Intelligent auxiliary getting-up method and system

Abstract

The invention relates to the technical field of intelligent cabins, and provides an intelligent auxiliary getting-up method and system, and the method comprises the steps: recognizing the sitting posture information of a sitting object, predicting the intention of a user based on the analysis of the limb movement of the sitting object, pre-judging the intention of the user in advance through motion capture, and improving the implementation sensitivity of seat adjustment; the target seat height conforming to the auxiliary getting-up height is calculated in combination with the user feature information and the basic information of the vehicle seat, personalized height adaptation is achieved, the seat height is dynamically adjusted in real time, and the user is assisted to get up safely; the vehicle seat is subjected to gradual height adjustment according to the target seat height, the adjustment rhythm is comfortable and gentle, and safety and comfort are better achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent cockpits, and in particular to an intelligent assisted standing-up method and system. Background Art

[0002] As the aging population intensifies, more and more elderly users still have the need to drive or ride in a car. However, issues such as seat height, joint mobility, and balance make getting up and down in a car a significant obstacle for these seniors, posing a significant risk of falls. For example, the risk of falls can arise from factors such as awkward seat height and angle, difficulty getting up due to decreased joint mobility, and decreased balance.

[0003] While existing vehicles feature electrically adjustable seats, most adjustments are geared towards a comfortable sitting position and lack automatic assistance mechanisms for easier exiting. Furthermore, in real-world driving, existing seat adjustments focus solely on comfort. When users exit the vehicle from a comfortable position, they often experience difficulty getting up and opening the door. These systems offer no real-time, dynamic adjustment of seat height based on the user's needs to assist in safely exiting. Summary of the Invention

[0004] The present invention provides an intelligent assisted standing-up method and system, which solves the technical problem that the existing vehicle seat adjustment lacks a "standing-up assistance" mechanism, cannot meet the user's need to get off the vehicle, and there is a risk of falling when the user gets off the vehicle.

[0005] To solve the above technical problems, the present invention provides an intelligent assisted standing method, comprising the steps of:

[0006] When a passenger is detected on a vehicle seat, user feature information of the passenger and seating posture information of the passenger on the vehicle seat are acquired in real time;

[0007] identifying a user's intention based on the riding posture information;

[0008] Calculating a target seat height that meets the assistive standing height based on the user intention, the user characteristic information, and basic information of the vehicle seat;

[0009] The vehicle seat is incrementally height-adjusted according to the target seat height.

[0010] This basic solution identifies the seating posture information of the occupant, predicts the user's intention based on the analysis of the occupant's body movements, and predicts the user's intention in advance through motion capture, thereby improving the sensitivity of seat adjustment implementation; combining user feature information and basic information of the vehicle seat, it calculates the target seat height that meets the auxiliary standing height, realizes personalized height adaptation, and adjusts the seat height in real time and dynamically to assist the user to stand up safely; the vehicle seat is gradually adjusted in height according to the target seat height, and the adjustment rhythm is comfortable and smooth, which is safer and more comfortable.

[0011] In a further embodiment, obtaining user characteristic information of a passenger in real time includes:

[0012] Collecting facial images of passengers in real time, performing facial recognition based on the facial images, and determining the identity information of the passengers;

[0013] User characteristic information of the passenger is obtained based on the identity information, where the user characteristic information includes at least one of user height, user age, and user gender.

[0014] This solution performs identity recognition for different passengers, thereby obtaining user feature information for subsequent personalized adjustments, which can better meet the user's personal needs and improve user satisfaction.

[0015] In a further embodiment, obtaining the seating posture information of the passenger on the vehicle seat in real time includes:

[0016] acquiring, in real time, pressure data borne by a seat cushion on the vehicle seat as first posture information;

[0017] Based on the seat adaptive adjustment mechanism, obtaining seat back angle data from the vehicle seat in real time as second posture information;

[0018] The first posture information and the second posture information are acquired as sitting posture information and stored.

[0019] This solution simultaneously collects seat cushion pressure data and seat back angle data as seating posture information, which can quantify the passenger's movements and posture on the car seat and effectively reduce the difficulty of acquiring posture data, thereby improving the accuracy of intention prediction and reducing the amount of calculation.

[0020] In a further embodiment, identifying the user intention based on the riding posture information includes:

[0021] Acquiring the first posture information from the sitting posture information, calculating a pressure change of the seat according to the first posture information, performing a nonlinear fitting calculation according to the pressure change, and executing intention prediction to obtain a first prediction parameter;

[0022] acquiring the second posture information from the sitting posture information, calculating a seat back angle change based on the second posture information, performing a nonlinear fitting calculation based on the angle change, and performing intention prediction to obtain a second prediction parameter;

[0023] A fusion calculation is performed based on the first prediction parameter and the second prediction parameter to identify the user intention.

[0024] In a further embodiment, the calculation formula of the first prediction parameter is as follows,

[0025]

[0026] The calculation formula of the second prediction parameter is as follows:

[0027]

[0028] Where, Represent the first prediction parameter and the second prediction parameter respectively; P t-1 Indicates the pressure data of the vehicle seat at the previous moment; P t Represents the pressure data of the vehicle seat at the current moment; θ t-1 Represents the angle data of the seat back at the previous moment; θ t Indicates the current seat back angle data; P base ,θ base They represent the initial default pressure and initial backrest index of the vehicle seat respectively.

[0029] This solution uses pressure changes and angle changes to predict user intentions, uses the hyperbolic tangent function to quantify action changes on the time axis, performs nonlinear fitting calculations from the two perspectives of pressure changes and angle changes, and identifies user intentions at the same time. Compared with linear models, it can more accurately describe the threshold effect (small pressure / angle changes will not trigger) and saturation effect (output is stable when the pressure / angle changes are too large), effectively improving the accuracy of user intention recognition.

[0030] In a further embodiment, the calculation formula for performing fusion calculation based on the first prediction parameter and the second prediction parameter is as follows:

[0031]

[0032] Where, I stand (t) represents the intention probability at the current moment, ranging from 0 to 1; Represent the first prediction parameter and the second prediction parameter respectively; ω θ They represent the pressure weight coefficient and the angle weight coefficient respectively; b represents the bias factor.

[0033] This solution combines the pressure and angle changes of the seat to perform multimodal fusion calculations to predict the intention probability of the occupant. Multi-dimensional mapping and comparison from the two aspects of pressure and angle can avoid misjudgment and effectively improve the prediction accuracy.

[0034] In a further embodiment, calculating a target seat height that meets the assisted standing height based on the user intention in combination with the user characteristic information and basic information of the vehicle seat includes:

[0035] Determine whether the user's intention is to stand up, and if so, proceed to the next step;

[0036] Obtaining the user characteristic information, and extracting the user height and user age therefrom, and then performing nonlinear fitting calculation in combination with the benchmark height and benchmark age to obtain adjustment parameters;

[0037] Extracting an initial default height from basic information of the vehicle seat, and calculating a target seat height that meets the assisted standing height based on the adjustment parameter and the initial default height;

[0038] Among them, the benchmark height represents the average height of middle-aged and elderly people across the country, and the benchmark age represents the age benchmark of middle-aged and elderly people.

[0039] In a further embodiment, the calculation formula of the adjustment parameter is as follows:

[0040]

[0041] Where, F represents the adjustment parameter; h u Indicates the user's height; h ref Indicates baseline height; age u Indicates the user's age; age ref represents the baseline age; α, b, and c are all constants;

[0042] H target =H0+(H max -H0)×F

[0043] Where H target Indicates the target seat height; H0 indicates the initial default height; H max Indicates the maximum adjustable height of the vehicle seat.

[0044] This solution performs dual-factor adjustment based on user height and age, fully considering the seat height requirements of people of different heights and people of different age groups, analyzing the movement flexibility caused by age and the personalized needs caused by height, and performing nonlinear fitting calculations based on baseline height and baseline age. This can improve the adaptability of the adjustment parameters to the passengers, thereby achieving efficient cooperation in assisting them to stand up and reduce the risk of falls.

[0045] The present invention provides an intelligent assisting system for getting up, comprising a processor and a memory connected thereto, a first acquisition module, a second acquisition module and a third acquisition module;

[0046] The first acquisition module is used to obtain the pressure data of the seat cushion from the vehicle seat in real time as the first posture information;

[0047] The second acquisition module is used to obtain seat back angle data from the vehicle seat in real time based on the seat adaptive adjustment mechanism as second posture information;

[0048] The third acquisition module is used to obtain user characteristic information of the passenger;

[0049] The memory stores computer instructions, and the processor executes the above-mentioned intelligent assisted standing up method by executing the computer instructions.

[0050] In a further embodiment, the first acquisition module includes a pressure sensor arranged under the seat cushion; the second acquisition module includes an angle sensor arranged on the seat back; and the third acquisition module is an image acquisition device arranged in the vehicle compartment, including a vehicle-mounted camera or an infrared sensor.

[0051] This basic solution uses sensors to automatically acquire information and execute an automatic assisted standing-up mechanism, which can effectively reduce the risk of falls for the elderly when standing up and sitting down, significantly improve the safety of in-car operations for the elderly, reduce safety hazards during the standing-up process, and indirectly improve the elderly's acceptance of smart cockpits and user experience satisfaction, thereby promoting the penetration and application of smart cockpits in the elderly market. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a workflow diagram of an intelligent assisted standing-up method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following describes the embodiments of the present invention in detail with reference to the accompanying drawings. The embodiments are provided for illustrative purposes only and are not to be construed as limiting the present invention. The accompanying drawings are provided for reference and illustration only and do not constitute a limitation on the scope of protection of the present invention. Many changes may be made to the present invention without departing from the spirit and scope of the present invention.

[0054] Example 1

[0055] An embodiment of the present invention provides an intelligent assisted standing method, such as Figure 1 As shown, in this embodiment, the steps include:

[0056] S1. When a passenger is detected on a vehicle seat, obtaining user feature information of the passenger and seating posture information of the passenger on the vehicle seat in real time;

[0057] In this embodiment, the user characteristic information of the passenger is obtained in real time, including:

[0058] Collecting facial images of passengers in real time, performing facial recognition based on the facial images, and determining the identity information of the passengers;

[0059] User characteristic information of the passenger is obtained based on the identity information, where the user characteristic information includes at least one of user height, user age, and user gender.

[0060] Among them, the passengers include the driver and the passenger in the front passenger seat.

[0061] This embodiment performs identity recognition for different passengers, thereby obtaining user feature information for subsequent personalized adjustments, which can better meet the user's personal needs and improve user satisfaction.

[0062] In this embodiment, real-time acquisition of the seating posture information of the passenger on the vehicle seat includes:

[0063] acquiring, in real time, pressure data borne by a seat cushion on the vehicle seat as first posture information;

[0064] Based on the seat adaptive adjustment mechanism, obtaining seat back angle data from the vehicle seat in real time as second posture information;

[0065] The first posture information and the second posture information are acquired as sitting posture information and stored.

[0066] This embodiment simultaneously collects the pressure data of the seat cushion and the angle data of the seat back as seating posture information, which can quantify the movement posture of the passenger on the seat in the car and effectively reduce the difficulty of obtaining posture data, thereby improving the accuracy of intention prediction and reducing the amount of calculation.

[0067] S2. Identifying the user's intention based on the riding posture information, including:

[0068] Acquiring the first posture information from the sitting posture information, calculating a pressure change of the seat according to the first posture information, performing a nonlinear fitting calculation according to the pressure change, and executing intention prediction to obtain a first prediction parameter;

[0069] acquiring the second posture information from the sitting posture information, calculating a seat back angle change based on the second posture information, performing a nonlinear fitting calculation based on the angle change, and performing intention prediction to obtain a second prediction parameter;

[0070] A fusion calculation is performed based on the first prediction parameter and the second prediction parameter to identify the user intention.

[0071] In this embodiment, the calculation formula of the first prediction parameter is as follows:

[0072]

[0073] The calculation formula of the second prediction parameter is as follows:

[0074]

[0075] Where, Represent the first prediction parameter and the second prediction parameter respectively; P t-1 Indicates the pressure data of the vehicle seat at the previous moment; P t Represents the pressure data of the vehicle seat at the current moment; θ t-1 Represents the angle data of the seat back at the previous moment; θ t Indicates the current seat back angle data; P base ,θ base They represent the initial default pressure and initial backrest index of the vehicle seat respectively.

[0076] This embodiment uses pressure changes and angle changes to predict user intentions, uses the hyperbolic tangent function to quantify motion changes on the time axis, performs nonlinear fitting calculations from the two perspectives of pressure changes and angle changes, and identifies user intentions at the same time. Compared with linear models, it can more accurately describe the threshold effect (small pressure / angle changes do not trigger) and saturation effect (output is stable when the pressure / angle changes are too large), effectively improving the accuracy of user intention recognition.

[0077] In this embodiment, the calculation formula for performing fusion calculation based on the first prediction parameter and the second prediction parameter is as follows:

[0078]

[0079] Where, I stand (t) represents the intention probability at the current moment, ranging from 0 to 1; Represent the first prediction parameter and the second prediction parameter respectively; ω θ They represent the pressure weight coefficient and the angle weight coefficient respectively; B represents the bias factor.

[0080] This embodiment combines the pressure changes and angle changes of the seat to perform multimodal fusion calculations to predict the intention probability of the passenger, and performs multi-dimensional mapping and comparison from the two aspects of pressure and angle to avoid misjudgment and effectively improve the prediction accuracy.

[0081] For example:

[0082] If the pressure when the passenger is seated is P t-1 =650N, when you are ready to stand up, the pressure is reduced to P t =450N;

[0083] The backrest angle when sitting firmly is θ t-1 =110°, when standing up, the backrest angle tilts forward to θ t =128°;

[0084] Let P base =100N,θ base =10°, ω θ =0.8, b=-1.8, then substitute into the formula to calculate the intention probability of the user's intention:

[0085]

[0086] Model training is performed based on actual riding scenarios, and probability thresholds can be set, for example:

[0087] The threshold is set to 0.7. The specific judgment conditions are as follows:

[0088]

[0089] In the above case, I stand (t)>0.7, proceed to the next step.

[0090] S3. Calculating a target seat height that meets the assisted standing height based on the user intention, the user characteristic information, and basic information of the vehicle seat, including:

[0091] Determine whether the user's intention is to stand up, and if so, proceed to the next step;

[0092] Obtaining the user characteristic information, and extracting the user height and user age therefrom, and then performing nonlinear fitting calculation in combination with the benchmark height and benchmark age to obtain adjustment parameters;

[0093] Extracting an initial default height from basic information of the vehicle seat, and calculating a target seat height that meets the assisted standing height based on the adjustment parameter and the initial default height;

[0094] The reference height represents the national average height of middle-aged and elderly people, and the reference age represents the age reference of middle-aged and elderly people. The basic information of the vehicle seat is the specification data of the vehicle itself, which can be obtained from the database.

[0095] In this embodiment, the calculation formula of the adjustment parameter is as follows:

[0096]

[0097] Where, F represents the adjustment parameter; h u Indicates the user's height; h ref Indicates baseline height; age u Indicates the user's age; age ref represents the baseline age; α, b, and c are all constants;

[0098] H target =H0+(H max -H0)×F

[0099] Where H target Indicates the target seat height; H0 indicates the initial default height; H max Indicates the maximum adjustable height of the vehicle seat.

[0100] For example, the user's height h u =1.70m, user age u =72 years old:

[0101] The initial seat height H0 = 0.4m, the maximum adjustable seat height H max =1.0m;

[0102] Let the base height be h ref =1.65m, the reference age is age ref =65:

[0103] a=5.0, b=0.05, c=-1.0m, then substitute into the formula to calculate the target adjustment height:

[0104]

[0105] That is, the seat height is adjusted to 0.6408m based on 0.4m.

[0106] This embodiment performs dual-factor adjustment based on the user's height and age, fully considering the seat height requirements of people of different heights and people of different age groups, analyzing the movement flexibility caused by age and the personalized needs caused by height, and performing nonlinear fitting calculations based on the baseline height and baseline age. This can improve the adaptability of the adjustment parameters to the passengers, thereby achieving efficient cooperation in assisting them to stand up and reducing the risk of falling.

[0107] S4. progressively adjusting the height of the vehicle seat according to the target seat height, specifically:

[0108] Based on the initial seat height and the target seat height, the adjustment coefficient is calculated using an exponential function to gradually adjust the vehicle seat height. The peak inertial force at the moment the seat is started is low, and the speed naturally decays as it approaches the target height over time, which meets the human body's physiological expectations for seat adjustment and improves user comfort.

[0109] The embodiments of the present invention identify the seating posture information of the occupant, predict the user's intention based on the analysis of the occupant's body movements, and predict the user's intention in advance through motion capture, thereby improving the implementation sensitivity of seat adjustment; combining the user's characteristic information and the basic information of the vehicle seat, the target seat height that meets the auxiliary standing height is calculated to achieve personalized height adaptation, and the seat height is adjusted in real time and dynamically to assist the user to stand up safely; the vehicle seat is gradually adjusted in height according to the target seat height, and the adjustment rhythm is comfortable and smooth, which is safer and more comfortable.

[0110] Example 2

[0111] An embodiment of the present invention provides an intelligent assistive standing system, comprising a processor and a memory connected thereto, a first acquisition module, a second acquisition module, and a third acquisition module;

[0112] The first acquisition module is used to obtain the pressure data of the seat cushion from the vehicle seat in real time as the first posture information;

[0113] The second acquisition module is used to obtain seat back angle data from the vehicle seat in real time based on the seat adaptive adjustment mechanism as second posture information;

[0114] The third acquisition module is used to obtain user characteristic information of the passenger;

[0115] The memory stores computer instructions, and the processor executes the computer instructions to perform an intelligent assisted standing up method as described in Example 1 above.

[0116] In this embodiment, the first acquisition module includes a pressure sensor arranged under the seat cushion; the second acquisition module includes an angle sensor arranged on the seat back; the third acquisition module is an image acquisition device arranged in the vehicle compartment, including a vehicle-mounted camera or an infrared sensor.

[0117] The embodiment of the present invention automatically acquires information through sensors and executes an automatic assisted standing-up mechanism, which can effectively reduce the risk of falling for the elderly when standing up and sitting down, significantly improve the safety of in-vehicle operations for the elderly, reduce safety hazards during the standing-up process, and indirectly improve the elderly's acceptance of smart cockpits and user experience satisfaction, thereby promoting the penetration and application of smart cockpits in the elderly market.

[0118] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be considered as equivalent replacement methods and are included in the scope of protection of the present invention.

Claims

1. An intelligent method for assisting people to stand up, characterized in that: Including steps: When a passenger is detected on a vehicle seat, user feature information of the passenger and seating posture information of the passenger on the vehicle seat are acquired in real time; identifying a user's intention based on the riding posture information; Calculating a target seat height that meets the assistive standing height based on the user intention, the user characteristic information, and basic information of the vehicle seat; The vehicle seat is incrementally height-adjusted according to the target seat height.

2. The intelligent assisted standing up method according to claim 1, characterized in that: Obtain user characteristic information of passengers in real time, including: Collecting facial images of passengers in real time, performing facial recognition based on the facial images, and determining the identity information of the passengers; User characteristic information of the passenger is obtained based on the identity information, where the user characteristic information includes at least one of user height, user age, and user gender.

3. The intelligent assisted standing up method according to claim 2, characterized in that: Acquiring in real time the seating posture information of the passenger on the vehicle seat, including: acquiring, in real time, pressure data borne by a seat cushion on the vehicle seat as first posture information; Based on the seat adaptive adjustment mechanism, obtaining seat back angle data from the vehicle seat in real time as second posture information; The first posture information and the second posture information are acquired as sitting posture information and stored.

4. The intelligent assisted standing up method according to claim 3, characterized in that: Identifying the user's intention based on the riding posture information includes: Acquiring the first posture information from the sitting posture information, calculating a pressure change of the seat according to the first posture information, performing a nonlinear fitting calculation according to the pressure change, and executing intention prediction to obtain a first prediction parameter; acquiring the second posture information from the sitting posture information, calculating a seat back angle change based on the second posture information, performing a nonlinear fitting calculation based on the angle change, and performing intention prediction to obtain a second prediction parameter; A fusion calculation is performed based on the first prediction parameter and the second prediction parameter to identify the user intention.

5. The intelligent assisted standing up method according to claim 4, characterized in that: The calculation formula of the first prediction parameter is as follows: The calculation formula of the second prediction parameter is as follows: Where, Represent the first prediction parameter and the second prediction parameter respectively; P t-1 Indicates the pressure data of the vehicle seat at the previous moment; P t Represents the pressure data of the vehicle seat at the current moment; θ t-1 Represents the angle data of the seat back at the previous moment; θ t Indicates the current seat back angle data; P base ,θ base They represent the initial default pressure and initial backrest index of the vehicle seat respectively.

6. The intelligent assisted standing up method according to claim 5, characterized in that: The calculation formula for performing fusion calculation based on the first prediction parameter and the second prediction parameter is as follows: Where, I stand (t) represents the intention probability at the current moment, ranging from 0 to 1; Represent the first prediction parameter and the second prediction parameter respectively; ω θ They represent the pressure weight coefficient and the angle weight coefficient respectively; b represents the bias factor.

7. The intelligent assisted standing up method according to claim 4, characterized in that: Calculating a target seat height that meets an assisted standing height based on the user intention, the user characteristic information, and basic information of the vehicle seat, including: Determine whether the user's intention is to stand up, and if so, proceed to the next step; Obtaining the user characteristic information, and extracting the user height and user age therefrom, and then performing nonlinear fitting calculation in combination with the benchmark height and benchmark age to obtain adjustment parameters; Extracting an initial default height from basic information of the vehicle seat, and calculating a target seat height that meets the assisted standing height based on the adjustment parameter and the initial default height; Among them, the benchmark height represents the average height of middle-aged and elderly people across the country, and the benchmark age represents the age benchmark of middle-aged and elderly people.

8. The intelligent assisted standing up method according to claim 7, characterized in that: The calculation formula of the adjustment parameter is as follows: Where, F represents the adjustment parameter; h u Indicates the user's height; h ref Indicates baseline height; age u Indicates the user's age; age ref represents the baseline age; α, b, and c are all constants; H target =H0+(H max -H0)×F Where H target Indicates the target seat height; H0 represents the initial default height; H max Indicates the maximum adjustable height of the vehicle seat.

9. An intelligent assistive standing system, characterized by: It includes a processor and a memory connected thereto, a first acquisition module, a second acquisition module and a third acquisition module; The first acquisition module is used to obtain the pressure data of the seat cushion from the vehicle seat in real time as the first posture information; The second acquisition module is used to obtain seat back angle data from the vehicle seat in real time as second posture information based on the seat adaptive adjustment mechanism; The third acquisition module is used to obtain user characteristic information of the passenger; The memory stores computer instructions, and the processor executes the intelligent assisted standing up method according to any one of claims 1 to 8 by executing the computer instructions.

10. The intelligent assisting system for getting up according to claim 9, characterized in that: The first acquisition module includes a pressure sensor arranged under the seat cushion; the second acquisition module includes an angle sensor arranged on the seat back; the third acquisition module is an image collector arranged in the vehicle compartment, including a vehicle-mounted camera or an infrared sensor.

Images