Seat adjustment method, device and vehicle

Abstract

The present application relates to the technical field of vehicle, disclose a seat adjustment method, device and vehicle, the seat adjustment method, including: collecting the human body posture parameter of the driver and passenger, based on the deviation value of the human body posture parameter and the standard posture parameter, determine the risk level of the current sitting posture of the driver and passenger and the associated risk type, according to the risk level matching trigger corresponding sitting posture prompting mode, the driver and passenger are reminded of sitting posture, based on the feedback result of the driver and passenger to the sitting posture prompting mode, combined with the deviation value and the risk type, the seat is adjusted, the present application can dynamically respond to the posture change demand in the driving process, timely correct the bad sitting posture, ensure the driving safety.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and more specifically to seat adjustment methods, devices, and vehicles. Background Technology

[0002] As the core interface between drivers and passengers and the vehicle, the comfort and support performance of car seats directly affect the quality of the driving experience and the guarantee of driving safety. However, most seat adjustment functions in related technologies rely on fixed preset modes or roughly estimated human body parameters, making it difficult to adapt to the personalized body characteristics and dynamic driving scenarios of different drivers and passengers. Summary of the Invention

[0003] This invention provides a seat adjustment method, device, and vehicle to solve the problem that most seat adjustment functions in related technologies rely on fixed preset modes or roughly estimated human body parameters, making it difficult to adapt to the personalized body characteristics of different drivers and passengers, and also failing to meet the needs of dynamic driving scenarios.

[0004] In a first aspect, the present invention provides a seat adjustment method, comprising: collecting human posture parameters of a driver or passenger; determining the risk level and associated risk type of the driver or passenger's current sitting posture based on the deviation value between the human posture parameters and standard posture parameters; triggering a corresponding sitting posture reminder method according to the risk level to remind the driver or passenger of their sitting posture; and adjusting the seat based on the feedback results of the driver or passenger regarding the sitting posture reminder method, combined with the deviation value and risk type.

[0005] The seat adjustment method provided by this invention can accurately identify the individual body characteristics and risk status of different drivers and passengers by collecting their human posture parameters and analyzing their deviation from standard posture parameters. This achieves effective adaptation to individual differences among drivers and passengers. At the same time, based on the risk level, corresponding reminders are triggered, and the seat is adjusted according to the feedback from drivers and passengers, combined with the deviation value and risk type. This can dynamically respond to the needs of posture changes during driving, correct poor posture in a timely manner, reduce fatigue and safety hazards caused by improper posture, significantly improve the comfort and support performance of the seat, thereby optimizing the overall driving experience and ensuring driving safety.

[0006] In one optional implementation, the risk level and associated risk type of the driver's current sitting posture are determined based on the deviation values ​​between the human posture parameters and the standard posture parameters. This includes: calculating the deviation values ​​between each parameter in the human posture parameters and the corresponding standard posture parameters; calculating the corresponding sitting posture risk score based on the deviation values; comparing the sitting posture risk score with a preset risk threshold to determine the risk level of the current sitting posture; and determining the risk type of the current sitting posture based on the human body part corresponding to each deviation value, the deviation direction, and the sitting posture risk score.

[0007] The seat adjustment method provided by this invention achieves a refined and quantitative assessment of sitting posture risks by calculating the deviation values ​​of various parameters of human posture from standard parameters in multiple dimensions. By comparing the sitting posture risk score with a preset threshold to determine the risk level, it provides a clear basis for triggering reminders of different intensities and seat adjustments. By combining the human body parts, directions, and risk scores corresponding to the deviations to determine the risk type, it can accurately locate the root cause of sitting posture problems, such as insufficient lumbar support, forward head posture, and other specific risk points, making subsequent seat adjustments more targeted, effectively improving the efficiency and accuracy of sitting posture correction, and further ensuring the physical comfort and driving safety of drivers and passengers.

[0008] In one optional implementation, the deviation values ​​between each parameter in the human posture parameters and the corresponding standard posture parameters are calculated, including: obtaining the posture point set of each part in the human posture parameters and determining the centroid of the posture point set; performing a decentralization process on the posture point set based on the centroid of the point set to obtain a posture processing point set; matching and aligning the posture processing point set with the standard posture point set corresponding to the standard posture parameters, and calculating the deviation value between each human posture parameter and the corresponding standard posture parameter.

[0009] The seat adjustment method provided by this invention effectively eliminates the interference of individual height and body shape differences of drivers and passengers on the comparison of posture parameters by calculating the centroid of the posture point set and decentralizing it, thereby improving the universality of deviation value calculation. By matching and aligning the processed posture point set with the standard point set, it ensures the accurate correspondence of each parameter dimension and avoids deviation calculation errors caused by point set misalignment, thus making the subsequent sitting posture risk assessment results more reliable and accurate.

[0010] In one optional implementation, a corresponding posture reminder method is triggered according to the risk level to remind the driver and passengers of their posture. This includes: matching the corresponding reminder level from a preset reminder strategy library according to the risk level; and reminding the driver and passengers of their posture according to the posture reminder method corresponding to the reminder level. The posture reminder method includes at least one of the following: voice prompt, interface pop-up, instrument light warning, and seat vibration.

[0011] The seat adjustment method provided by this invention precisely matches the risk level with the alert level, avoiding the interference caused to drivers and passengers by excessive alerts in low-risk scenarios, while ensuring the effective delivery of alert information in high-risk scenarios. At the same time, the multimodal alert method can adapt to different driving scenarios and human habits. For example, when driving at high speed, seat vibration or instrument light warnings can convey risk signals without distracting attention, while at low speeds or when parked, voice prompts or interface pop-ups can more clearly provide specific posture adjustment suggestions, thereby improving the pertinence and effectiveness of the alerts and further protecting the posture health and driving safety of drivers and passengers.

[0012] In one optional implementation, the seat is adjusted based on the feedback from the driver / passenger regarding the posture reminder method, combined with the deviation value and risk type. This includes: if the feedback indicates that the driver / passenger confirms the adjustment, then a seat adjustment command is generated and the seat position and posture are adjusted according to the risk type and the corresponding deviation value.

[0013] The seat adjustment method provided by this invention combines the active feedback of drivers and passengers with specific risk types and deviation values ​​to adjust the seat. This fully respects the subjective wishes of drivers and passengers while ensuring the accuracy and relevance of the adjustment. The automated seat adjustment operation eliminates the need for manual adjustment by drivers and passengers, effectively preventing distraction during driving and further improving driving safety. At the same time, the personalized adjustment scheme based on risk type and deviation value can better fit the physical characteristics and current sitting posture of drivers and passengers, accurately correct poor sitting posture, continuously optimize driving comfort and physical health, and provide drivers and passengers with a more intelligent and considerate seat adjustment experience.

[0014] In one optional implementation, a seat adjustment command is generated and the seat position and posture are adjusted according to the risk type and the corresponding deviation value. This includes: matching the corresponding adjustment target based on the risk type, and calculating the target adjustment amount of each adjustment component of the seat based on the deviation value; generating a seat adjustment command based on the adjustment target and the target adjustment amount, wherein the seat adjustment command includes at least one of the following: seat fore-aft position, height position, backrest angle, lumbar support, and headrest position; and driving the seat actuator to complete the adjustment of the seat position and posture according to the adjustment command, so that the seating posture of the driver and passenger returns to a safe and comfortable range.

[0015] The seat adjustment method provided by this invention ensures the scientific nature and accuracy of seat adjustment by precisely matching risk types and adjustment targets, and quantitatively calculating the adjustment amount of each adjustment component based on deviation values. Through multi-dimensional adjustment commands such as seat forward / backward movement, height, backrest angle, lumbar support, and headrest position, it comprehensively covers all aspects of driver and passenger posture issues, achieving all-round posture optimization. The adjustment is completed through an automatically driven actuator, avoiding the tediousness and safety hazards of manual operation by drivers and passengers, further improving the convenience of seat adjustment and driving safety. Ultimately, it allows drivers and passengers to quickly return to a safe and comfortable posture, effectively protecting physical health and riding experience during driving.

[0016] In an optional implementation, the method further includes: if the feedback result indicates that the driver or passenger refuses to adjust or ignores the reminder, then continuously monitor the human posture parameters and determine the risk level within a preset time period; if the risk level within the preset time period does not decrease or continues to increase, then upgrade the reminder level and trigger the reminder again; if the risk level within the preset time period drops below the safety threshold, then stop the active reminder for the current period.

[0017] The seat adjustment method provided by this invention achieves a balance between intelligence and humanization in seat adjustment reminders by setting up a feedback response mechanism and a dynamic risk monitoring process. When the driver or passenger is temporarily unable to cooperate with the adjustment, the method does not force the adjustment but continuously tracks changes in posture risk, respecting the driver's and passenger's immediate operational needs while avoiding risk accumulation due to negligence. Dynamic assessment of risk levels determines whether to escalate the reminder, ensuring timely attention to high-risk situations without causing excessive disturbance. By automatically stopping the reminder when the risk decreases to a safe threshold, unnecessary interference is effectively reduced, improving the comfort of the driving and riding experience.

[0018] In an optional implementation, the method further includes: if no feedback from the driver or passenger regarding the posture reminder method is received within a preset time or the risk level is not reduced, then the current reminder stage is obtained, and corresponding graded intervention is performed. The graded intervention includes at least one of the following: automatic fine-tuning, safety baseline adjustment, and emergency call.

[0019] The seat adjustment method provided by this invention slightly optimizes the seating posture to mitigate risks through automatic fine-tuning without interfering with the normal operation of the driver and passengers; it quickly adjusts the seat to a safe-verified standard posture when risks continue to accumulate through safety benchmark adjustment, effectively preventing the risk from escalating; and it promptly connects to external assistance in extremely dangerous situations through an emergency call function, providing life safety protection for the driver and passengers. This layered and progressive intervention strategy avoids the limitations of a single intervention method and ensures that each level of intervention matches the degree of risk, further enhancing the emergency response capability and safety protection level of seat adjustment, making driver and passenger safety protection more layered and comprehensive.

[0020] In a second aspect, the present invention provides a seat adjustment device, comprising: The parameter acquisition module collects the human posture parameters of drivers and passengers. The risk assessment module is used to determine the risk level and associated risk type of the driver and passengers' current sitting posture based on the deviation value between human posture parameters and standard posture parameters. The posture reminder module is used to match and trigger the corresponding posture reminder method according to the risk level to remind drivers and passengers of their posture. The seat adjustment module is used to adjust the seat based on feedback from drivers and passengers regarding the posture reminder method, combined with deviation values ​​and risk types.

[0021] Thirdly, the present invention provides a vehicle comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the seat adjustment method of the first aspect or any corresponding embodiment described above.

[0022] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the seat adjustment method of the first aspect or any corresponding embodiment thereof.

[0023] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the seat adjustment method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0024] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 This is a schematic flowchart of a first embodiment of a seat adjustment method according to the present invention; Figure 2 This is a schematic diagram of a second process for a seat adjustment method according to an embodiment of the present invention; Figure 3 This is a structural block diagram of a seat adjustment device according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the hardware structure of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0028] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0029] According to an embodiment of the present invention, a seat adjustment method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] This embodiment provides a seat adjustment method. Figure 1 This is a flowchart of a seat adjustment method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step S101: Collect the human posture parameters of the driver and passengers.

[0031] Among them, the human posture parameters include at least one of the posture angles, spatial positions and relative distances of the driver's head, chest, shoulders, elbows and body center of gravity.

[0032] In some optional implementations, when collecting the human posture parameters of drivers and passengers, vehicle-mounted millimeter-wave radar can be used to transmit detection signals and receive echo signals. The three-dimensional point cloud data of each body part of the driver and passengers can be obtained by processing and analyzing the echo signals. Furthermore, feature points of each body part are extracted to construct a posture point set, and human posture parameters such as head orientation angle, chest-steering wheel distance, shoulder forward tilt, elbow joint angle, and body center of gravity coordinates are determined based on the posture point set.

[0033] Specifically, vehicle-mounted millimeter-wave radar can be deployed in locations such as the A-pillar, dashboard, rearview mirror, ceiling, or seat back to continuously scan occupants in a non-contact, wearable manner. By performing point cloud clustering, feature extraction, and attitude estimation on the radar echo signals, it can accurately obtain the three-dimensional spatial coordinates and attitude angles of the occupants' head, chest, shoulders, elbows, and center of gravity, thereby generating human posture parameters for risk assessment.

[0034] Step S102: Based on the deviation between human posture parameters and standard posture parameters, determine the risk level and associated risk type of the driver's current sitting posture.

[0035] Among them, the standard posture parameters are the posture data of a standard human model constructed based on the target population's human proportion database in a preset safe sitting posture, including the standard position, standard angle and standard relative distance of the head, chest, shoulders, elbow joints and body center of gravity.

[0036] In some optional implementations, when determining the risk level and associated risk type of the driver's current sitting posture based on the deviation values ​​between the human posture parameters and the standard posture parameters, the deviation values ​​between each parameter in the human posture parameters and the corresponding standard posture parameters can be calculated separately; the corresponding sitting posture risk score can be calculated based on the deviation values, and the sitting posture risk score can be compared with a preset risk threshold to determine the risk level of the current sitting posture; the risk type of the current sitting posture can be determined according to the human body part corresponding to each deviation value, the deviation direction, and the sitting posture risk score.

[0037] Specifically, human posture parameters include the relative distance / angle between the head and headrest, the distance between the chest and the center of the steering wheel, the contact state between the shoulder and the backrest, the elbow angle, and the lateral offset of the body's center of gravity (spine, pelvis, thigh, calf, and feet). The deviation values ​​of each parameter from the corresponding standard posture parameters are calculated. Specifically, a whiplash risk score is calculated based on the deviation of the relative distance / angle between the head and headrest; a lying-down risk score is calculated based on the deviation of the distance between the chest and the center of the steering wheel and the elbow angle; an abdominal collision risk score is calculated based on the deviation of the distance between the chest and the center of the steering wheel, the elbow angle, the contact state between the shoulder and the backrest (shoulder forward tilt deviation), and the lateral offset of the body's center of gravity; an embracing risk score is calculated based on the deviation of the distance between the chest and the center of the steering wheel and the shoulder forward tilt deviation; and a lateral offset of the body's center of gravity is calculated based on the deviation of the distance between the chest and the center of the steering wheel and the shoulder forward tilt deviation. The risk score for incorrect sitting posture is calculated by angular deviation. The risk scores are weighted and summed to obtain a comprehensive sitting posture risk score, which is then compared with preset thresholds (0-25, 26-50, 51-75, 76-100) to classify the risk into four levels: low risk (Level 1), medium risk (Level 2), high risk (Level 3), and extremely high risk (Level 4). At the same time, based on the body part, deviation direction, and triggered risk score item corresponding to each deviation value, a preset risk type library is matched to determine the associated risk types such as whiplash injury, abdominal collision, lying down, hugging, and incorrect sitting posture corresponding to the current sitting posture.

[0038] As an example, suppose a driver or passenger, while in motion, is found to have a significantly smaller distance between their chest and the center of the steering wheel than the standard posture parameters, accompanied by excessive forward shoulder tilt, excessive elbow bending, and a noticeable forward shift in their center of gravity. This results in a high abdominal collision risk score and a high hugging posture risk score, while other risk scores fall within the normal range. The weighted sum of these risk scores yields a comprehensive sitting posture risk score of 68, falling within the preset threshold range of 51–75. Therefore, the current sitting posture risk level is determined to be Level 3, high risk. Furthermore, based on the body part corresponding to the deviation, the direction of the deviation, and the triggered risk score item, and after matching with a risk type database, it is determined that the current sitting posture carries both abdominal collision risk and hugging posture risk.

[0039] As another example, when it is detected that the distance between the driver / passenger's chest and the center of the steering wheel is significantly smaller than expected, the elbows are excessively bent, the shoulders are noticeably leaning forward, and the body's center of gravity is shifted towards the center of the cabin, calculations show that the deviations in chest distance, elbow angle, shoulder lean, and body center of gravity all exceed the safety thresholds. Based on these deviations, high risk scores are obtained for the lying-down posture, abdominal collision, and embracing posture. After weighted summation, the overall sitting posture risk score falls within the preset threshold range of 51–75, and is judged as Level 3 high risk. According to the body parts corresponding to each deviation, the direction of the deviation, and the risk score items triggered, a risk type library is matched to determine that the current driver / passenger's sitting posture simultaneously carries risks of abdominal collision, embracing posture, and lying-down posture.

[0040] As shown above, by calculating the deviation values ​​of various parameters of human posture from standard parameters in different dimensions, a refined and quantitative assessment of sitting posture risk is achieved. By comparing the sitting posture risk score with preset thresholds to determine the risk level, a clear basis is provided for triggering reminders of different intensities and adjusting the seat accordingly. By combining the body parts, directions, and risk scores corresponding to the deviations to determine the risk type, the root cause of sitting posture problems can be accurately located, such as insufficient lumbar support, forward head posture, and other specific risk points. This makes subsequent seat adjustments more targeted, effectively improving the efficiency and accuracy of sitting posture correction, and further ensuring the physical comfort and driving safety of drivers and passengers.

[0041] In some optional implementations, when calculating the deviation between each parameter in the human posture parameters and the corresponding standard posture parameters, the posture point set of each part in the human posture parameters can be obtained, and the centroid of the posture point set can be determined; the posture point set can be decentralized based on the centroid of the point set to obtain the posture processing point set; the posture processing point set can be matched and aligned with the standard posture point set corresponding to the standard posture parameters, and the deviation between each human posture parameter and the corresponding standard posture parameter can be calculated.

[0042] Specifically, a three-dimensional posture point set of the driver and passengers, including the head, chest, shoulders, elbows, torso, and lower limbs, can be collected by an in-vehicle millimeter-wave radar. The centroid of the entire point set is calculated based on the spatial coordinates of each posture point set. Using this centroid as a reference, all posture points are translated to achieve decentralization and eliminate the influence of positional offset, resulting in a posture processing point set. Then, the posture processing point set is rotated and optimally aligned with the standard posture point set corresponding to the preset standard posture parameters using a singular value decomposition algorithm. Based on the differences in the aligned points, the deviation values ​​of each human posture parameter, such as the distance and angle between the head and headrest, the distance between the chest and the steering wheel, the forward tilt of the shoulders, the elbow angle, and the lateral offset of the body's center of gravity, are calculated from the corresponding standard posture parameters.

[0043] In practice, the three-dimensional pose point set of various parts of the driver and passengers collected by the vehicle-mounted millimeter-wave radar is first used as the source point set P, and the standard pose point set corresponding to the parameterized standard human body model that conforms to the standard and covers different genders, heights, and percentiles is used as the target point set Q. The centroids of the source point set P and the target point set Q are calculated respectively. , The source set's centroid:

[0044] centroid of target point set Calculate in the same way; perform decentralization processing on the source and target point sets based on the centroids to obtain the centralized source point set P′. centered With the target point set Q′ centered , , ,in, The first point after centralization of the source point set i Three-dimensional attitude points of each part, For the first point in the source set i Three-dimensional attitude points of each part, The first point after centering the target point set i Three-dimensional attitude points of each part, For the first target point in the set i Three-dimensional attitude points of each part.

[0045] Subsequently, the covariance matrix is ​​constructed and the optimal rotation matrix R and translation vector T are solved by singular value decomposition to achieve optimal rigid registration between the source point set and the target point set. Finally, based on the spatial position difference of the registered point set, the deviation values ​​of various human posture parameters such as head-headrest distance / angle, chest-steering wheel distance, shoulder forward tilt, elbow joint angle, and body center of gravity offset are calculated from the corresponding standard posture parameters.

[0046] As shown above, by calculating the centroid of the posture point set and decentralizing it, the interference of individual height and body shape differences of drivers and passengers on the comparison of posture parameters is effectively eliminated, and the universality of deviation value calculation is improved. By matching and aligning the processed posture point set with the standard point set, the accurate correspondence of each parameter dimension is ensured, and deviation calculation errors caused by point set misalignment are avoided, thereby making the subsequent sitting posture risk assessment results more reliable and accurate.

[0047] Step S103: Match the corresponding posture reminder method according to the risk level to remind the driver and passengers of their posture.

[0048] The posture reminder methods include, but are not limited to, voice prompts, interface pop-ups, instrument light warnings, and seat vibration.

[0049] In some optional implementations, when triggering the corresponding posture reminder method according to the risk level to remind the driver and passengers of their posture, the corresponding reminder level can be matched from the preset reminder strategy library according to the risk level; and the driver and passengers can be reminded according to the posture reminder method corresponding to the reminder level.

[0050] Specifically, when the risk level is Level 1 (low risk, CRS 0-25), a mild reminder level is matched, triggering at least one of the following: a flashing pale yellow icon on the dashboard, a gentle alert sound, or a single slight vibration of the seat. This provides only a mild reminder without mandatory intervention and continuous monitoring is performed. When the risk level is Level 2 (medium risk, CRS 26-50), an enhanced reminder level is matched, triggering at least one of the following: a highlighted orange icon on the dashboard with text prompts, a rhythmic alert sound, three seat vibrations at 1-second intervals, or a slight increase in air conditioning vents. This prompts the driver and passengers to make immediate adjustments and a one-click optimization button pops up. When the risk level is Level 3 (high risk, CRS 51-75), a mandatory intervention reminder level is matched, triggering at least one of the following: a flashing red icon on the dashboard with a full-screen pop-up, continuous rapid beeps, or five strong seat vibrations. Simultaneously, the driver is restricted to functions such as a 50% reduction in the ACC speed limit and disabling L2+ autonomous driving functions, and an automatic optimization adjustment is initiated. When the risk level is Level 4 (extremely high risk, CRS 51-75), the driver is restricted to a lower risk level. When the system reaches a threshold of 76-100, it will take over the alert level and trigger at least one of the following: full-screen red warning + safety warning icon, maximum volume alarm + voice broadcast, or continuous seat vibration. Simultaneously, it will perform emergency intervention operations such as adjusting the seat / steering wheel to a safe reference position, disabling the autopilot function, and automatically dialing emergency rescue numbers (if configured), with personal safety as the highest priority.

[0051] In practice, two sets of millimeter-wave radars—one for the front row (driver and front passenger) and one for the rear row (passengers)—are used as data sources. The fusion content includes the original point clouds, range-Doppler spectra, and timestamps collected by the two sets of radars. A unified 10ms periodic trigger signal is generated through FPGA to ensure that the two sets of radars sample synchronously, and the sampling jitter is controlled within 1μs, eliminating time drift at the hardware level. Using the vehicle coordinate system (originating at the rear axle center) as the reference, the point clouds of the two sets of radars are unified to the same spatial coordinate system through the extrinsic parameter calibration matrix (RT matrix), eliminating spatial misalignment caused by different radar perspectives. For radar frames acquired asynchronously, a linear interpolation algorithm is used to unify the data to a 50ms reference frame, further eliminating time deviation and realizing "dual radar perspective fusion" to construct a complete 3D skeleton model of the driver and passengers.

[0052] The front radar collects posture data of the driver's head, shoulders, spine, arms, pelvis, thighs, calves, and feet, while the rear radar collects posture data of the corresponding parts of the passengers. Simultaneously, vehicle status data (vehicle speed, gear, ACC status, air conditioning settings, and steering wheel angle) is acquired. The point clouds from both the front and rear radars are processed to extract a 128-dimensional human skeleton feature vector, accurately capturing the posture details of each part of the body. The front and rear posture features are concatenated with the vehicle status vector to generate a 256-dimensional fused feature vector, achieving the integration of "human-vehicle-environment" data. A multimodal Transformer encoder is used to perform temporal modeling of the fused feature vector, capturing the dynamic correlation between "sitting posture and scene," such as posture changes during high-speed cruising when leaning back for fatigue or during parking when operating the central control. A singular value decomposition algorithm is used to calculate the cosine similarity between the current occupant's posture and a standard sitting posture library, outputting a 5-dimensional deviation score for spinal curvature deviation, headrest distance deviation, shoulder height difference, leg suspension, and arm extension angle deviation.

[0053] The system uses a comprehensive posture risk score (CRS) to provide tiered alerts. The CRS calculation formula is as follows: The scenario correction factor is used to adapt to the differences in posture risk assessment standards under different driving scenarios. For example, in the scenario of highway cruising, due to fatigue caused by long-term driving, the scenario correction factor can be set to 1.2 to amplify the risk score and provide early warning; when operating the central control during parking, since a brief forward lean is a normal operation, the correction factor is set to 0.8 to reduce the probability of misjudgment; when driving normally on urban roads, the correction factor is set to 1.0 to maintain the baseline assessment. The weight i needs to be determined based on ergonomic research, such as a weight of 0.3 for spinal curvature deviation, 0.25 for leg suspension, 0.2 for headrest distance deviation, 0.15 for shoulder height difference, and 0.1 for arm extension angle deviation, to ensure that the contribution of each deviation item is consistent with the degree of health impact.

[0054] Based on the CRS score, the risk levels are divided into four levels, with corresponding differentiated alert methods and response requirements, forming a complete safety closed loop.

[0055] Level 1 Alert (Low Risk, CRS 0-25): Triggering conditions (examples) include headrest distance > 5cm, slight shoulder shrugging, and slight leg dangling; alert methods include flashing dashboard icons (light yellow), gentle prompts (such as "Adjust headrest recommended"), and slight seat vibration (once); response requirements are negligible, and continuous monitoring is conducted without mandatory intervention. For minor posture deviations, only gentle prompts are given, ensuring driving and riding comfort while continuously monitoring posture changes to prepare for potential escalation of risks.

[0056] Level 2 Reminder (Medium Risk, CRS 26-50): Triggering conditions (examples) include scoliosis >10°, arm extension >120° (affecting control), and prolonged (>15 min) hunching; Reminder methods include dashboard icon brightening (orange) + text prompt, rhythmic prompt sound (e.g., "Please adjust your posture for safety"), seat vibration 3 times (1 second interval), and slight increase in air conditioning airflow (stimulating and waking); Response requirement is immediate adjustment suggestion, with an automatic pop-up "One-Click Optimization" button (clicking executes the recommended adjustment). For moderate poor posture, the reminder intensity is strengthened, waking up drivers and passengers through multimodal sensory stimulation, while providing a convenient one-click adjustment entry, proactively guiding users to optimize their posture and reduce safety risks.

[0057] Level 3 Reminder (High Risk, CRS 51-75): Triggering conditions (examples) include severe deviation of spinal curvature (<15° or >45°), headrest distance >8cm (airbag safety risk), legs dangling causing anterior pelvic tilt (prone to lumbar spine injury), and driver not adjusting for 30 consecutive minutes; Reminder methods include red flashing on the dashboard + full-screen pop-up, continuous rapid beeping ("Emergency: Dangerous sitting posture, please adjust immediately!"), and strong seat vibration (5 times); Functional intervention includes, if the driver is present, automatically reducing the ACC speed limit by 50% and disabling L2+ functions; The response requirement is mandatory intervention, which will automatically initiate one optimization adjustment and lock some functions until user confirmation. For serious safety hazards, mandatory intervention measures are implemented, forcing drivers and passengers to adjust their sitting posture through functional restrictions, while automatically performing seat optimization adjustments to proactively eliminate safety risks and ensure driving and riding safety.

[0058] Level 4 Alert (Extremely High Risk, CRS 76-100): Triggering conditions (examples) include driver inactivity for extended periods (>2 minutes), spinal curvature <10° (severe kyphosis), abnormal heart rate (detected by radar micro-motion), headrest distance >10cm + vehicle speed >60km / h; Alert methods include full-screen red warning + safety warning icon, maximum volume alarm + voice announcement: "Your current seating posture poses a serious safety risk, the system will activate emergency protection," and continuous seat vibration; Functional interventions include automatically adjusting the seat / steering wheel to a safe baseline position (airbag deployment space prioritized), disabling autonomous driving functions, and automatically dialing emergency rescue numbers (if eCall is configured); The response requirement is system takeover, ensuring personal safety as the highest priority. In extreme dangerous scenarios (such as sudden driver illness or unconsciousness), the system completely takes over vehicle-related operations, executes the highest priority safety operations, and simultaneously coordinates emergency rescue to ensure the safety of passengers and achieve all-scenario life protection.

[0059] As mentioned above, by precisely matching risk levels with alert levels, it avoids the interference caused to drivers and passengers by excessive alerts in low-risk scenarios, while ensuring the effective delivery of alert information in high-risk scenarios. At the same time, the multimodal alert method can adapt to different driving scenarios and human habits. For example, when driving at high speed, seat vibration or instrument light warnings can convey risk signals without distracting attention, while at low speeds or when parked, voice prompts or interface pop-ups can more clearly inform specific posture adjustment suggestions, thereby improving the pertinence and effectiveness of alerts and further protecting the posture health and driving safety of drivers and passengers.

[0060] Step S104: Based on the feedback from drivers and passengers regarding the posture reminder method, and in conjunction with the deviation value and risk type, adjust the seat.

[0061] Adjusting the seat includes adjusting the seat position and posture.

[0062] In some alternative implementations, when adjusting the seat based on the feedback from drivers and passengers regarding the posture reminder method, combined with the deviation value and risk type, the feedback results can be classified and identified first. Based on the magnitude of the deviation value of the current posture and the priority of the risk type, a differentiated seat adaptive adjustment strategy can be formulated.

[0063] Specifically, when the feedback result is "fully accepted," if the deviation value is large and the risk type is high priority (such as excessive forward tilting of the spine, excessive distance between the head and the seat headrest, etc., which seriously affect safety and health), then a rapid and large-amplitude adaptive adjustment will be performed. For example, the seat back angle will be adjusted to the ergonomically optimal range of 110°-120°, while the fore-and-aft position of the seat cushion will be adjusted to ensure natural leg bending and comfortable foot pedal operation. If the deviation value is small and the risk type is medium priority, such as slight shoulder deviation from the support area, then a small and gradual adjustment will be performed, adjusting the backrest angle by 1° or the seat cushion position by 2cm every 3 seconds to avoid interfering with driving and riding operations. When the feedback result is "partially accepted" (such as the driver and passengers only agreeing to adjust the backrest angle), then only that part will be adjusted according to the deviation value, while the rest of the parts will remain in their current state. When the feedback result is "rejected," automatic adjustment will not be performed.

[0064] The seat adjustment method provided in this embodiment can accurately identify the individual body characteristics and risk status of different drivers and passengers by collecting their human posture parameters and analyzing their deviation from standard posture parameters. This achieves effective adaptation to individual differences among drivers and passengers. At the same time, based on the risk level, corresponding reminder methods are triggered, and combined with the feedback results of drivers and passengers, the seat is adjusted according to the deviation value and risk type. This can dynamically respond to the needs of posture changes during driving, correct poor sitting posture in a timely manner, reduce fatigue and safety hazards caused by improper sitting posture, significantly improve the comfort and support performance of the seat, thereby optimizing the overall driving experience and ensuring driving safety.

[0065] In some optional implementations, when adjusting the seat based on the feedback from the driver / passenger regarding the posture reminder method, combined with the deviation value and risk type, if the feedback indicates that the driver / passenger confirms the adjustment, then a seat adjustment command is generated and the seat position and posture are adjusted according to the risk type and the corresponding deviation value.

[0066] Specifically, when drivers and passengers confirm the adjustment by clicking the "Confirm Adjustment" button on the vehicle's central control screen, responding with "Confirm" via voice, or using the steering wheel shortcut keys, the system immediately retrieves the currently identified risk type and the deviation values ​​of the corresponding human posture parameters from the standard posture parameters. It prioritizes the development of adjustment plans for risk types with high safety priority, ensuring that the adjustment actions accurately correspond to the potential risks, while also taking into account the comfort and safety of the adjustment, and avoiding excessive adjustment range that may affect the operation of drivers and passengers.

[0067] Different seat adjustment operations are performed based on different risk types and corresponding deviation values: If the risk type is whiplash risk, and the deviation value is that the relative distance between the head and the headrest exceeds the standard by 8cm and the angle deviation is 15°, then a headrest adjustment command is generated to control the headrest to adjust upward by 3cm and forward by 5cm, so that the headrest fits against the back of the head, correcting the relative distance and angle between the head and the headrest to the standard range, and eliminating the safety hazard of whiplash injury; If the risk type is abdominal collision risk, and the distance between the chest and the center of the steering wheel deviates by 6cm and the lateral offset of the body's center of gravity deviates by 4cm, then a seat adjustment command is generated to control the seat to move backward by 4cm and increase the backrest angle by 5°, while finely adjusting the left and right height of the seat to correct the offset of the body's center of gravity, increase the safe distance between the chest and the steering wheel, and reduce the risk of abdominal collision. If the risk type is a reclining risk, and the distance between the chest and the center of the steering wheel deviates by 5cm and the elbow angle deviates by 20°, then a command to adjust the seat back and lumbar support is generated. This controls the seat back tilt angle to decrease by 8° and the lumbar support strength to increase by 20%, guiding the driver and passengers to adopt a more upright posture and correcting the elbow angle to the standard range. If the risk type is an embracing risk, and the distance between the chest and the center of the steering wheel deviates by 7cm and the shoulder forward tilt deviates by 12°, then the seat is moved forward by 3cm and the side support of the backrest is tightened. At the same time, the headrest is adjusted back slightly by 2cm to correct the forward tilt of the shoulders and prevent the chest from getting too close to the steering wheel. If the risk type is an incorrect sitting posture risk, and the lateral offset of the body's center of gravity deviates by 5cm and the horizontal tilt angle of the shoulders deviates by 10°, then the left and right height difference of the seat is slightly adjusted by 3cm and the backrest tilt angle by 3° to correct the horizontal posture of the shoulders and guide the body's center of gravity back to the standard position.

[0068] During the execution of adjustment commands, human posture parameters are collected in real time, and the changes in deviation values ​​are dynamically calculated. If the deviation value has been corrected to below the standard threshold during the adjustment process, the adjustment action is terminated in advance. If the standard requirements are not met in one adjustment, the adjustment command is fine-tuned based on the real-time deviation value, and small-amplitude adjustments are continued until the deviation values ​​corresponding to all risk types are reduced to the safe range, completing the adaptive adjustment of seat position and posture. At the same time, voice and visual prompts are given to the driver and passengers that "the sitting posture has been optimized and the risk has been eliminated".

[0069] The seat adjustment method provided by this invention combines the active feedback of drivers and passengers with specific risk types and deviation values ​​to adjust the seat. This fully respects the subjective wishes of drivers and passengers while ensuring the accuracy and relevance of the adjustment. The automated seat adjustment operation eliminates the need for manual adjustment by drivers and passengers, effectively preventing distraction during driving and further improving driving safety. At the same time, the personalized adjustment scheme based on risk type and deviation value can better fit the physical characteristics and current sitting posture of drivers and passengers, accurately correct poor sitting posture, continuously optimize driving comfort and physical health, and provide drivers and passengers with a more intelligent and considerate seat adjustment experience.

[0070] In some optional implementations, when generating seat adjustment commands and performing seat position and posture adjustments based on risk type and corresponding deviation value, it is also possible to match corresponding adjustment targets based on risk type and calculate target adjustment amounts for each adjustment component of the seat based on deviation value. Based on the adjustment target and the target adjustment amount, a seat adjustment command is generated. The seat adjustment command includes at least one of the following: seat fore-aft position, height position, backrest angle, lumbar support, and headrest position. The seat actuator is driven to complete the adjustment of the seat position and posture according to the adjustment command so that the driver and passengers' sitting posture returns to a safe and comfortable range.

[0071] As an example, when drivers and passengers confirm the adjustment by clicking the "Confirm Adjustment" button on the vehicle's central control screen, responding with "Confirm" via voice, or using the steering wheel shortcut keys, the adjustment target is first matched based on the current risk type: if the risk type is a deviation related to the head and headrest, the adjustment target is to make the headrest fit the head and eliminate the distance deviation to ensure the airbag deployment space; if the risk type is a distance deviation between the chest and the steering wheel, the adjustment target is to maintain a safe distance between the chest and the steering wheel to avoid the collision risk when the airbag deploys; if the risk type is a deviation in limb posture, the adjustment target is to bring the body's center of gravity back to the standard range and ensure that the joint angles meet safety requirements. Simultaneously, based on the deviation between the current posture and the standard posture, the target adjustment amount of each adjustment component of the seat is calculated: if the headrest distance deviation is 8cm, combined with the standard posture requirements, it is calculated that the headrest needs to be adjusted forward by 5cm and upward by 3cm to ensure that the headrest fits the head; if the arm extension angle deviation is 20°, it is calculated that the seat needs to be moved forward by 4cm and the seat support at the corresponding arm position needs to be slightly adjusted by 10% to bring the arm extension angle back to the standard range; if the body center of gravity deviates laterally by 5cm, it is calculated that the seat needs to be slightly adjusted in the corresponding direction by 3cm to ensure that the center of gravity returns to the standard position.

[0072] Based on the above adjustment goals and target adjustment amounts, specific seat adjustment commands are generated, including adjustment parameters for seat fore-aft position, height position, backrest angle, lumbar support strength, and headrest position. The seat actuator is then driven to gradually complete the adjustment action according to the adjustment commands. During the process, posture data is collected in real time, and the deviation values ​​before and after adjustment are compared to ensure that the seating posture of the driver and passengers returns to a safe and comfortable range after adjustment.

[0073] As another example, when drivers and passengers confirm the adjustment by clicking the "Confirm Adjustment" button on the vehicle's central control screen, responding with "Confirm" via voice, or using the steering wheel shortcut keys, the system immediately retrieves the currently identified risk type and the deviation values ​​of the corresponding human posture parameters from the standard posture parameters. It prioritizes the development of adjustment plans for risk types with high safety priority, ensuring that the adjustment actions accurately correspond to the potential risks, while also taking into account the comfort and safety of the adjustment, and avoiding excessive adjustment range that may affect the operation of drivers and passengers.

[0074] Different seat adjustment operations are performed based on different risk types and corresponding deviation values: If the risk type is whiplash risk, and the deviation value is that the relative distance between the head and the headrest exceeds the standard by 8cm and the angle deviation is 15°, then a headrest adjustment command is generated to control the headrest to adjust upward by 3cm and forward by 5cm, so that the headrest fits against the back of the head, correcting the relative distance and angle between the head and the headrest to the standard range, and eliminating the safety hazard of whiplash injury; If the risk type is abdominal collision risk, and the distance between the chest and the center of the steering wheel deviates by 6cm and the lateral offset of the body's center of gravity deviates by 4cm, then a seat adjustment command is generated to control the seat to move backward by 4cm and increase the backrest angle by 5°, while finely adjusting the left and right height of the seat to correct the offset of the body's center of gravity, increase the safe distance between the chest and the steering wheel, and reduce the risk of abdominal collision. If the risk type is a reclining risk, and the distance between the chest and the center of the steering wheel deviates by 5cm and the elbow angle deviates by 20°, then a command to adjust the seat back and lumbar support is generated. This controls the seat back tilt angle to decrease by 8° and the lumbar support strength to increase by 20%, guiding the driver and passengers to adopt a more upright posture and correcting the elbow angle to the standard range. If the risk type is an embracing risk, and the distance between the chest and the center of the steering wheel deviates by 7cm and the shoulder forward tilt deviates by 12°, then the seat is moved forward by 3cm and the side support of the backrest is tightened. At the same time, the headrest is adjusted back slightly by 2cm to correct the forward tilt of the shoulders and prevent the chest from getting too close to the steering wheel. If the risk type is an incorrect sitting posture risk, and the lateral offset of the body's center of gravity deviates by 5cm and the horizontal tilt angle of the shoulders deviates by 10°, then the left and right height difference of the seat is slightly adjusted by 3cm and the backrest tilt angle by 3° to correct the horizontal posture of the shoulders and guide the body's center of gravity back to the standard position.

[0075] During the execution of adjustment commands, human posture parameters are collected in real time, and the changes in deviation values ​​are dynamically calculated. If the deviation value has been corrected to below the standard threshold during the adjustment process, the adjustment action is terminated in advance. If the standard requirements are not met in one adjustment, the adjustment command is fine-tuned based on the real-time deviation value, and small-amplitude adjustments are continued until the deviation values ​​corresponding to all risk types are reduced to the safe range, completing the adaptive adjustment of seat position and posture. At the same time, voice and visual prompts are given to the driver and passengers that "the sitting posture has been optimized and the risk has been eliminated".

[0076] The seat adjustment method provided by this invention ensures the scientific nature and accuracy of seat adjustment by precisely matching risk types and adjustment targets, and quantitatively calculating the adjustment amount of each adjustment component based on deviation values. Through multi-dimensional adjustment commands such as seat forward / backward movement, height, backrest angle, lumbar support, and headrest position, it comprehensively covers all aspects of driver and passenger posture issues, achieving all-round posture optimization. The adjustment is completed through an automatically driven actuator, avoiding the tediousness and safety hazards of manual operation by drivers and passengers, further improving the convenience of seat adjustment and driving safety. Ultimately, it allows drivers and passengers to quickly return to a safe and comfortable posture, effectively protecting physical health and riding experience during driving.

[0077] This embodiment provides a seat adjustment method. Figure 2 This is a flowchart of a seat adjustment method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Collect the human posture parameters of the driver and passengers. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0078] Step S202: Based on the deviation values ​​between human posture parameters and standard posture parameters, determine the risk level and associated risk type of the driver / passenger's current sitting posture. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0079] Step S203: Based on the risk level, trigger the corresponding posture reminder method to remind the driver and passengers of their posture. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0080] Step S204: Based on the feedback from drivers and passengers regarding the posture reminder method, and in conjunction with the deviation value and risk type, adjust the seat.

[0081] Specifically, step S204 includes: Step S2041: If the feedback result indicates that the driver or passenger refuses to adjust or ignores the reminder, then the human posture parameters are continuously monitored and the risk level within the preset time period is determined.

[0082] In determining whether a driver or passenger refuses to adjust or ignores the reminder, the driver or passenger can be identified as refusing to adjust by taking active action (such as manually closing the reminder pop-up or clearly expressing refusal via voice). If no interactive action is detected from the driver or passenger regarding the reminder within a preset time period (such as not clicking the adjustment button or issuing an adjustment command), the reminder is considered ignored.

[0083] In step S2042, if the risk level does not decrease or continues to increase within the preset time period, the alert level is upgraded and the alert is triggered again.

[0084] The upgrade reminder level can be implemented according to the preset level gradient. For example, it can be upgraded from the initial visual pop-up reminder to the voice broadcast reminder, seat vibration reminder, or a combination of visual and auditory reminders. Each upgraded reminder method should have a stronger sense of perception in order to enhance the driver's and passengers' awareness of posture risks.

[0085] Step S2043: If the risk level drops below the safety threshold within a preset time period, then stop the active reminder for the current period.

[0086] Among them, the safety threshold refers to a pre-set quantitative indicator system used to determine whether the posture of the driver and passengers is in a safe state, including but not limited to the backrest angle deviation range, the uniformity of seat cushion pressure distribution, and the body tilt angle.

[0087] Specifically, when drivers and passengers click the "Refuse Adjustment" button on the vehicle's central control screen, respond with "Refuse" via voice, or do not perform any operation on the posture reminder (i.e. ignore the reminder), the seat adjustment operation is not performed immediately. Instead, a continuous monitoring mode is activated, which collects human posture parameters every 5 seconds, calculates the deviation value and the corresponding posture risk score in real time, and dynamically tracks the risk level change trend within a preset time (such as 30 seconds).

[0088] If the risk level does not decrease (remains unchanged) or continues to increase (e.g., from Level 2 medium risk to Level 3 high risk) within the preset time period, the alert level will be upgraded. The multimodal alert will be triggered again according to the alert method corresponding to the upgraded level. For example, if the original alert level is Level 2 medium risk, after the upgrade, the alert will be triggered according to the Level 3 high risk alert standard, which will trigger red flashing on the dashboard, continuous rapid beeping, and strong seat vibration. At the same time, a function limitation prompt will be added to further enhance the safety awareness of the driver and passengers and urge them to adjust their sitting posture.

[0089] If, within a preset time period, the driver or passenger adjusts their posture voluntarily, reducing the deviation of human posture parameters and lowering the posture risk score below the safety threshold (i.e., the first-level low-risk range), then the active reminder for the current period will stop, and the system will switch back to the regular monitoring mode. Human posture parameters will be continuously collected, and the posture status will be assessed in real time. If the risk level increases again, the corresponding level of reminder will be triggered again to ensure posture safety while avoiding excessive reminders that could affect driving and riding comfort.

[0090] The seat adjustment method provided in this embodiment achieves a balance between intelligence and humanization in seat adjustment reminders by setting up a feedback response mechanism and a dynamic risk monitoring process. When the driver or passenger is temporarily unable to cooperate with the adjustment, the method does not force the adjustment but continuously tracks changes in posture risk, respecting the driver's and passenger's immediate operational needs while avoiding risk accumulation due to negligence. Dynamic assessment of risk levels determines whether to escalate the reminder, ensuring timely attention to high-risk situations without causing excessive disturbance. By automatically stopping the reminder when the risk decreases to a safe threshold, unnecessary interference is effectively reduced, improving the comfort of the driving experience.

[0091] In some optional implementations, if no feedback from the driver or passenger regarding the posture reminder method is received within a preset time or the risk level is not reduced, the current reminder stage is obtained, and corresponding graded intervention is performed. The graded intervention includes at least one of automatic fine-tuning, safety benchmark adjustment, and emergency call.

[0092] As an example, the preset time is set according to the current alert level. The preset time is 60 seconds for Level 1 (low risk), 30 seconds for Level 2 (medium risk), 15 seconds for Level 3 (high risk), and 5 seconds for Level 4 (extremely high risk). The current alert stage corresponds to the alert level and is divided into Level 1, Level 2, Level 3, and Level 4 alert stages. Different alert stages correspond to different graded intervention strategies to ensure that the intervention action matches the level of risk, taking into account both safety and driving experience.

[0093] If the current stage is Level 1, and no feedback is received from the driver or passengers or the risk level does not decrease within the preset time, automatic fine-tuning intervention will be executed: Based on the current risk type and deviation value, a small-amplitude, low-impact seat adjustment command will be generated, with the adjustment range controlled within 30%-40% of the deviation value. Fine-tuning will only be performed on the current core risk type (such as slightly moving the headrest forward or slightly increasing the pressure on the lumbar support). During the adjustment process, a message will be broadcast in real time: "The system is performing a seat posture fine-tuning, please pay attention" to avoid affecting the normal operation of the driver and passengers. After the fine-tuning, the risk level will be reassessed. If the risk decreases, the intervention will stop. If the risk does not decrease, the system will enter the Level 2 alert stage and upgrade the intervention method.

[0094] If the current alert level is Level 2 or Level 3 and no feedback is received or the risk level does not decrease within the preset time, a safety reference position adjustment intervention will be implemented: immediately retrieve the standard safe sitting posture reference parameters, generate a seat adjustment command, drive the seat actuator to adjust the seat's fore-aft position, height position, backrest angle, headrest position, etc. to the safe reference position, and disable L2+ autonomous driving, ACC and other assistance functions, trigger an enhanced reminder, inform the driver and passengers that "safe sitting posture adjustment has been performed, please confirm", forcibly guide the sitting posture back to the safe range, and continuously monitor changes in risk level after the adjustment is completed.

[0095] If the current stage is Level 4 and no feedback is received or the risk level is not reduced within the preset time, an emergency call intervention will be executed: Based on the adjustment of the safety baseline, the emergency call process will be initiated immediately, automatically dialing the preset emergency contact number and eCall emergency rescue number, and simultaneously uploading information such as the current human posture parameters, risk level, and vehicle location. At the same time, continuous seat vibration and maximum volume alarm will be triggered until a rescue response or feedback from the driver or passengers is received, so as to maximize the personal safety of the driver and passengers.

[0096] In addition, during the tiered intervention process, human posture parameters are collected in real time, and deviation values ​​and risk levels are dynamically updated. If the driver or passenger gives clear feedback during the intervention process (confirming adjustment or refusing adjustment), the current tiered intervention is stopped immediately, and the corresponding operation is performed according to the feedback result.

[0097] As another example, suppose a driver or passenger is on a long-distance drive and their posture, as detected by dual radar, is: head-to-headrest distance exceeds the standard by 5cm, scoliosis is 15°, classifying it as a level 2 medium risk (CRS score 38), triggering a level 2 alert (highlighted orange icon, rhythmic alert sound). If the driver or passenger does not provide any feedback, does not click the "Confirm Adjustment" button, and does not adjust their posture, this is considered "no feedback," initiating the tiered intervention process: First, automatic fine-tuning intervention is performed: Based on the current risk type (excessive headrest distance, scoliosis), an adjustment command is generated to move the headrest forward by 5cm (correcting the distance deviation between the head and the headrest), while simultaneously fine-tuning the seat back angle to keep the spine naturally straight, corresponding to the "automatic fine-tuning" step in the attached diagram. This ensures that the adjustment is gentle and does not affect the normal operation of the driver and passengers. After adjustment, posture data is re-collected. It is detected that the distance deviation between the head and the headrest has decreased to 2cm, the scoliosis deviation has decreased, the CRS score has decreased to 28 points, the risk level remains at level two (medium risk), and the reminder method remains unchanged.

[0098] Secondly, perform safety reference position adjustment: If the driver and passengers still do not provide any feedback, and the detected posture deviation has not improved (the distance between the head and the headrest is still more than 3cm beyond the standard, and there is no change in scoliosis), activate the safety reference position adjustment, adjust the seat back angle to the standard position, and disable the L2 level autonomous driving function, retaining only the basic driving function, corresponding to the "safety lock" requirement in the attached diagram, to avoid further escalation of risks.

[0099] Finally, emergency call intervention: If the driver or passenger remains unresponsive and an abnormal heart rate or lack of movement is detected, indicating a sudden illness or loss of consciousness, an emergency call is immediately triggered. The eCall emergency rescue number is automatically dialed, and the vehicle's location, seating posture data, and abnormal situation are uploaded. At the same time, the seat is adjusted to a safe reference position, the autonomous driving function is turned off, and the safety mode is activated to wait for rescue personnel to arrive, completing the emergency intervention loop and maximizing the safety of the driver and passenger.

[0100] In addition, a comprehensive posture scan can be automatically performed every 15 minutes (taking about 10-15 seconds) to compare the driver's posture with the initially set standard sitting posture. After the scan, if any areas for improvement are found, friendly suggestions can be given via voice or screen. At the end of the trip, a simple "Driving Posture Health Report" can be generated, showing the duration of good posture and major bad habits during the trip, helping drivers to make long-term self-improvements.

[0101] The seat adjustment method provided by this invention slightly optimizes the seating posture to mitigate risks through automatic fine-tuning without interfering with the normal operation of the driver and passengers; it quickly adjusts the seat to a safe-verified standard posture when risks continue to accumulate through safety benchmark adjustment, effectively preventing the risk from escalating; and it promptly connects to external assistance in extremely dangerous situations through an emergency call function, providing life safety protection for the driver and passengers. This layered and progressive intervention strategy avoids the limitations of a single intervention method and ensures that each level of intervention matches the degree of risk, further enhancing the emergency response capability and safety protection level of seat adjustment, making driver and passenger safety protection more layered and comprehensive.

[0102] This embodiment also provides a seat adjustment device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0103] This embodiment provides a seat adjustment device, such as Figure 3 As shown, it includes: The parameter acquisition module 301 collects the human posture parameters of the driver and passengers; The risk determination module 302 is used to determine the risk level and associated risk type of the driver's current sitting posture based on the deviation value between the human posture parameters and the standard posture parameters. The posture reminder module 303 is used to match and trigger the corresponding posture reminder method according to the risk level to remind the driver and passengers of their posture. The seat adjustment module 304 is used to adjust the seat based on the feedback from the driver and passengers regarding the posture reminder method, combined with the deviation value and risk type.

[0104] In some alternative implementations, the risk determination module 302 includes: The deviation calculation unit is used to calculate the deviation between each parameter in the human posture parameters and the corresponding standard posture parameters. The risk level determination unit is used to calculate the corresponding sitting posture risk score based on the deviation value, compare the sitting posture risk score with the preset risk threshold, and determine the risk level of the current sitting posture. The risk type determination unit is used to determine the risk type of the current sitting posture based on the body part, deviation direction, and sitting posture risk score corresponding to each deviation value.

[0105] In some optional implementations, the deviation value calculation unit includes: The centroid determination subunit is used to obtain the posture point set of each part in the human posture parameters and determine the centroid of the posture point set. The decentralized processing subunit is used to perform decentralized processing on the attitude point set based on the centroid of the point set to obtain the attitude processing point set; The deviation value calculation subunit is used to match and align the posture processing point set with the standard posture point set corresponding to the standard posture parameters, and calculate the deviation value between each human posture parameter and the corresponding standard posture parameter.

[0106] In some alternative implementations, the posture reminder module 303 includes: The alert level matching unit is used to match the corresponding alert level from the preset alert strategy library according to the risk level; The posture reminder unit is used to remind drivers and passengers according to the posture reminder method corresponding to the reminder level. The posture reminder method includes at least one of the following: voice prompt, interface pop-up window, instrument light warning, and seat vibration.

[0107] In some alternative implementations, the seat adjustment module 304 includes: The first seat adjustment unit is used to generate a seat adjustment command and execute the adjustment of seat position and posture based on the risk type and the corresponding deviation value if the feedback result indicates that the driver or passenger confirms the adjustment.

[0108] In some alternative implementations, the seat adjustment module 304 further includes: The adjustment calculation unit is used to match the corresponding adjustment target based on the risk type, and to calculate the target adjustment amount of each adjustment component of the seat based on the deviation value; The adjustment instruction generation unit is used to generate seat adjustment instructions based on the adjustment target and the target adjustment amount. The seat adjustment instructions include at least one of the following: seat fore-aft position, height position, backrest angle, lumbar support, and headrest position. The second seat adjustment unit is used to drive the seat actuator to adjust the seat position and posture according to the adjustment command, so that the driver and passengers can return to a safe and comfortable sitting position.

[0109] In some alternative implementations, the seat adjustment module 304 further includes: The continuous monitoring unit is used to continuously monitor human posture parameters and determine the risk level within a preset time period if the feedback results indicate that the driver or passenger refuses to adjust or ignores the reminder. The upgrade reminder unit is used to upgrade the reminder level and trigger the reminder again if the risk level does not decrease or continues to increase within a preset time period; The stop reminder unit is used to stop the active reminder for the current period if the risk level drops below the safety threshold within a preset time period.

[0110] In some alternative implementations, the seat adjustment module 304 further includes: The graded intervention unit is used to obtain the current reminder stage and execute the corresponding graded intervention if no feedback is received from the driver or passenger regarding the posture reminder method or the risk level is not reduced within a preset time. The graded intervention includes at least one of the following: automatic fine-tuning, safety benchmark adjustment, and emergency call.

[0111] The seat adjustment device provided in this embodiment of the invention can execute the seat adjustment method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0112] Figure 4 This is a structural schematic diagram of a vehicle provided in an embodiment of the present invention.

[0113] The following is a detailed reference. Figure 4 The diagram illustrates a structural schematic suitable for implementing a vehicle according to an embodiment of the present invention. The vehicle may include a processor (e.g., a central processing unit, graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from memory 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for vehicle operation. The processor 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0114] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows the vehicle to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 Vehicles with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0115] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 409, or installed from a memory 408, or installed from a ROM 402. When the computer program is executed by the processor 401, it performs the functions defined in the seat adjustment method of the embodiments of the present invention.

[0116] Figure 4 The vehicle shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0117] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the seat adjustment method shown in the above embodiments is implemented.

[0118] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0119] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for adjusting a seat, characterized in that, include: Collect human posture parameters of drivers and passengers; Based on the deviation between the human posture parameters and the standard posture parameters, the risk level and associated risk type of the driver's current sitting posture are determined. According to the risk level, the corresponding posture reminder method is triggered to remind the driver and passengers of their posture. Based on the feedback from the driver and passengers regarding the posture reminder method, and in conjunction with the deviation value and the risk type, the seat is adjusted.

2. The method according to claim 1, characterized in that, The process of determining the risk level and associated risk type of the driver / passenger's current sitting posture based on the deviation between the human posture parameters and standard posture parameters includes: Calculate the deviation value between each parameter in the human posture parameters and the corresponding standard posture parameters; Calculate the corresponding sitting posture risk score based on the deviation value, compare the sitting posture risk score with a preset risk threshold, and determine the risk level of the current sitting posture. Based on the body part corresponding to each deviation value, the direction of deviation, and the posture risk score, the risk type of the current posture is determined.

3. The method according to claim 2, characterized in that, The step of calculating the deviation between each parameter in the human posture parameters and the corresponding standard posture parameters includes: Obtain the set of posture points for each part of the human body posture parameters, and determine the centroid of the set of posture points; Based on the centroid of the point set, the attitude point set is decentralized to obtain the attitude processing point set; The posture processing point set is matched and aligned with the standard posture point set corresponding to the standard posture parameters, and the deviation value between each human posture parameter and the corresponding standard posture parameter is calculated.

4. The method according to claim 1, characterized in that, The method of matching and triggering a corresponding posture reminder according to the risk level to remind the driver and passengers of their posture includes: Based on the risk level, match the corresponding alert level from the preset alert strategy library; The driver and passengers are reminded according to the posture reminder method corresponding to the reminder level. The posture reminder method includes at least one of the following: voice prompt, interface pop-up, instrument light warning, and seat vibration.

5. The method according to claim 1, characterized in that, The adjustment of the seat based on the feedback from the driver / passenger regarding the posture reminder method, combined with the deviation value and the risk type, includes: If the feedback result indicates that the driver or passenger confirms the adjustment, then according to the risk type and the corresponding deviation value, a seat adjustment command is generated and the seat position and posture are adjusted.

6. The method according to claim 5, characterized in that, The step of generating a seat adjustment command and executing the adjustment of the seat position and posture based on the risk type and the corresponding deviation value includes: The adjustment target is matched based on the risk type, and the target adjustment amount of each adjustment component of the seat is calculated based on the deviation value; Based on the adjustment target and the target adjustment amount, the seat adjustment command is generated, and the seat adjustment command includes at least one of the following: seat fore-aft position, height position, backrest angle, lumbar support, and headrest position; The drive seat actuator adjusts the seat position and posture according to the adjustment command, so that the driver and passenger's sitting posture returns to a safe and comfortable range.

7. The method according to claim 1, characterized in that, The method further includes: If the feedback result indicates that the driver or passenger refuses to adjust or ignores the reminder, the human posture parameters will be continuously monitored and the risk level within a preset time period will be determined. If the risk level does not decrease or continues to increase within the preset time period, the alert level will be upgraded and the alert will be triggered again. If the risk level drops below the safety threshold within the preset time period, the proactive reminder for the current period will be stopped.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: If no feedback is received from the driver or passenger regarding the posture reminder method within the preset time or the risk level is not reduced, the current reminder stage is obtained, and corresponding graded intervention is executed. The graded intervention includes at least one of the following: automatic fine-tuning, safety baseline adjustment, and emergency call.

9. A seat adjustment device, characterized in that, include: The parameter acquisition module collects the human posture parameters of drivers and passengers. The risk determination module is used to determine the risk level and associated risk type of the driver's current sitting posture based on the deviation value between the human posture parameters and the standard posture parameters. The posture reminder module is used to match and trigger the corresponding posture reminder method according to the risk level, and to remind the driver and passengers of their posture. The seat adjustment module is used to adjust the seat based on the feedback from the driver / passenger regarding the posture reminder method, combined with the deviation value and the risk type.

10. A vehicle, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 8.

Images