the embodiment of the present application.

[0050] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0052] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0053] The main solution of the embodiment of the present application is: in response to meeting the preset preconditions, obtaining the facial image of at least one screen viewer; determining the target adjustment parameters according to the facial image of the at least one screen viewer based on a preset visual recognition model, and adjusting the vehicle screen according to the target adjustment parameters. When the preset preconditions are met, the facial image of at least one screen viewer is obtained in time, and then the target adjustment parameters are determined according to the facial image of the at least one screen viewer through the visual recognition model. There is no need for the user to manually adjust the vehicle screen, so that automatic adjustment of the vehicle screen is achieved, which improves the intelligence level of the vehicle screen adjustment and thus enhances the user experience.

[0054] In this embodiment, for the convenience of description, the following description is made with the screen adjustment device as the execution subject.

[0055] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a screen adjustment device, etc. The following takes the screen adjustment device as an example to illustrate this embodiment and the following embodiments.

[0056] Based on this, the present application embodiment provides a screen adjustment method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the screen adjustment method of the present application.

[0057] In this embodiment, the screen adjustment method includes steps S10 to S20:

[0058] Step S10, in response to satisfying a preset precondition, acquiring a facial image of at least one screen viewer;

[0059] Specifically, the screen adjustment method proposed in the embodiment of the present application provides an intelligent adjustment function of the vehicle-mounted screen, which is activated when preset preconditions are met, thereby avoiding unnecessary resource consumption or misoperation.

[0060] Optionally, a multi-level verification mechanism is adopted to first detect the seat occupancy status and then further confirm the status of the vehicle screen to determine whether to activate the intelligent adjustment function, that is, to determine the target adjustment parameters by collecting the facial image of at least one screen viewer.

[0061] Optionally, in response to satisfying a preset precondition, before the step of acquiring a facial image of at least one screen viewer, the step further includes:

[0062] In response to identifying data change information of the first sensor, determining whether a seat is occupied according to the data change information;

[0063] If there is a seat occupancy, identifying whether the vehicle screen is in an unfolded state;

[0064] If the vehicle-mounted screen is not in the unfolded state, generating a first prompt message for the user to confirm whether to unfold the vehicle-mounted screen;

[0065] If the vehicle-mounted screen is in the unfolded state, it is determined that the preset precondition is met.

[0066] Optionally, the first sensor may be a pressure sensor installed on a car seat, and the pressure sensor installed on the seat is used to monitor in real time whether a passenger is sitting. This method has the advantages of rapid response and high accuracy.

[0067] Optionally, the first sensor may also be a visual sensor such as an in-car camera, which uses the in-car camera in conjunction with a computer vision algorithm to identify the presence of a passenger. Although there may be a slight delay, it can provide richer information.

[0068] Optionally, the above two methods can be combined to ensure quick response and increase system reliability. For example, after initially determining that someone is present through the pressure sensor, a camera can be used for secondary confirmation.

[0069] For example, when a passenger opens the door and sits in the back seat, the seat sensor immediately detects the weight change, triggering the system to enter the next stage of inspection. If the in-vehicle screen is found to be in the retracted state at this time, a prompt is sent to the passenger to ask whether the screen needs to be unfolded; if the passenger confirms, the screen is unfolded and prepares to capture the facial image of at least one screen viewer.

[0070] Optionally, the vehicle-mounted screen is connected to a screen carrier, and the method further comprises:

[0071] When the vehicle-mounted screen is in an unfolded state, obtaining current position information and previous position information of the screen carrier;

[0072] Determining a position change value of the screen carrier according to current position information and previous position information of the screen carrier;

[0073] If the position change value is greater than or equal to a preset position change threshold, it is determined that the preset precondition is met.

[0074] Optionally, the screen carrier is a physical structure that carries or supports the vehicle screen, and may be a vehicle seat (such as a passenger seat, etc.), or a device on the top of the vehicle, etc. The vehicle screen is movably or fixedly connected to the screen carrier.

[0075] Optionally, the current position information refers to the specific position data of the current location of the screen carrier, and the previous position information refers to the previously recorded position data. By calculating the difference between the current position information and the previous position information of the screen carrier, it can be determined whether the screen carrier has moved and the degree of movement. The preset position change threshold can be set according to actual conditions. The smaller the preset position change threshold is, the higher the sensitivity of triggering the automatic adjustment of the screen position is.

[0076] Optionally, in the embodiment of the present application, the adjustment of the vehicle screen can be triggered when the vehicle screen is started, and the adjustment of the vehicle screen can also be triggered when the screen carrier is detected to be displaced during the use of the vehicle screen, thereby improving the trigger mechanism of screen adjustment and avoiding energy consumption problems caused by continuous detection. For example, the vehicle screen is connected to the vehicle seat. If it is detected that the position of the vehicle seat changes by more than 3 cm, the vehicle screen is automatically adjusted to the optimal viewing angle. Through the intelligent position adjustment mechanism, the need for manual adjustment is reduced, and the convenience and efficiency of use are improved. In addition, it can also prevent equipment loss problems caused by frequent manual adjustments.

[0077] Step S20, determining target adjustment parameters according to the facial image of the at least one screen viewer based on a preset visual recognition model, and adjusting the vehicle-mounted screen according to the target adjustment parameters.

[0078] Furthermore, in response to satisfying preset preconditions, after acquiring a facial image of at least one screen viewer, target adjustment parameters can be determined based on a preset visual recognition model according to the facial image of at least one screen viewer, and the vehicle-mounted screen can be adjusted according to the target adjustment parameters.

[0079] Optionally, in the embodiment of the present application, a deep learning model is pre-trained to extract key features from the facial image of at least one screen viewer, thereby predicting the optimal screen adjustment parameters. The target adjustment parameters refer to specific parameter values ​​set to achieve an ideal viewing effect, such as the angle, brightness, and contrast of the vehicle screen.

[0080] Optionally, the visual recognition model is trained with a large amount of sample data to understand the relationship between different user states and ideal screen settings, with the goal of providing each passenger with the most comfortable viewing experience while minimizing the impact on other passengers. A machine learning algorithm is used to analyze the facial image of at least one screen viewer, output a set of optimal target adjustment parameters, and adjust the various properties of the vehicle screen accordingly.

[0081] Optionally, a feedback mechanism is introduced in the embodiment of the present application to allow the visual recognition model to continuously self-correct and improve according to the actual effect. For example, user feedback after each adjustment is recorded to gradually optimize the parameter selection in similar situations in the future.

[0082] Through the above scheme, this embodiment specifically obtains the facial image of at least one screen viewer in response to meeting the preset precondition; determines the target adjustment parameters according to the facial image of the at least one screen viewer based on the preset visual recognition model, and adjusts the vehicle screen according to the target adjustment parameters. When the preset precondition is met, the facial image of at least one screen viewer is obtained in time, and then the target adjustment parameters are determined according to the facial image of the at least one screen viewer through the visual recognition model. There is no need for the user to manually adjust the vehicle screen, and automatic adjustment of the vehicle screen is achieved, thereby improving the intelligence level of the vehicle screen adjustment and thus enhancing the user experience.

[0083] Based on the first embodiment of the present application, a second embodiment of the present application is proposed. In the second embodiment of the present application, the same or similar contents as those of the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated later.

[0084] On this basis, please refer to Figure 2 , step S20 also includes steps S201 to S204:

[0085] Step S201, identifying the number of screen viewers corresponding to the facial image of the at least one screen viewer;

[0086] Step S202, if the facial image of the at least one screen viewer corresponds to a screen viewer, key point recognition is performed on the facial image using the visual recognition model to determine the eye position of the screen viewer;

[0087] Step S203, determining the binocular center coordinates of the screen viewer according to the eye positions, and determining the sitting height of the screen viewer according to the binocular center coordinates;

[0088] Step S204, selecting or determining the target adjustment parameter corresponding to the seat height.

[0089] Optionally, before the step of acquiring the facial image of at least one screen viewer, the step further includes:

[0090] Collecting the image of the interior space of the vehicle by means of a second sensor;

[0091] At least one of facial recognition, gesture recognition, and interactive behavior recognition is performed on the in-vehicle space image to determine at least one screen viewer in the in-vehicle space image.

[0092] Optionally, the second sensor can be a visual sensor such as an in-vehicle camera. By installing multiple high-resolution cameras in the rear row of the vehicle, especially devices with depth perception capabilities (such as 3D cameras or RGB-D sensors), the face and eye positions of passengers can be captured.

[0093] Optionally, deep learning models such as convolutional neural networks (CNN) are used to detect and recognize the facial features of each passenger. This not only helps to distinguish the identities of different passengers, but also provides support for subsequent personalized services.

[0094] Optionally, the eye key point positioning technology and geometric calculation method are combined to track the passenger's eye movement path in real time to determine whether the passenger's line of sight is directed to the on-board screen. By analyzing the position changes of the pupil center, eye corners and other parts, it can be more accurately determined whether the passenger is looking at the screen.

[0095] Optionally, in addition to directly observing the eyes, the judgment can also be assisted by analyzing the passenger's body posture and head orientation. For example, if the passenger is facing the screen and his body posture is relatively fixed, he may be one of the current viewers. Machine learning models can be trained to recognize these typical behavior patterns.

[0096] Optionally, the interaction between the passenger and the screen is monitored, such as touch operation, gesture control or voice command, etc. If a passenger is performing such interaction, it means that he is the current main viewer.

[0097] Optionally, in other embodiments, a simple way (such as a button, touch screen menu, or voice command) can be provided to passengers to indicate that they are the current viewer. Although this method is not part of the automated solution, it can be used as a supplementary means in some cases. Over time, the system can gradually form a data record by recording each passenger's habitual seat position and personal preferences, so as to more quickly and accurately identify who is most likely to be watching the screen.

[0098] Alternatively, considering that human attention is not constant but fluctuates over time, a time series analysis method can be introduced to predict future viewing trends based on historical data, so as to prepare in advance.

[0099] Optionally, the facial image is input into the visual recognition model, and the prediction results containing multiple key point coordinates are output. Using pre-trained deep learning models (such as OpenPose, HRNet, etc.), the location information of key points can be efficiently extracted from the facial image, especially the coordinates of the eyes. Performing facial detection and key point location tasks simultaneously in the same model can reduce redundant calculations and improve overall efficiency.

[0100] For example, once the system confirms that only one passenger is watching the screen, it immediately calls the visual recognition model to analyze the passenger’s facial image and accurately locate the specific position of his or her eyes.

[0101] Optionally, based on the known eye positions, the coordinates of the center of both eyes can be calculated through geometric relationships; combined with the seat height and other auxiliary information, the passenger's seat height can be calculated. By determining the passenger's seat height, it can provide a basis for subsequent screen angle and brightness adjustments to ensure that every passenger can get the best viewing experience.

[0102] Optionally, according to the seat height of the passenger, a pre-calibrated mapping table may be searched or a specific algorithm may be applied to determine the screen adjustment parameter combination that best suits the passenger, as shown in Table 1:

[0103] Table 1. Example of mapping between passenger seat height and vehicle screen angle

[0104]

[0105]

[0106] This embodiment adopts the above scheme, specifically by identifying the number of screen viewers corresponding to the facial image of the at least one screen viewer; if the facial image of the at least one screen viewer corresponds to one screen viewer, the key points of the facial image are identified by the visual recognition model to determine the eye position of the screen viewer; the center coordinates of both eyes of the screen viewer are determined according to the eye position, and the sitting height of the screen viewer is determined according to the center coordinates of both eyes; the target adjustment parameter corresponding to the sitting height is selected or determined, and the user does not need to manually adjust the vehicle screen, so that the automatic adjustment of the vehicle screen is realized, which improves the intelligence level of the vehicle screen adjustment, and can not only provide a personalized viewing experience in the case of a single screen viewer.

[0107] Based on any of the foregoing embodiments of the present application, a third embodiment of the present application is proposed. In the third embodiment of the present application, the same or similar contents as any of the foregoing embodiments can be referred to the above introduction and will not be described in detail later. Figure 3 , after step S201, steps S205 to S207 are also included:

[0108] Step S205, if the facial image of the at least one screen viewer corresponds to multiple screen viewers, key point recognition is performed on the facial image using the visual recognition model, eye positions of the multiple screen viewers are determined respectively, and weights corresponding to the multiple screen viewers are selected or determined;

[0109] Step S206, determining the binocular center coordinates of the multiple screen viewers respectively according to the eye positions of the multiple screen viewers, and determining the sitting heights of the multiple screen viewers according to the binocular center coordinates;

[0110] Step S207: determining the target adjustment parameter according to the sitting heights of the multiple screen viewers and the weights corresponding to the multiple screen viewers.

[0111] Optionally, for multiple screen viewers, their eye center coordinates and sitting heights can be calculated respectively, and then weights can be assigned according to preset rules, and finally the needs of all viewers can be comprehensively considered to determine a compromise optimal screen adjustment parameter. A set of weight allocation strategies can be designed, and then a mathematical model (such as linear programming, multi-objective optimization, etc.) can be used to solve the optimal solution.

[0112] Optionally, in the embodiment of the present application, computer vision and machine learning algorithms are used to analyze the facial image of at least one screen viewer, in particular, the eye position of each screen viewer is determined by key point recognition technology, and a weight value is assigned to each viewer. Commonly used technologies include convolutional neural networks (CNNs), models based on attention mechanisms, etc. Accurately determining the eye positions of multiple screen viewers is a prerequisite for accurate eye tracking, and the setting of weights helps the system decide how to balance the needs of different passengers and ensure that the adjusted screen settings can meet the viewing experience of everyone as much as possible.

[0113] Optionally, the facial images of at least one screen viewer are initially screened to exclude non-face areas, and then an efficient facial detection and key point recognition algorithm is applied to calculate the specific number of people and their eye positions. Next, a weight is assigned to each viewer based on preset rules or historical data, which may take into account factors such as seat position and age.

[0114] Optionally, based on the known eye position, the coordinates of the center of both eyes can be calculated through geometric relationships; combined with the seat height and other auxiliary information, the passenger's seat height can be calculated. By determining the seat height of each screen viewer, it can provide a basis for subsequent screen angle and brightness adjustments to ensure that every passenger has the best viewing experience. Based on geometric calculation or depth perception, combined with fixed reference points in the car (such as the top edge of the seat), the actual height of each passenger's eyes is calculated. At the same time, considering possible errors, a calibration mechanism is introduced to improve accuracy.

[0115] Optionally, according to the seat height of the passengers and the corresponding weights, a predefined mapping table is searched or a specific algorithm is applied to determine the combination of screen adjustment parameters that best suits the group of passengers. Common methods include mathematical models such as linear programming and multi-objective optimization. Ensure that every passenger can enjoy the most comfortable viewing experience while minimizing the impact on other passengers. By reasonably allocating weights, a compromise best solution can be found when multiple people are watching. Design a set of weight allocation strategies, such as front-row passengers first, children first, etc., and then use mathematical models to solve the optimal solution. Using linear programming or multi-objective optimization algorithms, find a set of adjustment parameters that maximize overall satisfaction based on the needs of all passengers. In addition, user preference settings can be introduced to allow passengers to manually adjust weights to enhance personalized experience.

[0116] This embodiment, through the above scheme, specifically includes: if the facial image of the at least one screen viewer corresponds to multiple screen viewers, then the visual recognition model is used to identify key points of the facial image, and the eye positions of the multiple screen viewers are respectively determined, and the weights corresponding to the multiple screen viewers are selected or determined; the center coordinates of the eyes of the multiple screen viewers are respectively determined according to the eye positions of the multiple screen viewers, and the sitting heights of the multiple screen viewers are determined according to the center coordinates of the eyes; the target adjustment parameters are determined according to the sitting heights of the multiple screen viewers and the weights corresponding to the multiple screen viewers, which can not only provide a personalized viewing experience in the case of a single screen viewer, but also effectively cope with the situation where multiple screen viewers coexist, ensuring that each screen viewer can obtain a relatively ideal viewing effect.

[0117] Based on any of the foregoing embodiments of the present application, a fourth embodiment of the present application is proposed. In the fourth embodiment of the present application, the same or similar contents as any of the foregoing embodiments can be referred to the above introduction and will not be described in detail later. Figure 4 , before or after step S10, steps S01 to S03 are also included:

[0118] Step S01, obtaining driving status information;

[0119] Optionally, driving state information refers to data collected by various sensors during the driving process of the vehicle, including but not limited to vehicle speed, acceleration, steering angle, brake status, etc. This information can reflect the current dynamic situation of the vehicle. In the embodiment of the present application, driving state information can be collected by various sensors installed in the vehicle (such as accelerometers, gyroscopes, GPS, CAN bus, etc.).

[0120] Optionally, multiple types of sensors are used to monitor the vehicle's operating parameters in real time and transmit this data to the central processing unit (ECU). The selection and arrangement of sensors should ensure comprehensive coverage and high enough accuracy to accurately capture every detail of the vehicle's movements. Driving status information is the basis for subsequent prediction of user posture changes. Only by accurately grasping the vehicle's driving conditions can reasonable adjustments and predictions be made. A multi-source data fusion platform can be built to integrate information from different sensors to form a complete description of the driving status. At the same time, an efficient data transmission mechanism is designed to ensure the timeliness and accuracy of information.

[0121] Optionally, more comprehensive driving status information can be provided by combining data from multiple sensors such as accelerometers, gyroscopes, and GPS. This approach can improve data integrity and reliability, but the problems of data synchronization and fusion need to be solved. Through CAN bus-based data acquisition, driving status information is read directly from the vehicle's CAN bus, which simplifies hardware connections and improves system integration. This method is suitable for modern cars and has a high data transmission rate. If the vehicle supports networking, some data can be uploaded to the cloud for analysis and processing, and powerful cloud computing resources can be used to improve data processing capabilities. This helps to meet data analysis needs in complex scenarios.

[0122] Step S02, predicting a user's posture change according to the driving state information to obtain a posture change prediction result;

[0123] Furthermore, after acquiring the facial image of at least one screen viewer, the user posture change prediction can be performed according to the driving state information to obtain a posture change prediction result.

[0124] Optionally, user posture change prediction refers to predicting the trend of body posture changes of passengers during vehicle driving based on driving status information using machine learning or deep learning algorithms. The posture change prediction result is the predicted possible posture changes of passengers in the future, such as head tilt angle, body center of gravity transfer direction, etc.

[0125] Optionally, in the embodiments of the present application, models such as time series analysis, recursive neural network (RNN), long short-term memory network (LSTM) are used to model the driving state information and predict the changes in passenger posture in the short term in the future. These models are good at processing time-dependent data and can effectively capture the trend of passenger posture evolution over time. By understanding the changes in passenger body posture in advance, the system can better plan the screen adjustment strategy, avoid the impact on the passenger's viewing experience due to sudden bumps and other situations, and reduce the discomfort caused by repeated adjustments of the passenger's viewing angle when watching videos during the ride.

[0126] Optionally, in the embodiment of the present application, a prediction model can be trained by establishing a data set including historical driving status and corresponding passenger posture changes. Then, in actual application, the current driving status information is input and the predicted passenger posture change result is output.

[0127] Optionally, a static prediction model is used to directly predict the current driving status information using a pre-trained model, which is suitable for scenarios with simple processing and fixed patterns. The advantages are small computational complexity and fast response speed, but poor adaptability. An adaptive prediction model can also be used to introduce an online learning mechanism, allowing the model to continuously update its own parameters based on the latest driving status information and gradually optimize the prediction effect. This method can maintain a high prediction accuracy in a changing actual environment. Context-aware enhanced prediction can also be performed, combining real-time traffic information and map data, so that the prediction model not only considers internal vehicle factors, but also takes into account the influence of the external environment, such as road curvature, traffic light location, etc., thereby improving the accuracy of the prediction.

[0128] For example, when the vehicle is about to enter a sharp turn, the system predicts that the passenger may lean to one side based on the driving status information (such as the increase in the steering angle). This prediction result will be used for the next screen adjustment decision.

[0129] Step S03, determining screen adaptation adjustment parameters according to the posture change prediction result, and adjusting the vehicle-mounted screen according to the screen adaptation adjustment parameters.

[0130] Furthermore, the user posture change prediction is performed based on the driving status information. After the posture change prediction result is obtained, the screen adaptation adjustment parameter can be determined according to the posture change prediction result, and the vehicle-mounted screen can be adjusted according to the screen adaptation adjustment parameter.

[0131] Optionally, the screen adaptation adjustment parameter refers to a set of specific parameter values ​​set to achieve an ideal viewing effect, such as screen angle, brightness, contrast, etc. The posture change prediction result is a prediction of the possible future body posture change of the passenger obtained in the previous step.

[0132] Optionally, based on the predicted change in passenger posture, a predefined mapping table is searched or a specific algorithm is applied to determine the combination of screen adjustment parameters that best suits the change. Common methods include mathematical models such as linear programming and multi-objective optimization. Ensure that every passenger can enjoy the most comfortable viewing experience while minimizing the impact on other passengers. By setting the screen parameters reasonably, a compromise best solution can be found when multiple people are watching. A set of weight allocation strategies can be designed, such as front-row passenger priority, child priority, etc., and then a mathematical model can be used to solve the optimal solution. In addition, user preference settings can be introduced to allow passengers to manually adjust weights to enhance the personalized experience.

[0133] For example, based on the prediction results, the system knows that the passenger may lean slightly to the right when the vehicle turns. Therefore, it decides to adjust the screen angle slightly to the left by 5 degrees in advance and increase the brightness appropriately to ensure that the passenger can still watch the screen content comfortably during the turn.

[0134] This embodiment adopts the above scheme, specifically by acquiring driving status information; predicting user posture changes based on the driving status information to obtain posture change prediction results; determining screen adaptation adjustment parameters based on the posture change prediction results, and adjusting the vehicle-mounted screen according to the screen adaptation adjustment parameters. Through driving status information and user posture change prediction, a more intelligent adjustment scheme is provided, which further improves the intelligence level of vehicle-mounted screen adjustment and improves user experience.

[0135] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the screen adjustment method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0136] This application also provides a screen adjustment device, please refer to Figure 5 , the screen adjustment device comprises:

[0137] A response module 10, configured to obtain a facial image of at least one screen viewer in response to satisfying a preset precondition;

[0138] The adjustment module 20 is used to determine target adjustment parameters according to the facial image of the at least one screen viewer based on a preset visual recognition model, and adjust the vehicle-mounted screen according to the target adjustment parameters.

[0139] The screen adjustment device provided by the present application adopts the screen adjustment method in the above embodiment to solve the technical problem of screen adjustment. Compared with the prior art, the beneficial effects of the screen adjustment device provided by the present application are the same as the beneficial effects of the screen adjustment method provided by the above embodiment, and other technical features in the screen adjustment device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0140] The present application provides a screen adjustment device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the screen adjustment method in the above-mentioned embodiment 1.

[0141] Reference below Figure 6, which shows a schematic diagram of the structure of a screen adjustment device suitable for implementing the embodiment of the present application. The screen adjustment device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The screen adjustment device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0142] like Figure 6 As shown, the screen adjustment device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the screen adjustment device are also stored. The processing device 1001, ROM1002, and RAM1004 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: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a 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 screen adjustment device to communicate with other devices wirelessly or by wire to exchange data. Although the screen adjustment device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0143] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0144] The screen adjustment device provided by the present application adopts the screen adjustment method in the above embodiment to solve the technical problem of screen adjustment. Compared with the prior art, the beneficial effects of the screen adjustment device provided by the present application are the same as the beneficial effects of the screen adjustment method provided by the above embodiment, and other technical features in the screen adjustment device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0145] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0146] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0147] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the screen adjustment method in the above-mentioned embodiment.

[0148] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, 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 this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0149] The computer-readable storage medium may be included in the screen adjustment device; or may exist independently without being assembled into the screen adjustment device.

[0150] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the screen adjustment device, the screen adjustment device: obtains the facial image of at least one screen viewer in response to meeting the preset precondition; determines the target adjustment parameters according to the facial image of the at least one screen viewer based on the preset visual recognition model, and adjusts the vehicle-mounted screen according to the target adjustment parameters. When the preset precondition is met, the facial image of at least one screen viewer is obtained in time, and then the target adjustment parameters are determined according to the facial image of the at least one screen viewer through the visual recognition model. There is no need for the user to manually adjust the vehicle-mounted screen, so that automatic adjustment of the vehicle-mounted screen is achieved, thereby improving the intelligence level of the vehicle-mounted screen adjustment and thus improving the user experience.

[0151] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a 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 may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0152] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0153] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0154] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned screen adjustment method, and can solve the technical problem of screen adjustment. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the screen adjustment method provided in the above-mentioned embodiment, and will not be repeated here.

[0155] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned screen adjustment method when executed by a processor.

[0156] The computer program product provided by the present application can solve the technical problem of screen adjustment. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the screen adjustment method provided by the above embodiment, which will not be repeated here.

[0157] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A screen adjustment method, characterized in that: The method comprises: In response to satisfying a preset precondition, acquiring a facial image of at least one screen viewer; Based on a preset visual recognition model, target adjustment parameters are determined according to the facial image of the at least one screen viewer, and the vehicle-mounted screen is adjusted according to the target adjustment parameters.

2. The method according to claim 1, characterized in that In response to satisfying the preset precondition, the step of acquiring the facial image of at least one screen viewer also includes: In response to identifying data change information of the first sensor, determining whether a seat is occupied according to the data change information; If there is a seat occupancy, identifying whether the vehicle screen is in an unfolded state; If the vehicle-mounted screen is not in the unfolded state, generating a first prompt message for the user to confirm whether to unfold the vehicle-mounted screen; If the vehicle-mounted screen is in the unfolded state, it is determined that the preset precondition is met.

3. The method according to claim 2, characterized in that The vehicle-mounted screen is connected to a screen carrier, and the method further comprises: When the vehicle-mounted screen is in an unfolded state, obtaining current position information and previous position information of the screen carrier; Determining a position change value of the screen carrier according to current position information and previous position information of the screen carrier; If the position change value is greater than or equal to a preset position change threshold, it is determined that the preset precondition is met.

4. The method according to claim 1, characterized in that The step of obtaining the facial image of at least one screen viewer also includes: Collecting the image of the interior space of the vehicle by means of a second sensor; At least one of facial recognition, gesture recognition, and interactive behavior recognition is performed on the in-vehicle space image to determine at least one screen viewer in the in-vehicle space image.

5. The method according to claim 1, characterized in that The step of determining the target adjustment parameter according to the facial image of the at least one screen viewer based on the preset visual recognition model comprises: identifying the number of screen viewers corresponding to the facial image of the at least one screen viewer; If the facial image of the at least one screen viewer corresponds to a screen viewer, performing key point recognition on the facial image by using the visual recognition model to determine the eye position of the screen viewer; Determine the binocular center coordinates of the screen viewer according to the eye positions, and determine the sitting height of the screen viewer according to the binocular center coordinates; Select or determine the target adjustment parameter corresponding to the seat height.

6. The method according to claim 5, characterized in that After the step of identifying the number of screen viewers corresponding to the facial image of at least one screen viewer, the step further includes: If the facial image of the at least one screen viewer corresponds to multiple screen viewers, performing key point recognition on the facial image by using the visual recognition model, respectively determining eye positions of the multiple screen viewers, and selecting or determining weights corresponding to the multiple screen viewers; Determine the binocular center coordinates of the multiple screen viewers respectively according to the eye positions of the multiple screen viewers, and determine the sitting heights of the multiple screen viewers according to the binocular center coordinates; The target adjustment parameter is determined according to the sitting heights of the multiple screen viewers and in combination with the weights corresponding to the multiple screen viewers.

7. The method according to claim 1, characterized in that Before or after the step of acquiring the facial image of at least one screen viewer, the following steps may also be included: Get driving status information; Predicting a user's posture change according to the driving state information to obtain a posture change prediction result; A screen adaptation adjustment parameter is determined according to the posture change prediction result, and the vehicle-mounted screen is adjusted according to the screen adaptation adjustment parameter.

8. A screen adjustment device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the screen adjustment method according to any one of claims 1 to 7.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the screen adjustment method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the screen adjustment method according to any one of claims 1 to 7 are implemented.

Images