Man-machine interaction method of zero-gravity and intelligent interaction fused intelligent seat

Abstract

The invention relates to the technical field of man-machine interaction, and particularly discloses a man-machine interaction method of a zero-gravity and intelligent interaction fused intelligent seat, which comprises the following steps of: S1, setting a pre-action sequence, executing the pre-action sequence after a user sits on the intelligent seat, the intelligent seat collects hip and back pressure distribution data in the process that the user executes the pre-action sequence; s2, a pre-action sequence is set, the pre-action sequence is executed after a user sits on the intelligent seat, and the intelligent seat collects hip and back pressure distribution data in the process that the user executes the pre-action sequence; s3, based on the biological characteristic model, the intelligent seat obtains adjusting parameters of the intelligent seat, and the side wing supporting strength and the zero-gravity backrest angle of the seat are adjusted according to the adjusting parameters; the key problem of body type misjudgment in a complex environment is solved through a technical path of dynamic micro-action excitation and skeleton rigid feature recognition.

Description

Technical Field

[0001] The present invention relates to the field of human-computer interaction technology, and in particular to a human-computer interaction method for a smart seat that integrates zero gravity and intelligent interaction. Background Art

[0002] In the wave of automotive intelligence, smart seats that integrate zero-gravity and intelligent interaction have become an important vehicle for improving the driving experience. However, current technology still faces key challenges, such as the significant flaws in the method of judging body shape based on weight. The human-computer interaction of smart seats relies on data collected by pressure sensors to identify the user's physical characteristics. However, in actual use, factors such as the thickness of clothing and the weight of personal belongings can seriously interfere with measurement accuracy. Especially in winter scenarios, when users are wearing thick cotton or down jackets, test data shows that the system mistakenly identifies them as obese. This misperception directly leads to the incorrect adjustment of the seat side support strength, which fails to provide accurate wrapping and stability for users of different body shapes.

[0003] In-depth analysis revealed that traditional solutions use a single threshold algorithm to process raw data, lacking a mechanism to compensate for environmental variables. When the extra weight is added to the actual body weight, the control unit struggles to distinguish between the increase in weight inherent to the body and the increase in weight due to external factors.

[0004] Existing solutions attempt to optimize by increasing the number of sensors or introducing machine learning models, but these efforts are limited by cost constraints and real-time requirements. Therefore, developing a new human-computer interaction method that can accurately identify the user's true body shape in complex environments and dynamically adjust seat support strategies has become a technical bottleneck that the industry urgently needs to overcome. Summary of the Invention

[0005] The purpose of the present invention is to provide a human-computer interaction method for an intelligent seat that integrates zero gravity and intelligent interaction, and to solve the following technical problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A human-computer interaction method for a zero-gravity and intelligent interactive integrated intelligent seat comprises the following steps: Step S1: setting a pre-action sequence, which is executed after the user sits on the smart chair, and collecting hip and back pressure distribution data during the user's execution of the pre-action sequence; Step S2: identifying all stable pressure points based on the buttocks and back pressure distribution data; obtaining a spatial structure model of all stable pressure points; obtaining the user's ischial tuberosity distance and sacral triangle area based on the spatial structure model; and establishing a biometric model of the user; Step S3: Based on the biometric model, the smart seat obtains adjustment parameters of the smart seat, and adjusts the seat side support strength and the zero-gravity backrest angle according to the adjustment parameters.

[0007] As a further solution of the present invention: the setting process of the pre-action sequence includes: The maximum displacement range of the smart seat cushion is obtained, and a displacement threshold d is set. The user periodically moves the seat cushion forward within the maximum displacement range, with each forward movement having a displacement of d, and periodically moves the seat cushion backward, with each backward movement having a displacement of d, to obtain a set of seat cushion adjustment micro-movements. The maximum tilt angle range of the smart seat backrest is obtained, and the tilt angle threshold θ is set, θ∈[0.5°, 2°]. The user periodically tilts the backrest forward within the maximum tilt angle range, and each time the forward tilt angle is θ, and periodically reclines the backrest, and each time the reclining angle is θ, to obtain a new set of backrest adjustment micro-movements; the pre-action sequence is composed of all seat cushion adjustment micro-movements and all backrest adjustment micro-movements.

[0008] As a further solution of the present invention: the process of collecting the buttocks and back pressure distribution data includes: A rectangular grid is formed under the seat cushion of the smart seat to obtain a rectangular grid. All intersections of the rectangular grid are obtained and recorded as pressure points. Similarly, all pressure points on the backrest of the smart seat are obtained, and a micro-pressure collection point is set at each pressure point. The pressure distribution data of the buttocks and back are obtained by collecting data at each micro-pressure collection point.

[0009] As a further solution of the present invention: the process of collecting the buttocks and back pressure distribution data includes: A rectangular grid is formed under the seat cushion of the smart seat to obtain a rectangular grid. All intersections of the rectangular grid are obtained and recorded as pressure points. Similarly, all pressure points on the backrest of the smart seat are obtained, and a micro-pressure collection point is set at each pressure point. The pressure distribution data of the buttocks and back are obtained by collecting data at each micro-pressure collection point.

[0010] As a further solution of the present invention, the identification process of the stable pressure point includes: The pressure change rate of each pressure point is obtained, and a pressure point whose pressure change rate is less than a preset change rate threshold is recorded as a stable pressure point; otherwise, it is recorded as an unstable pressure point.

[0011] As a further solution of the present invention: the process of obtaining the pressure change rate of the pressure point includes: Get the time interval between each two adjacent time nodes, recorded as T; for any pressure point, get the pressure value of the pressure point at each time node in the action cycle, and number each time node to get the pressure change rate of the pressure value , where P i Represents the pressure value of the pressure point at the i-th time node, n is the total number of time nodes, i∈[2,n] and i is a positive integer.

[0012] As a further solution of the present invention, the process of obtaining the spatial distribution of all stable pressure points includes: Obtain the hinge connection points of the backrest and the seat cushion, take the hinge connection points as the origin, set the horizontal direction along the seat as the X-axis, the vertical direction along the seat as the Y-axis, and the direction perpendicular to the surface of the seat as the Z-axis to obtain a three-dimensional coordinate system; in the three-dimensional coordinate system, obtain the three-dimensional coordinates of each stable pressure point to obtain a three-dimensional coordinate set; and establish a three-dimensional spatial distribution model, convert the three-dimensional coordinate set into point cloud data, and input the point cloud data into the three-dimensional spatial distribution model to obtain a spatial structure model of all stable pressure points.

[0013] As a further solution of the present invention, the process of obtaining the user's ischial tuberosity distance and sacral triangle area includes: Several volunteers were selected as human specimens, and a human coordinate system was established. Within the human coordinate system, three-dimensional data of the buttocks of the human specimens was acquired using a non-contact three-dimensional scanner. Based on anatomical principles, the three-dimensional coordinate data of the distance between the ischial tuberosities was inferred from the three-dimensional data. The three-dimensional coordinate data of each human specimen was acquired, and the geometric features of the distance between the ischial tuberosities were extracted from each three-dimensional coordinate data using principal component analysis, which were recorded as ischium features. Similarly, the geometric features of the sacral triangle were acquired, which were recorded as sacrum features. In the spatial structure model, the structural area with the highest similarity to the ischium feature is selected and recorded as the user's ischial tuberosity area. The structural area is an area composed of several pressure points. Based on the ischial tuberosity area, the user's ischial tuberosity distance is obtained; similarly, in the spatial structure model, the structural area with the highest similarity to the sacrum feature is selected and recorded as the user's sacral triangle area. Based on the sacral triangle area, the user's sacral triangle area is obtained.

[0014] Beneficial effects of the present invention: Traditional body shape recognition methods based on weight are susceptible to interference from factors such as the thickness of clothing and the weight of belongings, leading to high misjudgment rates, particularly in winter when wearing heavy clothing. This invention employs a pre-motion sequence to trigger differential deformation responses between the human skeleton and clothing. Specifically, skeletal support points, due to their rigidity, have a low rate of pressure change, while flexible interference objects, such as clothing and objects, have a high rate of pressure change. By screening for stable pressure points with a pressure change rate below a threshold, skeletal contact points can be precisely located, effectively eliminating external interference and significantly improving body shape recognition accuracy in complex environments. Based on a spatial structural model of stable pressure points, core anatomical parameters such as the distance between the ischial tuberosities and the area of ​​the sacral triangle are extracted to create a biometric model. This model links the user's true body shape with seat adjustment parameters, dynamically matching support strategies for users of different body types. This avoids misjudgments that result in insufficient side support strength or uncomfortable angles, thereby improving seat fit, stability, and comfort. This invention also achieves precise recognition by collecting data through a pressure sensor array and combining algorithms such as micro-motion stimulation and pressure change rate analysis. This eliminates the need for a large number of additional high-end sensors, ensuring both real-time performance and accuracy while controlling hardware costs. Compared with solutions that rely on complex machine learning models or multi-sensor fusion, it is easier to achieve batch applications.

[0015] The present invention uses micro-motion sequences to stimulate differentiated deformation responses of human bones and clothing, and screens stable pressure points, i.e., bone contact points, through the pressure change rate. A biometric model is established based on the ischial distance and the area of ​​the sacral triangle to dynamically match the side support force and zero-gravity angle. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below with reference to the accompanying drawings.

[0017] Figure 1 It is a structural schematic diagram of a human-computer interaction method for a smart seat that integrates zero gravity and intelligent interaction according to the present invention. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0019] See also Figure 1 As shown, the present invention is a human-computer interaction method for a zero-gravity and intelligent interactive integrated intelligent seat, comprising the following steps: Step S1: setting a pre-action sequence, which is executed after the user sits on the smart chair, and collecting hip and back pressure distribution data during the user's execution of the pre-action sequence; Specifically, the maximum displacement range of the smart seat cushion is first obtained, and a displacement threshold is set. The user periodically moves the seat cushion forward within the maximum displacement range, with each forward displacement being d, and periodically moves it backward at a displacement of d each time, forming a set of seat cushion adjustment micro-movements. The maximum tilt angle range of the smart seat backrest is then obtained, and a tilt angle threshold is set. The user periodically tilts the backrest forward within the maximum tilt angle range, with each forward tilt angle being θ, and periodically leans back at a tilt angle being θ each time, forming a set of backrest adjustment micro-movements. All the above-mentioned seat cushion adjustment micro-movements and backrest adjustment micro-movements together constitute a pre-action sequence. A rectangular grid is formed under the seat cushion of the smart seat, and all the intersection points of the grid are obtained as pressure points. Similarly, all the pressure points on the backrest are determined, and micro-pressure collection points are set at each pressure point. The time period in which the user performs the pre-action sequence, that is, the action cycle, is recorded. Several time nodes are selected at equal intervals within the cycle, and the pressure values ​​of each pressure point at these time nodes are obtained through micro-pressure collection points, and the pressure distribution data of the buttocks and back are obtained by integration.

[0020] As a preferred embodiment of the present invention, the setting process of the pre-action sequence includes: The maximum displacement range of the smart seat cushion is obtained, and a displacement threshold d is set. The user periodically moves the seat cushion forward within the maximum displacement range, with each forward movement having a displacement of d, and periodically moves the seat cushion backward, with each backward movement having a displacement of d, to obtain a set of seat cushion adjustment micro-movements. The maximum tilt angle range of the smart seat backrest is obtained, and a tilt angle threshold θ is set, θ∈[0.5°, 2°]. The user periodically tilts the backrest forward within the maximum tilt angle range, with each tilt angle being θ, and periodically reclines the backrest, with each reclining angle being θ, to obtain a new set of backrest adjustment micro-movements. The pre-action sequence is composed of all seat cushion adjustment micro-movements and all backrest adjustment micro-movements. Specifically, in the pressure distribution between the human body and the seat, the skeletal support points, due to their rigid structure, have strong resistance to pressure transmission with the seat. That is, when the seat undergoes micro-movements (tilting forward, reclining, moving forward, or moving backward), the pressure change rate in the skeletal contact area is low. The skeletal support points mentioned above include the ischial tuberosity and sacrum. On the other hand, due to their flexible characteristics, the pressure transmission resistance of clothing or soft tissue is weak, that is, micro-movements of the seat can cause rapid pressure fluctuations. Through periodic micro-movements, pressure disturbances are actively created, which changes the difference in the pressure change rate between bones and soft tissue from static and difficult to distinguish to dynamic and easy to identify. In a preferred embodiment of the present invention, the process of collecting the buttocks and back pressure distribution data includes: A rectangular grid is formed under the seat cushion of the smart seat to obtain a rectangular grid. All intersections of the rectangular grid are obtained and recorded as pressure points. Similarly, all pressure points on the backrest of the smart seat are obtained, and micro pressure collection points are set at each pressure point. The pressure distribution data of the buttocks and back are obtained by collecting data at each micro pressure collection point. The process of collecting the buttocks and back pressure distribution data further includes: Obtain the time period consumed by the user in executing the pre-action sequence, recorded as an action cycle, select several time nodes at equal intervals within the action cycle, obtain the pressure value of the pressure point at each time node, and obtain the buttocks and back pressure distribution data; Specifically, by gridding the seat surface, each pressure point corresponds to a unique coordinate, converting the contact between the human body and the seat into a spatialized pressure matrix. The pressure value of each point in the pressure matrix is ​​associated with position information. Pressure is collected at equal intervals within the micro-motion cycle, and a dynamic curve of pressure changes with seat posture is recorded to avoid fuzzy pressure distribution caused by a single acquisition. Step S2: identifying all stable pressure points based on the buttocks and back pressure distribution data; obtaining a spatial structure model of all stable pressure points; obtaining the user's ischial tuberosity distance and sacral triangle area based on the spatial structure model; and establishing a biometric model of the user; Specifically, the following operations are performed on the collected buttocks and back pressure distribution data: 1. Delete abnormal points whose pressure values ​​exceed the sensor range and replace them with the historical mean value of the grid point. If it is the first time to collect the data, mark it as an invalid point. 2. Based on the micro-motion cycle, the pressure data at different time points are aligned according to the seat posture to ensure that the same posture corresponds to the same set of pressure values; Furthermore, the pre-processed pressure data is screened for stable pressure points according to the following rules: for each grid pressure point, the pressure change within the micro-motion cycle is calculated, and a pressure change rate threshold is set. The pressure points are screened, requiring that stable pressure points form a continuous area on the seat surface (e.g., at least three adjacent grid points are stable pressure points), eliminating isolated stable points caused by sensor noise. The verified stable pressure points are organized into a set of spatial coordinates based on the seat grid coordinates, which serve as the basis for the spatial distribution of the rigidity features. In a preferred embodiment of the present invention, the process of identifying the stable pressure point includes: Obtaining the pressure change rate of each pressure point, and recording the pressure point whose pressure change rate is less than a preset change rate threshold as a stable pressure point; otherwise, recording it as an unstable pressure point; The process of obtaining the pressure change rate of the pressure point includes: Get the time interval between each two adjacent time nodes, recorded as T; for any pressure point, get the pressure value of the pressure point at each time node in the action cycle, and number each time node to get the pressure change rate of the pressure value , where P i represents the pressure value of the pressure point at the i-th time node, n is the total number of time nodes, i∈[2,n] and i is a positive integer; Specifically, is the instantaneous pressure change rate, the pressure difference between adjacent time nodes divided by the time interval, reflecting the severity of pressure fluctuation at a certain moment; taking the arithmetic average of all instantaneous change rates to obtain the average pressure change rate R, which represents the average severity of pressure fluctuation during the entire micro-action cycle; When the human body contacts the seat, pressure fluctuations are dynamic and complex. For example, slipping clothing can cause a sudden change in pressure at a certain moment, but the overall fluctuation may not be significant. Averaging can filter out transient interference, such as sudden pressure changes caused by the user's sudden adjustment of their sitting posture, while preserving the overall trend. This also makes the calculation results more robust and insensitive to local outliers, ensuring that the selection of stable pressure points is more consistent with the actual human contact characteristics. As a preferred embodiment of the present invention, the process of obtaining the spatial distribution of all stable pressure points includes: Obtaining the hinge connection point of the backrest and the seat cushion, using the hinge connection point as the origin, setting the horizontal direction along the seat as the X-axis, the vertical direction along the seat as the Y-axis, and the direction perpendicular to the seat surface as the Z-axis to obtain a three-dimensional coordinate system; obtaining the three-dimensional coordinates of each stable pressure point in the three-dimensional coordinate system to obtain a three-dimensional coordinate set; and establishing a three-dimensional spatial distribution model, converting the three-dimensional coordinate set into point cloud data, and inputting the point cloud data into the three-dimensional spatial distribution model to obtain a spatial structural model of all stable pressure points; Specifically, an XYZ three-dimensional coordinate system is established with the hinge connection point between the backrest and the seat cushion as the origin. The X-axis, the horizontal direction, is associated with the fore-aft displacement of the seat, corresponding to the depth direction of the human body when sitting; the Y-axis, the vertical direction, is associated with the seat height and the backrest inclination, corresponding to the height direction of the human body when sitting; the Z-axis, the vertical surface, is associated with the depth of fit between the seat and the human body, such as the concave backrest and the elastic deformation of the seat cushion, corresponding to the pressure direction of the human body when sitting; the coordinate system accurately binds the physical structure of the seat to the contact position of the human body; the three-dimensional coordinates of each stable pressure point are regarded as point cloud data and input into the three-dimensional modeling algorithm; the algorithm fits a continuous three-dimensional spatial structure model based on the spatial distribution of the point cloud; Different users have different body shapes and sitting postures, resulting in significant differences in pressure distribution. Through a unified three-dimensional coordinate system, pressure points can be mapped to the same spatial reference, regardless of the user's height or sitting posture, whether leaning forward or backward. This eliminates the interference of individual spatial differences on subsequent calculations, making the pressure distribution of different users comparable. In a preferred embodiment of the present invention, the process of obtaining the user's ischial tuberosity distance and sacral triangle area includes: Several volunteers were selected as human specimens, and a human coordinate system was established. Within the human coordinate system, three-dimensional data of the buttocks of the human specimens was acquired using a non-contact three-dimensional scanner. Based on anatomical principles, the three-dimensional coordinate data of the distance between the ischial tuberosities was inferred from the three-dimensional data. The three-dimensional coordinate data of each human specimen was acquired, and the geometric features of the distance between the ischial tuberosities were extracted from each three-dimensional coordinate data using principal component analysis, which were recorded as ischium features. Similarly, the geometric features of the sacral triangle were acquired, which were recorded as sacrum features. In the spatial structure model, the structural region with the highest similarity to the ischium feature is selected and recorded as the user's ischial tuberosity region. The structural region is a region composed of a plurality of pressure points. Based on the ischial tuberosity region, the user's ischial tuberosity distance is obtained. Similarly, in the spatial structure model, the structural region with the highest similarity to the sacrum feature is selected and recorded as the user's sacral triangle region. Based on the sacral triangle region, the user's sacral triangle area is obtained. Specifically, a 3D scanner is used to obtain surface data of the volunteer's buttocks, such as the 3D coordinates of the skin surface. Combined with anatomical knowledge, such as the depth and position of bones under the body surface, the 3D coordinates of the bones are inferred. For the bone coordinates of multiple samples, the PCA algorithm is used to extract the most representative geometric features, such as the mean and variance of the ischial tuberosity distance, and the shape parameters of the sacral triangle. For the user's seat pressure space model, the spatial distribution characteristics of the pressure points are extracted, such as the position, shape, and spacing of the clustered areas. The user's pressure characteristics are compared with the sample feature library to find the most similar template, such as the spacing and shape of the user's pressure clustering area, which best matches the standard body shape template in the ischial feature library, thereby determining the user's bone area. As a preferred embodiment of the present invention, the process of establishing the user's biometric model includes: Select several sample users, obtain the distance between the ischial tuberosities and the area of ​​the sacral triangle of the sample users in a standard sitting posture, and obtain the body characteristics of the sample users, wherein the body characteristics include several body parameters, including body mass index, pelvic morphology, and lower limb length and proportion; the standard sitting posture is an upright sitting posture with the buttocks close to the backrest and the knees flexed 90 degrees; Recording the distance between the ischial tuberosities and the area of ​​the sacral triangle of the sample user in a standard sitting posture, as well as the body shape characteristics, as the sample user's in-sample data; establishing a first regression model, inputting the sample data into the first regression model, training the first regression model, and obtaining a body shape characteristic model; and obtaining support parameters for each sample user, including the side support strength and zero-gravity backrest angle of the smart chair; establishing a second regression model, using the body shape characteristics and support parameters of each sample user as new sample data, and inputting the second regression model into the second regression model, training the second regression model to obtain a biometric model; Specifically, there are statistical patterns in the bone parameters of users of different body shapes. By collecting a large number of sample bone parameter and body shape feature data, the correlation between the two is learned using regression models, such as multivariate linear regression and random forest. Seat adaptation parameters vary for users of different body shapes. By collecting a large number of body shape characteristics and adjustment parameter data, a regression model is used to learn the correlation between the two. Step S3: Based on the biometric model, the smart seat obtains adjustment parameters of the smart seat, and adjusts the seat wing support strength and the zero-gravity backrest angle according to the adjustment parameters; As a preferred embodiment of the present invention, the process of obtaining the adjustment parameters includes: Inputting the user's ischial tuberosity distance and the sacral triangle area into the body shape feature model to obtain the user's body shape parameters, which are recorded as user body shape parameters, and inputting the user's body shape parameters into the biometric model to obtain the user's support parameters, which are recorded as user support parameters; obtaining the current support parameters of the smart seat, which are recorded as current support parameters, and comparing the current support parameters with the user support parameters to obtain adjustment parameters of the smart seat; Specifically, the user's skeletal parameters are input, and the model outputs the user's body parameters. When the user's body parameters are input, the model outputs the user's ideal support parameters. The actual support parameters of the seat are obtained, and the difference between the ideal support parameters and the actual support parameters is calculated. The difference is the adjustment parameter. For example, the current flank strength is 20N, the ideal strength is 30N - the current strength is 20N = +10N, and the flank strength needs to be increased by 10N.

[0021] The above is a detailed description of one embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the present invention.

Claims

1. A human-computer interaction method for a zero-gravity and intelligent interactive integrated intelligent seat, characterized in that: The following steps are involved: Step S1: setting a pre-action sequence, which is executed after the user sits on the smart chair, and collecting hip and back pressure distribution data during the user's execution of the pre-action sequence; Step S2: identifying all stable pressure points based on the buttocks and back pressure distribution data; obtaining a spatial structure model of all stable pressure points; obtaining the user's ischial tuberosity distance and sacral triangle area based on the spatial structure model; and establishing a biometric model of the user; Step S3: Based on the biometric model, the smart seat obtains adjustment parameters of the smart seat, and adjusts the seat side support strength and the zero-gravity backrest angle according to the adjustment parameters.

2. The human-computer interaction method for a zero-gravity and intelligent interactive integrated smart chair according to claim 1, characterized in that: In step S1, the process of setting the pre-action sequence includes: The maximum displacement range of the smart seat cushion is obtained, and a displacement threshold d is set. The user periodically moves the seat cushion forward within the maximum displacement range, with each forward movement having a displacement of d, and periodically moves the seat cushion backward, with each backward movement having a displacement of d, to obtain a set of seat cushion adjustment micro-movements. The maximum tilt angle range of the smart seat backrest is obtained, and the tilt angle threshold θ is set, θ∈[0.5°, 2°]. The user periodically tilts the backrest forward within the maximum tilt angle range, and each time the forward tilt angle is θ, and periodically reclines the backrest, and each time the reclining angle is θ, to obtain a new set of backrest adjustment micro-movements; the pre-action sequence is composed of all seat cushion adjustment micro-movements and all backrest adjustment micro-movements.

3. The human-computer interaction method for a zero-gravity and intelligent interactive integrated smart chair according to claim 1, characterized in that: In step S1, the process of collecting the buttocks and back pressure distribution data includes: A rectangular grid is formed under the seat cushion of the smart seat to obtain a rectangular grid. All intersections of the rectangular grid are obtained and recorded as pressure points. Similarly, all pressure points on the backrest of the smart seat are obtained, and a micro-pressure collection point is set at each pressure point. The pressure distribution data of the buttocks and back are obtained by collecting data at each micro-pressure collection point.

4. The human-computer interaction method for a zero-gravity and intelligent interactive integrated smart chair according to claim 3, characterized in that: In step S1, the process of collecting the buttocks and back pressure distribution data further includes: The time period consumed by the user in executing the pre-action sequence is obtained and recorded as the action cycle. Several time nodes are selected at equal intervals within the action cycle, and the pressure value of the pressure point at each time node is obtained to obtain the buttocks and back pressure distribution data.

5. The human-computer interaction method for a zero-gravity and intelligent interactive integrated smart chair according to claim 1, characterized in that: In step S2, the process of identifying stable pressure points includes: The pressure change rate of each pressure point is obtained, and a pressure point whose pressure change rate is less than a preset change rate threshold is recorded as a stable pressure point; otherwise, it is recorded as an unstable pressure point.

6. The human-computer interaction method for a zero-gravity and intelligent interactive integrated smart chair according to claim 5, characterized in that: In step S2, the process of obtaining the pressure change rate of the pressure point includes: Get the time interval between each two adjacent time nodes, recorded as T; for any pressure point, get the pressure value of the pressure point at each time node in the action cycle, and number each time node to get the pressure change rate of the pressure value , where P i Represents the pressure value of the pressure point at the i-th time node, n is the total number of time nodes, i∈[2,n] and i is a positive integer.

7. The human-computer interaction method for a zero-gravity and intelligent interactive integrated smart chair according to claim 1, characterized in that: In step S2, the process of obtaining the spatial distribution of all stable pressure points includes: Obtain the hinge connection points of the backrest and the seat cushion, take the hinge connection points as the origin, set the horizontal direction along the seat as the X-axis, the vertical direction along the seat as the Y-axis, and the direction perpendicular to the surface of the seat as the Z-axis to obtain a three-dimensional coordinate system; in the three-dimensional coordinate system, obtain the three-dimensional coordinates of each stable pressure point to obtain a three-dimensional coordinate set; and establish a three-dimensional spatial distribution model, convert the three-dimensional coordinate set into point cloud data, and input the point cloud data into the three-dimensional spatial distribution model to obtain a spatial structure model of all stable pressure points.

8. The human-computer interaction method for a zero-gravity and intelligent interactive integrated smart chair according to claim 1, characterized in that: In step S2, the process of obtaining the user's ischial tuberosity distance and sacral triangle area includes: Several volunteers were selected as human specimens, and a human coordinate system was established. Within the human coordinate system, three-dimensional data of the buttocks of the human specimens was acquired using a non-contact three-dimensional scanner. Based on anatomical principles, the three-dimensional coordinate data of the distance between the ischial tuberosities was inferred from the three-dimensional data. The three-dimensional coordinate data of each human specimen was acquired, and the geometric features of the distance between the ischial tuberosities were extracted from each three-dimensional coordinate data using principal component analysis, which were recorded as ischium features. Similarly, the geometric features of the sacral triangle were acquired, which were recorded as sacrum features. In the spatial structure model, the structural area with the highest similarity to the ischium feature is selected and recorded as the user's ischial tuberosity area. The structural area is an area composed of several pressure points. Based on the ischial tuberosity area, the user's ischial tuberosity distance is obtained; similarly, in the spatial structure model, the structural area with the highest similarity to the sacrum feature is selected and recorded as the user's sacral triangle area. Based on the sacral triangle area, the user's sacral triangle area is obtained.

9. The human-computer interaction method for a zero-gravity and intelligent interactive integrated smart chair according to claim 1, characterized in that: In step S2, the process of establishing the user's biometric model includes: Select several sample users, obtain the distance between the ischial tuberosities and the area of ​​the sacral triangle of the sample users in a standard sitting posture, and obtain the body characteristics of the sample users, wherein the body characteristics include several body parameters, including body mass index, pelvic morphology, and lower limb length and proportion; the standard sitting posture is an upright sitting posture with the buttocks close to the backrest and the knees flexed 90 degrees; Recording the distance between the ischial tuberosities and the area of ​​the sacral triangle of the sample user in a standard sitting posture, as well as the body shape characteristics, as the sample user's in-sample data; establishing a first regression model, inputting the sample data into the first regression model, training the first regression model, and obtaining a body shape characteristic model; And obtain the support parameters of each sample user, which include the side support strength and zero-gravity backrest angle of the smart seat; establish a second regression model, use the body shape characteristics and support parameters of each sample user as new sample data, and input them into the second regression model, train the second regression model, and obtain a biometric model.

Images