Pressure feedback control method and system of stroke patient closestool sitting assisting system

Abstract

The invention provides a pressure feedback control method and system of a stroke patient closestool sitting assisting system. The method comprises the following steps: firstly, acquiring a pressure distribution data sequence; secondly, acquiring an electric signal intensity data sequence; then, the pressure center track and the muscle activation time sequence are subjected to cooperative calculation, and an abnormal force exerting mode generated by dyskinesia after stroke is obtained; a dynamic auxiliary torque instruction is generated based on the dynamic identification result; and finally outputting auxiliary torque to guide the gravity center of the body of the patient to move along a preset safe sitting track. According to the technical scheme provided by the invention, the abnormal force exerting mode of the stroke patient is dynamically identified by fusing the pressure signal and the electromyographic signal, the personalized auxiliary torque complementary to the abnormal force exerting mode is generated, and the gravity center of the body of the patient is guided to move along the safe track in real time through closed-loop adjustment; therefore, the naturalness and coordination of action completion are improved while the safety is ensured.

Description

Technical Field

[0001] This application relates to the field of medical device control technology, and in particular to a pressure feedback control method and system for a toilet sitting assistance system for stroke patients. Background Technology

[0002] Stroke patients often experience limb motor dysfunction due to nerve damage. When transitioning between sitting down and standing up on the toilet, they face a very high risk of falling. Therefore, there is an urgent need for an intelligent system that can provide real-time, adaptive assistance to ensure their safety and independence during toilet use.

[0003] There is a pressure-sensing sitting assistance system in the prior art, which uses a pressure sensor installed in the seat to sense changes in the user's center of gravity and controls the lifting mechanism accordingly to provide simple upward or downward assistance.

[0004] However, the existing solution has obvious drawbacks. It only responds mechanically based on pressure information and cannot identify abnormal force patterns caused by specific motor dysfunctions in patients. As a result, the auxiliary force provided is fixed and unidirectional and cannot coordinate with the patient's real-time muscle strength and postural changes. Therefore, it is inadequate to cope with complex and personalized rehabilitation needs, and may even interfere with the patient's natural movement trajectory due to improper assistance. Summary of the Invention

[0005] This application provides a pressure feedback control method and system for a toilet sitting assistance system for stroke patients, which solves the problem that the existing technology relies on only a single pressure information, resulting in mechanical and fixed assist force, which cannot adapt to the patient's real-time changing muscle strength state and abnormal force exertion patterns, thus leading to poor assist effect and lack of personalized coordination.

[0006] In a first aspect, this application provides a pressure feedback control method for a toilet sitting-up assist system for stroke patients, comprising: During the transition from sitting to standing on the toilet, the pressure distribution data of the stroke patient's buttocks is collected in real time by a pressure sensor array pre-installed under the seat cushion, and a pressure distribution data sequence is obtained. Electromyographic signal data of specific muscle groups in the affected lower limb of the stroke patient were collected simultaneously to obtain an electrical signal intensity data sequence; The pressure center trajectory reflected by the pressure distribution data sequence and the muscle activation timing represented by the electromyographic signal data sequence are co-calculated to dynamically identify the abnormal force patterns of the stroke patient due to post-stroke motor dysfunction and output the dynamic identification results. Based on the dynamic identification results, a dynamic auxiliary torque command is generated to counteract the abnormal force application mode; According to the dynamic auxiliary torque command, the sitting assistance actuator is controlled to output an auxiliary torque that complements the direction of the stroke patient's own force, so as to guide the stroke patient's center of gravity to move along a preset safe sitting trajectory.

[0007] Optionally, during the transition from sitting to standing on the toilet, a pressure sensor array pre-installed under the seat collects pressure distribution data of the stroke patient's buttocks in real time, resulting in a pressure distribution data sequence, including: When the total pressure value sensed by the pressure sensor array continuously increases from zero and exceeds the first preset pressure threshold, it is determined that the stroke patient has begun to sit down, and the data recording process is initiated. During the transition between sitting and standing, the pressure sensor array is used to collect the instantaneous pressure values ​​of all pressure sensor units at a preset fixed time interval. The collection of instantaneous pressure values ​​from all pressure sensing units acquired in each acquisition constitutes a pressure distribution snapshot. Multiple pressure distribution snapshots are recorded sequentially in chronological order, and the pressure distribution snapshots arranged in chronological order are combined to form a pressure distribution data sequence.

[0008] Optionally, electromyographic signal data of specific muscle groups in the affected lower limb of the stroke patient are collected simultaneously to obtain an electrical signal intensity data sequence, including: When the total pressure value sensed by the pressure sensing array exceeds the first preset pressure threshold, the electromyography signal acquisition electrode is simultaneously activated to acquire data. Each of the electromyography (EMG) signal acquisition electrodes acquires an instantaneous electrical signal intensity value at the same fixed time interval as the pressure distribution snapshot acquired by the pressure sensing array; Multiple instantaneous electrical signal intensity values ​​obtained from all electromyography (EMG) signal acquisition electrodes at the same time interval are aggregated to form a multi-channel EMG signal snapshot; Multiple multi-channel electromyographic signal snapshots are recorded sequentially in chronological order, and the chronologically arranged multi-channel electromyographic signal snapshots are combined to form the electrical signal intensity data sequence.

[0009] Optionally, the pressure center trajectory reflected by the pressure distribution data sequence and the muscle activation timing represented by the electromyographic signal data sequence are co-calculated to dynamically identify the abnormal force patterns of the stroke patient due to post-stroke motor dysfunction and output the dynamic identification results, including: For each pressure distribution snapshot in the pressure distribution data sequence, the position of the pressure center point is calculated, and the pressure center point positions are connected in chronological order to form the pressure center movement trajectory. For each multi-channel electromyography (EMG) snapshot in the electrical signal intensity data sequence, the activation levels of extensor muscles and flexor muscles are calculated. The direction and speed of the movement of the pressure center trajectory are compared with the proportional relationship between the activation degree of the extensor muscle group and the activation degree of the flexor muscle group to obtain the comparison results. Based on the pairing comparison results, dynamic identification results with abnormal force exertion mode categories are output in real time.

[0010] Optionally, based on the dynamic identification result, a dynamic auxiliary torque command to counteract the abnormal force application mode is generated, including: Receive the dynamic identification results, and generate an initial auxiliary torque command for the abnormal force application patterns identified in the dynamic identification results; The directional component of the torque in the initial auxiliary torque command is determined based on the direction and distance of the pressure center movement trajectory deviating from the preset safe sitting trajectory in real time; Based on the proportional relationship between the activation levels of the extensor muscle group and the activation levels of the flexor muscle group, and the moving speed of the pressure center trajectory, the magnitude component of the torque in the initial auxiliary torque command is determined; By fusing the directional and magnitude components of the torque, a dynamic auxiliary torque command is obtained.

[0011] Optionally, according to the dynamic assist torque command, the sitting assist actuator is controlled to output an assist torque that complements the direction of the stroke patient's own force exertion, so as to guide the stroke patient's center of gravity to move along a preset safe sitting trajectory, including: Receive the dynamic auxiliary torque command and parse out the target torque direction and target torque magnitude to be output; Based on the target torque direction obtained from the analysis, determine the specific unit in the assist actuator that needs to provide thrust; Based on the target torque obtained from the analysis, it is converted into the power parameters required to drive the specific unit, and the power source is controlled to output the corresponding power. When the specific unit receives power from the power source, it generates an artificial thrust with a specific direction and magnitude. The artificial thrust works in conjunction with the stroke patient's own muscle strength to form a complementary auxiliary torque. During the output of the artificial thrust, new pressure distribution data sequences and new electrical signal strength data sequences are continuously acquired, and the direction and magnitude of the artificial thrust are adjusted in real time based on the new dynamic identification results to form a closed-loop control process until the total pressure value of the pressure sensor array is detected to drop below the second preset pressure threshold, indicating that the sitting and standing action conversion is completed. Then, the output of auxiliary torque is stopped to complete the pressure feedback control.

[0012] Optionally, receiving the dynamic auxiliary torque command and parsing the target torque direction and target torque magnitude to be output includes: Read the direction vector and numerical parameter portions contained in the dynamic auxiliary torque command; The direction of the target torque is determined based on the orientation of the direction vector portion in a predefined coordinate system; The command intensity value represented by the numerical parameter is converted into a physical quantity that the sitting auxiliary actuator can directly execute according to a preset mapping relationship, and the physical quantity is defined as the target torque magnitude. The direction and magnitude of the target torque are combined to form control parameters for controlling the actions of specific units in the power assist actuator.

[0013] Secondly, this application provides a pressure feedback control system for a toilet sitting assistance system for stroke patients, comprising: The first acquisition module is used to acquire pressure distribution data of the stroke patient's buttocks in real time through a pressure sensor array pre-installed under the seat cushion during the transition between sitting and standing on the toilet, and to obtain a pressure distribution data sequence. The second acquisition module is used to synchronously acquire electromyographic signal data of specific muscle groups in the affected lower limb of the stroke patient to obtain an electrical signal intensity data sequence. The calculation module is used to perform collaborative calculation of the pressure center trajectory reflected by the pressure distribution data sequence and the muscle activation timing represented by the electromyographic signal data sequence, so as to dynamically identify the abnormal force pattern generated by the stroke patient due to post-stroke motor dysfunction and output the dynamic identification result. The generation module is used to generate a dynamic auxiliary torque command to counteract the abnormal force application mode based on the dynamic identification results. The control module is used to control the sitting assistance actuator to output an auxiliary torque that complements the direction of the stroke patient's own force, according to the dynamic auxiliary torque command, so as to guide the stroke patient's center of gravity to move along a preset safe sitting trajectory.

[0014] Thirdly, this application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a pressure feedback control method for a toilet sitting assistance system for stroke patients as described in the first aspect above.

[0015] Fourthly, this application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a pressure feedback control method for a toilet sitting assistance system for stroke patients as described in the first aspect.

[0016] This application simultaneously collects pressure distribution data from the buttocks of stroke patients and electromyographic signal data from the affected lower limb. It collaboratively calculates the trajectory of the pressure center reflecting the shift of the body's center of gravity and the muscle activation sequence reflecting the intention of muscle nerve control. This allows for the dynamic and precise identification of specific abnormal force patterns caused by post-stroke motor dysfunction. Based on this identification, targeted dynamic assistive torque commands are generated, and the actuator outputs an assistive torque complementary to the patient's own force direction. Ultimately, this achieves personalized and adaptive guidance of the patient's body's center of gravity movement, effectively improving the safety and naturalness of the assistive process in accordance with rehabilitation principles.

[0017] Furthermore, the specific process of parsing the dynamic auxiliary torque command from the higher-level controller into executable control parameters was clarified. By reading the direction vector and numerical parameters in the command and mapping them to specific torque directions and magnitudes, it was ensured that the control intent was accurately and unambiguously converted into the action basis for driving the execution unit. This step ensured that the personalized auxiliary strategy generated by the aforementioned method could be executed precisely, forming a reliable closed loop from intelligent decision-making to physical action, thus enhancing the response accuracy and control reliability of the entire system.

[0018] These or other aspects of this application will become more apparent from the description of the following embodiments. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart of a pressure feedback control method for a toilet sitting assistance system for stroke patients provided in this application is shown; Figure 2 This invention provides a schematic diagram of the pressure feedback control system of a toilet sitting assistance system for stroke patients. Figure 3 A schematic diagram of the structure of a computing device provided in this application is shown. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present application, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0022] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0023] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] Figure 1 This application provides a flowchart of a pressure feedback control method for a toilet sitting assistance system for stroke patients, as shown in the flowchart. Figure 1 As shown, the method includes: Step 101: During the transition from sitting to standing on the toilet, the pressure distribution data of the stroke patient's buttocks is collected in real time by a pressure sensor array pre-installed under the seat cushion to obtain a pressure distribution data sequence.

[0025] Optionally, step 101 may specifically include the following steps: Step 1011: When the total pressure value sensed by the pressure sensor array is detected to continuously increase from zero and exceed the first preset pressure threshold, it is determined that the stroke patient has started to sit down and the data recording process is initiated. Step 1012: During the sitting-standing transition, the pressure sensor array is used to collect the instantaneous pressure values ​​of all pressure sensor units once at a preset fixed time interval. Step 1013: Collect the instantaneous pressure values ​​of all pressure sensing units obtained from each acquisition to form a pressure distribution snapshot. Step 1014: Record multiple pressure distribution snapshots sequentially in chronological order, and combine the chronologically arranged pressure distribution snapshots to form a pressure distribution data sequence.

[0026] In the above scheme, the sitting-to-standing transition process refers to the two continuous postural changes that a stroke patient completes on the toilet: from standing to sitting, and from sitting to standing. The pressure sensor array is a pad-like structure composed of multiple miniature sensor units arranged in a regular grid, capable of sensing the magnitude of physical pressure. It is placed on the toilet seat to sense the pressure distribution when the buttocks contact the seat.

[0027] Pressure distribution data refers to the set of pressure values ​​simultaneously measured by all sensor units in the pressure sensing array at a specific instant, reflecting the two-dimensional spatial distribution of hip pressure at that moment. A pressure distribution data sequence refers to a sequence of multiple consecutive pressure distribution data arranged chronologically, recording the continuous change in hip pressure distribution during the transition from sitting to standing. The total pressure value is the sum of the pressure values ​​measured by all sensor units in the pressure sensing array at the same instant, used to roughly characterize the overall load applied by the patient to the cushion. The first preset pressure threshold is a pre-set reference line for determining whether the patient has begun sitting; when the total pressure value exceeds this reference line, the system considers the effective sitting action to have begun. The data recording process refers to a series of operations in which the system transitions from sleep or standby mode to active operation, continuously collecting and saving sensor data according to predetermined rules. An instantaneous pressure value refers to a pressure reading collected by a single pressure sensing unit within a very short measurement time window. A pressure distribution snapshot is a visual synonym for the pressure distribution data, specifically referring to a complete, static image of the pressure distribution captured at a single point in time.

[0028] In this scheme, firstly, step 1011 involves the system continuously monitoring the total pressure value sensed by the pressure sensor array. When the total pressure value is detected to be continuously increasing from zero and exceeding a first preset pressure threshold, the system determines that the patient has begun to sit down and automatically initiates the formal data recording process, enabling the system to transition from a waiting state to a high-speed data acquisition state. Secondly, in step 1012, after the system determines that the sitting-up transition process has begun, the pressure sensor array is triggered at preset fixed time intervals (e.g., 100 times per second). Each trigger synchronously collects the instantaneous pressure value of each pressure sensor unit in the array.

[0029] Next, step 1013 aggregates the instantaneous pressure values ​​from all pressure sensing units acquired during each synchronous acquisition in step 1012 to form a pressure distribution snapshot representing the overall pressure status of the buttocks at that moment. Finally, step 1014 continuously records and strings together each pressure distribution snapshot generated in step 1013 in chronological order, ultimately forming a complete pressure distribution data sequence that records the history of pressure changes throughout the entire sitting-standing transition process, providing a data foundation for subsequent analysis.

[0030] For example, patient A enters the bathroom to use the toilet. As patient A begins to sit down, their body weight gradually applies pressure to the pressure sensor array under the seat. The system calculates the sum of all pressure sensor readings in real time, i.e., the total pressure value. When the system detects that this total pressure value rises from zero and exceeds a set 5 kg threshold (the first preset pressure threshold), it immediately determines that patient A has begun to sit down and automatically initiates the data recording process. Subsequently, during the entire sitting-standing transition process of patient A—from sitting down to sitting still and then standing up—the pressure sensor array continuously collects instantaneous pressure data at a frequency of 100 times per second. Each collection generates a pressure distribution snapshot containing the instantaneous readings of all pressure sensors. The system saves these pressure distribution snapshots in chronological order, ultimately forming a complete pressure distribution data sequence depicting the dynamic changes in buttock pressure during patient A's toilet use.

[0031] This solution systematically captures the continuous and dynamic changes in hip pressure when stroke patients perform sitting or standing movements on the toilet through intelligent triggering and high-speed sampling, forming a highly timely pressure distribution data sequence, which provides a reliable and complete data foundation for subsequent accurate analysis of the patient's posture and force exertion patterns.

[0032] Step 102: Simultaneously collect electromyographic signal data of specific muscle groups in the affected lower limb of the stroke patient to obtain an electrical signal intensity data sequence.

[0033] Optionally, step 102 may specifically include the following steps: Step 1021: When the total pressure value sensed by the pressure sensing array exceeds the first preset pressure threshold, the electromyography signal acquisition electrode is simultaneously activated to acquire data. Step 1022: Each of the electromyography signal acquisition electrodes acquires an instantaneous electrical signal intensity value at the same fixed time interval as the pressure distribution snapshot acquired by the pressure sensing array; Step 1023: Collect multiple instantaneous electrical signal intensity values ​​obtained from all electromyography signal acquisition electrodes at the same time interval to form a multi-channel electromyography signal snapshot; Step 1024: Record multiple multi-channel electromyographic signal snapshots sequentially in chronological order, and combine the sequentially arranged multi-channel electromyographic signal snapshots to form the electrical signal intensity data sequence.

[0034] In the above scheme, the specific muscle group of the lower limb refers to the main muscle group in the thigh of the side of the stroke patient whose mobility is impaired due to stroke; electromyography (EMG) signal data refers to the weak bioelectrical signals generated when muscle fibers contract in response to brain commands; the electrical signal intensity data sequence is a set of data that records the changes in the intensity of these EMG signals, arranged in chronological order; EMG signal acquisition electrodes are conductive elements attached to the skin surface for detecting muscle electrical activity; the instantaneous electrical signal intensity value is the reading of the electrical signal amplitude measured by each acquisition electrode in a very short time; and the multi-channel EMG signal snapshot is the set of electrical signal intensity values ​​obtained from all acquisition electrodes at the same time.

[0035] In this scheme, firstly, in step 1021, when the total pressure value detected by the pressure sensor array exceeds a first preset pressure threshold (indicating that the patient has begun sitting), the system simultaneously sends a start command to all electromyography (EMG) signal acquisition electrodes, ensuring that EMG signal acquisition and pressure sensor array acquisition begin synchronously. Secondly, in step 1022, each EMG signal acquisition electrode operates at the same fixed time rhythm (e.g., 100 times per second) as the pressure sensor array acquisition, recording the instantaneous electrical signal intensity value of the attached muscle at each acquisition point. Next, in step 1023, the system packages multiple instantaneous electrical signal intensity values ​​obtained from all EMG signal acquisition electrodes at the same acquisition point together, forming a multi-channel EMG signal snapshot reflecting the coordinated activity state of multiple muscles at that moment. Finally, in step 1024, the system continuously saves these multi-channel EMG signal snapshots in chronological order and connects them into a complete electrical signal intensity data sequence, thereby recording the dynamic changes in muscle activity throughout the entire sitting process.

[0036] Following the specific implementation of the previous solution, in the scenario of step 101, when patient A sits down and the total pressure value exceeds the threshold to activate the system, the electromyography (EMG) signal acquisition electrodes attached to the quadriceps and hamstring muscles of the affected thigh are also activated simultaneously. These EMG signal acquisition electrodes acquire data synchronously with the pressure sensor array at a frequency of 100 times per second, recording the instantaneous electrical signal intensity value of the corresponding muscle with each acquisition. The system combines multiple instantaneous electrical signal intensity values ​​acquired from different muscles at the same time into a multi-channel EMG signal snapshot, and continuously records as the movement continues, ultimately forming an electrical signal intensity data sequence that is perfectly aligned with the pressure data sequence time and reflects the muscle activity of the affected leg during patient A's entire sitting up and sitting down process.

[0037] This solution achieves precise time synchronization with the pressure acquisition system, fully recording the activation sequence and intensity changes of the main muscle groups in the affected lower limb when stroke patients perform sitting movements. This generates an electrical signal intensity data sequence that matches the pressure data, providing crucial muscle activity data for subsequent comprehensive analysis of motor intention and posture control.

[0038] Step 103: The pressure center trajectory reflected by the pressure distribution data sequence and the muscle activation timing represented by the electromyographic signal data sequence are co-calculated to dynamically identify the abnormal force patterns of the stroke patient caused by post-stroke motor dysfunction and output the dynamic identification results.

[0039] Optionally, step 103 may specifically include the following steps: Step 1031: For each pressure distribution snapshot in the pressure distribution data sequence, calculate the position of the pressure center point, and connect the pressure center point positions in chronological order to form a pressure center movement trajectory. Step 1032: For each multi-channel electromyography (EMG) signal snapshot in the electrical signal intensity data sequence, calculate the activation level of the extensor muscle group and the activation level of the flexor muscle group. Step 1033: The direction and speed of the movement of the pressure center trajectory are compared with the proportional relationship between the activation degree of the extensor muscle group and the activation degree of the flexor muscle group to obtain the comparison result. Step 1034: Output dynamic identification results in real time based on the pairing comparison results, with the abnormal force exertion mode category as the content.

[0040] In the above scheme, the pressure center trajectory refers to the movement path of the projection point of the body's center of gravity on the support surface; muscle activation sequence refers to the temporal relationship between the start of contraction and the peak contraction intensity of different muscle groups; motor dysfunction refers to the decline or incoordination of muscle control due to damage to the nervous system; abnormal force exertion pattern refers to the incorrect muscle exertion pattern exhibited by the patient due to functional impairment; dynamic identification result refers to the specific type of abnormal force exertion pattern judged by the system in real time; pressure center point position is a single coordinate representing the overall pressure concentration point calculated based on a pressure distribution snapshot; pressure center movement trajectory is a continuous path formed by connecting each pressure center point in chronological order; extensor group activation degree is the comprehensive value of the electrical signal intensity of the muscle group responsible for extending the joint; flexor group activation degree is the comprehensive value of the electrical signal intensity of the muscle group responsible for bending the joint; movement direction is the forward direction of the pressure center trajectory in the plane; movement speed is the speed of the pressure center movement trajectory; paired comparison result is the correspondence obtained after correlation analysis of kinematic parameters and electromyographic parameters.

[0041] In this scheme, firstly, step 1031 processes each pressure distribution snapshot in the pressure distribution data sequence, calculating the pressure center point representing the overall pressure concentration point of the buttocks based on the position and readings of each pressure sensing unit. Then, these points generated in chronological order are connected to form a continuous pressure center movement trajectory. Secondly, step 1032 simultaneously processes each multi-channel electromyography (EMG) signal snapshot in the electrical signal intensity data sequence, calculating the combined EMG values ​​for the muscle groups responsible for knee extension and flexion, respectively, to obtain two key indicators: extensor activation and flexor activation. Next, step 1033 compares and analyzes the real-time movement direction and speed of the pressure center trajectory with the proportional relationship between the extensor and flexor activation at the same time. Finally, step 1034, based on the comparison results, determines in real-time whether the patient is exhibiting a specific abnormal force exertion pattern and immediately outputs the specific dynamic identification results.

[0042] Following the specific implementation of the previous scheme, in step 102, the system uses the pressure distribution data sequence of patient A to calculate the position of the pressure center point at each moment and connects them to form a trajectory describing the movement of the pressure center during the patient's ascent. Simultaneously, the system processes the electromyographic signal data sequence to calculate the real-time activation levels of the anterior thigh extensor and posterior thigh flexor muscles. When the system detects that patient A's pressure center trajectory abnormally moves posteriorly towards the affected side at an accelerated speed, and simultaneously finds that the flexor muscle activation is significantly higher than the extensor muscle activation, it indicates that the patient is attempting to stand with an incorrect muscle exertion pattern. The system immediately identifies this as an abnormal "flexor dominance compensation" pattern and outputs this dynamic identification result.

[0043] This approach achieves real-time and accurate identification of specific abnormal force patterns in stroke patients by synergistically analyzing the kinematic information represented by the movement trajectory of the center of pressure and the physiological information represented by the muscle activation sequence. This provides a key basis for the subsequent generation of targeted auxiliary strategies, enabling the system to understand the underlying causes of the patient's movement difficulties rather than merely observing the symptoms.

[0044] Step 104: Based on the dynamic identification results, generate a dynamic auxiliary torque command to counteract the abnormal force application mode.

[0045] Optionally, step 104 may specifically include the following steps: Step 1041: Receive the dynamic identification result, and generate an initial auxiliary torque command for the abnormal force application pattern in the dynamic identification result; Step 1042: Based on the direction and distance of the pressure center movement trajectory deviating from the preset safe sitting trajectory in real time, determine the directional component of the torque in the initial auxiliary torque command; Step 1043: Based on the proportional relationship between the activation levels of the extensor muscle group and the activation levels of the flexor muscle group, and the moving speed of the pressure center trajectory, determine the magnitude component of the torque in the initial auxiliary torque command; Step 1044: Combine the direction component and magnitude component of the torque to obtain the dynamic auxiliary torque command.

[0046] In the above scheme, the dynamic auxiliary torque command is the final generated control command used to control the actuator to output auxiliary force, containing torque direction and magnitude information; the dynamic identification result is a description of the specific type of abnormal force exertion pattern of the patient as judged by the system in real time; the initial auxiliary torque command is a control command framework that is initially generated based on the dynamic identification result and does not yet contain specific parameters; the pressure center movement trajectory is the continuous path of the patient's center of gravity projection point on the cushion; the direction and distance of the preset safe sitting trajectory refer to the degree of deviation of the ideal safe movement path direction from the actual position relative to the path; the directional component of the torque is the direction of the auxiliary force determined based on the direction of the pressure center deviating from the safe trajectory; the movement speed of the pressure center movement trajectory is the rate of change of the center of gravity position; and the magnitude component of the torque is the auxiliary force value determined based on the muscle activation state and movement speed.

[0047] In this scheme, firstly, step 1041 receives the dynamic identification results through the system and generates a corresponding initial auxiliary torque command framework based on the identified abnormal force application pattern type. Secondly, step 1042 calculates the offset between the pressure center movement trajectory and the preset safe sitting trajectory in real time through the system, determines the specific location where the auxiliary force needs to be applied based on the offset direction, and thus determines the directional component of the torque in the initial auxiliary torque command. Next, step 1043 analyzes the ratio of extensor muscle activation to flexor muscle activation and the real-time movement speed of the pressure center movement trajectory through the system, and comprehensively judges the required auxiliary force based on these parameters to determine the magnitude component of the torque in the initial auxiliary torque command. Finally, step 1044 fuses the determined torque directional and magnitude components through the system to generate a complete and executable dynamic auxiliary torque command.

[0048] Following the specific implementation of the previous scheme, in step 103, when patient C is identified as exhibiting an abnormal "flexor dominance compensation" pattern, the system first generates an initial auxiliary torque command for this pattern. Subsequently, it detects that patient C's center of gravity shifts posterolaterally, so the directional component of the torque is set to anteromedial. Simultaneously, it detects that the patient's flexor activation is significantly higher than that of the extensors and that the center of gravity shifts too quickly, calculating the magnitude component of the torque accordingly. Finally, the system fuses the direction and magnitude parameters to generate a dynamic auxiliary torque command with an appropriate magnitude and an anteromedial direction.

[0049] This solution combines abnormal pattern recognition results with real-time motion parameters to generate auxiliary instructions with clear directionality and quantification, realizing the transformation from problem diagnosis to solution generation, providing the actuator with precise action basis, and ensuring that the provided assistance is targeted and adaptable.

[0050] Step 105: According to the dynamic auxiliary torque command, control the sitting assistance actuator to output an auxiliary torque that complements the direction of the stroke patient's own force, so as to guide the stroke patient's body center of gravity to move along a preset safe sitting trajectory.

[0051] Optionally, step 105 may specifically include the following steps: Step 1051: Receive the dynamic auxiliary torque command and parse out the target torque direction and target torque magnitude to be output; Step 1051 may specifically include the following steps: The direction vector and numerical parameter portions of the dynamic auxiliary torque command are read; the direction of the target torque is determined according to the orientation of the direction vector portion in a predefined coordinate system; the command intensity value represented by the numerical parameter portion is converted into a physical quantity that the sitting auxiliary actuator can directly execute according to a preset mapping relationship, and the physical quantity is defined as the target torque magnitude; the target torque direction and the target torque magnitude are combined to form control parameters for controlling the actions of specific units in the auxiliary actuator.

[0052] Step 1052: Based on the target torque direction obtained from the analysis, determine the specific unit in the assist execution unit that needs to provide thrust; Step 1053: Based on the target torque obtained from the analysis, convert it into the power parameters required to drive the specific unit, and control the power source to output the corresponding power; Step 1054: When the specific unit receives the power output from the power source, it generates an artificial thrust with a specific direction and magnitude. The artificial thrust works in conjunction with the stroke patient's own muscle strength to form a complementary auxiliary torque. Step 1055: During the output of the artificial thrust, new pressure distribution data sequences and new electrical signal strength data sequences are continuously acquired, and the direction and magnitude of the artificial thrust are adjusted in real time based on the new dynamic identification results to form a closed-loop control process until the total pressure value of the pressure sensor array is detected to drop below the second preset pressure threshold, indicating that the sitting action conversion is completed. Then, the output of auxiliary torque is stopped to complete the pressure feedback control.

[0053] In the above scheme, the dynamic assist torque command is a control command generated by the system that includes the direction and magnitude of the assist; the sitting assist actuator is a mechanical device installed on the toilet to provide physical assistance; the complementary assist torque refers to the assist force that coordinates with the direction of the patient's own muscle force to complete the movement; the preset safe sitting trajectory movement refers to the ideal human body center of gravity movement path set by the system; the target torque direction is the spatial orientation where the assist force needs to act; the target torque magnitude is the intensity value of the assist force; the direction vector part is the mathematical description of the direction in the command; the numerical parameter part is the numerical value of the magnitude in the command; the command intensity value is the intensity level of the assist force; the physical quantity is the electrical signal or mechanical quantity that the actuator can directly process; the control parameters of a specific unit action are the specific operation commands that control a certain actuator; the assist actuator is an independent mechanical component that generates assist force; the power source is a motor or hydraulic device that provides energy; the artificial thrust in a specific direction and magnitude is the specific force generated by the actuator; the new pressure distribution data sequence is a set of pressure data that is updated in real time; and the new electrical signal intensity data sequence is a set of electromyographic data that is updated in real time.

[0054] In this scheme, firstly, step 1051 reads the direction vector and numerical parameters from the dynamic assist torque command through the system. The target torque direction is determined based on the angle of the direction vector in the coordinate system. Simultaneously, the numerical parameters are converted into physical quantities recognizable by the actuator through a preset mapping relationship, serving as the target torque magnitude, and combined to generate control parameters. Secondly, step 1052 selects a specific unit to be activated from multiple assist actuators based on the target torque direction in the control parameters. Next, step 1053 converts the target torque magnitude into power parameters such as drive voltage or current, controlling the power source to output corresponding power. Then, step 1054, after receiving power, the specific unit generates an artificial thrust matching the actual need through mechanical transmission. This thrust, in conjunction with the patient's own muscle strength, forms a complementary assist torque. Finally, step 1055 continuously acquires new sensor data and updates the control parameters. When the total pressure value is detected to be below a second preset threshold, assistance is stopped.

[0055] Following the specific embodiment of the previous solution, in step 104, when patient D stands up, the system generates a dynamic assist torque command of 30 degrees to the right front and 70% of its magnitude. After the actuator analyzes the command, it selects the right front assist unit, converts the command into a corresponding voltage to drive the motor, and generates a lifting force on the right front side of the patient's waist through the transmission device. During this process, the system continuously monitors changes in the patient's posture, and automatically stops assisting when the pressure sensor indicates that the patient has fully stood up.

[0056] This solution transforms control commands into precise mechanical movements, enabling personalized assistance that matches the patient's real-time motion state. Furthermore, a closed-loop control mechanism ensures a smooth and safe assistance process, ultimately effectively guiding the patient to transition between sitting and standing positions.

[0057] Figure 2 This application provides a schematic diagram of the pressure feedback control system of a toilet sitting assistance system for stroke patients, as shown in the figure. Figure 2 As shown, the system includes: The first acquisition module 21 is used to acquire pressure distribution data of the stroke patient's buttocks in real time through a pressure sensor array pre-installed under the seat cushion during the transition between sitting and standing on the toilet, and obtain a pressure distribution data sequence. The second acquisition module 22 is used to synchronously acquire electromyographic signal data of specific muscle groups in the affected lower limb of the stroke patient to obtain an electrical signal intensity data sequence. The calculation module 23 is used to perform collaborative calculation of the pressure center trajectory reflected by the pressure distribution data sequence and the muscle activation timing represented by the electromyographic signal data sequence, so as to dynamically identify the abnormal force pattern generated by the stroke patient due to post-stroke motor dysfunction and output the dynamic identification result. The generation module 24 is used to generate a dynamic auxiliary torque command to counteract the abnormal force application mode based on the dynamic identification result. The control module 25 is used to control the sitting assistance actuator to output an auxiliary torque that is complementary to the direction of the stroke patient's own force, according to the dynamic auxiliary torque command, so as to guide the stroke patient's body center of gravity to move along a preset safe sitting trajectory.

[0058] Figure 2 The pressure feedback control system of the toilet sitting assistance system for stroke patients can perform... Figure 1 The pressure feedback control method for a toilet sitting assistance system for stroke patients described in the illustrated embodiment will not be elaborated further on its implementation principle and technical effects. The specific operation methods of each module and unit in the pressure feedback control system of the toilet sitting assistance system for stroke patients in the above embodiments have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0059] In one possible design, Figure 2 The pressure feedback control system of the toilet sitting assistance system for stroke patients in the illustrated embodiment can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0060] The processing component 32 is used for the above Figure 1 The embodiment describes a pressure feedback control method for a toilet sitting assistance system for stroke patients.

[0061] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0062] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0063] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0064] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0065] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0066] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0067] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The embodiment shown illustrates a pressure feedback control method for a toilet sitting-up assist system for stroke patients.

[0068] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0069] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0070] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A pressure feedback control method for a toilet sitting-up assist system for stroke patients, characterized in that, include: During the transition from sitting to standing on the toilet, the pressure distribution data of the stroke patient's buttocks is collected in real time by a pressure sensor array pre-installed under the seat cushion, and a pressure distribution data sequence is obtained. Electromyographic signal data of specific muscle groups in the affected lower limb of the stroke patient were collected simultaneously to obtain an electrical signal intensity data sequence; The pressure center trajectory reflected by the pressure distribution data sequence and the muscle activation timing represented by the electromyographic signal data sequence are co-calculated to dynamically identify the abnormal force patterns of the stroke patient due to post-stroke motor dysfunction and output the dynamic identification results. Based on the dynamic identification results, a dynamic auxiliary torque command is generated to counteract the abnormal force application mode; According to the dynamic auxiliary torque command, the sitting assistance actuator is controlled to output an auxiliary torque that complements the direction of the stroke patient's own force, so as to guide the stroke patient's center of gravity to move along a preset safe sitting trajectory.

2. The method according to claim 1, characterized in that, During the transition from sitting to standing on the toilet, a pressure sensor array pre-installed under the seat collects real-time pressure distribution data of the stroke patient's buttocks, resulting in a pressure distribution data sequence, including: When the total pressure value sensed by the pressure sensor array continuously increases from zero and exceeds the first preset pressure threshold, it is determined that the stroke patient has begun to sit down, and the data recording process is initiated. During the transition between sitting and standing, the pressure sensor array is used to collect the instantaneous pressure values ​​of all pressure sensor units at a preset fixed time interval. The collection of instantaneous pressure values ​​from all pressure sensing units acquired in each acquisition constitutes a pressure distribution snapshot. Multiple pressure distribution snapshots are recorded sequentially in chronological order, and the pressure distribution snapshots arranged in chronological order are combined to form a pressure distribution data sequence.

3. The method according to claim 1, characterized in that, Electromyographic (EMG) signal data of specific muscle groups in the affected lower limb of the stroke patient were simultaneously acquired to obtain an EMG signal intensity data sequence, including: When the total pressure value sensed by the pressure sensing array exceeds the first preset pressure threshold, the electromyography signal acquisition electrode is simultaneously activated to acquire data. Each of the electromyography (EMG) signal acquisition electrodes acquires an instantaneous electrical signal intensity value at the same fixed time interval as the pressure distribution snapshot acquired by the pressure sensing array; Multiple instantaneous electrical signal intensity values ​​obtained from all electromyography (EMG) signal acquisition electrodes at the same time interval are aggregated to form a multi-channel EMG signal snapshot; Multiple multi-channel electromyographic signal snapshots are recorded sequentially in chronological order, and the chronologically arranged multi-channel electromyographic signal snapshots are combined to form the electrical signal intensity data sequence.

4. The method according to claim 1, characterized in that, The pressure center trajectory reflected by the pressure distribution data sequence and the muscle activation timing represented by the electromyographic signal data sequence are co-calculated to dynamically identify the abnormal force patterns of stroke patients caused by post-stroke motor dysfunction and output the dynamic identification results, including: For each pressure distribution snapshot in the pressure distribution data sequence, the position of the pressure center point is calculated, and the pressure center point positions are connected in chronological order to form the pressure center movement trajectory. For each multi-channel electromyography (EMG) snapshot in the electrical signal intensity data sequence, the activation levels of extensor muscles and flexor muscles are calculated. The direction and speed of the movement of the pressure center trajectory are compared with the proportional relationship between the activation degree of the extensor muscle group and the activation degree of the flexor muscle group to obtain the comparison results. Based on the pairing comparison results, dynamic identification results with abnormal force exertion mode categories are output in real time.

5. The method according to claim 1, characterized in that, Based on the dynamic identification results, a dynamic auxiliary torque command is generated to counteract the abnormal force application pattern, including: Receive the dynamic identification results, and generate an initial auxiliary torque command for the abnormal force application patterns identified in the dynamic identification results; The directional component of the torque in the initial auxiliary torque command is determined based on the direction and distance of the pressure center movement trajectory deviating from the preset safe sitting trajectory in real time; Based on the proportional relationship between the activation levels of the extensor muscle group and the activation levels of the flexor muscle group, and the moving speed of the pressure center trajectory, the magnitude component of the torque in the initial auxiliary torque command is determined; By fusing the directional and magnitude components of the torque, a dynamic auxiliary torque command is obtained.

6. The method according to claim 1, characterized in that, According to the dynamic auxiliary torque command, the sitting assistance actuator is controlled to output an auxiliary torque that complements the direction of the stroke patient's own force, so as to guide the stroke patient's center of gravity to move along a preset safe sitting trajectory, including: Receive the dynamic auxiliary torque command and parse out the target torque direction and target torque magnitude to be output; Based on the target torque direction obtained from the analysis, determine the specific unit in the assist actuator that needs to provide thrust; Based on the target torque obtained from the analysis, it is converted into the power parameters required to drive the specific unit, and the power source is controlled to output the corresponding power. When the specific unit receives power from the power source, it generates an artificial thrust with a specific direction and magnitude. The artificial thrust works in conjunction with the stroke patient's own muscle strength to form a complementary auxiliary torque. During the output of the artificial thrust, new pressure distribution data sequences and new electrical signal strength data sequences are continuously acquired, and the direction and magnitude of the artificial thrust are adjusted in real time based on the new dynamic identification results to form a closed-loop control process until the total pressure value of the pressure sensor array is detected to drop below the second preset pressure threshold, indicating that the sitting and standing action conversion is completed. Then, the output of auxiliary torque is stopped to complete the pressure feedback control.

7. The method according to claim 6, characterized in that, Receiving the dynamic auxiliary torque command and parsing the target torque direction and magnitude to be output includes: Read the direction vector and numerical parameter portions contained in the dynamic auxiliary torque command; The direction of the target torque is determined based on the orientation of the direction vector portion in a predefined coordinate system; The command intensity value represented by the numerical parameter is converted into a physical quantity that the sitting auxiliary actuator can directly execute according to a preset mapping relationship, and the physical quantity is defined as the target torque magnitude. The direction and magnitude of the target torque are combined to form control parameters for controlling the actions of specific units in the power assist actuator.

8. A pressure feedback control system for a toilet sitting-up assist system for stroke patients, characterized in that, include: The first acquisition module is used to acquire pressure distribution data of the stroke patient's buttocks in real time through a pressure sensor array pre-installed under the seat cushion during the transition between sitting and standing on the toilet, and to obtain a pressure distribution data sequence. The second acquisition module is used to synchronously acquire electromyographic signal data of specific muscle groups in the affected lower limb of the stroke patient to obtain an electrical signal intensity data sequence. The calculation module is used to perform collaborative calculation of the pressure center trajectory reflected by the pressure distribution data sequence and the muscle activation timing represented by the electromyographic signal data sequence, so as to dynamically identify the abnormal force pattern generated by the stroke patient due to post-stroke motor dysfunction and output the dynamic identification result. The generation module is used to generate a dynamic auxiliary torque command to counteract the abnormal force application mode based on the dynamic identification results. The control module is used to control the sitting assistance actuator to output an auxiliary torque that complements the direction of the stroke patient's own force, according to the dynamic auxiliary torque command, so as to guide the stroke patient's center of gravity to move along a preset safe sitting trajectory.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a pressure feedback control method for a toilet sitting assistance system for stroke patients as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The system contains a computer program that, when executed by a computer, implements a pressure feedback control method for a toilet sitting assistance system for stroke patients as described in any one of claims 1 to 7.

Images