Vehicle control methods, electronic devices, storage media, products and vehicles

Abstract

This application relates to a vehicle control method, electronic device, storage medium, product, and vehicle. It involves acquiring first perception data corresponding to a target seat in the vehicle; determining target control information corresponding to the target seat based on the first perception data using a target model; and adjusting the target seat according to the target control information. This application enables fine-tuning of the seat.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle control method, electronic device, storage medium, product, and vehicle. Background Technology

[0002] With the improvement of people's living standards and the development of intelligent electric vehicle technology, car seats not only pursue functional diversity, but also pay more attention to comfort and humanized design.

[0003] The relevant technologies generally use data collected by sensors as a reference to adjust the posture of the seat. This adjustment method is very crude and results in poor seat comfort. Summary of the Invention

[0004] This application provides a vehicle control method, electronic device, computer-readable storage medium, computer program product, and vehicle to improve seat comfort and thus enhance the user's driving experience, thereby at least partially solving the aforementioned technical problems.

[0005] To achieve the above objectives, according to a first aspect of this application, a vehicle control method is provided, comprising:

[0006] Acquire the first perception data corresponding to the target seat in the vehicle;

[0007] Based on the first perception data, the target control information corresponding to the target seat is determined through the target model;

[0008] The target seat is adjusted according to the target control information.

[0009] Optionally, determining the target control information corresponding to the target seat based on the perceived data and using a target model includes:

[0010] The first sensed data is processed to obtain the first target data corresponding to the first sensed data;

[0011] The target data is processed by the target model to obtain target control information for controlling the target seat.

[0012] Optionally, the first sensing data includes sensing data collected by at least one first sensor disposed on the target seat.

[0013] Optionally, the first sensor includes at least one of a pressure sensor, a pulse sensor, an accelerometer, and a gyroscope.

[0014] Optionally, when the first sensing data is sensing data collected by a pressure sensor, the first sensing data includes multiple sets of sensing data collected by the pressure sensor multiple times.

[0015] Optionally, processing the first sensing data to obtain the first target data corresponding to the first sensing data includes:

[0016] At least one set of sensing data from multiple sets of sensing data is processed to obtain the first target data corresponding to the first sensing data.

[0017] Optionally, the target control information is control information used to ensure that the target seat is in the target seat mode after adjustment.

[0018] Optionally, the multiple sets of sensing data include at least two sets of first sensing data collected before the target seat mode is activated and at least one set of first sensing data collected after the target seat mode is activated.

[0019] Optionally, processing at least one set of sensing data from multiple sets of sensing data to obtain the first target data corresponding to the first sensing data includes:

[0020] At least one set of first perception data is determined from at least two sets of first perception data collected before the target seat mode is activated, and at least one set of second perception data is determined from at least one set of first perception data collected after the target seat mode is activated.

[0021] The first set of sensing data and / or the second set of sensing data are processed to obtain the first target data corresponding to the first sensing data.

[0022] Optionally, the first target data includes pressure characteristic information of the area where the pressure sensor is located.

[0023] Optionally, the pressure characteristic information includes at least one of the following: total pressure, peak pressure, pressure area, and average pressure.

[0024] Optionally, the method further includes:

[0025] If the target control information meets the preset evaluation criteria, the target seat is adjusted according to the target control information.

[0026] Optionally, the method further includes:

[0027] If the target control information does not meet the preset evaluation criteria, the target control information corresponding to the target seat is re-determined through the target model.

[0028] Optionally, the preset evaluation criteria include a deviation between the target control information and the preset standard control information that is not greater than a preset deviation threshold.

[0029] Optionally, the target model includes models corresponding to at least two occupant sitting postures.

[0030] Optionally, the target model includes a first model corresponding to a standard occupant sitting posture and a second model corresponding to a non-standard occupant sitting posture.

[0031] Optionally, the method further includes:

[0032] If the occupant body pressure distribution corresponding to the first target data meets the preset distribution conditions, the target model is the first model.

[0033] Optionally, if the occupant body pressure distribution corresponding to the first target data does not meet the preset distribution conditions, the target model is the second model.

[0034] Optionally, after adjusting the target seat according to the target control information, the method further includes:

[0035] Obtain the evaluation results corresponding to the adjusted target seat;

[0036] Based on the evaluation results, the target seat is adjusted.

[0037] Optionally, the evaluation results include at least one of the following: the occupant's subjective evaluation of the adjusted target seat, the occupant's physiological information, the occupant's posture information, and the occupant's body pressure distribution information on the target seat.

[0038] Optionally, before adjusting the target seat according to the target control information, the method further includes:

[0039] Acquire the second perception data corresponding to the target seat in the vehicle;

[0040] The target control information is adjusted based on the second sensing data.

[0041] Optionally, the second sensing data includes: sensing data collected by at least one second sensor.

[0042] Optionally, the second sensor includes at least one of a biomedical sensor, an accelerometer, and a gyroscope.

[0043] Optionally, adjusting the target control information based on the second sensing data includes:

[0044] The second sensed data is processed to obtain the second target data;

[0045] The target control information is adjusted based on the second target data.

[0046] Optionally, processing the second sensed data to obtain the second target data includes:

[0047] When the second sensing data is sensing data collected by a biomedical sensor, the signal features of the second sensing data collected by the biomedical sensor are extracted.

[0048] Second target data of the occupant in the target seat is determined based on the signal characteristics, wherein the second target data includes the occupant's physiological characteristic data.

[0049] Optionally, the biomedical sensor includes a pulse sensor.

[0050] Optionally, processing the second sensed data to obtain the second target data includes:

[0051] When the second sensing data includes the first sub-sensing data collected by the gyroscope and the second sub-sensing data collected by the accelerometer, the first signal feature corresponding to the first sub-sensing data and the second signal feature corresponding to the second sub-sensing data are extracted.

[0052] The second target data is determined based on the first signal feature and the second signal feature.

[0053] Optionally, determining the second target data based on the first signal feature and the second signal feature includes:

[0054] The first signal feature and the second signal feature are fused to obtain the fused feature;

[0055] Based on the fusion features, the second target data is obtained.

[0056] Optionally, the second target data includes the occupant's user posture change characteristics and the corresponding motion information of the vehicle.

[0057] Optionally, the method further includes:

[0058] Obtain the configuration parameters associated with the target model;

[0059] The configuration parameters are sent to the cloud server so that the cloud server can configure the target model according to the configuration parameters.

[0060] Optionally, the configuration parameters include at least one of the evaluation criteria corresponding to the target model and the model parameters of the target model.

[0061] Optionally, the method further includes:

[0062] When the zero-gravity mode of the target seat is activated, the following steps are performed: determining the target control information corresponding to the target seat based on the first perception data and the target model; and adjusting the target seat according to the target control information.

[0063] Optionally, the method further includes:

[0064] When the target seat is not in the zero-gravity mode, the target seat is adjusted based on the occupant's posture information and the vehicle's motion information.

[0065] Optionally, the method further includes:

[0066] When the vehicle is in an unsafe scenario corresponding to zero gravity mode, the zero gravity mode is controlled to be turned off.

[0067] Optionally, the unsafe scenario includes: the vehicle's speed is greater than a preset speed threshold; and / or, the occupant in the target seat meets the corresponding health indicators.

[0068] Secondly, this embodiment also provides an electronic device, which includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the above-described method.

[0069] Thirdly, this embodiment also provides a computer-readable storage medium including a computer program, which, when run on an electronic device, causes the electronic device to perform the steps of the above-described method.

[0070] Fourthly, this embodiment also provides a computer program product, including a computer program stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, causing the electronic device to perform the steps of the above method.

[0071] Fifthly, this embodiment also provides a vehicle, wherein at least one of the above-mentioned electronic devices, computer-readable storage media, and computer program products is provided on the vehicle.

[0072] In summary, this application embodiment obtains first perception data corresponding to the target seat of the vehicle through the above technical solution, and determines the target control information corresponding to the target seat based on the first perception data through a target model, and then adjusts the target seat according to the target control information. Compared with the prior art that directly uses data collected by sensors to control the posture of the seat, this application determines the target control information through a target model after obtaining the perception data, and uses the target control information to adjust the seat, achieving more precise adjustment of the seat, thereby effectively improving seat comfort and enhancing user experience.

[0073] Other features and advantages of this application will be described in detail in the following detailed description section. Attached Figure Description

[0074] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0075] To gain a more complete understanding of this application and its beneficial effects, the following description will be provided in conjunction with the accompanying drawings, wherein the same reference numerals in the following description denote the same parts.

[0076] Figure 1 This is a first schematic diagram of the related technology provided in this application;

[0077] Figure 2 This is a second schematic diagram of the related technology provided in this application;

[0078] Figure 3 This is a first schematic diagram of seat adjustment provided in an exemplary embodiment of this application;

[0079] Figure 4 This is a first schematic diagram of the vehicle control process provided in the exemplary embodiments of this application;

[0080] Figure 5 This is a second schematic diagram of seat adjustment provided in an exemplary embodiment of this application;

[0081] Figure 6 This is a third schematic diagram of seat adjustment provided in an exemplary embodiment of this application;

[0082] Figure 7 This is a fourth schematic diagram of seat adjustment provided in an exemplary embodiment of this application;

[0083] Figure 8This is a schematic diagram of the architecture of an electronic device provided in an exemplary embodiment of this application. Detailed Implementation

[0084] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the protection scope of this application.

[0085] With the improvement of people's living standards and the development of intelligent electric vehicle technology, car seats are no longer just pursuing functional diversity, but also focusing on comfort and human-centered design. Adjustments have evolved from simple fore-and-aft adjustment of seat position to multi-component adjustments such as backrest angle, seat height, footrest position, and armrests; and from one or more fixed adjustment angles to designs with multiple adjusters for fine-tuning. In the pursuit of seat comfort, safety, and intelligent design, a seating posture used by astronauts in space capsules has been applied to the car driving experience. This posture provides even pressure distribution on the human body, greatly reducing pressure on muscles and bones and providing ultimate comfort. Zero-gravity seat design is now widely researched and applied, providing occupants with a more comfortable riding experience.

[0086] For example, related technologies disclose a zero-gravity seat safety control method, system, vehicle, and storage medium, such as Figure 1 As shown, by acquiring vehicle gear and speed signals, it determines whether the driver's zero-gravity system is off and adjusts the backrest angle of the zero-gravity seat in the passenger seat to a collision-safe angle. Manual adjustment is prioritized over automatic adjustment, and the seat assembly is driven for adjustment via seat controller signals. This invention only uses a combination of manual and electronic control signals to adjust to a fixed zero-gravity seat tilt angle, lacking consideration for the various uses of zero-gravity seats in different scenarios and for intelligent control.

[0087] For example, a zero-gravity seat motor control method and system are disclosed in related technologies, such as... Figure 2 As shown, determining whether the positions of the various motors in the seat need adjustment requires considering the corresponding motor range. Information commands can come from the touchscreen controller, button controls, or the magnitude and direction of pressure sensors, adjusting the specific motor rotation range. This adjustment of the motor positions, thereby regulating corresponding parts of the seat, reduces manual adjustments to the zero-gravity seat. However, this zero-gravity seat motor control method and system only considers one fixed posture mode in terms of zero-gravity attitude. The added pressure sensors only check whether the magnitude and direction trigger set thresholds, failing to meet the user's pursuit of a personalized, optimal zero-gravity seat experience and high intelligence.

[0088] To address the aforementioned issues, this application targets existing automotive seats, which suffer from limitations in ergonomic design, personalized seat posture, and adjustment functions, thus affecting driving and riding comfort. It proposes mimicking the zero-gravity state of space science to provide superior body support for the seat. Furthermore, considering that current zero-gravity research focuses on seat posture, and each team's understanding of posture differs, a standard seat posture suitable for everyone is lacking.

[0089] This application combines sensor technology, AI big data models, cloud interaction technology, and intelligent control systems to automatically adjust the seat posture based on the user's sitting habits, body characteristics, and vehicle status, thus realizing an intelligent adaptive zero-gravity seat evaluation and control method and system.

[0090] Specifically, this application proposes a vehicle control method, electronic device, computer-readable storage medium, computer program product, and vehicle that can adaptively adjust the seat posture according to the user's sitting habits, body characteristics, and personal preferences, thereby improving seat comfort.

[0091] like Figure 3 As shown, the adaptive zero-gravity seat evaluation and control system in this embodiment may include a sensor integration module, a data preprocessing module, a model algorithm module, a motor control module, and a cloud interaction module.

[0092] The sensor module is used to deploy different types of sensors in multiple areas of the seat to detect the user's vital signs. For example, pressure sensors detect the real-time pressure applied by the user to the seat, with each sensor sending pressure test signals on a point-by-point basis, simultaneously constructing a numerical matrix of body pressure distribution based on the divided areas. Pulse wave sensors monitor the user's heart rate characteristics, and combined with pressure and temperature sensors, they can provide more comprehensive health monitoring, fatigue warnings, and comfort adjustments. In addition, gyroscopes monitor changes in the user's sitting posture, and combined with pressure sensors, they adjust the overall posture.

[0093] In this application, the sensors can collect data regardless of whether the Zero Gravity Mode (ZGM) is activated, providing users with the best comfort experience.

[0094] The data preprocessing module is mainly used to acquire, process, and analyze numerical matrices. It optimizes the acquisition scheme for each sensor's detection signal to ensure data accuracy, performs filtering and noise reduction, and data compensation to reduce bias. Corresponding features are extracted through algorithms, and all influencing variables and numerical matrices are standardized. Then, analysis of variance (ANOVA) and principal component analysis (PCA) are used to analyze the factor effects between numerical matrices, thereby obtaining the contribution of each influencing factor to system variation and extracting principal components to predict seat adjustment patterns. Based on this, this application can also refine characteristic elements such as total pressure, peak pressure, contact area, and average pressure in different areas of the seat. Furthermore, based on the new characteristic variables, contribution weights, and regional characteristic elements obtained through ANOVA and PCA, an adaptive zero-gravity seat large-scale model can be trained.

[0095] The algorithm and evaluation module will receive the processed set of numerical matrices and dynamically adjust the adaptive zero-gravity attitude through training with algorithms and large machine learning models.

[0096] The adaptive zero-gravity seat posture evaluation criteria in this application may include at least the following: Evaluation criterion one: the position of the motor Hall effect corresponding to the zero-gravity posture output by the machine learning model, ensuring that the seat posture greatly reduces the pressure on muscles and bones, and that the body pressure distribution value detected by the sensor at the contact point is less than the threshold and is evenly distributed; Evaluation criterion two: the user's subjective evaluation of the sitting experience in this posture serves as an auxiliary reference, and the comfort evaluation table and heart rate value change trend graph at different positions can be used to further fine-tune the local motors, improve the rationality of the seat posture and provide health monitoring; Evaluation criterion three: the gyroscope and accelerometer detect the user's posture changes, and the algorithm adjusts the overall seat posture based on the sensor feedback value of the contact area at this time, with the body pressure distribution value uniformity error less than 5%, solving the problem of excessive local pressure caused by posture changes; Evaluation criterion four: setting minimum pressure thresholds for vehicle speed and seat pressure detection respectively, ensuring that the zero-gravity seat mode will not be activated during vehicle movement or by young children, and detecting the seat and vehicle status to provide safety warnings when the vehicle is bumpy, and the collision protection measures activated by the seat in the event of a vehicle collision include emergency stop of zero-gravity posture adjustment and rapid return to the original position after injury.

[0097] The motor control module receives control commands from the car's central control screen controller, armrest screen controller, physical buttons, and model algorithm module. It adjusts the rotation position of the corresponding motor by measuring the Hall position of each Hall motor. Among these, the control command signal for manual adjustment has a higher priority than that for automatic adjustment, while the warning unit has the highest priority, in order to ensure the safety of the occupants to the greatest extent possible.

[0098] The cloud-based interactive module enables personalized customization of zero-gravity seating solutions. A large cloud-based model can learn each user's body type, sitting habits, and optimal sitting posture in different scenarios. Through cloud interaction, the model can be downloaded and associated based on user preferences. Similarly, this application is not limited to existing comfort evaluation standards for zero-gravity seats; users can store custom settings and pre-configure updated models as technology rapidly advances.

[0099] Based on this, such as Figure 4 As shown, the vehicle control method in this application may include at least the following steps:

[0100] S10, acquire the first perception data corresponding to the target seat of the vehicle;

[0101] In this embodiment, the target seat can be the seat to be adjusted.

[0102] It should be noted that the seat in this embodiment is designed based on ergonomic principles. The frame can be an adjustable frame structure, using lightweight and high-strength materials such as aluminum alloy. The seat fabric is made of breathable and comfortable materials such as leather, fabric, or synthetic fibers, and the user experience is enhanced with exquisite craftsmanship. The filling material pursues comfort and support by using high-density sponge, memory foam, etc. The multi-layer partition structure design can provide comfort and support according to the needs of different body parts. Through unique design and material combination, the seat hardware conditions are ensured to meet the user's safety and comfort experience.

[0103] The initial perception data can be data collected by sensors installed on the target seat.

[0104] In one embodiment, the first sensing data includes sensing data collected by at least one first sensor disposed on the target seat.

[0105] The first sensor includes at least one of a pressure sensor, a pulse sensor, an accelerometer, and a gyroscope.

[0106] Specifically, for example, in this embodiment, the sensor integration module consists of a pressure sensor, a pulse sensor, an accelerometer, and a gyroscope, which monitor the driver's body posture and pressure distribution in real time, thereby adjusting the posture of the seat support points. In order to study the influence of seat posture on human body pressure distribution, heart rate, and blood pressure, the positional arrangement of the sensors can be analyzed to obtain an accurate user dataset.

[0107] For example, pressure sensors are evenly distributed in the contact area between the human body and the seat, and the pressure sensors in each area collect pressure values ​​to form a pressure value matrix; pulse sensors are installed in the neck area of ​​the seat and in the hidden armrests to monitor the pulse and obtain the user's real-time heart rate; a three-axis accelerometer is installed at the center of the bottom of the seat near the frame to monitor the overall motion state of the seat; and three-axis gyroscopes are installed at the top of the seat back and the bottom of the seat to detect changes in the user's posture.

[0108] Specifically, for example, such as Figure 3 As shown, the data preprocessing module includes a data acquisition unit, a data processing unit, and an analysis unit. Its purpose is to acquire sensor data and process and analyze the numerical matrix. The data acquisition unit employs different strategies when acquiring data from different sensors: when acquiring human body pressure distribution data, the user is kept as close to the seat as possible, and data is collected from three preset seat positions after the pressure stabilizes (described in subsequent embodiments); heart rate monitoring data is acquired from the hand and neck areas using real-time monitoring; the accelerometer and gyroscope respond promptly to changes in data and acquire the data. The collected data undergoes filtering and noise reduction in the data processing unit to remove interference signals and improve data quality. Then, corresponding features are calculated using numerical matrices: for pressure sensor data, total pressure, peak pressure, contact area, and average pressure for each region are calculated; for pulse sensor data, relevant indicators such as heart rate (Beats Per Minute, BPM), heart rate variability (HRV), heart rate trend, and heart rate intensity are extracted; for gyroscope data, local posture tilt angle changes are extracted from angular velocity data to construct overall user posture changes; and for accelerometer data, acceleration magnitude and direction information are extracted from acceleration change data to obtain seat and vehicle motion information. The processed pressure data undergoes both influencing factor analysis and predictive analysis to jointly calibrate zero-gravity seat posture evaluation. The data analysis unit uses analysis of variance and principal component analysis to analyze the factor effects between data matrices, thereby obtaining the contribution of each influencing factor to system variation and extracting principal components through dimensionality reduction. This data analysis method can intuitively demonstrate the impact of influencing factors on the body pressure distribution evaluation results of seat posture and summarize the seat posture adjustment rules. Furthermore, predictive analytics can use the collected data to directly predict the optimal motor position for the zero-gravity seat using an adaptive algorithm-based large model.

[0109] S20, based on the first perception data, determine the target control information corresponding to the target seat through the target model;

[0110] It should be noted that in this embodiment, the target model can be a large AI model. This embodiment does not specifically limit the type or structure of the model. For example, the model can be a machine learning model or a neural network model. The role of the target model is to predict the control information of the seat based on the perception data so that the seat can enter the zero-gravity mode. In this posture, the occupant on the seat has a uniform pressure distribution, which greatly reduces the pressure on muscles and bones and provides ultimate comfort.

[0111] S30, the target seat is adjusted according to the target control information.

[0112] In this embodiment, after determining the target control information, the vehicle can use the target control information to adjust the target seat.

[0113] In this embodiment, the control information may include information for controlling the motor of the seat, such as the Hall position of the Hall motor of the seat, and using the Hall position to adjust the rotation position of the corresponding motor to adjust the posture of the seat.

[0114] Therefore, this application acquires first perception data corresponding to the target seat in the vehicle, and based on this first perception data, determines the target control information corresponding to the target seat through a target model, and then adjusts the target seat according to the target control information. Compared with the prior art that directly uses data collected by sensors to control the seat posture, this application, after acquiring the perception data, determines the target control information through a target model and uses this target control information to adjust the seat, achieving more precise adjustment of the seat, thereby effectively improving seat comfort and enhancing the user experience.

[0115] In one embodiment, S20 above, "determining the target control information corresponding to the target seat based on the first perception data and the target model", may include:

[0116] S201, process the first sensing data to obtain the first target data corresponding to the first sensing data;

[0117] S202, the first target data is processed through the target model to obtain target control information for controlling the target seat.

[0118] In this embodiment, the sensor data collected by the sensor can be processed first, such as feature extraction and data fusion, to obtain the first target data. Then, the first target data can be input into the target model to obtain the target control information of the target seat.

[0119] In one embodiment, when the first sensing data is sensing data collected by a pressure sensor, the first sensing data includes multiple sets of sensing data collected by the pressure sensor multiple times.

[0120] It should be noted that, in this embodiment, as Figure 5 The adaptive zero-gravity seat surface pressure distribution control and posture adjustment method shown ensures that the total body pressure of the occupant is minimized and evenly distributed in zero-gravity mode. For example... Figure 5 The pressure sensors in the sensor integration module shown are triggered by commands, and each sensor sends signals on a point-based basis to acquire pressure information on the surface of the zero-gravity seat.

[0121] This embodiment studies the sensor placement to obtain accurate user data. For example, the seat is divided into six areas based on the contact points between the user and the seat surface: headrest, shoulders, back, waist, seat cushion, and leg rest. The back, waist, and seat cushion areas have the largest proportion of body pressure values, and adjusting the seat posture mainly alleviates the pressure in these areas. The body pressure distribution in the back and waist areas is mainly affected by the backrest angle, with the seat cushion height having a smaller impact; the pressure distribution in the hip and leg areas is mainly affected by the seat cushion height and backrest angle, with the seat position having a smaller impact. Therefore, in this embodiment, the backrest angle and seat cushion height are the main adjustment targets. A larger number of pressure sensors are arranged in an array with a spacing of 3.6 cm on the backrest and seat cushion to reconstruct the user's body pressure distribution information with the most cost-effective sensor arrangement.

[0122] In this embodiment, multiple data collections were performed to ensure accuracy when acquiring the body pressure distribution data on the seat surface, resulting in multiple sets of sensing data.

[0123] In one embodiment, S201 above, "processing the first sensing data to obtain the first target data corresponding to the first sensing data", may include:

[0124] S2011, at least one set of sensing data from multiple sets of sensing data is processed to obtain the first target data corresponding to the first sensing data.

[0125] In this embodiment, the vehicle can obtain at least one set of perception data from multiple sets of perception data for processing to obtain the first target data corresponding to the first perception data.

[0126] In one embodiment, the target control information is control information for causing the target seat to be in the target seat mode after adjustment.

[0127] It is understood that the target seat mode in this embodiment can be divided into target seat mode and non-target seat mode, and the target seat mode can specifically be zero gravity mode, as described in the above embodiment, and will not be repeated here.

[0128] In one embodiment, the multiple sets of sensing data include at least two sets of first sensing data collected before the target seat mode is activated and at least one set of first sensing data collected after the target seat mode is activated.

[0129] In this embodiment, taking three pressure sensor acquisitions as an example, the first acquisition is conducted when the user is sitting normally in a standard upright position on a seat. Real-time pressure sensor data applied by the user to the seat is collected for 10 seconds at 3-minute intervals, and the average value of each sensor during the acquisition time is stored. This process is repeated 5 times and automatically ends the acquisition in this state (n>3, where n is an integer). Optionally, since there may be situations where some areas have pressure information or the number of acquisitions is insufficient, the data from the last two acquisitions is used.

[0130] Second data collection: Triggered when a user sitting in the seat sends a command to enter zero-gravity mode via buttons, armrest screen, or central control screen. At this time, maintain an upright sitting posture according to the instruction manual or voice prompts, and quickly collect sensor data at a sampling frequency of 100Hz (m>10, where m is a positive integer). A standard sitting posture ensures that the user's body is as close to the seat as possible to ensure accurate detection of body pressure distribution values.

[0131] It is understandable that the first two sets of perception data collected are the at least two sets of first perception data collected before the target seat mode is activated in this embodiment.

[0132] Third data collection: The seat enters the preset default zero-gravity posture and quickly collects data in the current state at 100Hz, which serves as at least one set of first-sensory data collected after the target seat mode is activated.

[0133] In one embodiment, S2011 above, "processing at least one set of sensing data from multiple sets of sensing data to obtain the first target data corresponding to the first sensing data", may include:

[0134] At least one set of first perception data is determined from at least two sets of first perception data collected before the target seat mode is activated, and at least one set of second perception data is determined from at least one set of first perception data collected after the target seat mode is activated.

[0135] The first set of sensing data and / or the second set of sensing data are processed to obtain the first target data corresponding to the first sensing data.

[0136] It should be noted that in this embodiment, the vehicle can calculate the variance between the five sets of data acquired in the first instance, and compare the three sets of data with the smallest mean square deviation, which reflects the body pressure distribution under normal posture, with the data acquired in the second instance. The best data is selected to represent the surface body pressure distribution before zero gravity seat adjustment (i.e., the first set of sensing data in this embodiment).

[0137] The third set of data obtained in zero gravity mode (i.e., the second set of sensing data in this embodiment) is sufficient to ensure the accuracy of the data.

[0138] In this embodiment, the processing of pressure sensor data effectively avoids interference caused by random touches and other factors.

[0139] In one embodiment, the first target data includes pressure characteristic information of the area where the pressure sensor is located.

[0140] Specifically, the pressure characteristic information includes at least one of the following: total pressure, peak pressure, pressure area, and average pressure.

[0141] Based on the above description, the sensing data in this embodiment can be processed to obtain the sensing data before and after the zero gravity mode is activated.

[0142] Then, based on the sensing data (which could be the first set of sensing data before zero gravity mode was activated, the second set of sensing data after zero gravity mode was activated, or the fused data from the first and second sets of sensing data), the total pressure in each area of ​​the pressure sensor's location can be calculated. = Peak pressure in each region average pressure and the actual pressure area ( (where i is the number of sensors in each region i), so that the above data can be input into the target model later.

[0143] In addition, such as Figure 5 As shown, this embodiment can also use variance and principal component analysis methods to generate a data matrix (containing the sum of pressures in each of the aforementioned regions). = Peak pressure in each region average pressure and the actual pressure area This involves decomposing the data to explore the effects of influencing factors across different regions. ,in This refers to the effect of a certain factor (the factor could be the seat back angle, footrest angle, seat cushion angle, seat height, etc. This analysis primarily examines the influence of other factors on data such as body pressure in the variance analysis). For observed variables (such as factors to be adjusted). The average offset of all variables is used to explain the influence of each seat adjustment operation on the measured variable, so that the percentage of the total change in the data represented by the sum of squares of each factor can be used to assess the contribution of each variable to the system results, summarize the posture adjustment rules, and output and display the posture adjustment rules to the occupant so that the occupant can manually adjust the seat, etc.

[0144] In one embodiment, the vehicle control method of this application may further include:

[0145] S40, if the target control information meets the preset evaluation criteria, the target seat is adjusted according to the target control information.

[0146] It should be noted that, in this embodiment, as Figure 3 As shown, the model algorithm module (i.e., the target model in this embodiment) may include large model prediction, model evaluation, and feedback adjustment units. First, model training is required. A large amount of volunteer test data is acquired on a zero-gravity seat equipped with a data acquisition system. The input data for model training needs to be standardized, and then a large model is trained based on the zero-gravity evaluation target.

[0147] Specifically, the first step is to select a suitable large-scale model and use a large dataset of volunteer test data as input for training the model. The algorithm then optimizes the training speed, generalization ability, and system stability of the large-scale model. Optionally, determining whether the data is sensor data collected under different standard sitting postures for the same body type or under the same standard sitting posture for different body types helps optimize for deviations between predicted results and actual conditions, improving the model's generalization ability. The model training output consists of motor position and occupant body type data for the corresponding standard zero-gravity posture. Evaluation criteria for the zero-gravity standard posture can include minimum total pressure and uniform distribution of body pressure data, body trunk blood pressure levels, heart rate indicators, and subjective evaluations.

[0148] The trained large model (i.e. the target model in this embodiment) uses the data from the data preprocessing module as input to perform adaptive zero-gravity seat posture prediction, and outputs the Hall values ​​of each motor position of the zero-gravity seat and the user's body shape data.

[0149] In this embodiment, the evaluation unit implements two schemes simultaneously (i.e., the preset evaluation criteria in this embodiment). The first scheme involves error analysis of the predicted zero-gravity seat motor Hall position; if the error exceeds 5%, the result enters the feedback unit. The second scheme involves the subjective evaluation signal sent by the user in the zero-gravity seat posture and whether the real-time sensor data of the seat deviates from the evaluation criteria. If the subjective evaluation is discomfort or the sensor data deviates too much from the evaluation criteria (heart rate value, posture change), the result enters the feedback unit. Upon receiving information from the evaluation unit, the feedback unit performs adaptive zero-gravity seat adjustment feedback. At this time, it can re-acquire pre-processed sensor data and add user body parameters as input for model prediction. Furthermore, detecting abnormal user health-related data, abnormal seat adjustment movements, or sudden vehicle malfunctions can trigger the warning unit, activating zero-gravity seat safety measures such as a buzzer, a health warning upload system, and rapid seat angle return to ensure safety.

[0150] Based on this, the preset evaluation criteria in this embodiment may include a deviation between the target control information and the preset standard control information not exceeding a preset deviation threshold.

[0151] Specifically, for example, the deviation between the Hall position corresponding to the Hall motor in the target control information and the preset standard control information (such as the standard Hall position, which can be obtained during model training) is not greater than a preset deviation threshold.

[0152] In one embodiment, the target model includes models corresponding to at least two occupant sitting postures.

[0153] It should be noted that, in this embodiment, as Figure 5 As shown, the first target data (i.e., the data obtained by processing the sensing data collected by the pressure sensor in the above embodiment) can be subjected to numerical matrix standardization processing first, and then it can be determined whether the pressure distribution is symmetrical and whether the force exerted is by a child or other objects.

[0154] Based on this, the two occupant sitting postures in this embodiment can include at least a standardized sitting posture and a non-standardized sitting posture.

[0155] Based on this, if the occupant body pressure distribution corresponding to the first target data meets the preset distribution conditions, the target model is the first model.

[0156] If the occupant body pressure distribution corresponding to the first target data does not meet the preset distribution conditions, the target model is the second model.

[0157] The preset distribution conditions can include that each region corresponding to the sensor has a value and is approximately symmetrical.

[0158] In this embodiment, if all areas of the body pressure distribution have values ​​and are approximately symmetrical, the standard sitting posture model (i.e., the first model in this embodiment) is used for prediction. If some areas of the body pressure distribution have no pressure values ​​or the distribution is asymmetrical, the non-standard sitting posture model (i.e., the second model in this embodiment) is used for prediction. If the force is applied by a child or other object, the zero gravity mode is not activated.

[0159] In this embodiment, the occupant body pressure distribution can be obtained by analyzing the first target data, which will not be elaborated here.

[0160] In one embodiment, after S30, "adjusting the target seat according to the target control information," the following may be included:

[0161] S50, obtain the evaluation results corresponding to the adjusted target seat;

[0162] S60, Based on the evaluation results, adjust the target seat.

[0163] In this embodiment, the vehicle can obtain the evaluation result corresponding to the adjusted target seat and adjust the target seat based on the evaluation result.

[0164] In one embodiment, the evaluation results include at least one of the following: the occupant's subjective evaluation of the adjusted target seat, the occupant's physiological information, the occupant's posture information, and the occupant's body pressure distribution information on the target seat.

[0165] Understandably, in this embodiment, the vehicle can determine whether the evaluation result meets its corresponding evaluation criteria. For example, if the prediction result deviation is less than 5% and the subjective evaluation is a comfort evaluation, then the evaluation is passed; if the prediction result deviation is more than 5% or the subjective evaluation is uncomfortable, then a feedback signal is sent to the data preprocessing unit to re-collect and process the perception data to obtain new target control information, so as to optimize and adjust the target seat using the new target control information.

[0166] Based on this, if the evaluation result of the adjusted target seat meets the corresponding evaluation criteria, the target control information can be transmitted to the motor control module to control the motor to adjust the seat to a zero-gravity posture. In addition, motor control commands can also be sent via the armrest screen, central control screen, buttons, and warning units (signal priority and validity need to be handled here; for example, the warning unit has the highest priority to ensure user safety). Upon receiving the command signal, the Hall positions of the corresponding multi-adjustment lever and fine-tuning motor are adjusted to achieve more dimensional adjustments. All sensor data are comprehensively processed for collision protection and seat posture adjustment analysis. At this zero-gravity seat posture, the average pressure of the pressure sensors in each area... Even at its minimum, it can be determined by the static seat pressure distribution in each area. This characterizes the uniformity of the region; a smaller value indicates a more uniform distribution. The pressure detected by each sensor, This represents the maximum pressure detected by the sensor.

[0167] In addition, in this embodiment, when the seat malfunctions or the vehicle experiences an emergency, the motor can take safety measures such as emergency stop and quick return to the seat protection position. Users can personalize the model according to their preferences, adjust the model's evaluation indicators for adaptive adjustment, and update and iterate the large model.

[0168] In one embodiment, before step S30, "adjusting the target seat according to the target control information," the following may be included:

[0169] S70, acquires the second perception data corresponding to the target seat in the vehicle;

[0170] S80, the target control information is adjusted based on the second sensing data.

[0171] In this embodiment, the vehicle can also acquire second perception data corresponding to the target seat, and use the second perception data to adjust the target control information to optimize the zero-gravity posture of the seat and further improve user comfort.

[0172] In one embodiment, the second sensing data includes sensing data collected by at least one second sensor.

[0173] Specifically, the second sensor includes at least one of a biomedical sensor, an accelerometer, and a gyroscope.

[0174] It is understandable that when the first sensor is specifically a pressure sensor, the second sensor can be at least one of biomedical sensors, accelerometers, and gyroscopes, in order to optimize the results predicted by the target model using data collected by other sensors. For example, the second sensing data can be combined with the zero-gravity seat posture standard predicted by the above model, that is, the surface pressure distribution and pulse signal characteristics together regulate the seat posture, and the comfort in the zero-gravity mode can be evaluated in a multi-dimensional way through data fusion, thereby adjusting the motor module.

[0175] In one embodiment, the biomedical sensor includes a pulse sensor.

[0176] In one embodiment, the above-described S80 step of "adjusting the target control information based on the second sensing data" may include:

[0177] S801, process the second sensed data to obtain the second target data;

[0178] S802, the target control information is adjusted according to the second target data.

[0179] It is understood that the processing methods for the second sensing data collected by different types of sensors in this embodiment are different, and the corresponding second target data is obtained.

[0180] When adjusting the target control information based on the second target data, the target control information can be fine-tuned using the second target data to obtain the final control information to control the motor of the seat. Refer to the following embodiments, which will not be repeated here.

[0181] In one embodiment, S801 above, "processing the second sensed data to obtain the second target data" may include:

[0182] S8011, when the second sensing data is sensing data collected by a biomedical sensor, extract the signal features of the second sensing data collected by the biomedical sensor.

[0183] S8012, determine second target data of the occupant in the target seat based on the signal characteristics, wherein the second target data includes the occupant's physiological characteristic data.

[0184] It should be noted that, in this embodiment, as Figure 6 The adaptive zero-gravity seat's health assessment and cloud interaction system shown is designed to monitor the user's health and improve the comfort of the adaptive zero-gravity seat. The pulse sensor in the sensor integration module is triggered by a command to acquire photoelectric signals and convert them into digital signals.

[0185] In this embodiment, a pulse sensor can be installed in the neck area of ​​the seat and in the hidden armrest to monitor the pulse and obtain the user's real-time heart rate. The installation in the neck area of ​​the seat back is an adjustable and hidden design, which can be adjusted within a preset range to avoid affecting the user experience. The inner side of the armrest screen near the wrist is an embedded installation design, hidden in the armrest screen to maintain an aesthetic appearance.

[0186] For the driver and front passenger adaptive zero-gravity seats, pulse sensors in the neck area collect data in real time when the user leans against the seat; while the rear adaptive zero-gravity seats with armrest screens can collect data from the wrist and neck areas.

[0187] Considering that a high acquisition frequency may capture more noise, the acquired raw data needs to be filtered and denoised to remove interference signals and improve data quality. In this embodiment, the physiological characteristic data of the passenger, such as BPM, HRV, heart rate trend and heart rate intensity, can be extracted by an algorithm based on the signal characteristics of the pulse sensor (i.e., the signal characteristics of the second sensing data acquired by the pulse sensor in this embodiment).

[0188] Based on this, in this embodiment, physiological characteristic data can be combined with the zero-gravity seat posture standard predicted by the large model. That is, surface pressure distribution and pulse signal characteristics are used together to regulate seat posture. The comfort in zero-gravity mode is evaluated in a multi-dimensional way through data fusion, thereby adjusting the motor module. In addition, the evaluation index corresponding to the optimal position of the zero-gravity seat mode can be updated and iterated through the cloud interaction module, and user personalized settings can be recorded and re-imported into the large model for prediction.

[0189] As can be seen, the adaptive zero-gravity seat standard can be updated in this embodiment: by integrating the pressure distribution on the seat surface and heart rate characteristics, the optimal adaptive zero-gravity seat adjustment is judged based on the human blood pressure level, thereby further improving comfort.

[0190] In addition, the pulse feature data extracted by the algorithm can also be used for seat posture adjustment and health monitoring. In zero gravity mode, it is integrated with other data for adjustment, while in non-zero gravity mode, it can adjust according to heart rate. If the heart rate rises, it will automatically adjust the leaning angle to relax the user. Furthermore, the recorded pulse data analysis helps users understand their own condition and provides safety warnings such as fatigue driving reminders.

[0191] In one embodiment, S801 above, "processing the second sensed data to obtain the second target data" may include:

[0192] S8013, when the second sensing data includes the first sub-sensing data collected by the gyroscope and the second sub-sensing data collected by the accelerometer, extract the first signal feature corresponding to the first sub-sensing data and the second signal feature corresponding to the second sub-sensing data;

[0193] S8014, determine the second target data based on the first signal feature and the second signal feature.

[0194] It should be noted that, in this embodiment, as Figure 7The adaptive zero-gravity seat's overall adaptive adjustment and safety system includes several main modules: data acquisition, data processing, zero-gravity seat pressure unit control system, and result prediction and analysis. It can select high-precision three-axis gyroscopes to be installed at the top of the seat back and the bottom of the seat to detect changes in the user's posture. This allows the system to collect posture change data from the backrest and bottom of the seat while the user is seated. After noise reduction and zero-point drift compensation using algorithms, the data is stored and sent to the data processing unit. The system extracts offset angle, angular velocity, and angular acceleration data (i.e., the first signal feature in this embodiment) from the signal characteristics, and uses changes in the user's local posture tilt angle to construct the user's overall posture change.

[0195] Similarly, a triaxial accelerometer can be installed at the center of the seat bottom, close to the frame, with a consistent coordinate system, to monitor the overall motion state of the seat. The collected acceleration data is filtered and compensated to extract relevant indicators of motion characteristics, such as the magnitude and direction of acceleration and the direction of motion (i.e., the second signal feature in this embodiment).

[0196] Then, based on the first signal feature and the second signal feature, the second target data can be determined.

[0197] In a specific embodiment, in S8014 above, "determining the second target data based on the first signal feature and the second signal feature" may include:

[0198] The first signal feature and the second signal feature are fused to obtain the fused feature;

[0199] Based on the fusion features, the second target data is obtained.

[0200] In this embodiment, the data collected by the accelerometer and the data collected by the gyroscope can be fused to obtain a more comprehensive feature of the user's posture change.

[0201] In one embodiment, the second target data includes the occupant's user posture change characteristics and the vehicle's corresponding motion information.

[0202] Specifically, for example, this embodiment can use motion algorithms based on data fusion and machine learning to identify motion, which helps predict the complete motion information of the seat and the car by taking into account changes in the user's posture offset angle, the magnitude of the angular velocity, and the magnitude and direction of the seat's acceleration.

[0203] In addition, such as Figure 7As shown in this embodiment, the user's sitting posture habits can be analyzed based on the sitting posture, and the head offset angle of the driver's seat and side-lying posture can be monitored to determine whether the user is fatigued. Furthermore, safety assistance and measures for emergencies can be set according to the seat's movement, such as bumpy road warnings, emergency stops during seat adjustments, and quick return to the optimal protection angle position.

[0204] In addition, in non-zero gravity mode, the seat can be automatically adjusted according to changes in user posture and vehicle motion information to improve comfort and safety; in zero gravity seat mode, more data information can be provided to the zero gravity seat pressure unit control system to predict the seat posture, and global posture adjustment can be performed based on the monitored seat motion state.

[0205] In one embodiment, the vehicle control method of this application may further include:

[0206] Obtain the configuration parameters associated with the target model;

[0207] The configuration parameters are sent to the cloud server so that the cloud server can configure the target model according to the configuration parameters.

[0208] Specifically, the configuration parameters include at least one of the evaluation criteria corresponding to the target model and the model parameters of the target model.

[0209] It is understandable that, such as Figure 6 As shown and Figure 7 As shown, the cloud interactive control system in this embodiment allows users to set personalized parameters according to their preferences and pre-configure new zero-gravity seat prediction models, giving full play to the interactive capabilities of the network cloud. This not only increases the flexibility of the adaptive zero-gravity seat evaluation and control system, but also adapts to the updates and iterations of technological development.

[0210] Furthermore, to adapt to the rapid development of AI large models, a large model pre-configuration function has been added. The evaluation criteria for different zero-gravity modes can be updated and the latest large model can be pre-configured. For example, pulse information and body pressure distribution, human blood pressure level and body pressure distribution can be used to optimize the user posture in zero-gravity mode.

[0211] In one embodiment, when the zero-gravity mode of the target seat is activated, the steps of determining the target control information corresponding to the target seat based on the first sensing data and the target model, and adjusting the target seat according to the target control information are performed.

[0212] When the target seat is not in the zero-gravity mode, the target seat is adjusted based on the occupant's posture information and the vehicle's motion information.

[0213] In this embodiment, if the zero-gravity mode of the target seat is detected to be activated, the target seat can be adjusted based on the sensing data and the target model.

[0214] If the zero-gravity mode of the target seat is not detected to be activated, the seat can be adjusted directly using the perception data, without relying on the target model for prediction.

[0215] In one embodiment, when the vehicle is in an unsafe scenario corresponding to zero gravity mode, the zero gravity mode is controlled to be turned off.

[0216] Specifically, the unsafe scenarios include: the vehicle's speed is greater than a preset speed threshold; and / or, the occupant in the target seat meets the corresponding health indicators.

[0217] In this embodiment, the vehicle speed and seat pressure detection minimum pressure threshold can be preset to ensure that the zero-gravity seat mode is not activated while the vehicle is in motion or by the child.

[0218] Among them, the corresponding health indicators that the occupant meets can be the occupant's weight. Considering that young children are relatively light, if the pressure applied to the seat by the occupant is less than the set minimum pressure threshold, it can be determined that the occupant does not meet the health indicators, and the zero gravity mode of the seat will not be activated.

[0219] In addition, this application can also detect the operating status of the seat and the vehicle to provide safety warnings when the vehicle is bumpy, and activate collision protection measures in the event of a collision to enable posture adjustment emergency stop and rapid return to the original position in case of damage.

[0220] In summary, the solution adopted in this application for addressing the issue of car seat comfort is a zero-gravity seat designed based on ergonomic principles. Its seat frame, fabric, manufacturing process, and filling materials pursue optimal performance. Unlike traditional car seats, it can provide comfort and support for the user's body contact areas, satisfying their aesthetic, safety, and comfort experience.

[0221] The adaptive zero-gravity seat evaluation and control system proposed in this application is an intelligent control system that combines sensor technology, machine learning algorithms, AI large-scale models, and cloud interaction technology. Unlike traditional seats with manual adjustment or a single fixed posture mode, this system can adaptively adjust the seat posture according to different user body types based on sensor and prediction large-scale models, and can also recognize dynamic postures within the same body type for compensation adjustments. Furthermore, the combination of multiple zero-gravity mode standard evaluations makes the adaptive zero-gravity seat prediction results more generalizable, providing a more targeted and comfortable and safe experience for different users in different scenarios.

[0222] The sensor interaction evaluation and health monitoring control system proposed in this application adaptively studies and adjusts different sensors in terms of sensor placement, data acquisition, and data processing methods to ensure the accuracy of preprocessed data and enhance the robustness of the adaptive zero-gravity seat control system. The sensor data fusion and interaction evaluation system effectively assesses the posture of the zero-gravity seat mode and can dynamically adjust the seat posture based on changes in user posture, heart rate characteristics, and vehicle status. Compared to zero-gravity seats based solely on pressure sensors, this application can achieve health monitoring for users with different characteristics, safety warnings for different scenarios, and adaptive zero-gravity seat adjustment.

[0223] The cloud-based interactive control system proposed in this application allows users to personalize parameter settings according to their preferences and pre-configure new zero-gravity seat prediction models, fully leveraging the interactive capabilities of the cloud. This not only increases the flexibility of the adaptive zero-gravity seat evaluation and control system but also adapts to the continuous updates and iterations of technological development.

[0224] The safety warning module proposed in this application monitors safety across the entire adaptive zero-gravity seat assessment and control system, setting pressure thresholds to prevent accidental activation or initiation of the zero-gravity seat mode by young children. Unlike traditional seats that rely solely on seatbelt protection, this module activates safety warnings and measures based on sensor-detected health abnormalities, seat malfunctions, and sudden vehicle conditions, resulting in enhanced safety.

[0225] Accordingly, embodiments of this application also provide a vehicle control device, which may include:

[0226] The acquisition module is used to acquire the first perception data corresponding to the target seat in the vehicle;

[0227] The determination module is used to determine the target control information corresponding to the target seat based on the first perception data and through the target model;

[0228] The first adjustment module is used to adjust the target seat according to the target control information.

[0229] Optionally, the determining module is also used for:

[0230] The first sensed data is processed to obtain the first target data corresponding to the first sensed data;

[0231] The target data is processed by the target model to obtain target control information for controlling the target seat.

[0232] Optionally, the first sensing data includes sensing data collected by at least one first sensor disposed on the target seat.

[0233] Optionally, the first sensor includes at least one of a pressure sensor, a pulse sensor, an accelerometer, and a gyroscope.

[0234] Optionally, when the first sensing data is sensing data collected by a pressure sensor, the first sensing data includes multiple sets of sensing data collected by the pressure sensor multiple times.

[0235] Optionally, the determining module is also used for:

[0236] At least one set of sensing data from multiple sets of sensing data is processed to obtain the first target data corresponding to the first sensing data.

[0237] Optionally, the target control information is control information used to ensure that the target seat is in the target seat mode after adjustment.

[0238] Optionally, the multiple sets of sensing data include at least two sets of first sensing data collected before the target seat mode is activated and at least one set of first sensing data collected after the target seat mode is activated.

[0239] Optionally, the determining module is also used for:

[0240] At least one set of first perception data is determined from at least two sets of first perception data collected before the target seat mode is activated, and at least one set of second perception data is determined from at least one set of first perception data collected after the target seat mode is activated.

[0241] The first set of sensing data and / or the second set of sensing data are processed to obtain the first target data corresponding to the first sensing data.

[0242] Optionally, the first target data includes pressure characteristic information of the area where the pressure sensor is located.

[0243] Optionally, the pressure characteristic information includes at least one of the following: total pressure, peak pressure, pressure area, and average pressure.

[0244] Optionally, the vehicle control device in this application further includes:

[0245] The second adjustment module is used to adjust the target seat according to the target control information if the target control information meets the preset evaluation criteria. If the target control information does not meet the preset evaluation criteria, the target control information corresponding to the target seat is re-determined through the target model.

[0246] Optionally, the preset evaluation criteria include a deviation between the target control information and the preset standard control information that is not greater than a preset deviation threshold.

[0247] Optionally, the target model includes models corresponding to at least two occupant sitting postures.

[0248] Optionally, the target model includes a first model corresponding to a standard occupant sitting posture and a second model corresponding to a non-standard occupant sitting posture.

[0249] Optionally, if the occupant body pressure distribution corresponding to the first target data meets the preset distribution conditions, the target model is the first model.

[0250] Optionally, if the occupant body pressure distribution corresponding to the first target data does not meet the preset distribution conditions, the target model is the second model.

[0251] Optionally, the vehicle control device in this application further includes:

[0252] The evaluation result acquisition module is used to acquire the evaluation results corresponding to the adjusted target seat;

[0253] The third adjustment module is used to adjust the target seat based on the evaluation results.

[0254] Optionally, the evaluation results include at least one of the following: the occupant's subjective evaluation of the adjusted target seat, the occupant's physiological information, the occupant's posture information, and the occupant's body pressure distribution information on the target seat.

[0255] Optionally, the vehicle control device in this application further includes:

[0256] The fourth adjustment module is used to acquire second perception data corresponding to the target seat in the vehicle; and to adjust the target control information based on the second perception data.

[0257] Optionally, the second sensing data includes: sensing data collected by at least one second sensor.

[0258] Optionally, the second sensor includes at least one of a biomedical sensor, an accelerometer, and a gyroscope.

[0259] Optionally, the fourth adjustment module is also used for:

[0260] The second sensed data is processed to obtain the second target data;

[0261] The target control information is adjusted based on the second target data.

[0262] Optionally, the fourth adjustment module is also used for:

[0263] When the second sensing data is sensing data collected by a biomedical sensor, the signal features of the second sensing data collected by the biomedical sensor are extracted.

[0264] Second target data of the occupant in the target seat is determined based on the signal characteristics, wherein the second target data includes the occupant's physiological characteristic data.

[0265] Optionally, the biomedical sensor includes a pulse sensor.

[0266] Optionally, the fourth adjustment module is also used for:

[0267] When the second sensing data includes the first sub-sensing data collected by the gyroscope and the second sub-sensing data collected by the accelerometer, the first signal feature corresponding to the first sub-sensing data and the second signal feature corresponding to the second sub-sensing data are extracted.

[0268] The second target data is determined based on the first signal feature and the second signal feature.

[0269] Optionally, the fourth adjustment module is also used for:

[0270] The first signal feature and the second signal feature are fused to obtain the fused feature;

[0271] Based on the fusion features, the second target data is obtained.

[0272] Optionally, the second target data includes the occupant's user posture change characteristics and the corresponding motion information of the vehicle.

[0273] Optionally, the vehicle control device in this application further includes:

[0274] The configuration parameter acquisition module is used to obtain the configuration parameters associated with the target model;

[0275] The sending module is used to send the configuration parameters to the cloud server so that the cloud server can configure the target model according to the configuration parameters.

[0276] Optionally, the configuration parameters include at least one of the evaluation criteria corresponding to the target model and the model parameters of the target model.

[0277] Optionally, the vehicle control device in this application further includes:

[0278] The execution module is configured to, when the zero-gravity mode of the target seat is activated, perform the following steps: determining the target control information corresponding to the target seat based on the first sensing data and the target model; and adjusting the target seat according to the target control information.

[0279] Optionally, the vehicle control device in this application further includes:

[0280] The fifth adjustment module is further configured to: adjust the target seat based on the occupant's posture information and the vehicle's motion information when the target seat is not in the zero-gravity mode.

[0281] Optionally, the vehicle control device in this application further includes:

[0282] The shutdown module is used to control the zero-gravity mode to be turned off when the vehicle is in an unsafe scenario corresponding to the zero-gravity mode.

[0283] Optionally, the unsafe scenario includes: the vehicle's speed is greater than a preset speed threshold; and / or, the occupant in the target seat meets the corresponding health indicators.

[0284] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0285] Accordingly, embodiments of this application also provide an electronic device, such as... Figure 8 As shown, Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 1100 includes a processor 1101 with one or more processing cores, a memory 1102 with one or more computer-readable storage media, and a computer program stored on the memory 1102 and executable on the processor. The processor 1101 and the memory 1102 are electrically connected. Those skilled in the art will understand that the vehicle structure shown in the figure does not constitute a limitation on the vehicle and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0286] The processor 1101 is the control center of the electronic device 1100. It connects various parts of the electronic device 1100 via various interfaces and lines. By running or loading software programs and / or units stored in the memory 1102, and by calling data stored in the memory 1102, it executes various functions and processes data of the electronic device 1100, thereby providing overall monitoring of the electronic device 1100. The processor 1101 can be a processor (Central Processing Unit, CPU), a graphics processing unit (GPU), a network processor (NP), etc., and can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0287] In this embodiment, the processor 1101 in the electronic device 1100 loads the instructions corresponding to the processes of one or more applications into the memory 1102 according to the following steps, and the processor 1101 runs the applications stored in the memory 1102 to realize various functions, such as:

[0288] Acquire the first perception data corresponding to the target seat in the vehicle;

[0289] Based on the first perception data, the target control information corresponding to the target seat is determined through the target model;

[0290] The target seat is adjusted according to the target control information.

[0291] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0292] Optional, such as Figure 8 As shown, the electronic device 1100 also includes: a touch display screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106, and a power supply 1107. The processor 1101 is electrically connected to the touch display screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106, and the power supply 1107. Those skilled in the art will understand that... Figure 8 The vehicle structure shown does not constitute a limitation on the vehicle and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0293] The touch display screen 1103 can be used to display a graphical user interface (GUI) and receive operation commands generated by the user interacting with the GUI. The touch display screen 1103 may include a display panel and a touch panel. The display panel can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the vehicle. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. Optionally, the display panel can be configured using a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar technologies. The touch panel can be used to collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel), generate corresponding operation commands, and execute the corresponding program according to the operation commands. Optionally, the touch panel may include two parts: a touch display system and a touch controller. The touch display system detects the user's touch location and the signal generated by the touch operation, transmitting the signal to the touch controller. The touch controller receives touch information from the touch display system, converts it into touch point coordinates, and sends it to the processor 1101. It can also receive and execute commands from the processor 1101. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it transmits the information to the processor 1101 to determine the type of touch event. Subsequently, the processor 1101 provides corresponding visual output on the display panel based on the type of touch event. In this embodiment, the touch panel and the display panel can be integrated into the touch display screen 1103 to achieve input and output functions. However, in some embodiments, the touch panel and the touch display screen 1103 can be implemented as two independent components to achieve input and output functions. That is, the touch display screen 1103 can also be used as part of the input unit 1106 to achieve input functions.

[0294] The radio frequency circuit 1104 can be used to transmit and receive radio frequency signals to establish wireless communication with network devices or other vehicles, and to transmit and receive signals with network devices or other vehicles.

[0295] Audio circuit 1105 can be used to provide an audio interface between the user and the vehicle via a speaker and a microphone. Audio circuit 1105 can convert received audio data into electrical signals and transmit them to the speaker, where the speaker converts them into sound signals for output. Conversely, the microphone converts collected sound signals into electrical signals, which are then received by audio circuit 1105, converted back into audio data, and processed by processor 1101 before being transmitted via radio frequency circuit 1104 to, for example, another vehicle, or output to memory 1102 for further processing. Audio circuit 1105 may also include an earphone jack to provide communication between external headphones and the vehicle.

[0296] The input unit 1106 can be used to receive input numbers, characters, or user characteristic information (such as fingerprints, iris, facial information, etc.), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.

[0297] Power supply 1107 is used to supply power to various components of electronic device 1100. Optionally, power supply 1107 can be logically connected to processor 1101 through a power management device, thereby enabling functions such as charging, discharging, and power consumption management through the power management device. Power supply 1107 may also include one or more DC or AC power supplies, recharge power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0298] although Figure 8 As not shown in the diagram, the electronic device 1100 may also include a camera, sensor, wireless fidelity module, Bluetooth module, etc., which will not be described in detail here.

[0299] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0300] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0301] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of computer programs. These computer programs can be loaded by a processor to execute any of the vehicle control methods provided in this application. The computer program can execute the steps of the following vehicle control method:

[0302] Acquire the first perception data corresponding to the target seat in the vehicle;

[0303] Based on the first perception data, the target control information corresponding to the target seat is determined through the target model;

[0304] The target seat is adjusted according to the target control information.

[0305] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0306] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0307] Since the computer program stored in the computer-readable storage medium can execute any of the vehicle control methods provided in the embodiments of this application, the beneficial effects that any of the vehicle control methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0308] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0309] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0310] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0311] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0312] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0313] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0314] Computer-readable media include both permanent and non-permanent, removable and non-removable media, which can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient media, such as modulated communication signals and carrier waves.

[0315] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0316] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0317] The embodiments, implementation methods, and related technical features of this application can be combined and substituted for each other without conflict.

[0318] The above are merely preferred embodiments of this application and are not intended to limit this application in any way. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of this application without departing from the scope of the technical solution of this application shall still fall within the scope of the technical solution of this application.

Claims

1. A vehicle control method, characterized in that, The method includes: Acquire the first perception data corresponding to the target seat in the vehicle; Based on the first perception data, the target control information corresponding to the target seat is determined through the target model; The target seat is adjusted according to the target control information; The target model includes models corresponding to at least two occupant sitting postures; The target model includes a first model corresponding to the standard occupant sitting posture and a second model corresponding to the non-standard occupant sitting posture. Before adjusting the target seat according to the target control information, the method further includes: Acquire the second perception data corresponding to the target seat in the vehicle; The target control information is adjusted based on the second sensing data; The second sensing data includes: sensing data collected by at least one second sensor; The second sensor includes at least one of a biomedical sensor, an accelerometer, and a gyroscope.

2. The vehicle control method according to claim 1, characterized in that, The step of determining the target control information corresponding to the target seat based on the perceived data and through the target model includes: The first sensed data is processed to obtain the first target data corresponding to the first sensed data; The target data is processed by the target model to obtain target control information for controlling the target seat.

3. The vehicle control method according to claim 2, characterized in that, The first perception data includes perception data collected by at least one first sensor disposed on the target seat.

4. The vehicle control method according to claim 3, characterized in that, The first sensor includes at least one of a pressure sensor, a pulse sensor, an accelerometer, and a gyroscope.

5. The vehicle control method according to claim 4, characterized in that, When the first sensing data is sensing data collected by a pressure sensor, the first sensing data includes multiple sets of sensing data collected by the pressure sensor multiple times.

6. The vehicle control method according to claim 5, characterized in that, The step of processing the first sensed data to obtain the first target data corresponding to the first sensed data includes: At least one set of sensing data from multiple sets of sensing data is processed to obtain the first target data corresponding to the first sensing data.

7. The vehicle control method according to claim 6, characterized in that, The target control information is control information used to ensure that the target seat is in the target seat mode after adjustment.

8. The vehicle control method according to claim 7, characterized in that, The multiple sets of perception data include at least two sets of first perception data collected before the target seat mode is activated and at least one set of first perception data collected after the target seat mode is activated.

9. The vehicle control method according to claim 8, characterized in that, The step of processing at least one set of sensing data from multiple sets of sensing data to obtain the first target data corresponding to the first sensing data includes: At least one set of first perception data is determined from at least two sets of first perception data collected before the target seat mode is activated, and at least one set of second perception data is determined from at least one set of first perception data collected after the target seat mode is activated. The first set of sensing data and / or the second set of sensing data are processed to obtain the first target data corresponding to the first sensing data.

10. The vehicle control method according to claim 6, characterized in that, The first target data includes pressure characteristic information of the area where the pressure sensor is located.

11. The vehicle control method according to claim 10, characterized in that, The pressure characteristic information includes at least one of the following: total pressure, peak pressure, pressure area, and average pressure.

12. The vehicle control method according to claim 2, characterized in that, The method further includes: If the target control information meets the preset evaluation criteria, the target seat is adjusted according to the target control information.

13. The vehicle control method according to claim 12, characterized in that, The method further includes: If the target control information does not meet the preset evaluation criteria, the target control information corresponding to the target seat is re-determined through the target model.

14. The vehicle control method according to claim 13, characterized in that, The preset evaluation criteria include the requirement that the deviation between the target control information and the preset standard control information is no greater than a preset deviation threshold.

15. The vehicle control method according to claim 2, characterized in that, The method further includes: If the occupant body pressure distribution corresponding to the first target data meets the preset distribution conditions, the target model is the first model.

16. The vehicle control method according to claim 2, characterized in that, If the occupant body pressure distribution corresponding to the first target data does not meet the preset distribution conditions, the target model is the second model.

17. The vehicle control method according to claim 1, characterized in that, After adjusting the target seat according to the target control information, the process further includes: Obtain the evaluation results corresponding to the adjusted target seat; Based on the evaluation results, the target seat is adjusted.

18. The vehicle control method according to claim 17, characterized in that, The evaluation results include at least one of the following: the occupant's subjective evaluation of the adjusted target seat, the occupant's physiological information, the occupant's posture information, and the occupant's body pressure distribution information on the target seat.

19. The vehicle control method according to claim 1, characterized in that, Adjusting the target control information based on the second sensing data includes: The second sensed data is processed to obtain the second target data; The target control information is adjusted based on the second target data.

20. The vehicle control method according to claim 19, characterized in that, The process of processing the second sensed data to obtain the second target data includes: When the second sensing data is sensing data collected by a biomedical sensor, the signal features of the second sensing data collected by the biomedical sensor are extracted. Second target data of the occupant in the target seat is determined based on the signal characteristics, wherein the second target data includes the occupant's physiological characteristic data.

21. The vehicle control method according to claim 20, characterized in that, The biomedical sensor includes a pulse sensor.

22. The vehicle control method according to claim 1, characterized in that, The process of processing the second sensed data to obtain the second target data includes: When the second sensing data includes the first sub-sensing data collected by the gyroscope and the second sub-sensing data collected by the accelerometer, the first signal feature corresponding to the first sub-sensing data and the second signal feature corresponding to the second sub-sensing data are extracted. The second target data is determined based on the first signal feature and the second signal feature.

23. The vehicle control method according to claim 22, characterized in that, The step of determining the second target data based on the first signal feature and the second signal feature includes: The first signal feature and the second signal feature are fused to obtain the fused feature; Based on the fusion features, the second target data is obtained.

24. The vehicle control method according to claim 23, characterized in that, The second target data includes the occupant's user posture change characteristics and the corresponding motion information of the vehicle.

25. The vehicle control method according to claim 1, characterized in that, The method further includes: Obtain the configuration parameters associated with the target model; The configuration parameters are sent to the cloud server so that the cloud server can configure the target model according to the configuration parameters.

26. The vehicle control method according to claim 25, characterized in that, The configuration parameters include at least one of the evaluation criteria corresponding to the target model and the model parameters of the target model.

27. The vehicle control method according to claim 1, characterized in that, The method further includes: When the zero-gravity mode of the target seat is activated, the following steps are performed: determining the target control information corresponding to the target seat based on the first perception data and the target model; and adjusting the target seat according to the target control information.

28. The vehicle control method according to claim 27, characterized in that, The method further includes: When the target seat is not in the zero-gravity mode, the target seat is adjusted based on the occupant's posture information and the vehicle's motion information.

29. The vehicle control method according to claim 27, characterized in that, The method further includes: When the vehicle is in an unsafe scenario corresponding to zero gravity mode, the zero gravity mode is controlled to be turned off.

30. The vehicle control method according to claim 29, characterized in that, The unsafe scenarios include: the vehicle's speed is greater than a preset speed threshold; and / or the occupant in the target seat meets the corresponding health indicators.

31. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the method of any one of claims 1 to 30.

32. A computer-readable storage medium, characterized in that, It includes a computer program that, when run on an electronic device, causes the electronic device to perform the method of any one of claims 1 to 30.

33. A computer program product, characterized in that, The method includes a computer program stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, causing the electronic device to perform the method of any one of claims 1 to 30.

34. A vehicle, characterized in that, The vehicle is equipped with one of the electronic devices of claim 31, the computer-readable storage medium of claim 32, and the computer program product of claim 33.

Images