Control method and device of intelligent health seat, electronic equipment and storage medium

Abstract

The application discloses a control method and device of an intelligent health seat, electronic equipment and a storage medium. The actual pressure distribution of a passenger is collected in real time, the real-time sitting posture is estimated, the actual pressure distribution is dynamically deviated from the initial target pressure distribution generated based on basic body shape data, and then a driving instruction is generated to independently control a plurality of independent support force adjusting units in different zones, so that the actual pressure distribution continuously converges to the target pressure distribution, thereby realizing real-time adaptive matching of the seat support characteristics to the micro-motion and fatigue state of the passenger's sitting posture, avoiding the blood circulation obstruction and the increased risk of lumbar strain caused by the fact that the seat support force cannot be dynamically adjusted according to the change of the sitting posture in the prior art, and achieving the technical effects of improving the adaptive adjustment capability of the seat, improving the riding comfort and spine health of the passenger, and realizing truly personalized intelligent support.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle technology, and in particular to a control method, device, electronic device, and storage medium for an intelligent health seat. Background Technology

[0002] As a core component of the vehicle's human-machine interface system, car seats are widely used to enhance driving comfort and safety. With the development of smart cockpit technology, existing high-end seats typically construct a multi-dimensional posture adjustment system through the coordinated operation of electric adjustment mechanisms, basic pneumatic lumbar support, and memory modules. Specifically, this system covers the entire process from macroscopic position adjustment to local support changes, including key aspects such as fore-and-aft height displacement, backrest angle adjustment, and lumbar support adjustment, aiming to adapt to the basic needs of users of different body types.

[0003] Existing seat adjustment methods cannot adaptively match the seat support force to the slight changes in the occupant's sitting posture and the fatigue state during long journeys, thereby affecting the blood circulation health of drivers and passengers and exacerbating the risk of lumbar strain, making it difficult to achieve truly personalized intelligent health support. Summary of the Invention

[0004] This disclosure provides a control method, device, electronic device, and storage medium for an intelligent health seat. Its main purpose is to address the problem of difficulty in achieving truly personalized intelligent health support, which affects the blood circulation health of drivers and passengers and exacerbates the risk of lumbar strain.

[0005] According to a first aspect of this disclosure, a control method for an intelligent health seat is provided, comprising:

[0006] Acquire basic body shape data of the occupants, and based on the basic body shape data, call the preset ergonomic model to generate initial target pressure distribution corresponding to different body zones; The actual pressure distribution of the occupant is collected in real time by a sensor array set on the seat contact surface, and the occupant's real-time sitting posture is estimated based on the actual pressure distribution. Calculate the deviation between the actual pressure distribution and the initial target pressure distribution, and generate drive commands for multiple independent support force adjustment units based on the deviation; Based on the driving instructions, the support characteristics of each partition are dynamically adjusted to make the actual pressure distribution converge towards the target pressure distribution.

[0007] Optionally, the step of obtaining the occupant's basic body shape data and, based on the basic body shape data, calling a preset ergonomic model to generate an initial target pressure distribution corresponding to different body zones includes: The system receives the passenger's height and weight data through a user input interface or biometric system. Based on the height and weight data, the target pressure values ​​for different body zones are obtained by matching or interpolating the data in a preset ergonomic model database. The target pressure value is mapped to multiple functional zones of the seat cushion and backrest to generate the initial target pressure distribution.

[0008] Optionally, estimating the occupant's real-time sitting posture based on the actual pressure distribution includes: The actual pressure distribution is integrated with the macroscopic position data of the seat; The fused data is input into a machine learning-based sitting posture estimation model to obtain the occupant's pelvic angle, spinal curvature, and shoulder posture.

[0009] Optionally, calculating the deviation between the actual pressure distribution and the initial target pressure distribution, and generating drive commands for multiple independent support force adjustment units based on the deviation, includes: Calculate the spatial distribution and amplitude of the pressure deviation between the real-time pressure distribution and the target pressure distribution; The target functional zones that need to be adjusted and their adjustment directions are determined based on the spatial distribution of the pressure deviation. Send a drive command to at least one support force adjustment unit within the target functional area.

[0010] Optionally, the method further includes: Record the manual adjustment operations performed by the user on the basis of automatic adjustment, and update the personalized adaptation model corresponding to the current user based on the recorded manual adjustment operations; When the identification result is the user, the personalized adaptation model is invoked to generate the initial target pressure distribution.

[0011] Optionally, the method further includes: When it is determined that the real-time sitting posture deviates from the preset healthy sitting posture model, a correction target pressure distribution is generated; The drive command is updated based on the target pressure distribution to guide the occupant back to a healthy sitting posture.

[0012] Optionally, when it is determined that the real-time sitting posture deviates from the preset healthy sitting posture model, generating the correction target pressure distribution includes: The estimated real-time sitting posture is compared with a standard healthy sitting posture model to calculate the posture deviation. When the posture deviation exceeds a preset threshold, a corrective target pressure distribution that is different from the initial target pressure distribution is generated; wherein, the corrective target pressure distribution is configured to guide the occupant's spine to extend toward a standard healthy sitting posture by adjusting the support force of each zone; The current target pressure distribution is smoothly transitioned from the initial target pressure distribution to the corrected target pressure distribution, and the drive command is updated according to the corrected target pressure distribution.

[0013] According to a second aspect of this disclosure, a control device for an intelligent health chair is provided, comprising: The acquisition unit is used to acquire the basic body shape data of the occupants, and based on the basic body shape data, call the preset ergonomic model to generate the initial target pressure distribution corresponding to different body zones. The first calculation unit is used to collect the actual pressure distribution of the occupant in real time through a sensor array set on the seat contact surface, and estimate the occupant's real-time sitting posture based on the actual pressure distribution. The second calculation unit is used to calculate the deviation between the actual pressure distribution and the initial target pressure distribution, and to generate drive commands for multiple independent support force adjustment units based on the deviation. The adjustment unit is used to dynamically adjust the support characteristics of each partition based on the driving command so that the actual pressure distribution converges to the target pressure distribution.

[0014] Optionally, the acquisition unit is further configured to: The system receives the passenger's height and weight data through a user input interface or biometric system. Based on the height and weight data, the target pressure values ​​for different body zones are obtained by matching or interpolating the data in a preset ergonomic model database. The target pressure value is mapped to multiple functional zones of the seat cushion and backrest to generate the initial target pressure distribution.

[0015] Optionally, the first computing unit is further configured to: The actual pressure distribution is integrated with the macroscopic position data of the seat; The fused data is input into a machine learning-based sitting posture estimation model to obtain the occupant's pelvic angle, spinal curvature, and shoulder posture.

[0016] Optionally, the second computing unit is further configured to: Calculate the spatial distribution and amplitude of the pressure deviation between the real-time pressure distribution and the target pressure distribution; The target functional zones that need to be adjusted and their adjustment directions are determined based on the spatial distribution of the pressure deviation. Send a drive command to at least one support force adjustment unit within the target functional area.

[0017] Optionally, the device further includes: The recording unit is used to record the manual adjustment operations performed by the user on the basis of automatic adjustment, and to update the personalized adaptation model corresponding to the current user based on the recorded manual adjustment operations. The first generation unit is used to call the personalized adaptation model to generate an initial target pressure distribution in response to the identification result being the user.

[0018] Optionally, the device further includes: The second generation unit is used to generate a correction target pressure distribution when it is determined that the real-time sitting posture deviates from the preset healthy sitting posture model. The updating unit is used to update the driving command based on the correction target pressure distribution to guide the occupant back to a healthy sitting posture.

[0019] Optionally, the second generating unit is further configured to: The estimated real-time sitting posture is compared with a standard healthy sitting posture model to calculate the posture deviation. When the posture deviation exceeds a preset threshold, a corrective target pressure distribution that is different from the initial target pressure distribution is generated; wherein, the corrective target pressure distribution is configured to guide the occupant's spine to extend toward a standard healthy sitting posture by adjusting the support force of each zone; The current target pressure distribution is smoothly transitioned from the initial target pressure distribution to the corrected target pressure distribution, and the drive command is updated according to the corrected target pressure distribution.

[0020] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0021] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0022] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0023] The intelligent health seat control method, device, electronic equipment, and storage medium disclosed herein, through real-time acquisition of the actual pressure distribution of the occupant and estimation of the real-time sitting posture, dynamically calculates the deviation between the actual pressure distribution and the initial target pressure distribution generated based on basic body shape data, and then generates drive commands to independently control multiple independent support force adjustment units in zones, so that the actual pressure distribution continuously converges to the target pressure distribution. This achieves real-time adaptive matching of seat support characteristics to the occupant's sitting posture micro-movements and fatigue state, avoiding the obstruction of blood circulation and increased risk of lumbar strain caused by the inability of seat support force to dynamically adjust with changes in sitting posture in the prior art. Therefore, it can solve the technical problems of existing seat adjustment methods that are difficult to achieve personalized intelligent health support and cannot effectively protect the long-term health of drivers and passengers, and achieve the technical effects of improving the seat's adaptive adjustment capability, improving occupant sitting comfort and spinal health, and realizing truly personalized intelligent support.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0025] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 A flowchart illustrating a control method for an intelligent health chair provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of the structure of a control device for an intelligent health seat provided in an embodiment of the present disclosure; Figure 3 A schematic diagram of the structure of another intelligent health seat control device provided in an embodiment of this disclosure; Figure 4 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0026] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0027] The control method, apparatus, electronic device, and storage medium of the smart health chair according to embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0028] Figure 1This is a schematic flowchart illustrating a control method for an intelligent health chair provided in an embodiment of this disclosure.

[0029] like Figure 1 As shown, the method includes the following steps: Step 101: Obtain the basic body shape data of the occupants, and based on the basic body shape data, call the preset ergonomic model to generate the initial target pressure distribution corresponding to different body zones; Acquire basic body shape data that can characterize the occupant's body size and mass distribution. This data serves as input parameters for subsequent personalized adjustments and is used to retrieve or generate a target pressure distribution model that matches the occupant's body shape from a pre-set ergonomic knowledge base.

[0030] The ergonomic model, based on biomechanical principles, pre-establishes a mapping relationship between different body shape characteristics and the ideal pressure distribution in various functional zones of the seat (such as the weight-bearing zone, support zone, and fit zone). Based on this, the system calls the corresponding model according to the acquired basic body shape data to calculate and generate an initial target pressure distribution map. This map defines the desired pressure value or pressure distribution pattern for each independent adjustment zone of the seat in a zoned manner, thus providing a benchmark for subsequent closed-loop adjustments.

[0031] As a specific implementation method, height and weight can be obtained through user input or automatic recognition, and then a basic ergonomic model built for different percentile populations can be invoked to interpolate and calculate the initial target pressure value set corresponding to the ischial tuberosity area, thigh area, lumbar area, thoracic spine area and shoulder area.

[0032] Step 102: The actual pressure distribution of the occupant is collected in real time by a sensor array set on the seat contact surface, and the real-time sitting posture of the occupant is estimated based on the actual pressure distribution. In some embodiments, a pressure-sensing array deployed on the contact surface between the seat and the occupant continuously collects real-time pressure distribution data of the occupant acting on various areas of the seat at a set sampling frequency. This pressure distribution data not only reflects the spatial distribution characteristics of the occupant's weight on the seat cushion and backrest but also implicitly contains mechanical information about the occupant's current posture. The system processes and analyzes the collected raw pressure distribution data, combining it with the seat's own structural parameters (such as seat cushion tilt angle, backrest angle, etc.), and uses a mechanical model or data-driven model to infer the occupant's current three-dimensional sitting posture. The sitting posture includes at least parameters such as pelvic posture, spinal curvature, and relative trunk position. Thus, the system can obtain a quantitative assessment of the occupant's sitting posture solely through contact pressure sensing without adding additional non-contact sensors (such as image acquisition devices).

[0033] As one implementation method, a high-resolution flexible pressure sensor array can be embedded under the seat cushion and backrest cover to obtain a two-dimensional body pressure distribution map. Then, by integrating signals from seat track position sensors, backrest angle sensors, and other sources, a pre-trained machine learning model (such as a convolutional neural network) can be used to estimate the occupant's three-dimensional sitting posture information, such as pelvic angle, spinal curvature, and shoulder posture.

[0034] Step 103: Calculate the deviation between the actual pressure distribution and the initial target pressure distribution, and generate drive commands for multiple independent support force adjustment units based on the deviation; The control module compares the real-time collected actual pressure distribution data with the initial target pressure distribution data generated for the current occupant, region by region or point by point, calculating the difference between the two. This difference forms a deviation distribution map in space. Based on this deviation distribution map, the system determines the seat area that needs adjustment, the adjustment direction (e.g., increasing or decreasing support), and the adjustment range. Subsequently, the control module converts the deviation distribution map into execution parameters for multiple independent support force adjustment units according to a preset control strategy, generating corresponding drive commands. These independent support force adjustment units are distributed in different functional zones of the seat cushion and backrest. Each unit can be independently driven to change the local support force, support height, surface profile, or hardness characteristics of its area. By sending coordinated drive commands to these units, the system can gradually approximate the target pressure distribution in space from the actual pressure distribution.

[0035] As a specific implementation method, the difference ΔP between the actual body pressure and the target body pressure can be calculated, and according to the spatial pattern and amplitude of ΔP, inflation or deflation commands can be sent to the airbag array in different areas of the seat cushion and backrest, corresponding current signals can be applied to the electronically controlled memory material module, or stroke adjustment commands can be sent to the micro electric screw mechanism to drive the actuators to work together, thereby minimizing the pressure deviation.

[0036] Step 104: Dynamically adjust the support characteristics of each partition based on the driving command to make the actual pressure distribution converge to the target pressure distribution.

[0037] The drive commands generated by the control module are transmitted to multiple support force adjustment units distributed in different areas of the seat cushion and backrest. Each unit responds to the corresponding command and independently changes the local support characteristics of its area. These support characteristics include at least one or more of the following: the magnitude of the support force provided by the area, the spatial contour of the support surface, the stiffness or hardness of the local area, and the extension or retraction stroke of the support point. Through differentiated and dynamic adjustments to the support characteristics of different zones, the actual pressure distribution of the seat contact surface continuously changes in spatial shape, gradually approaching the pre-set target pressure distribution. This convergence process is a continuous closed-loop iterative process: the adjusted actual pressure distribution is re-acquired and compared with the target value; the next round of drive commands is generated based on the new deviation, until the deviation is controlled within a preset threshold range. Thus, the system can dynamically adapt to subtle differences in occupant body shape, real-time changes in sitting posture, and muscle fatigue or posture drift caused by prolonged sitting.

[0038] As a specific implementation method, the support firmness of the area can be increased by inflating the independent airbag below the ischial tuberosity of the seat cushion, while the airbag in the thigh area can be appropriately deflated to reduce the distal pressure. Alternatively, the lumbar support rod can be moved forward by a micro motor to fill the gap between the waist and the backrest, thereby causing the real-time body pressure distribution to continuously converge toward the target pressure distribution generated for the occupant.

[0039] In some embodiments, obtaining the occupant's basic body shape data and, based on the basic body shape data, calling a preset ergonomic model to generate an initial target pressure distribution corresponding to different body zones includes: The system receives the passenger's height and weight data through a user input interface or biometric system. Based on the height and weight data, the target pressure values ​​for different body zones are obtained by matching or interpolating the data in a preset ergonomic model database. The target pressure value is mapped to multiple functional zones of the seat cushion and backrest to generate the initial target pressure distribution. The system receives height and weight data actively input or automatically identified by the occupant through a human-machine interface located on the vehicle's central control screen, the side control panel of the seat, or linked to the vehicle's biometric system. For example, the occupant can input their height (in centimeters) and weight (in kilograms) via a touchscreen, or the system can automatically obtain these parameters through a weight sensor built into the seat in conjunction with a user identification module. Subsequently, the system uses the acquired height and weight data as a search index to perform matching or interpolation calculations in a pre-stored ergonomic model database within the controller. This database contains optimal target body pressure values ​​for each body zone for different height and weight percentiles (such as the 5th, 50th, and 95th percentiles), derived from extensive biomechanical research.

[0040] If the current occupant's height and weight perfectly match a standard model in the database, the corresponding zone target pressure value is directly retrieved. If not, the system uses a linear or nonlinear interpolation algorithm to calculate between adjacent percentile models, generating a zone target pressure value adapted to the current occupant's body type. The body zones include at least the ischial tuberosity zone and thigh zone corresponding to the seat cushion, and the lumbar zone, thoracic spine zone, and shoulder zone corresponding to the backrest. Each zone corresponds to a target pressure value or target pressure range. Finally, the system maps the calculated zone target pressure values ​​to coordinates according to the physical zone layout of the seat cushion and backrest, generating an initial target pressure distribution map covering the entire seat contact surface. This distribution map records the expected pressure target for each independent adjustment zone in the form of a two-dimensional grid or zone labels, serving as a benchmark for subsequent closed-loop adjustment.

[0041] In some embodiments, estimating the occupant's real-time sitting posture based on the actual pressure distribution includes: The actual pressure distribution is integrated with the macroscopic position data of the seat; The fused data is input into a machine learning-based sitting posture estimation model to obtain the occupant's pelvic angle, spinal curvature, and shoulder posture.

[0042] The system uses a high-resolution flexible pressure sensor array embedded under the seat cushion and backrest upholstery to collect real-time two-dimensional body pressure distribution data of the occupant acting on the seat surface at a preset sampling frequency (e.g., 10 to 50 times per second). This data is represented in the form of a gridded pressure value matrix. Simultaneously, the system acquires macroscopic position data of the seat, including at least the seat's fore-and-aft displacement output by the seat track fore-and-aft position sensor, the seat cushion's height from the ground output by the seat height sensor, and the backrest's tilt angle relative to the seat cushion output by the backrest angle sensor.

[0043] The aforementioned sensors can be implemented using conventional position detection elements such as Hall effect sensors, potentiometers, or rotary encoders. Subsequently, the system spatiotemporally fuses the real-time acquired pressure distribution matrix with the macroscopic position data of the seat to form a multi-dimensional feature vector or multi-channel input data. For example, seat position parameters can be concatenated with the pressure distribution matrix as an additional channel, or the pressure distribution matrix can be first processed through a convolutional layer to extract feature maps before being fused with the position feature vector. The fused data is then input into a pre-trained machine learning posture estimation model.

[0044] The model is preferably a convolutional neural network or a deep neural network, and its training process is based on a large amount of sample data labeled with real sitting posture parameters (including pelvic angle, spinal curvature, and shoulder posture). During operation, the model directly regresses and outputs the occupant's current three-dimensional sitting posture quantification values ​​based on the input fusion features: pelvic angle (e.g., the angle of pelvic tilt or posterior tilt relative to the horizontal plane, in degrees), spinal curvature (e.g., a quantification of lumbar lordosis or thoracic kyphosis), and shoulder posture (e.g., the height difference between the shoulders relative to the horizontal plane or the degree of scapular protraction). These output results serve as the basis for subsequent sitting posture health assessments.

[0045] In some embodiments, calculating the deviation between the actual pressure distribution and the initial target pressure distribution, and generating drive commands for multiple independent support force adjustment units based on the deviation, includes: Calculate the spatial distribution and amplitude of the pressure deviation between the real-time pressure distribution and the target pressure distribution; The target functional zones that need to be adjusted and their adjustment directions are determined based on the spatial distribution of the pressure deviation. Send a drive command to at least one support force adjustment unit within the target functional area.

[0046] First, the control module performs point-by-point or region-by-region differential calculations on the real-time acquired two-dimensional actual pressure distribution matrix and the initial target pressure distribution matrix to calculate the pressure deviation value in each pressure sampling point or each functional zone, thereby obtaining a spatial distribution map of the pressure deviation and statistically analyzing the deviation amplitude (e.g., maximum deviation value, average deviation value, or deviation integral value) in each region.

[0047] The spatial distribution map of the deviation indicates which areas have actual pressure higher than the target value (overpressure areas) and which areas have actual pressure lower than the target value (underpressure areas). Subsequently, based on the spatial distribution map of the deviation and the functional zoning definitions of the seat cushion and backrest (such as the ischial tuberosity area, thigh area, lumbar area, thoracic spine area, scapular area, etc.), the system determines the target functional zone that needs adjustment. For example, if the deviation distribution map shows that the actual pressure in the ischial tuberosity area of ​​the seat cushion is significantly lower than the target value, it is determined that this area needs increased support; if the actual pressure in the lumbar area of ​​the backrest is higher than the target value, it is determined that this area needs reduced support.

[0048] After determining the target functional zone and its required adjustment direction (increasing or decreasing support), the system generates corresponding drive commands based on the type of support force adjustment unit configured within that zone. Taking a zone equipped with a miniature air pump and an independent airbag array as an example, if increased support is required, an inflation command is generated for the airbags in that zone, and the inflation time or target air pressure value is calculated based on the deviation amplitude; if decreased support is required, a deflation command is generated.

[0049] For zones equipped with electrically controlled memory materials (such as shape memory alloy springs), the system generates current signals of corresponding amplitude to change the local stiffness of that area. For zones equipped with miniature electric lead screws or worm gear mechanisms (such as lumbar support points), the system generates motor drive commands to control the push rod to advance or retract a specific stroke distance. These drive commands can be sent to a single type of actuator within the same zone, or they can be sent collaboratively to multiple types of actuators in multiple zones to achieve multi-point synchronous adjustment.

[0050] In some embodiments, the method further includes: Record the manual adjustment operations performed by the user on the basis of automatic adjustment, and update the personalized adaptation model corresponding to the current user based on the recorded manual adjustment operations; When the identification result is the user, the personalized adaptation model is invoked to generate the initial target pressure distribution.

[0051] During automatic adjustment mode, if an occupant is dissatisfied with the current seat support and performs a manual adjustment via a human-machine interface (such as the firmness adjustment slider on the central touchscreen, physical buttons on the side of the seat, or the in-vehicle voice control system), the system will record the specific details of the manual adjustment. The manual adjustment includes at least one or more of the following types: requests to increase or decrease support in a specific functional area (such as the lumbar support area or the thigh area of ​​the seat cushion), fine-tuning the fore-and-aft travel of the lumbar support point, adjusting the clamping force of the lateral airbags, or making localized corrections to the overall seat cushion tilt angle. While recording, the system simultaneously captures the occupant's identity at the current moment (e.g., through user ID selection, biometric recognition, or association with the seat memory button), as well as the operating conditions corresponding to the manual adjustment (such as driving duration, vehicle speed, road conditions, etc.).

[0052] The system converts the aforementioned manual adjustments into corrections to the target pressure distribution parameters in the user's existing personalized adaptation model. Specifically, the personalized adaptation model uses a basic ergonomic model as a base, with an additional layer of user-specific offset parameters. When a user performs a manual adjustment, the system uses an incremental learning algorithm to update the user's offset parameters: for example, if the user manually increases the stiffness of the lumbar support area, the system will increase the current target pressure value in the lumbar area by a preset step size or increase it according to the user's input ratio, and record this correction in the user's personalized adaptation model.

[0053] The model is stored in the controller's non-volatile memory and associated with the user ID. When the system subsequently identifies the same occupant again (e.g., through facial recognition, fingerprint recognition, key recognition, or manual ID selection by the user), the controller prioritizes calling that user's personalized adaptation model, using its corrected zone target pressure values ​​as the basis for generating the initial target pressure distribution, rather than recalculating using the basic ergonomic model. If the user performs manual fine-tuning again during this usage, the system continues to update the user's personalized adaptation model based on the previous correction, thereby achieving continuous iterative optimization.

[0054] In some embodiments, the method further includes: When it is determined that the real-time sitting posture deviates from the preset healthy sitting posture model, a correction target pressure distribution is generated; The drive command is updated based on the target pressure distribution to guide the occupant back to a healthy sitting posture.

[0055] The healthy sitting posture model defines reference values ​​for a neutral pelvic position (e.g., anterior pelvic tilt angle of 5° to 15°), a natural lumbar lordosis curvature range, and slight thoracic kyphosis, all conforming to biomechanical optimal principles. When the system determines that a certain sitting posture parameter continuously exceeds the threshold range defined by the health model for a preset duration (e.g., continuously for 30 seconds), such as detecting a posterior pelvic tilt angle greater than 20° and a significant increase in thoracic kyphosis curvature, the system determines that the occupant is in a poor "hunchback" sitting posture. In this case, the system does not directly and drastically adjust the seat contour, but instead generates a corrective target pressure distribution.

[0056] The corrective target pressure distribution is calculated based on the current target pressure distribution and the biomechanical guidance strategy for healthy sitting posture. For example, to guide anterior pelvic tilt and spinal extension, the system appropriately increases the target pressure value in the ischial tuberosity area to provide a more stable support base. Simultaneously, it increases the target pressure value in the lower lumbar region by a preset step size compared to the comfort target value and also moderately increases the target pressure value in the upper thoracic region, forming a gentle "pushing" force distribution that induces the occupant's lumbar lordosis to recover and the thoracic spine to extend backward. After generating the corrective target pressure distribution, the system updates the drive commands in a progressive manner. Specifically, the control module does not directly switch the current target pressure distribution to the corrective target pressure distribution. Instead, within a preset time window (e.g., 5 to 30 seconds), it gradually transitions the target pressure distribution used for each closed-loop adjustment from the comfort target to the corrective target through linear interpolation or exponential smoothing algorithms. During this process, the execution layer generates drive commands based on the intermediate target pressure distribution at each moment, causing a slow and continuous change in the seat's support contour and local firmness. Occupants will feel the seat gently "pushing" their lower back and upper back, thus unconsciously adjusting their posture to seek a new balance. Once the real-time sitting posture parameters fall back into the health model threshold range and remain stable, the system can automatically switch the target pressure distribution back to the initial target pressure distribution in the comfort adjustment mode, or maintain the corrected posture as the new comfort benchmark.

[0057] In some embodiments, generating a correction target pressure distribution when it is determined that the real-time sitting posture deviates from a preset healthy sitting posture model includes: The estimated real-time sitting posture is compared with a standard healthy sitting posture model to calculate the posture deviation. When the posture deviation exceeds a preset threshold, a corrective target pressure distribution that is different from the initial target pressure distribution is generated. This corrective target pressure distribution is configured to guide the occupant's spine to extend toward a standard healthy sitting posture by adjusting the support force of each zone. The current target pressure distribution is smoothly transitioned from the initial target pressure distribution to the corrected target pressure distribution, and the drive command is updated according to the corrected target pressure distribution.

[0058] The estimated real-time occupant posture parameters (including pelvic angle θ_pelvis, lumbar curvature κ_lumbar, thoracic curvature κ_thoracic, and shoulder height difference Δh_shoulder, etc.) are compared item by item with the standard healthy sitting posture model pre-stored in the controller. The standard healthy sitting posture model defines the ideal range of each parameter, such as the pelvic angle range of 5° to 15° forward tilt corresponding to the neutral pelvic position, the reference value of the natural lumbar lordosis curvature of 0.25 to 0.35 rad / m, and the reference value of the thoracic kyphosis curvature of 0.15 to 0.25 rad / m, etc.

[0059] The system calculates the postural deviation between the real-time sitting posture and the health model. This deviation can be quantified using weighted Euclidean distance or a normalized weighted sum of the deviations of each parameter, for example, D = w1·|θ_pelvis - θ_target| + w2·|κ_lumbar - κ_lumbar_target| + w3·|κ_thoracic - κ_thoracic_target|. When the calculated postural deviation D exceeds a preset threshold D_th (e.g., D>0.3, the threshold can be calibrated based on clinical biomechanical data) and the duration exceeds a preset time window (e.g., 10 seconds), the system determines that active sitting posture correction needs to be initiated.

[0060] The system then generates a corrective target pressure distribution that differs from the initial comfort target pressure distribution. This corrective target pressure distribution is configured to guide the occupant's spine toward a standard healthy sitting posture by adjusting the support force in specific functional zones. For example, for a typical "posterior pelvic tilt with excessive thoracic kyphosis" (hunchback) posture, the corrective target pressure distribution increases the target pressure value in the ischial tuberosity zone from the initial 10 kPa to 12 kPa to provide a more stable pelvic support base, increases the target pressure value in the lower lumbar region (corresponding to L4-L5 segments) from the initial 8 kPa to 11 kPa to generate a forward pushing torque on the lumbar spine, and simultaneously increases the target pressure value in the upper thoracic region (corresponding to T5-T8 segments) from the initial 5 kPa to 8 kPa to guide the upper back to extend backward.

[0061] The adjustment range of the aforementioned target values ​​is proportional to the posture deviation D; the larger the deviation, the larger the adjustment step size. Finally, to avoid sudden changes in support causing occupant discomfort, the system smoothly transitions the target pressure distribution upon which the current closed-loop adjustment is based from the initial target pressure distribution to the corrected target pressure distribution. This smooth transition is achieved within a preset transition time window T_trans (e.g., 15 to 30 seconds) using the linear interpolation formula P_target(t) = (1-α)·P_initial+ α·P_correction, where α increases linearly from 0 to 1. During this transition, the system updates the drive commands sent to each actuator in real time according to the intermediate target pressure distribution at each moment, causing a slow and continuous change in the seat contour and local support force, thereby inducing the occupant's posture to gradually return to a healthy standard without their awareness.

[0062] Corresponding to the control method for the intelligent health seat described above, this invention also proposes a control device for the intelligent health seat. Since the device embodiment of this invention corresponds to the method embodiment described above, details not disclosed in the device embodiment can be referred to in the method embodiment described above, and will not be repeated here.

[0063] Figure 2 This is a schematic diagram of the structure of a control device for an intelligent health chair provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, it includes: The acquisition unit 21 is used to acquire the basic body shape data of the occupants, and based on the basic body shape data, call the preset ergonomic model to generate the initial target pressure distribution corresponding to different body zones. The first calculation unit 22 is used to collect the actual pressure distribution of the occupant in real time through a sensor array set on the seat contact surface, and estimate the occupant's real-time sitting posture based on the actual pressure distribution. The second calculation unit 23 is used to calculate the deviation between the actual pressure distribution and the initial target pressure distribution, and generate drive commands for multiple independent support force adjustment units based on the deviation. The adjustment unit 24 is used to dynamically adjust the support characteristics of each partition based on the driving command so that the actual pressure distribution converges to the target pressure distribution.

[0064] Furthermore, in one possible implementation of this disclosure, the acquisition unit 21 is further configured to: The system receives the passenger's height and weight data through a user input interface or biometric system. Based on the height and weight data, the target pressure values ​​for different body zones are obtained by matching or interpolating the data in a preset ergonomic model database. The target pressure value is mapped to multiple functional zones of the seat cushion and backrest to generate the initial target pressure distribution.

[0065] Furthermore, in one possible implementation of this disclosure embodiment, the first computing unit 22 is further configured to: The actual pressure distribution is integrated with the macroscopic position data of the seat; The fused data is input into a machine learning-based sitting posture estimation model to obtain the occupant's pelvic angle, spinal curvature, and shoulder posture.

[0066] Furthermore, in one possible implementation of this embodiment, the second computing unit 23 is further configured to: Calculate the spatial distribution and amplitude of the pressure deviation between the real-time pressure distribution and the target pressure distribution; The target functional zones that need to be adjusted and their adjustment directions are determined based on the spatial distribution of the pressure deviation. Send a drive command to at least one support force adjustment unit within the target functional area.

[0067] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 3 As shown, the device further includes: The recording unit 25 is used to record the manual adjustment operations performed by the user on the basis of automatic adjustment, and to update the personalized adaptation model corresponding to the current user based on the recorded manual adjustment operations. The first generation unit 26 is used to call the personalized adaptation model to generate an initial target pressure distribution in response to the recognition result being the user.

[0068] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 3 As shown, the device further includes: The second generation unit 27 is used to generate a correction target pressure distribution when it is determined that the real-time sitting posture deviates from the preset healthy sitting posture model. The updating unit 28 is used to update the driving command based on the correction target pressure distribution to guide the occupant back to a healthy sitting posture.

[0069] Furthermore, in one possible implementation of this disclosure embodiment, the second generating unit 27 is further configured to: The estimated real-time sitting posture is compared with a standard healthy sitting posture model to calculate the posture deviation. When the posture deviation exceeds a preset threshold, a corrective target pressure distribution that is different from the initial target pressure distribution is generated; wherein, the corrective target pressure distribution is configured to guide the occupant's spine to extend toward a standard healthy sitting posture by adjusting the support force of each zone; The current target pressure distribution is smoothly transitioned from the initial target pressure distribution to the corrected target pressure distribution, and the drive command is updated according to the corrected target pressure distribution.

[0070] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this disclosure, and the principle is the same. Therefore, the embodiments of this disclosure are not limited thereto.

[0071] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0072] Figure 4A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. 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 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, 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 disclosure described and / or claimed herein.

[0073] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.

[0074] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0075] The computing unit 401 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the control method for a smart health seat. For example, in some embodiments, the control method for a smart health seat may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned control method for the smart health seat by any other suitable means (e.g., by means of firmware).

[0076] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0077] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0078] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0079] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0080] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0081] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0082] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0083] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0084] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. 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 principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A control method for an intelligent health seat, characterized in that, include: Acquire basic body shape data of the occupants, and based on the basic body shape data, call the preset ergonomic model to generate initial target pressure distribution corresponding to different body zones; The actual pressure distribution of the occupant is collected in real time by a sensor array set on the seat contact surface, and the occupant's real-time sitting posture is estimated based on the actual pressure distribution. Calculate the deviation between the actual pressure distribution and the initial target pressure distribution, and generate drive commands for multiple independent support force adjustment units based on the deviation; Based on the driving instructions, the support characteristics of each partition are dynamically adjusted to make the actual pressure distribution converge towards the target pressure distribution.

2. The method according to claim 1, characterized in that, The step of acquiring the occupant's basic body shape data and, based on the basic body shape data, calling a preset ergonomic model to generate an initial target pressure distribution corresponding to different body zones includes: The system receives the passenger's height and weight data through a user input interface or biometric system. Based on the height and weight data, the target pressure values ​​for different body zones are obtained by matching or interpolating the data in a preset ergonomic model database. The target pressure value is mapped to multiple functional zones of the seat cushion and backrest to generate the initial target pressure distribution.

3. The method according to claim 1, characterized in that, The estimation of the occupant's real-time sitting posture based on the actual pressure distribution includes: The actual pressure distribution is integrated with the macroscopic position data of the seat; The fused data is input into a machine learning-based sitting posture estimation model to obtain the occupant's pelvic angle, spinal curvature, and shoulder posture.

4. The method according to claim 1, characterized in that, The step of calculating the deviation between the actual pressure distribution and the initial target pressure distribution, and generating drive commands for multiple independent support force adjustment units based on the deviation, includes: Calculate the spatial distribution and amplitude of the pressure deviation between the real-time pressure distribution and the target pressure distribution; The target functional zones that need to be adjusted and their adjustment directions are determined based on the spatial distribution of the pressure deviation. Send a drive command to at least one support force adjustment unit within the target functional area.

5. The method according to claim 1, characterized in that, The method further includes: Record the manual adjustment operations performed by the user on the basis of automatic adjustment, and update the personalized adaptation model corresponding to the current user based on the recorded manual adjustment operations; When the identification result is the user, the personalized adaptation model is invoked to generate an initial target pressure distribution.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: When it is determined that the real-time sitting posture deviates from the preset healthy sitting posture model, a correction target pressure distribution is generated; The drive command is updated based on the target pressure distribution to guide the occupant back to a healthy sitting posture.

7. The method according to claim 6, characterized in that, When it is determined that the real-time sitting posture deviates from the preset healthy sitting posture model, the generation of the correction target pressure distribution includes: The estimated real-time sitting posture is compared with a standard healthy sitting posture model to calculate the posture deviation. When the posture deviation exceeds a preset threshold, a corrective target pressure distribution that is different from the initial target pressure distribution is generated; wherein, the corrective target pressure distribution is configured to guide the occupant's spine to extend toward a standard healthy sitting posture by adjusting the support force of each zone; The current target pressure distribution is smoothly transitioned from the initial target pressure distribution to the corrected target pressure distribution, and the drive command is updated according to the corrected target pressure distribution.

8. A control device for an intelligent health seat, characterized in that, include: The acquisition unit is used to acquire the basic body shape data of the occupants, and based on the basic body shape data, call the preset ergonomic model to generate the initial target pressure distribution corresponding to different body zones. The first calculation unit is used to collect the actual pressure distribution of the occupant in real time through a sensor array set on the seat contact surface, and estimate the occupant's real-time sitting posture based on the actual pressure distribution. The second calculation unit is used to calculate the deviation between the actual pressure distribution and the initial target pressure distribution, and to generate drive commands for multiple independent support force adjustment units based on the deviation. The adjustment unit is used to dynamically adjust the support characteristics of each partition based on the driving command so that the actual pressure distribution converges to the target pressure distribution.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

Images