Self-adaptive waist chasing method, computer readable storage medium and intelligent seat

Abstract

The invention discloses a self-adaptive waist tracking method, a computer readable storage medium and an intelligent seat, the self-adaptive waist tracking method is used for the intelligent seat, the intelligent seat is provided with a pressure sensor array and a waist support adjusting mechanism, and the method comprises the following steps: acquiring real-time pressure data of a current user collected by the pressure sensor array; extracting pressure characteristic parameters according to the real-time pressure data, and determining the body type category of the current user according to the pressure characteristic parameters by using a pre-trained body type recognition model; determining a current sitting posture type and an initial pressure threshold value of the current user according to the real-time pressure data by utilizing a pre-trained sitting posture recognition model; determining a target pressure threshold value according to the real-time pressure data, the body type category and the initial pressure threshold value; according to the target pressure threshold value, supporting parameters of a waist support adjusting mechanism are adjusted, so that the waist support is matched with the waist state of the user. According to the self-adaptive waist-following method, personalized waist-following adaptation of the user in multiple scenes is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent seats, and in particular to an adaptive waist tracking method, a computer-readable storage medium, and an intelligent seat. Background Art

[0002] Smart seats often use fixed thresholds or preset modes to adjust lumbar support. These methods don't provide effective lumbar support and can't meet the lumbar support needs of different users. Summary of the Invention

[0003] The present invention aims to address, at least to some extent, one of the technical problems in the related art. To this end, one objective of the present invention is to propose an adaptive waist tracking method that combines pressure data collected in real time by a pressure sensor array, the user's body shape, and the current sitting posture to determine a target pressure threshold. The method then adjusts the support parameters of the lumbar support adjustment mechanism based on the target pressure threshold, achieving personalized waist tracking adaptation for the user.

[0004] A second object of the present invention is to provide a computer-readable storage medium.

[0005] A third object of the present invention is to provide an electronic device.

[0006] A fourth object of the present invention is to provide a vehicle.

[0007] To achieve the above-mentioned objectives, an embodiment of the first aspect of the present invention proposes an adaptive waist tracking method for a smart seat, wherein the smart seat is equipped with a pressure sensor array and a lumbar support adjustment mechanism, and the method includes: obtaining real-time pressure data of the current user collected by the pressure sensor array; extracting pressure characteristic parameters based on the real-time pressure data, and using a pre-trained body shape recognition model to determine the body type of the current user based on the pressure characteristic parameters; using a pre-trained sitting posture recognition model to determine the current sitting posture type and initial pressure threshold of the current user based on the real-time pressure data; determining a target pressure threshold based on the real-time pressure data, the body type category and the initial pressure threshold; and adjusting the support parameters of the lumbar support adjustment mechanism based on the target pressure threshold so that the lumbar support matches the user's lumbar state.

[0008] According to the adaptive waist tracking method of an embodiment of the present invention, features are extracted from real-time pressure data, and a pre-trained body shape recognition model is used to determine the current user's body shape category based on the extracted pressure feature parameters. A pre-trained sitting posture recognition model is used to determine the current user's current sitting posture type and initial pressure threshold based on the real-time pressure data. The initial pressure threshold is adjusted according to the real-time pressure data and body shape category to determine the target pressure threshold. The support parameters of the lumbar support adjustment mechanism are adjusted according to the target pressure threshold to achieve personalized waist tracking adaptation for the user.

[0009] In addition, the adaptive waist-chasing method proposed in the above embodiment of the present invention may also have the following additional technical features:

[0010] According to an embodiment of the present invention, before acquiring the real-time pressure data of the current user collected by the pressure sensor array, the method further includes: preprocessing the real-time pressure data of the current user collected by the pressure sensor array.

[0011] According to one embodiment of the present invention, the pressure characteristic parameters include the pressure center of gravity position and the contact area, and the use of a pre-trained body shape recognition model to determine the body shape category of the current user based on the pressure characteristic parameters includes: inputting the pressure center of gravity position and the contact area into the pre-trained body shape recognition model to obtain the body shape category of the current user.

[0012] According to one embodiment of the present invention, the method of determining the current sitting posture type and the initial pressure threshold of the current user based on the real-time pressure data using a pre-trained sitting posture recognition model includes: inputting the real-time pressure data into the pre-trained sitting posture recognition model to obtain the current sitting posture type and the initial pressure threshold.

[0013] According to one embodiment of the present invention, the real-time pressure data includes waist pressure, and determining the target pressure threshold based on the real-time pressure data, the body shape category and the initial pressure threshold includes: adjusting the initial pressure threshold according to the waist pressure and the body shape category to obtain the target pressure threshold, wherein adjusting the initial pressure threshold according to the waist pressure includes: if the waist pressure is greater than the initial pressure threshold and lasts for a preset time, increasing the initial pressure threshold; if the waist pressure is less than the initial pressure threshold and lasts for a preset time, reducing the initial pressure threshold.

[0014] According to an embodiment of the present invention, the support parameter includes support strength, and adjusting the support parameter of the lumbar support adjustment mechanism according to the target pressure threshold includes: adjusting the support strength of the lumbar support adjustment mechanism according to the target pressure threshold.

[0015] According to one embodiment of the present invention, the method further includes: after determining the body type category of the current user, establishing a user profile based on the body type category, and recording in real time the target pressure thresholds corresponding to different sitting postures of the body type category and the support parameters of the lumbar support adjustment mechanism, wherein the user profile includes at least the user's body type category, the target pressure thresholds and initial pressure thresholds under different sitting postures, and the support parameters of the lumbar support adjustment mechanism.

[0016] According to one embodiment of the present invention, the method further includes: obtaining the user profile, training the pre-trained sitting posture recognition model according to the target pressure threshold and initial pressure threshold corresponding to different sitting postures of the same body type category in the user profile, and updating the pre-trained sitting posture recognition model.

[0017] To achieve the above objectives, a second embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the adaptive waist tracking method provided in the first embodiment of the present invention is implemented.

[0018] To achieve the above-mentioned objectives, the third embodiment of the present invention proposes an intelligent chair, comprising: a pressure sensor array; a lumbar support adjustment mechanism; and a controller, wherein the controller comprises a memory and a processor, the memory storing a computer program, and when the computer program is executed by the processor, the adaptive lumbar tracking method proposed in the first embodiment of the present invention is implemented.

[0019] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of an adaptive waist tracking method according to an embodiment of the present invention;

[0021] Figure 2 This is a flow chart of an adaptive waist-chasing method according to a specific embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of a smart chair according to an embodiment of the present invention;

[0023] Figure 4 4 is a structural block diagram of a controller according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0025] Related technologies use fixed thresholds to adjust lumbar support, or preset modes to select settings. For example, after obtaining pressure data from a pressure sensor, a simple threshold is used to determine the user's sitting posture, and the lumbar support structure is adjusted according to fixed parameters.

[0026] The above-mentioned lumbar support adjustment method has obvious defects: First, it cannot adapt to the basic pressure differences of users of different body shapes. The pressure data of fatter and thinner users in the same sitting posture are different, and the fixed threshold is difficult to accurately identify; second, for a variety of sitting postures, such as left leaning, right leaning, forward leaning, leaning back and other dynamically changing postures, the fixed threshold judgment method cannot be adjusted in real time, resulting in a mismatch between lumbar support and human needs; third, the behavioral habits of different users vary greatly, and existing seats lack the ability to learn and adapt to user habits, and cannot achieve a personalized comfort experience.

[0027] To solve the above problems, the present invention provides an adaptive waist tracking method, a computer-readable storage medium, and a smart seat. The adaptive waist tracking method, computer-readable storage medium, and smart seat of the present invention are described in detail below with reference to the accompanying drawings and specific implementations.

[0028] The adaptive waist tracking method of the embodiment of the present invention is used in a smart seat, which is equipped with a pressure sensor array and a waist support adjustment mechanism.

[0029] In practice, multiple pressure sensors can be arranged in the seat cushion, lumbar support, backrest support, and other locations of the smart chair to form a pressure sensor array. This can collect pressure data at different points on the smart chair after the user sits in the smart chair. It should be noted that the embodiments of the present invention do not limit the number of pressure sensors in the pressure sensor array.

[0030] Practically, the lumbar support adjustment mechanism can adjust the lumbar support parameters such as the left and right support strength, support angle, etc. It should be noted that the embodiment of the present invention does not limit the specific structure of the lumbar support adjustment mechanism.

[0031] Figure 1 FIG. 1 is a flow chart of an adaptive waist tracking method according to an embodiment of the present invention. Figure 1 As shown, the adaptive waist tracking method may include:

[0032] S101, obtaining real-time pressure data of the current user collected by the pressure sensor array;

[0033] S102, extracting pressure characteristic parameters based on the real-time pressure data, and using a pre-trained body shape recognition model to determine the current user's body shape category based on the pressure characteristic parameters;

[0034] S103, using a pre-trained sitting posture recognition model to determine the current sitting posture type and initial pressure threshold of the current user based on the real-time pressure data;

[0035] S104, determining a target pressure threshold based on the real-time pressure data, the body type category, and the initial pressure threshold;

[0036] S105 , adjusting the support parameters of the lumbar support adjustment mechanism according to the target pressure threshold, so that the lumbar support matches the user's lumbar condition.

[0037] In order to achieve a personalized comfort experience for users, the embodiments of the present invention determine the target pressure threshold by combining the real-time pressure data collected by the pressure sensor array, the user's body shape and current sitting posture, and adjust the support parameters of the lumbar support adjustment mechanism according to the target pressure threshold to perform personalized lumbar adaptation.

[0038] Specifically, the pressure data of the current user at different points on the smart seat collected in real time by the pressure sensor array configured on the smart seat is obtained to obtain real-time pressure data. The pressure data includes at least cushion pressure, waist pressure, back pressure and other data. The real-time pressure data characteristics are analyzed to extract pressure characteristic parameters, and the extracted pressure characteristic parameters are input into a pre-trained body shape recognition model to obtain the body shape category of the current user. The real-time pressure data is input into a pre-trained sitting posture recognition model to obtain the current sitting posture type of the current user and the initial pressure threshold of the lumbar support. The initial pressure threshold is adjusted according to the real-time pressure data and body shape category to determine the target pressure threshold, and the support parameters of the lumbar support adjustment mechanism are adjusted according to the target pressure threshold to match the lumbar support with the user's lumbar condition, thereby realizing personalized lumbar support adjustment for the user and improving the user's comfort experience.

[0039] The present invention utilizes a closed-loop feedback mechanism during the adaptive tracking process. Specifically, during lumbar support adjustment, the adjustment strategy is further optimized based on real-time pressure data feedback, forming a closed-loop system of "data acquisition - analysis and processing - support adjustment - feedback optimization," achieving dynamic tracking and effective tracking of the lumbar support adjustment mechanism.

[0040] The adaptive waist tracking method in the embodiment of the present invention extracts features from real-time pressure data, uses a pre-trained body shape recognition model to determine the current user's body shape category based on the extracted pressure feature parameters, uses a pre-trained sitting posture recognition model to determine the current user's current sitting posture type and initial pressure threshold based on the real-time pressure data, adjusts the initial pressure threshold based on the real-time pressure data and body shape category, determines the target pressure threshold, and adjusts the support parameters of the lumbar support adjustment mechanism based on the target pressure threshold to perform personalized waist tracking adaptation and achieve a personalized comfort experience for the user.

[0041] In one embodiment of the present invention, before acquiring the real-time pressure data of the current user collected by the pressure sensor array, the adaptive waist tracking method may further include:

[0042] Preprocess the real-time pressure data of the current user collected by the pressure sensor array.

[0043] Specifically, the pressure data collected by the pressure sensor array is pre-processed, including filtering, to obtain real-time pressure data after filtering and other pre-processing, thereby obtaining authentic and valid pressure data. Pressure feature extraction, body shape recognition, and sitting posture recognition are then performed based on this processed real-time pressure data to obtain accurate body shape and sitting posture recognition results.

[0044] Implementable, such as Figure 2 As shown, the Kalman filter algorithm is used to filter the real-time pressure data of the current user collected by the pressure sensor array to eliminate random noise in the real-time pressure data and extract real and effective pressure data.

[0045] In one embodiment of the present invention, pressure characteristic parameters are extracted based on real-time pressure data, including: feature extraction of real-time seat cushion pressure data, real-time waist pressure data, real-time back pressure data and other data to obtain pressure characteristic parameters, wherein the pressure characteristic parameters may include parameters such as the pressure center of gravity position and contact area.

[0046] In one embodiment of the present invention, Figure 2 As shown, the pressure characteristic parameters include the pressure center position and the contact area. The pre-trained body shape recognition model is used to determine the current user's body shape category based on the pressure characteristic parameters, which may include:

[0047] The pressure center position and contact area are input into a pre-trained body shape recognition model to obtain the body shape category of the current user.

[0048] Specifically, if Figure 2 As shown, the pressure center position and contact area are input into a pre-trained body shape recognition model to obtain the body shape category of the current user.

[0049] In the embodiment of the present invention, the body type categories include at least thin, medium, obese, etc. It should be noted that the embodiment of the present invention does not limit the specific body type categories, and the body type categories can be further subdivided.

[0050] As a specific example, the training process of a body shape recognition model includes: obtaining a pressure feature training set, wherein the pressure feature training set includes the pressure center of gravity position, contact area, and actual body shape category corresponding to users of different body shapes. The pressure center of gravity position and contact area in the pressure feature training set are input into the body shape recognition model to obtain a predicted body shape category. The body shape recognition model loss function is determined based on the actual body shape category and the predicted body shape category. Based on the body shape recognition model loss function, the parameters in the body shape recognition model are adjusted to obtain a trained body shape recognition model. The trained body shape recognition model is then tested and verified using a pressure feature test set and a pressure feature validation set. The trained body shape recognition model that meets preset requirements is recorded as a trained body shape recognition model.

[0051] It should be noted that the embodiment of the present invention does not limit the training method of the body shape recognition model.

[0052] In one embodiment of the present invention, Figure 2 As shown, using a pre-trained sitting posture recognition model to determine the current sitting posture type and initial pressure threshold of the current user according to real-time pressure data may include:

[0053] The real-time pressure data is input into the pre-trained sitting posture recognition model to obtain the current sitting posture type and initial pressure threshold.

[0054] In the embodiment of the present invention, the sitting posture type can at least include leaning left, leaning right, leaning forward, leaning back, etc. It should be noted that the embodiment of the present invention does not limit the specific sitting posture type, and the sitting posture type can be further subdivided.

[0055] Practically, the sitting posture recognition model adopts a self-organizing neural network model.

[0056] As a specific example, the training process of the sitting posture recognition model includes: obtaining a pressure data training set, wherein the pressure data training set includes pressure data of different users in different sitting postures, real sitting posture types and real pressure thresholds. The pressure data in the pressure data training set is input into the sitting posture recognition model to obtain a predicted sitting posture type and a predicted pressure threshold. The sitting posture loss function is determined according to the real sitting posture type and the predicted sitting posture type, the pressure threshold loss function is determined according to the real pressure threshold and the real pressure threshold, and the parameters of the sitting posture recognition model are adjusted based on the sitting posture loss function and the pressure threshold loss function. The trained sitting posture recognition model is then tested and verified using the pressure data test set and the pressure feature verification set, and the trained sitting posture recognition model that meets the preset requirements is recorded as a trained sitting posture recognition model.

[0057] It should be noted that the embodiment of the present invention does not limit the training method of the sitting posture recognition model.

[0058] The embodiment of the present invention can also monitor the changes in pressure data in real time, that is, calculate the changes in pressure data based on the pressure data at the current moment and the pressure data at the previous moment, and use adaptive algorithms, such as the extended Kalman filter algorithm, to re-train the trained sitting posture recognition model to predict the user's sitting posture state at the next moment, thereby achieving accurate tracking of the user's dynamic sitting posture.

[0059] In one embodiment of the present invention, the real-time pressure data includes waist pressure, and determining the target pressure threshold according to the real-time pressure data, the body type category, and the initial pressure threshold includes:

[0060] Adjusting the initial pressure threshold according to waist pressure and body type to obtain a target pressure threshold, wherein adjusting the initial pressure threshold according to waist pressure includes:

[0061] If the waist pressure is greater than the initial pressure threshold and lasts for a preset time, the initial pressure threshold is increased;

[0062] If the waist pressure is less than the initial pressure threshold and lasts for a preset time, the initial pressure threshold is reduced.

[0063] In one embodiment, when adjusting the initial pressure threshold based on body type, if the body type is thin (small base), the initial pressure threshold is decreased by a preset ratio. If the body type is obese (large base), the initial pressure threshold is increased by a preset ratio.

[0064] In one specific embodiment, when adjusting the initial pressure threshold based on lumbar pressure, if the lumbar pressure detected by the pressure sensor array is continuously greater than the initial pressure threshold, it indicates that the current lumbar support does not meet the lumbar support needs of the current user, and the initial pressure threshold can be increased by a preset step length. If the lumbar pressure detected by the pressure sensor array is continuously less than the initial pressure threshold, it indicates that the current lumbar support does not meet the lumbar support needs of the current user, and the initial pressure threshold can be decreased by a preset step length.

[0065] In a specific embodiment, after adjusting the initial pressure threshold according to the body type category, the adjusted initial pressure threshold is adjusted again according to the waist pressure, and when the waist pressure collected by the pressure sensor array is equal to the adjusted initial pressure threshold, the adjusted initial pressure threshold is recorded as the target pressure threshold.

[0066] In an embodiment of the present invention, the pressure threshold may be a specific pressure value or a pressure range. When the pressure threshold is a pressure range, if the waist pressure is greater than the upper limit of the initial pressure range and persists for a preset time, the initial pressure threshold is increased; if the waist pressure is less than the lower limit of the initial pressure range and persists for a preset time, the initial pressure threshold is decreased.

[0067] The embodiment of the present invention dynamically adjusts the target pressure threshold under different sitting postures through the extended Kalman filter algorithm according to the current user's body type, current sitting posture type and real-time pressure data, automatically moves the threshold up or down, and realizes adaptive target threshold adjustment.

[0068] In one embodiment of the present invention, the support parameter includes support strength, and adjusting the support parameter of the lumbar support adjustment mechanism according to the target pressure threshold may include:

[0069] The support strength of the lumbar support adjustment mechanism is adjusted according to the target pressure threshold.

[0070] Specifically, the lumbar support adjustment mechanism adjusts the support strength based on the target pressure threshold, and the support angle can be adjusted based on the sitting posture. During this adjustment process, real-time pressure data is continuously monitored, and the support strength and angle of the lumbar support adjustment mechanism are further adjusted based on this real-time pressure data.

[0071] This embodiment of the present invention controls the operation of the lumbar support adjustment mechanism based on the target pressure threshold and real-time pressure data, adjusting parameters such as the force and angle of the lumbar support to match the user's physical condition. During the adjustment process, pressure data is continuously monitored, and the lumbar support adjustment strategy is further optimized based on this data feedback.

[0072] In one embodiment of the present invention, Figure 2 As shown, the adaptive waist-chasing method may further include:

[0073] After determining the current user's body type, a user profile is created based on the body type, and the target pressure thresholds corresponding to different sitting postures for the body type and the support parameters of the lumbar support adjustment mechanism are recorded in real time. The user profile includes at least the user's body type, the target pressure thresholds and initial pressure thresholds for different sitting postures, and the support parameters of the lumbar support adjustment mechanism.

[0074] After determining the user's body type, the embodiment of the present invention creates a profile for the user to record the user's sitting posture data, target pressure threshold, and support parameters of the lumbar support adjustment mechanism in different time periods and different usage scenarios.

[0075] Specifically, when creating a user profile, data generated by the current user while using the smart chair is recorded under the same body type category as the current user's profile. For example, the data generated by the current user while using the smart chair may include sitting posture data for different time periods and usage scenarios, target and initial pressure thresholds for different sitting postures, and support parameters for the lumbar support adjustment mechanism.

[0076] The embodiment of the present invention utilizes a pre-trained body shape recognition model and pressure characteristic parameters to accurately distinguish users of different body shapes and establish a personalized profile for each user, thus solving the problem that a fixed threshold cannot adapt to body shape differences and can accurately adapt to different body shapes.

[0077] It should be noted that user profiles can be updated and saved in real time, or automatically updated and saved when a preset time is reached, such as 10 minutes or 30 minutes.

[0078] In one embodiment of the present invention, the adaptive waist tracking method may further include:

[0079] Obtain a user profile, train a pre-trained sitting posture recognition model based on target pressure thresholds and initial pressure thresholds corresponding to different sitting postures of the same body type in the user profile, and update the pre-trained sitting posture recognition model.

[0080] In order to further improve the accuracy of the initial pressure threshold generated by the sitting posture recognition model, learn user habits, use the established user profile to further train the sitting posture recognition model, and update the pre-trained sitting posture recognition model.

[0081] Specifically, real-time pressure data after Kalman filtering is fed into the body shape recognition model and sitting posture recognition model deployed on the smart chair. The body shape recognition model identifies the user's body shape based on pressure feature parameters extracted from the real-time pressure data. The sitting posture recognition model identifies the user's current sitting posture based on the real-time pressure data and generates an initial pressure threshold. During further training of the sitting posture recognition model, the body shape category, current sitting posture type, and initial pressure threshold output by the body shape recognition model are obtained. Simultaneously, target pressure thresholds corresponding to different sitting postures within the same body shape category are retrieved from the user's profile. The user's sitting habits are then compared and inferred, and the pressure threshold distribution associated with these sitting postures is compared. The parameters of the sitting posture recognition model are updated based on the initial pressure threshold for the specific sitting posture generated by the sitting posture recognition model and the pressure threshold distribution for the same body shape category and sitting posture recorded in the user's profile. After the update is complete, the parameters of the sitting posture recognition model are evaluated multiple times to see if they meet the requirements according to pre-set evaluation criteria. If they do not meet the requirements, the model immediately enters the fast update channel for another update. After the update, the model continues to be evaluated until the pre-set evaluation criteria are met.

[0082] The embodiment of the present invention utilizes a body shape recognition model to identify the body shape of the user, creates separate files according to body shape categories, and retains parameters of multiple sets of adaptive sitting posture recognition models to meet the needs of users of different body shapes.

[0083] This embodiment of the present invention records and updates user profiles by recording user sitting posture data and lumbar support adjustment parameters across different time periods and usage scenarios. Using an incremental learning algorithm, it incorporates new data into the user profile, updates the user's sitting posture recognition model and pressure threshold parameters, and learns and adapts to user behavior habits.

[0084] It should be noted that when updating the pre-trained sitting posture recognition model, the user profile and sitting posture recognition model update process can be automatically triggered when the current user uses the seat for a preset time.

[0085] The adaptive waist tracking method of an embodiment of the present invention creates independent files for different users, records information such as body type, target pressure thresholds under different sitting posture types, support parameters of the lumbar support adjustment mechanism, and user usage habits, and uses incremental learning to dynamically update the files and the sitting posture recognition model. This allows personalized waist tracking adaptation in multi-user scenarios.

[0086] The adaptive waist tracking method in this embodiment of the present invention utilizes a Kalman filter algorithm to preprocess pressure data, effectively suppressing noise interference, improving data accuracy and stability, and providing a reliable basis for subsequent identification and adjustment. This embodiment of the present invention uses a Kalman filter algorithm to filter the noise floor of the raw pressure data before importing it into a sitting posture recognition model. This method updates and compares the user's sitting posture habits, dynamically adjusting the parameters of the adaptive sitting posture recognition model in real time to achieve optimal waist tracking.

[0087] The adaptive waist tracking method in the embodiment of the present invention combines the self-organizing network model and the extended Kalman filter algorithm to achieve real-time recognition and accurate prediction of the user's dynamic sitting posture. Whether it is a static sitting posture or a dynamically changing posture, the waist support can be adjusted in time to achieve dynamic tracking of various sitting postures.

[0088] The adaptive waist tracking method in the embodiment of the present invention creates a profile based on the body shape recognition result. Users with large body shape differences are separately profiled. The profile content is the pressure threshold corresponding to the sitting posture recognized by the sitting posture recognition model.

[0089] The adaptive waist tracking method in the embodiment of the present invention efficiently learns user habits, adopts an incremental learning algorithm, continuously learns user behavioral habits, and automatically updates user profiles. The longer the seat is used, the higher the adaptability to the user, greatly improving the user's personalized comfort experience.

[0090] The adaptive waist tracking method in the embodiment of the present invention adopts a multi-dimensional user adaptation strategy to build a complete adaptive adjustment system from four dimensions: body shape recognition, dynamic sitting posture tracking, threshold adaptive adjustment, and user habit learning.

[0091] The present invention provides a computer-readable storage medium.

[0092] In this embodiment, a computer program is stored on a computer-readable storage medium. When the computer program is executed by a processor, the above-mentioned adaptive waist tracking method is implemented.

[0093] The invention provides an intelligent chair.

[0094] Figure 3 FIG is a schematic diagram of a smart chair according to an embodiment of the present invention. Figure 3 As shown, the smart chair 1000 may include: a pressure sensor array 100; a lumbar support adjustment mechanism 200; and a controller 500, wherein the controller 500 includes a memory and a processor, and a computer program is stored in the memory. When the computer program is executed by the processor, the adaptive lumbar tracking method as described above is implemented.

[0095] Figure 4 4 is a structural block diagram of a controller according to an embodiment of the present invention.

[0096] like Figure 4 As shown, controller 500 includes a processor 501 and a memory 503. Processor 501 and memory 503 are connected, for example, via a bus 502. Optionally, controller 500 may further include a transceiver 504. It should be noted that in practical applications, the number of transceivers 504 is not limited to one, and the structure of controller 500 does not constitute a limitation on the embodiments of the present invention.

[0097] The processor 501 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the present disclosure. The processor 501 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0098] The bus 502 may include a path for transmitting information between the above components. The bus 502 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 502 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0099] The memory 503 is used to store a computer program corresponding to the adaptive waist tracking method of the above embodiment of the present invention, and the computer program is controlled and executed by the processor 501. The processor 501 is used to execute the computer program stored in the memory 503 to implement the content shown in the above method embodiment. Figure 4 The controller 500 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0100] The computer-readable storage medium and the smart seat in the embodiments of the present invention can implement adaptive waist tracking in multiple scenarios based on the above-mentioned adaptive waist tracking method.

[0101] It should be noted that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion having one or more wires (electronic device), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0102] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0103] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0104] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0105] Furthermore, 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 the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0106] In the present invention, unless otherwise specified or limited, the terms "installed," "connected," "connect," "fixed," etc. should be understood in a broad sense. For example, they can refer to fixed connection, detachable connection, or integration; mechanical connection, electrical connection; direct connection, or indirect connection through an intermediate medium; internal communication between two components, or interaction between two components, unless otherwise specified. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0107] In the present invention, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediary. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0108] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. An adaptive waist tracking method, characterized in that: For a smart seat equipped with a pressure sensor array and a lumbar support adjustment mechanism, the method includes: Acquiring real-time pressure data of the current user collected by the pressure sensor array; Extracting pressure characteristic parameters according to the real-time pressure data, and determining the body type category of the current user according to the pressure characteristic parameters using a pre-trained body type recognition model; Determine the current sitting posture type and initial pressure threshold of the current user according to the real-time pressure data using a pre-trained sitting posture recognition model; determining a target pressure threshold according to the real-time pressure data, the body type category, and the initial pressure threshold; The support parameters of the lumbar support adjustment mechanism are adjusted according to the target pressure threshold so that the lumbar support matches the user's lumbar condition.

2. The adaptive waist tracking method according to claim 1, characterized in that: Before acquiring the real-time pressure data of the current user collected by the pressure sensor array, the method further includes: Preprocessing is performed on the real-time pressure data of the current user collected by the pressure sensor array.

3. The adaptive waist tracking method according to claim 1, characterized in that: The pressure characteristic parameters include the pressure center position and the contact area, and the determining the body type of the current user based on the pressure characteristic parameters using a pre-trained body type recognition model includes: The pressure center position and the contact area are input into the pre-trained body shape recognition model to obtain the body shape category of the current user.

4. The adaptive waist tracking method according to claim 1, characterized in that: The determining the current sitting posture type and the initial pressure threshold of the current user according to the real-time pressure data using a pre-trained sitting posture recognition model includes: The real-time pressure data is input into the pre-trained sitting posture recognition model to obtain the current sitting posture type and the initial pressure threshold.

5. The adaptive waist tracking method according to claim 1, characterized in that: The real-time pressure data includes waist pressure, and determining the target pressure threshold according to the real-time pressure data, the body type category, and the initial pressure threshold includes: Adjusting the initial pressure threshold according to the waist pressure and the body type category to obtain the target pressure threshold, wherein adjusting the initial pressure threshold according to the waist pressure includes: If the waist pressure is greater than the initial pressure threshold and lasts for a preset time, increasing the initial pressure threshold; If the waist pressure is less than the initial pressure threshold and lasts for a preset time, the initial pressure threshold is reduced.

6. The adaptive waist tracking method according to claim 1, characterized in that: The support parameter includes support strength, and adjusting the support parameter of the lumbar support adjustment mechanism according to the target pressure threshold includes: The support strength of the lumbar support adjustment mechanism is adjusted according to the target pressure threshold.

7. The adaptive waist tracking method according to claim 1, characterized in that: The method further comprises: After determining the body type category of the current user, a user profile is established based on the body type category, and the target pressure thresholds corresponding to different sitting postures of the body type category and the support parameters of the lumbar support adjustment mechanism are recorded in real time, wherein the user profile includes at least the user's body type category, the target pressure thresholds and initial pressure thresholds under different sitting postures, and the support parameters of the lumbar support adjustment mechanism.

8. The adaptive waist tracking method according to claim 1, characterized in that: The method further comprises: The user profile is obtained, and the pre-trained sitting posture recognition model is trained according to the target pressure thresholds and initial pressure thresholds corresponding to different sitting postures of the same body type in the user profile, and the pre-trained sitting posture recognition model is updated.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the adaptive waist tracking method according to any one of claims 1 to 8 is implemented.

10. A smart chair, characterized in that: include: pressure sensor array; Lumbar support adjustment mechanism; A controller, wherein the controller comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the adaptive waist tracking method according to any one of claims 1 to 8 is implemented.

Images