Cockpit attitude dynamic adjustment method, device and equipment and storage medium

Abstract

The invention discloses a cockpit attitude dynamic adjustment method, device and equipment and a storage medium. The method comprises the steps of determining a height parameter and a weight parameter of a target driver; acquiring historical attitude parameters in the previous attitude adjustment period; and according to the height parameter, the weight parameter and the historical attitude parameter of the target driver, generating a model based on a linkage adjustment strategy obtained by pre-training, generating a current attitude adjustment amount in a current attitude adjustment period, and based on the current attitude adjustment amount, controlling a corresponding cockpit adjustment unit in a vehicle to which the target driver belongs to perform attitude adjustment. According to the technical scheme, dynamic adjustment of the postures of the seat, the backrest and the steering wheel in the vehicle driving process is achieved, the individual requirements of drivers with different physical characteristics are met, and the comfort of the drivers in the driving process is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automotive intelligent cockpits, and particularly to a method, device, equipment and storage medium for dynamically adjusting the posture of a cockpit. Background Art

[0002] With the continuous improvement of the intelligence level of automobiles, driver comfort and fatigue alleviation have become important directions in modern vehicle design. During long-term driving, drivers are prone to muscle fatigue and decreased attention due to maintaining a fixed sitting posture. Ergonomic research shows that reasonable adjustment of seat position, backrest angle and steering wheel position is the key to achieving comfortable driving and fatigue alleviation.

[0003] Traditional seat and steering wheel adjustment methods are mostly manual or preset modes, which are difficult to dynamically optimize the driving posture during vehicle driving, cannot meet the personalized needs of drivers with different body type characteristics, and affect the comfort of the driving process. Summary of the Invention

[0004] The present invention provides a method, device, equipment and storage medium for dynamically adjusting the posture of a cockpit, so as to realize the dynamic adjustment of the postures of the seat, backrest and steering wheel during vehicle driving, meet the personalized needs of drivers with different body type characteristics, and improve the comfort of drivers during the driving process.

[0005] According to one aspect of the present invention, there is provided a method for dynamically adjusting the posture of a cockpit, the method comprising:

[0006] Determine the height parameter and weight parameter of the target driver;

[0007] Obtain the historical posture parameters in the previous posture adjustment cycle;

[0008] According to the height parameter, weight parameter and historical posture parameters of the target driver, based on a linkage adjustment strategy generation model obtained by pre-training, generate a current posture adjustment amount in the current posture adjustment cycle, and based on the current posture adjustment amount, control the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs to perform posture adjustment.

[0009] According to another aspect of the present invention, there is provided a device for dynamically adjusting the posture of a cockpit, the device comprising:

[0010] A physical sign parameter determination module, configured to determine the height parameter and weight parameter of the target driver;

[0011] A historical posture acquisition module, configured to obtain the historical posture parameters in the previous posture adjustment cycle;

[0012] The posture adjustment module is used to generate a current posture adjustment amount in the current posture adjustment period based on a linkage adjustment strategy generation model obtained by pre-training according to the height parameter, weight parameter, and historical posture parameter of the target driver, and based on the current posture adjustment amount, control the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs to perform posture adjustment.

[0013] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the cockpit posture dynamic adjustment method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for implementing the cockpit posture dynamic adjustment method according to any embodiment of the present invention when executed by a processor.

[0018] The technical solution of the embodiment of the present invention determines the height parameter and weight parameter of the target driver, obtains the historical posture parameter in the previous posture adjustment period, generates a current posture adjustment amount in the current posture adjustment period based on the height parameter, weight parameter, and historical posture parameter of the target driver, and based on the current posture adjustment amount, controls the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs to perform posture adjustment. The above technical solution improves the prediction accuracy of the posture adjustment parameter by performing real-time prediction of the posture adjustment parameter based on the linkage adjustment strategy generation model and the physical signs parameters of the driver, realizes the dynamic adjustment of the seat, backrest, and steering wheel postures during the vehicle driving process, meets the personalized needs of drivers with different body type characteristics, and improves the comfort of the driver during the driving process.

[0019] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0021] Figure 1 is a flowchart of a method for dynamically adjusting the cockpit attitude according to Embodiment 1 of the present invention;

[0022] Figure 2A is a flowchart of a method for dynamically adjusting the cockpit attitude according to Embodiment 2 of the present invention;

[0023] Figure 2B is a schematic structural diagram of a system for dynamically adjusting the cockpit attitude according to Embodiment 2 of the present invention;

[0024] Figure 3 is a schematic structural diagram of a device for dynamically adjusting the cockpit attitude according to Embodiment 3 of the present invention;

[0025] Figure 4 is a schematic structural diagram of an electronic device for implementing the method for dynamically adjusting the cockpit attitude in the embodiments of the present invention. Detailed Embodiments

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily need to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0028] Embodiment 1

[0029] Figure 1 The figure is a flowchart of a method for dynamically adjusting the attitude of a cockpit provided in the first embodiment of the present invention. This embodiment is applicable to the situation of real-time and dynamic adjustment of the driver's steering wheel, seat, and backrest during vehicle driving. This method can be executed by a cockpit attitude dynamic adjustment device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. As Figure 1 shown, the method includes:

[0030] S110. Determine the height parameter and weight parameter of the target driver.

[0031] S120. Obtain the historical attitude parameters in the previous attitude adjustment cycle.

[0032] S130. Based on the height parameter, weight parameter, and historical attitude parameters of the target driver, generate a current attitude adjustment amount in the current attitude adjustment cycle based on a pre-trained linkage adjustment strategy generation model, and control the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs to perform attitude adjustment based on the current attitude adjustment amount.

[0033] It should be noted that the attitude adjustment in this embodiment is specifically performed in real time or at regular intervals during vehicle driving. Or, attitude adjustment is performed based on a set adjustment frequency or adjustment speed. Taking regular adjustment as an example, assuming that the adjustment interval time period is 10 minutes, and the driver starts driving at 2025 / 04 / 20 / 09:00, the first dynamic adjustment time is 2025 / 04 / 20 / 09:10, and the second dynamic adjustment time is 2025 / 04 / 20 / 09:20. If the current attitude adjustment cycle is 2025 / 04 / 20 / 09:30, then the previous attitude adjustment cycle is 2025 / 04 / 20 / 09:20.

[0034] Among them, the height parameter and weight parameter of the target driver can be automatically determined after the driver is monitored to get on the vehicle. Or, the height parameter, weight parameter, and facial image information of different drivers are pre-stored in the database. When the target driver is monitored to get on the vehicle, facial image acquisition is performed on the target driver, and the acquired image information is compared with the facial image information stored in the database for similarity. If there is facial image information with a similarity reaching the set threshold, the height parameter and weight parameter corresponding to the facial image information are used as the height parameter and weight parameter of the target driver. If there is no facial image information with a similarity reaching the set threshold, the height parameter and weight parameter of the target driver are detected online. Among them, the facial image information of the target driver can be acquired by an image acquisition device deployed directly in front of the vehicle driver's seat.

[0035] It should be noted that before the vehicle starts moving, when the boarding behavior of the target driver is detected, the initial posture parameters can be automatically determined for the target driver, and based on the initial posture parameters, the initial posture adjustment before driving can be performed for the target driver, including the adjustment of the seat, backrest, and steering wheel. Currently, the existing technical solutions usually require the driver to manually adjust the seat, backrest, and steering wheel to a comfortable position after getting in the vehicle, with a low degree of automation.

[0036] In an optional embodiment, before generating the current posture adjustment amount in the current posture adjustment cycle based on the linkage adjustment strategy generation model pre-trained according to the height parameter, weight parameter, and historical posture parameter of the target driver, it further includes: when the boarding behavior of the target driver is monitored, obtaining the seat cushion pressure value and the backrest pressure value of the target vehicle; determining the height parameter and weight parameter of the driver according to the seat cushion pressure value and the backrest pressure value; determining the initial posture parameter according to the height parameter and weight parameter; and controlling the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs to perform posture adjustment based on the initial posture parameter.

[0037] Among them, the initial posture parameter includes the seat setting parameter and the steering wheel setting parameter. Correspondingly, the cockpit adjustment unit includes a seat adjustment unit and a steering wheel adjustment unit. Among them, the seat setting parameter and the backrest setting parameter are used to perform posture adjustment on the seat adjustment unit; the steering wheel setting parameter is used to perform posture adjustment on the steering wheel adjustment unit.

[0038] Among them, the seat cushion pressure value can be obtained by collecting pressure through a pressure sensor array deployed at the seat cushion position of the target vehicle. The numerical expression form of the seat cushion pressure value can be a pressure value matrix, and different rows and different columns in the matrix are used to represent the pressure values at the corresponding array points. The backrest pressure value can be obtained by collecting pressure through a pressure sensor array deployed at the backrest position of the target vehicle. The numerical expression form of the backrest pressure value is also a pressure value matrix, and different rows and different columns in the matrix are used to represent the pressure values at the corresponding array points.

[0039] According to the seat cushion pressure value and the backrest pressure value, the height parameter and weight parameter of the driver can be determined. In an optional embodiment, determining the height parameter and weight parameter of the driver according to the seat cushion pressure value and the backrest pressure value includes: determining the weight parameter of the target driver according to the seat cushion pressure value and the backrest pressure value; and determining the height parameter of the target driver according to the seat cushion pressure value, the backrest pressure value, and the weight parameter.

[0040] Exemplarily, a weight prediction model for weight determination can be pre-trained in advance, and based on the pre-trained weight prediction model, weight prediction is performed based on the seat cushion pressure value and the backrest pressure value to obtain the predicted weight.

[0041] Specifically, the model training method of the weight prediction model is as follows: A pressure sensor matrix is used to detect the backrest pressure of the tested person with different weights to obtain the backrest pressure value, and the seat cushion pressure value is detected. The backrest pressure value and the seat cushion pressure value of the tested person are used as training sample data, and the standard weight of the corresponding tester is used as the label value of the training sample of the tester, that is, the standard weight is used as the label value of the backrest pressure value and the seat cushion pressure value, and the training sample data with label values is obtained. The training sample data is input into a preset initial model to obtain the predicted weight output by the model; according to the standard weight and the predicted weight, the loss value is determined, and the initial model is trained according to the loss value until the loss value tends to be stable or the loss value reaches the set threshold or the number of iterations reaches the set threshold, and the training ends to obtain the weight prediction model. Among them, the initial model can be selected as a random forest (Random Forest) or a neural network model, such as a CNN (Convolutional Neural Network, convolutional neural network), etc.

[0042] Optionally, according to the seat cushion pressure value, the backrest pressure value and the weight parameter, the height parameter of the target driver is determined, including: according to the seat cushion pressure value, the center of gravity of the seat cushion pressure distribution and the variance of the seat cushion pressure distribution are determined; and, according to the backrest pressure value, the center of gravity of the backrest pressure distribution and the variance of the backrest pressure distribution are determined; according to the center of gravity of the seat cushion pressure distribution, the variance of the seat cushion pressure distribution, the center of gravity of the backrest pressure distribution, the variance of the backrest pressure distribution and the weight parameter, the height parameter of the target driver is determined.

[0043] Specifically, the determination method of the center of gravity of the backrest pressure distribution (C x , C y ) is as follows:

[0044]

[0045] Among them, is the pressure value at the i-th row and j-th column of the backrest pressure matrix, that is, the backrest pressure value detected at the point position of the i-th row and j-th column of the pressure sensor array; x i,j represents the abscissa of the i-th row and j-th column; y i,j represents the ordinate of the i-th row and j-th column.

[0046] Specifically, the determination method of the center of gravity of the seat cushion pressure distribution (Z x , Z y ) is as follows:

[0047]

[0048] Among them, is the pressure value at the i-th row and j-th column in the seat cushion pressure matrix, that is, the seat cushion pressure value detected at the position of the i-th row and j-th column in the pressure sensor array; x i,j represents the abscissa of the i-th row and j-th column; y i,j represents the ordinate of the i-th row and j-th column.

[0049] Specifically, the variance of the backrest pressure distribution is determined as follows:

[0050]

[0051] where m and n respectively represent the number of rows and columns of the array or matrix; is the pressure value at the i-th row and j-th column in the backrest pressure matrix, that is, the backrest pressure value detected at the position of the i-th row and j-th column in the pressure sensor array; is the average pressure value of the backrest pressure values at all row and column positions.

[0052] Specifically, the variance of the seat cushion pressure distribution is determined as follows:

[0053]

[0054] where m and n respectively represent the number of rows and columns of the array or matrix; is the pressure value at the i-th row and j-th column in the seat cushion pressure matrix, that is, the seat cushion pressure value detected at the position of the i-th row and j-th column in the pressure sensor array; is the average pressure value of the seat cushion pressure values at all row and column positions.

[0055] Based on the center of gravity of the seat cushion pressure distribution, the variance of the seat cushion pressure distribution, the center of gravity of the backrest pressure distribution, the variance of the backrest pressure distribution, and the body weight parameter, and using a pre-trained height prediction model, determine the height parameter of the target driver.

[0056] Specifically, the model training method for the height prediction model is as follows: Obtain the center of gravity of the seat cushion pressure distribution, the variance of the seat cushion pressure distribution, the center of gravity of the backrest pressure distribution, the variance of the backrest pressure distribution, the standard weight, and the standard height of different measured persons. Use the center of gravity of the seat cushion pressure distribution, the variance of the seat cushion pressure distribution, the center of gravity of the backrest pressure distribution, the variance of the backrest pressure distribution, and the standard weight of different measured persons as training sample data, and use the corresponding standard height as the label value of the training sample to obtain the training sample data with label values. Input the training sample data into a preset initial model to obtain the predicted height output by the model; Determine the loss value based on the standard height and the predicted height, and perform model training on the initial model according to the loss value until the loss value tends to be stable or the loss value reaches the set threshold or the number of iterations reaches the set threshold to end the training and obtain the weight prediction model. Among them, the initial model can be a random forest or a neural network model, such as CNN, etc.

[0057] In the process of determining the height parameter and weight parameter of the target driver, the above technical solution comprehensively considers the pressure value, the center of gravity of the pressure distribution, and the variance of the pressure distribution of the driver at different positions, and respectively performs height and weight prediction based on the pre-trained height prediction model and weight prediction model, improving the accuracy of determining the height parameter and weight parameter of the target driver, thereby further improving the precise attitude adjustment of the cockpit adjustment unit.

[0058] Determine the initial attitude parameters according to the height parameter and the weight parameter. Among them, the initial attitude parameters may include the seat height, the seat backrest inclination angle, the seat cushion inclination angle, the orientation parameter in the X direction of the seat, that is, the forward or backward movement distance relative to the zero position of the seat, the distance in the Z direction from the center point of the steering wheel to the ground, and the steering wheel inclination angle and other parameters.

[0059] Specifically, according to the height parameter and the weight parameter, based on the pre-trained attitude prediction model, the initial attitude parameters can be predicted. The attitude prediction model can be pre-trained by relevant technical personnel. The specific model training method can be: Obtain the height parameter and the weight parameter of different measured persons, and determine the standard attitude parameters of the corresponding test persons in the most comfortable state, and use the standard attitude parameters as the label values of the height parameter and the weight parameter of the measured persons to generate the training sample data with label values. Input the training sample data into a preset network model, such as CNN, to obtain the predicted attitude parameters output by the model; Determine the loss value based on the standard attitude parameters and the predicted attitude parameters, and perform model training on the network model based on the loss value until the loss value reaches the set threshold or the loss value tends to be stable to obtain the attitude prediction model for attitude prediction.

[0060] Further, this embodiment also provides another method for determining the initial attitude parameters. In an alternative embodiment, the initial attitude parameters are determined according to the height parameter and the weight parameter, including: determining the initial attitude parameters according to the height parameter and the weight parameter based on a pre-constructed mapping relationship table between human characteristics and postures; the mapping relationship table between human characteristics and postures stores the mapping relationship between height and weight and the attitude parameters.

[0061] To further determine the accuracy of the height parameter and the weight parameter of the target driver determined automatically, so as to facilitate subsequent accurate attitude adjustment, the automatically determined height parameter and weight parameter of the target driver can be fed back to the target driver, and the target driver is asked to confirm whether they are accurate. If so, the initial attitude parameters are determined based on the current height parameter and weight parameter. If the target driver modifies the height parameter and / or the weight parameter, the modification instruction of the target driver is received, the modification instruction is parsed to obtain the modified height and the modified weight, and then the initial attitude parameters are determined based on the modified height and the modified weight.

[0062] Among them, the mapping relationship table between human characteristics and postures can be pre-constructed and stored by relevant technicians. The mapping relationship table between human characteristics and postures stores the mapping relationship between height and weight and the attitude parameters.

[0063] The construction method of the mapping relationship table between human characteristics and postures can be: screening people with different height and weight levels. For example, the height range can be set at 160-190 cm, and the height is divided into seven levels H = [160 165 170 175 180 185 190] at intervals of 5 cm. The weight range can be set at 50 kg-100 kg, and the weight is divided into eleven levels W = [50 55 60 65 70 75 80 85 90 95 100] at intervals of 5 kg. The attitude parameters of each test subject in the most comfortable state are collected. Among them, the attitude parameters of the steering wheel can be obtained by displacement sensors and angle sensors deployed on the steering wheel; the attitude parameters of the seat can be obtained by angle sensors and displacement sensors deployed on the seat. The attitude parameters can include parameters such as seat height, seat back inclination angle, seat cushion inclination angle, orientation parameter in the X direction of the seat, distance in the Z direction from the center point of the steering wheel to the ground, and steering wheel inclination angle.

[0064] Define the above attitude parameters such as seat height h, seat back inclination angle α, seat cushion inclination angle β, orientation parameter d in the X direction of the seat, distance s in the Z direction from the center point of the steering wheel to the ground, and steering wheel inclination angle θ. The attitude parameter P = [h α β d s θ]. The constructed mapping relationship table between human characteristics and postures can be seen in Table 1.

[0065] Table 1

[0066]

[0067] Optionally, the determined initial posture parameters can be fed back to the target driver for confirmation. If the target driver confirms that there is no error, the posture adjustment is performed based on the determined initial posture parameters; if the target driver adjusts the initial posture parameters, the adjusted posture parameters after the target driver's adjustment are obtained, and the posture adjustment is performed based on the adjusted posture parameters. At the same time, according to the adjusted posture parameters, the human feature and posture mapping relationship table is updated.

[0068] It should be noted that when the adjusted posture parameters obtained after the posture adjustment of drivers with the same height and weight are different, the average value of the adjusted posture parameters can be determined within a certain time period, and the obtained average value is used as the posture parameters corresponding to the height and weight. Or, the median or mode of the adjusted posture parameters can also be used as the posture parameters corresponding to the height and weight.

[0069] Based on the initial posture parameters, the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs is controlled to perform posture adjustment. Among them, the cockpit adjustment unit includes a steering wheel adjustment unit and a seat adjustment unit. Based on the seat height, seat back inclination angle, seat cushion inclination angle, and the orientation parameter in the X direction of the seat in the initial posture parameters, the seat adjustment unit is controlled to make adjustments; based on parameters such as the distance s in the Z direction from the center point of the steering wheel to the ground and the steering wheel inclination angle θ, the steering wheel adjustment unit is controlled to make adjustments.

[0070] The above technical solution obtains the seat cushion pressure value and the backrest pressure value of the target vehicle when detecting the boarding behavior of the target driver; determines the height parameter and weight parameter of the driver according to the seat cushion pressure value and the backrest pressure value; determines the initial posture parameters according to the height parameter and the weight parameter; and controls the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs to perform posture adjustment based on the initial posture parameters. The above technical solution realizes the automatic determination of the driver's height and weight according to the seat cushion pressure value and the backrest pressure value, and realizes the automatic and accurate determination of the initial posture parameters based on the height and weight, without the target driver manually adjusting the posture, which improves the use experience while satisfying the driver's comfort.

[0071] It should be noted that the initial posture parameters are the initial posture adjustment after the driver gets on the vehicle, and the posture dynamic adjustment described in the present invention is the real-time dynamic posture adjustment during the vehicle driving process. Taking the timed adjustment as an example, a posture adjustment will be performed when the posture adjustment time period is met, so as to satisfy the driver's comfort and avoid the driving fatigue caused by sitting in the same posture for a long time.

[0072] Among them, the historical posture parameters are related to the initial posture parameters. For example, after the posture is adjusted based on the initial posture parameter M0, the vehicle enters the driving state, and it is set to perform posture adjustment under the adjustment time periods T1, T2, … Tn. For the adjustment time period T1, the historical posture parameter used in determining and obtaining the current posture adjustment amount of this adjustment time period is the initial posture parameter M, and the current posture adjustment amount obtained for this adjustment time period is Δm0, that is, the current posture parameter is M1 = M0 + Δm0; for the adjustment time period T2, the historical posture parameter used in determining and obtaining the current posture adjustment amount of this adjustment time period is M1, and so on.

[0073] Among them, the linkage adjustment strategy generation model can be pre-constructed and trained by relevant technical personnel. The linkage adjustment strategy generation model includes a strategy generation network and a score prediction network; the strategy generation network is used to generate a posture adjustment strategy, and the score prediction network is used to score the posture adjustment strategy to verify the accuracy of the strategy, and further verify whether this strategy can be used for posture adjustment. This embodiment also provides a model training method for the linkage adjustment strategy generation model.

[0074] In an optional embodiment, the model training method of the linkage adjustment strategy generation model is as follows: construct sample data; the sample data includes height parameters, weight parameters, posture parameters, posture range intervals, and posture scores; input at least one set of sample data into the linkage adjustment strategy generation model, and the strategy generation network performs model training based on the height parameters, weight parameters, posture parameters, and posture range intervals to obtain the predicted posture adjustment amount within the posture range interval; input the predicted posture adjustment amount and the posture score into the score prediction network to output the adjustment amount prediction score; according to the predicted posture adjustment amount, the historical posture adjustment amount of the strategy generation network in the previous iteration period, the predicted score, and the posture score, perform model training on the linkage adjustment strategy generation model until the preset model training end condition is met, and obtain the trained linkage adjustment strategy generation model.

[0075] Among them, the strategy generation network can be set as CGAN (Conditional Generative Adversarial Network), and the score prediction network can be set as SVM (Support Vector Machine).

[0076] Input at least one set of sample data into the linkage adjustment strategy generation model. The CGAN model is trained based on height parameters, weight parameters, pose parameters, and pose range intervals to obtain the predicted pose adjustment amount within the pose range interval. In the process of constructing the CGAN model, a staged learning method can be adopted: Stage 1 (basic strategy): Only learn small adjustments (±5mm) and fix the steering wheel angle. Stage 2 (advanced strategy): Introduce linkage adjustment (the seat and the steering wheel move proportionally); Stage 3 (complete strategy): Open full parameter adjustment and add random perturbations. Among them, the predicted pose adjustment amount is the adjustment amplitude based on the previous historical pose parameters.

[0077] Input the predicted pose adjustment amount and the pose score into the score prediction network to output the predicted score for the adjustment amount. Based on the predicted pose adjustment amount, the historical pose adjustment amount of the strategy generation network in the previous iteration cycle, the predicted score, and the pose score, determine the target loss value based on the target loss function; where the target loss function is defined as follows:

[0078]

[0079] Among them, Δ pred is the predicted pose adjustment amount, Δ opt is the historical selection strategy of the model, that is, the historical pose adjustment amount, S pred is the predicted score, S real is the pose score; α and β are adjustable parameter items required in the model training process.

[0080] Train the linkage adjustment strategy generation model according to the target loss value until the preset model training end condition is met to obtain the trained linkage adjustment strategy generation model. Among them, the model training end condition can be that the target loss value reaches the set threshold, or the target loss value tends to be stable, etc.

[0081] In the above process of training the linkage adjustment strategy generation model, height parameters, weight parameters, pose parameters, pose range intervals, and pose scores are combined. The pose adjustment strategy is predicted by the strategy generation network and evaluated by the score prediction network. And in the process of determining the target loss value, two influencing factors of score and strategy are comprehensively considered, which improves the training accuracy of the linkage adjustment strategy generation model.

[0082] The linkage adjustment strategy generation model is used to predict the current posture adjustment amount in the current posture adjustment cycle. In an alternative embodiment, based on the height parameter, weight parameter, and historical posture parameter of the target driver, the linkage adjustment strategy generation model pre-trained is used to generate the current posture adjustment amount in the current posture adjustment cycle, and based on the current posture adjustment amount, the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs is controlled to perform posture adjustment, including: inputting the height parameter, weight parameter, and historical posture parameter of the target driver into the policy generation network in the linkage adjustment strategy generation model, and the policy generation network predicts the posture adjustment amount to obtain the current posture adjustment amount output by the policy generation network; inputting the current posture adjustment amount into the score prediction network in the linkage adjustment strategy generation model, and the score prediction network predicts the score of the current posture adjustment amount to obtain the score prediction result; if the score prediction result meets the preset policy output judgment condition, based on the current posture adjustment amount, the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs is controlled to perform posture adjustment.

[0083] Among them, the policy output judgment condition can be set to judge whether the scoring value of the score prediction result is greater than the preset scoring threshold. If the scoring value of the score prediction result is greater than the preset scoring threshold, it can be considered that the prediction result of the policy generation network is accurate enough, and based on the predicted current posture adjustment amount, the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs can be controlled to perform posture adjustment. If the scoring value of the score prediction result is not greater than the preset scoring threshold, it can be considered that the prediction result of the policy generation network is not accurate enough, and posture adjustment is not performed in this adjustment cycle.

[0084] Based on the seat height adjustment amount, seat back inclination adjustment amount, seat cushion inclination adjustment amount, and seat X-direction orientation parameter adjustment amount in the current posture adjustment amount, the seat adjustment unit is controlled to make adjustments; based on parameters such as the distance adjustment amount of the center point of the steering wheel from the ground in the Z direction and the steering wheel inclination adjustment amount, the steering wheel adjustment unit is controlled to make adjustments.

[0085] The posture adjustment strategy is generated by the policy generation network in the linkage adjustment strategy generation model, and the score prediction network evaluates the generated posture adjustment strategy of the policy generation network to obtain the evaluation score. According to the evaluation score, the accuracy of the posture adjustment strategy generated by the policy generation network is judged. When the evaluation score is high, it indicates that the accuracy of the posture adjustment strategy generated by the policy generation network is high, and this posture adjustment strategy can be used for posture adjustment, thereby improving the prediction accuracy of the posture adjustment strategy.

[0086] In the technical solution of the embodiment of the present invention, by determining the height parameter and weight parameter of the target driver, obtaining the historical posture parameter in the previous posture adjustment cycle, and based on the height parameter, weight parameter and historical posture parameter of the target driver, generating a current posture adjustment amount in the current posture adjustment cycle by using a linkage adjustment strategy generation model pre-trained, and based on the current posture adjustment amount, controlling the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs to perform posture adjustment. The above technical solution realizes real-time prediction of posture adjustment parameters based on the linkage adjustment strategy generation model and the physical signs parameters of the driver, etc., improves the prediction accuracy of the posture adjustment parameters, realizes dynamic adjustment of the postures of the seat, backrest and steering wheel during the vehicle driving process, meets the personalized needs of drivers with different body type characteristics, and improves the comfort of the driver during the driving process.

[0087] Embodiment 2

[0088] Figure 2A FIG. is a flowchart of a method for dynamically adjusting the posture of a cockpit provided by Embodiment 2 of the present invention, which is applied to a cockpit posture dynamic adjustment system and is executed by a microprocessor of the cockpit posture dynamic adjustment system. Figure 2B FIG. is a schematic structural diagram of a cockpit posture dynamic adjustment system provided by Embodiment 2 of the present invention. On the basis of the above embodiment, this embodiment provides a preferred example.

[0089] As Figure 2B shown, the cockpit posture dynamic adjustment system includes three major components, namely a perception layer, a decision-making layer and an execution layer. Among them, the perception layer collects external sensor signals. When the central processor has a data request requirement, it packs and organizes the data to meet various data analysis requirements of the decision-making layer. The decision-making layer, that is, the central processor, is the core brain of the system. All function item models and algorithms are embedded inside, including various mathematical models or mathematical algorithms for making decisions or predictions. The central processor processes the data to form a decision and transmits it to the execution layer to execute the instruction.

[0090] The execution layer is composed of a steering wheel adjustment unit, a seat adjustment unit, a status indication module and a communication port. The steering wheel adjustment unit and the seat adjustment unit are physical adjustment mechanisms, which adjust the position and angle of the steering wheel and the seat according to the instruction. The status indication module displays the execution status of the function command, and can be indicated by "red" / "green" lights; the communication port realizes the interaction between the decision-making layer and the execution layer, and can feedback the positioning parameters of the seat and the steering wheel to the central processor in real time.

[0091] As Figure 2A shown, the specific implementation process preferred in this embodiment is as follows:

[0092] Step 21: Construct a human-machine parameter database.

[0093] The human-machine parameter database stores a mapping relationship table between human body characteristics and postures. Specifically, different height and weight level populations can be screened through methods such as questionnaires and volunteer recruitment tests. The height range is 160 cm to 190 mm, and the height is divided into seven levels H = [160 165 170 175 180 185 190] at 5 cm intervals; the weight range is 50 kg to 100 kg, and the weight is divided into eleven levels W = [50 55 60 65 70 75 80 85 90 95 100] at 5 kg intervals.

[0094] The posture parameters are obtained by sensors such as displacement and angle integrated on the steering wheel and seat. Definition of the steering wheel position parameters: the Z-direction distance s from the center point of the steering wheel to the floor, and the steering wheel inclination angle θ; Definition of the seat position parameters: the seat height h, the seat back inclination angle α, the seat cushion inclination angle β, and the seat X-direction positioning parameter d. Define the human-machine parameter scheme P = [h α β d s θ]. Based on the foregoing definitions, a 7*11*6 matrix of a comfortable human-machine parameter database is constructed as shown in Table 2.

[0095] Table 2

[0096]

[0097] Step 22: When it is detected that the driver is seated, obtain the seat cushion pressure value and the backrest pressure value of the target vehicle.

[0098] The seat cushion pressure value can be obtained by collecting pressure through a pressure sensor array deployed at the seat cushion position of the target vehicle. The numerical expression form of the seat cushion pressure value can be a pressure value matrix, where different rows and different columns in the matrix are used to represent the pressure values at the corresponding array points. The backrest pressure value can be obtained by collecting pressure through a pressure sensor array deployed at the backrest position of the target vehicle. The numerical expression form of the backrest pressure value is also a pressure value matrix, where different rows and different columns in the matrix are used to represent the pressure values at the corresponding array points.

[0099] Step 23: Determine the height parameter and weight parameter of the driver according to the seat cushion pressure value and the backrest pressure value.

[0100] Based on a pre-trained weight prediction model, the weight is predicted based on the seat cushion pressure value and the backrest pressure value to obtain the predicted weight. According to the seat cushion pressure value, determine the center of gravity of the seat cushion pressure distribution and the variance of the seat cushion pressure distribution; and, according to the backrest pressure value, determine the center of gravity of the backrest pressure distribution and the variance of the backrest pressure distribution; according to the center of gravity of the seat cushion pressure distribution, the variance of the seat cushion pressure distribution, the center of gravity of the backrest pressure distribution, the variance of the backrest pressure distribution, and the weight parameter, determine the height parameter of the target driver.

[0101] Specifically, the center of gravity of the backrest pressure distribution (C x ,Cy ) is determined as follows:

[0102]

[0103] Among them, is the pressure value at the i-th row and j-th column in the backrest pressure matrix, that is, the backrest pressure value detected at the point of the i-th row and j-th column in the pressure sensor array; x i,j represents the abscissa of the i-th row and j-th column; y i,j represents the ordinate of the i-th row and j-th column.

[0104] Specifically, the center of gravity of the seat cushion pressure distribution (Z x , Z y ) is determined as follows:

[0105]

[0106] Among them, is the pressure value at the i-th row and j-th column in the seat cushion pressure matrix, that is, the seat cushion pressure value detected at the point of the i-th row and j-th column in the pressure sensor array; x i,j represents the abscissa of the i-th row and j-th column; y i,j represents the ordinate of the i-th row and j-th column.

[0107] Specifically, the variance of the backrest pressure distribution is determined as follows:

[0108]

[0109] Among them, m and n respectively represent the number of rows and columns of the array or matrix; is the pressure value at the i-th row and j-th column in the backrest pressure matrix, that is, the backrest pressure value detected at the point of the i-th row and j-th column in the pressure sensor array; is the average pressure value of the backrest pressure values at all row and column points.

[0110] Specifically, the variance of the seat cushion pressure distribution is determined as follows:

[0111]

[0112] Among them, m and n respectively represent the number of rows and columns of the array or matrix; is the pressure value at the i-th row and j-th column in the seat cushion pressure matrix, that is, the seat cushion pressure value detected at the point of the i-th row and j-th column in the pressure sensor array; is the average pressure value of the seat cushion pressure values at all row and column points.

[0113] Based on the center of gravity of the seat pressure distribution, the variance of the seat pressure distribution, the center of gravity of the backrest pressure distribution, the variance of the backrest pressure distribution, and the weight parameter, determine the height parameter of the target driver based on a pre-trained height prediction model.

[0114] Step 24: Feedback the height parameter and the weight parameter to the driver. If the driver modifies them, based on the modified height parameter and weight parameter of the driver, determine the initial pose parameter based on a pre-constructed mapping relationship table between human characteristics and poses; if the driver does not modify them, based on the height parameter and the weight parameter, determine the initial pose parameter based on a pre-constructed mapping relationship table between human characteristics and poses.

[0115] Step 25: Feedback the initial pose parameter to the driver, and let the driver judge whether to adjust the initial pose parameter; if the driver adjusts it, based on the adjusted initial pose parameter, control the corresponding cockpit adjustment unit in the vehicle to which the driver belongs to perform the initial pose adjustment; if the driver does not adjust it, based on the initial pose parameter, control the corresponding cockpit adjustment unit in the vehicle to which the driver belongs to perform the initial pose adjustment. At the same time, if the driver adjusts it, update the mapping relationship table between human characteristics and poses stored in the human-machine parameter database based on the adjusted initial pose parameter.

[0116] Specifically, based on the initial pose parameter, control the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs to perform pose adjustment. Among them, the cockpit adjustment unit includes a steering wheel adjustment unit and a seat adjustment unit. Based on the seat height, seat backrest inclination angle, seat cushion inclination angle, and the orientation parameter in the X direction of the seat in the initial pose parameter, control the seat adjustment unit to make adjustments; based on parameters such as the distance s in the Z direction from the center point of the steering wheel to the ground and the steering wheel inclination angle θ, control the steering wheel adjustment unit to make adjustments.

[0117] Step 26: When it is determined that the vehicle starts to drive, according to the set pose adjustment frequency and pose adjustment speed, the policy generation network in the co-adjustment policy generation model obtained by pre-training generates the current pose adjustment amount, that is, the pose adjustment policy, based on the height parameter, weight parameter, and initial pose parameter of the driver.

[0118] Step 27: The score prediction network in the co-adjustment policy generation model obtained by pre-training predicts the score of the current pose adjustment amount or the pose adjustment policy.

[0119] Step 28: If the score prediction result is that the score is greater than the preset score threshold, such as 6 points, then based on the current posture adjustment amount or posture adjustment strategy, control the corresponding cockpit adjustment unit in the vehicle where the driver is located to perform posture adjustment. If the score prediction result is that the score is not greater than the preset score threshold, then the policy generation network continues to predict the posture adjustment amount or posture adjustment strategy based on the driver's height parameter, weight parameter, and initial posture parameter until the condition judgment of the score threshold is satisfied.

[0120] The technical solution of this embodiment realizes the real-time generation of adjustment strategies during driving, including the steering wheel position parameters (the Z-direction distance from the center point of the steering wheel to the floor, the steering wheel inclination angle), the seat position parameters (the seat height, the seat back inclination angle, the seat cushion inclination angle, the seat X-direction positioning parameter), and predicts the comfort score of the human-machine parameters after adjustment. According to the preset score threshold, judge whether to retain the adjustment strategy; based on the preset adjustment speed and frequency, and the adopted adjustment strategy, control the real-time linkage adjustment of the seat and the steering wheel to realize "non-perceptible" healthy driving posture management. Avoid the driver staying in the same driving posture for a long time, reduce the driver's fatigue, and improve the comfort of the driver during driving.

[0121] Embodiment III

[0122] Figure 3 It is a schematic structural diagram of a cockpit posture dynamic adjustment device provided by Embodiment III of the present invention. A cockpit posture dynamic adjustment device provided by an embodiment of the present invention can be applied to the situation of real-time and dynamic adjustment of the steering wheel, seat, and backrest of a driver during vehicle driving. The cockpit posture dynamic adjustment device can be implemented in the form of hardware and / or software, such as Figure 3 shown, the device specifically includes: a physical sign parameter determination module 301, a historical posture acquisition module 302, and a posture adjustment module 303. Among them,

[0123] The physical sign parameter determination module 301 is used to determine the height parameter and weight parameter of the target driver;

[0124] The historical posture acquisition module 302 is used to acquire the historical posture parameters in the previous posture adjustment cycle;

[0125] The posture adjustment module 303 is used to generate the current posture adjustment amount in the current posture adjustment cycle based on the height parameter, weight parameter, and historical posture parameter of the target driver, based on a pre-trained linkage adjustment strategy generation model, and based on the current posture adjustment amount, control the corresponding cockpit adjustment unit in the vehicle where the target driver is located to perform posture adjustment.

[0126] In the technical solution of the embodiment of the present invention, by determining the height parameter and weight parameter of the target driver, obtaining the historical posture parameter in the previous posture adjustment cycle, and based on the height parameter, weight parameter and historical posture parameter of the target driver, a linkage adjustment strategy generation model is generated through pre-training, and the current posture adjustment amount in the current posture adjustment cycle is generated. And based on the current posture adjustment amount, the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs is controlled to perform posture adjustment. The above technical solution improves the prediction accuracy of the posture adjustment parameter by performing real-time prediction of the posture adjustment parameter based on the linkage adjustment strategy generation model and the physical signs parameters of the driver, etc., realizes the dynamic adjustment of the posture of the seat, backrest and steering wheel during the vehicle driving process, meets the personalized needs of drivers with different body type characteristics, and improves the comfort of the driver during the driving process.

[0127] Optionally, the linkage adjustment strategy generation model includes a strategy generation network and a score prediction network; correspondingly, the posture adjustment module 303 is specifically configured to:

[0128] Input the height parameter, weight parameter and historical posture parameter of the target driver into the strategy generation network in the linkage adjustment strategy generation model, and the strategy generation network predicts the posture adjustment amount to obtain the current posture adjustment amount output by the strategy generation network;

[0129] Input the current posture adjustment amount into the score prediction network in the linkage adjustment strategy generation model, and the score prediction network predicts the score of the current posture adjustment amount to obtain a score prediction result;

[0130] If the score prediction result meets the preset strategy output judgment condition, then based on the current posture adjustment amount, control the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs to perform posture adjustment.

[0131] Optionally, the model training method of the linkage adjustment strategy generation model is as follows:

[0132] Construct sample data; the sample data includes height parameter, weight parameter, posture parameter, posture range interval and posture score;

[0133] Input at least one set of sample data into the linkage adjustment strategy generation model, and the strategy generation network performs model training based on the height parameter, weight parameter, posture parameter and posture range interval to obtain a predicted posture adjustment amount within the posture range interval;

[0134] Input the predicted posture adjustment amount and the posture score into the score prediction network, and output an adjustment amount prediction score;

[0135] Based on the predicted posture adjustment amount, the historical posture adjustment amount of the policy generation network in the previous iteration cycle, the predicted score, and the posture score, the linkage adjustment policy generation model is trained until the preset model training end condition is satisfied, and the trained linkage adjustment policy generation model is obtained.

[0136] Optionally, the device further includes:

[0137] A pressure value acquisition module, configured to acquire the seat cushion pressure value and the backrest pressure value of the target vehicle when detecting the boarding behavior of the target driver before generating the current posture adjustment amount in the current posture adjustment cycle based on the linkage adjustment policy generation model pre-trained according to the height parameter, weight parameter, and historical posture parameter of the target driver.

[0138] A physical sign parameter determination module, configured to determine the height parameter and weight parameter of the target driver according to the seat cushion pressure value and the backrest pressure value.

[0139] An initial posture determination module, configured to determine the initial posture parameter according to the height parameter and the weight parameter.

[0140] An initial posture adjustment module, configured to control the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs to perform posture adjustment based on the initial posture parameter.

[0141] Optionally, the physical sign parameter determination module includes:

[0142] A weight parameter determination unit, configured to determine the weight parameter of the target driver according to the seat cushion pressure value and the backrest pressure value.

[0143] A height parameter determination unit, configured to determine the height parameter of the target driver according to the seat cushion pressure value, the backrest pressure value, and the weight parameter.

[0144] Optionally, the height parameter determination unit is specifically configured to:

[0145] Determine the seat cushion pressure distribution centroid and the seat cushion pressure distribution variance according to the seat cushion pressure value; and,

[0146] Determine the backrest pressure distribution centroid and the backrest pressure distribution variance according to the backrest pressure value;

[0147] Determine the height parameter of the target driver according to the seat cushion pressure distribution centroid, the seat cushion pressure distribution variance, the backrest pressure distribution centroid, the backrest pressure distribution variance, and the weight parameter.

[0148] Optionally, the initial posture determination module is specifically configured to:

[0149] Based on the height parameter and the weight parameter, determine an initial pose parameter according to a pre-constructed mapping relationship table between human body features and poses; the mapping relationship table between human body features and poses stores the mapping relationship between height, weight and pose parameters.

[0150] The cockpit attitude dynamic adjustment device provided by the embodiments of the present invention can execute the cockpit attitude dynamic adjustment method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0151] Embodiment Four

[0152] Figure 4 FIG. shows a schematic structural diagram of an electronic device 40 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0153] As Figure 4 shown, the electronic device 40 includes at least one processor 41, and a memory communicatively connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc. Among them, the memory stores a computer program executable by the at least one processor, and the processor 41 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 into the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. The input / output (I / O) interface 45 is also connected to the bus 44.

[0154] A plurality of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a magnetic disk, an optical disc, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0155] The processor 41 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as the cockpit attitude dynamic adjustment method.

[0156] In some embodiments, the cockpit attitude dynamic adjustment method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the cockpit attitude dynamic adjustment method described above may be executed. Alternatively, in other embodiments, the processor 41 may be configured to execute the cockpit attitude dynamic adjustment method by any other suitable means (e.g., by means of firmware).

[0157] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-a-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0158] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0159] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0160] For providing interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used for providing interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0161] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0162] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is created by computer programs that run on respective computers and have a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0163] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0164] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A cockpit attitude dynamic adjustment method, characterized in that: include: Determine the height and weight parameters of the target driver; Get the historical posture parameters of the previous posture adjustment cycle; According to the height parameters, weight parameters and historical posture parameters of the target driver, a linkage adjustment strategy generation model obtained based on pre-training is used to generate a current posture adjustment amount in a current posture adjustment cycle, and based on the current posture adjustment amount, a corresponding cockpit adjustment unit in the vehicle to which the target driver belongs is controlled to perform posture adjustment.

2. The method according to claim 1, characterized in that The linkage adjustment strategy generation model includes a strategy generation network and a score prediction network; accordingly, according to the height parameter, weight parameter and historical posture parameter of the target driver, based on the linkage adjustment strategy generation model obtained by pre-training, a current posture adjustment amount in the current posture adjustment cycle is generated, and based on the current posture adjustment amount, a corresponding cockpit adjustment unit in the vehicle to which the target driver belongs is controlled to perform posture adjustment, including: Inputting the height parameter, weight parameter and historical posture parameter of the target driver into the strategy generation network in the linkage adjustment strategy generation model, and using the strategy generation network to predict the posture adjustment amount to obtain the current posture adjustment amount output by the strategy generation network; Inputting the current posture adjustment amount into the score prediction network in the linkage adjustment strategy generation model, and using the score prediction network to perform score prediction on the current posture adjustment amount to obtain a score prediction result; If the score prediction result meets the preset strategy output judgment condition, then based on the current posture adjustment amount, the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs is controlled to perform posture adjustment.

3. The method according to claim 2, characterized in that The model training method of the linkage adjustment strategy generation model is as follows: Constructing sample data; the sample data includes height parameters, weight parameters, posture parameters, posture range intervals and posture scores; Inputting at least one set of sample data into a linkage adjustment strategy generation model, wherein the strategy generation network performs model training based on the height parameter, weight parameter, posture parameter and posture range interval to obtain a predicted posture adjustment amount within the posture range interval; Inputting the predicted posture adjustment amount and the posture score into the score prediction network, and outputting the adjustment amount prediction score; According to the predicted posture adjustment amount, the historical posture adjustment amount of the strategy generation network in the previous iteration cycle, the predicted score and the posture score, the linkage adjustment strategy generation model is trained until the preset model training end condition is met to obtain a trained linkage adjustment strategy generation model.

4. The method according to claim 1, characterized in that: Before generating the current posture adjustment amount in the current posture adjustment cycle based on the linkage adjustment strategy generation model obtained by pre-training according to the height parameter, weight parameter and historical posture parameter of the target driver, the method further includes: When the target driver's behavior of getting into the vehicle is monitored, obtaining a seat cushion pressure value and a backrest pressure value of the target vehicle; Determining a height parameter and a weight parameter of the target driver according to the seat cushion pressure value and the backrest pressure value; Determining initial posture parameters according to the height parameter and the weight parameter; Based on the initial posture parameters, a corresponding cockpit adjustment unit in the vehicle to which the target driver belongs is controlled to perform posture adjustment.

5. The method according to claim 4, characterized in that Determining the height parameter and weight parameter of the target driver according to the seat cushion pressure value and the backrest pressure value includes: Determining a weight parameter of the target driver according to the seat cushion pressure value and the backrest pressure value; A height parameter of the target driver is determined according to the seat cushion pressure value, the backrest pressure value and the weight parameter.

6. The method according to claim 5, characterized in that The step of determining the height parameter of the target driver according to the seat cushion pressure value, the backrest pressure value and the weight parameter comprises: Determining the center of gravity of the seat cushion pressure distribution and the seat cushion pressure distribution variance according to the seat cushion pressure value; and Determining the backrest pressure distribution center of gravity and the backrest pressure distribution variance according to the backrest pressure value; The height parameter of the target driver is determined according to the seat cushion pressure distribution center of gravity, the seat cushion pressure distribution variance, the backrest pressure distribution center of gravity, the backrest pressure distribution variance and the weight parameter.

7. The method according to claim 4, characterized in that Determining initial posture parameters according to the height parameter and the weight parameter includes: According to the height parameter and the weight parameter, initial posture parameters are determined based on a pre-constructed human body feature and posture mapping relationship table; the human body feature and posture mapping relationship table stores a mapping relationship between height, weight and posture parameters.

8. A cockpit attitude dynamic adjustment device, characterized in that: include: A physical sign parameter determination module, used to determine the height parameter and weight parameter of the target driver; A historical posture acquisition module is used to obtain historical posture parameters in the previous posture adjustment cycle; The posture adjustment module is used to generate a current posture adjustment amount in a current posture adjustment cycle based on the height parameter, weight parameter and historical posture parameter of the target driver and a linkage adjustment strategy generation model obtained based on pre-training, and based on the current posture adjustment amount, control the corresponding cockpit adjustment unit in the vehicle to which the target driver belongs to perform posture adjustment.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the cockpit attitude dynamic adjustment method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the cockpit attitude dynamic adjustment method according to any one of claims 1 to 7 when executed.

Images