Electric wheelchair backrest adjustment method, device, electronic device and storage medium

Abstract

The present application provides a method, device, electronic device and storage medium for adjusting the backrest of an electric wheelchair, which relates to the technical field of wheelchair backrest adjustment. The key points of the technical solution are: obtaining the pressure distribution data, temperature data and physiological index data of the contact surface between the user and the wheelchair backrest; generating a backrest adjustment strategy for preventing pressure sores and skin injuries based on the acquired data, combined with the user's rehabilitation stage and historical rehabilitation data; when the generated adjustment strategy meets the requirements of a smooth transition, adjusting the pressure and temperature of each point of the backrest; during the adjustment process, continuously monitoring the changes in the user's physiological indicators and discomfort feedback signals; when abnormal changes are detected, optimizing the adjustment strategy in real time, and storing the optimized adjustment parameters in the user rehabilitation database. The present application provides a method, device, electronic device and storage medium for adjusting the backrest of an electric wheelchair, which have the advantage of effectively preventing pressure sores and skin injuries.

Description

Technical Field

[0001] The present application relates to the technical field of wheelchair backrest adjustment, and in particular to a method, device, electronic device and storage medium for adjusting the backrest of an electric wheelchair. Background Art

[0002] In the field of rehabilitation medicine, the rehabilitation process faces many challenges for users who are extremely weak due to serious diseases (such as neuromuscular diseases, spinal cord injuries, severe arthritis or muscle atrophy caused by long-term bed rest). Such users are highly sensitive to external pressure and cannot maintain the same posture for a long time. Any continuous pressure may cause new complications such as pressure sores, skin damage or circulatory disorders.

[0003] In the early stages of rehabilitation, users can only sit for a short time each day and need to adjust their posture frequently to prevent physical discomfort or secondary injury. As rehabilitation progresses, users need to gradually increase their sitting time and start joint mobility training. However, since users are highly sensitive to pain, any discomfort will trigger a strong sense of discomfort or pain response. In addition, the user's physical condition changes every day, and some parts are recovering while other parts may still have inflammation or damage.

[0004] Taking into account the user's pain sensitivity, any posture adjustment must be slow and smooth, and the user's physiological indicators must be monitored in real time, such as skin temperature, local pressure, blood flow, etc. In addition, in order to cooperate with joint mobility training, the wheelchair backrest needs to be able to provide specific posture support while ensuring the user's safety, so as to assist the user in progressive rehabilitation training.

[0005] However, existing electric wheelchair backrest systems are still insufficient in meeting these complex needs. They usually lack precise multi-point pressure and temperature regulation capabilities, cannot dynamically adjust according to the user's real-time physiological condition, and are difficult to adapt to the user's changing needs during rehabilitation. These limitations make it difficult for existing systems to provide users with optimal rehabilitation support, while also increasing the workload of medical staff.

[0006] In view of the above problems, the existing technology needs to be improved urgently. Summary of the invention

[0007] The purpose of the present application is to provide an electric wheelchair back adjustment method, device, electronic device and storage medium, which have the advantages of being able to perform precise multi-point pressure and temperature adjustment according to the user's real-time physiological condition, effectively preventing pressure sores and skin injuries, and supporting progressive rehabilitation training.

[0008] The present application provides a method for adjusting the backrest of an electric wheelchair, and the technical solution is as follows: The method includes: obtaining pressure distribution data, temperature data and physiological index data including skin temperature and local blood flow status of the contact surface between the user and the wheelchair backrest based on a multi-point sensor network; generating a backrest adjustment strategy for preventing pressure sores and skin injuries based on the acquired data and in combination with the user's rehabilitation stage and historical rehabilitation data; when the generated adjustment strategy meets the requirements of smooth transition, adjusting the pressure and temperature of each backrest point at a preset adjustment speed; during the adjustment process, continuously monitoring the changes in the user's physiological indicators and discomfort feedback signals; when abnormal changes are detected, optimizing the adjustment strategy in real time based on the monitoring results and user feedback, and storing the optimized adjustment parameters in the user rehabilitation database.

[0009] Furthermore, the present application also proposes that the step of generating a back-rest adjustment strategy for preventing pressure sores and skin injuries based on the acquired data in combination with the user's rehabilitation stage and historical rehabilitation data includes: receiving rehabilitation safety limit parameters input by medical staff, including the maximum allowable continuous pressure time, pressure threshold, and temperature change range, and based on the acquired pressure distribution data, temperature data, and physiological indicator data, in combination with the user's rehabilitation stage and historical rehabilitation data, constructing a multi-objective optimization model with the prevention of pressure sores as the main goal and the maintenance of blood circulation and muscle function recovery as secondary goals; when the constructed multi-objective optimization model meets the safety limit parameters set by the medical staff, a back-rest adjustment strategy that balances the immediate pressure release requirements and the progressive rehabilitation training requirements is calculated.

[0010] Furthermore, the present application also proposes that the steps of constructing a multi-objective optimization model with the prevention of pressure sores as the main goal and the maintenance of blood circulation and muscle function recovery as the secondary goals include: based on the user's rehabilitation stage and historical rehabilitation data, combined with the acquired pressure distribution data, temperature data and physiological indicator data, determine the main weight coefficient for preventing the occurrence of pressure sores and the secondary weight coefficient for maintaining blood circulation and muscle function recovery; according to the determined weight coefficients, construct a multidimensional objective function including a pressure distribution function, a temperature distribution function and a physiological indicator function, wherein the pressure distribution function is used to quantify the impact of continuous pressure on the risk of pressure sores, the temperature distribution function is used to evaluate the local blood circulation status, and the physiological indicator function is used to characterize the degree of muscle function recovery; the constructed multidimensional objective function is combined with the rehabilitation safety limit parameters to form a multi-objective optimization model with the prevention of pressure sores as the main goal and the maintenance of blood circulation and muscle function recovery as the secondary goals.

[0011] Furthermore, the present application also proposes that when the constructed multi-objective optimization model meets the safety limit parameters set by medical staff, the step of calculating a backrest adjustment strategy that balances the immediate pressure release demand and the progressive rehabilitation training requirements includes: when it is detected that the user is in the early stage of rehabilitation and has low physiological tolerance, based on the user's muscle atrophy degree and joint mobility data, the baseline weight of the immediate pressure release demand is set to be higher than the baseline weight of the progressive rehabilitation training requirements; while continuously monitoring the pressure distribution data and local blood flow conditions of the user's contact surface with the wheelchair backrest, the user's current pressure load index is calculated based on the pressure duration, pressure intensity and blood flow change rate; when the calculated pressure load index exceeds the safety limit parameters set by medical staff and abnormal local blood flow conditions are detected, the weight of the immediate pressure release demand is increased, and the weight of the progressive rehabilitation training requirements is correspondingly reduced; the dynamically adjusted weights are substituted into the multi-objective optimization model to generate a backrest adjustment strategy.

[0012] Furthermore, the present application also proposes that the step of increasing the weight of the immediate pressure release demand and correspondingly reducing the weight of the progressive rehabilitation training requirement includes: when an abnormal local blood flow condition of the user is detected, based on the blood flow abnormality judgment standard and weight adjustment rules preset by the medical staff, dynamically calculating the increase in the weight of the immediate pressure release demand and the decrease in the weight of the progressive rehabilitation training requirement; wherein, the judgment of the abnormal local blood flow condition includes: when the local blood flow change rate is lower than the preset minimum threshold or the blood flow fluctuation frequency is higher than the preset maximum threshold, it is judged that the local blood flow condition is abnormal.

[0013] Furthermore, the present application also proposes that the step of setting the baseline weight of the immediate pressure release demand to be higher than the baseline weight required for progressive rehabilitation training based on the user's muscle atrophy degree and joint mobility data includes: when the user's muscle atrophy degree and joint mobility data are received by medical staff through the user interface, calculating the user's comprehensive physiological condition index based on the preset scoring weight; according to the calculated comprehensive physiological condition index, determining the immediate pressure release demand baseline weight and the progressive rehabilitation training demand baseline weight from a preset weight configuration model; when the determined immediate pressure release demand baseline weight is lower than the system preset safety threshold, adjusting the immediate pressure release demand baseline weight to a value not lower than the safety threshold, and adjusting the progressive rehabilitation training demand baseline weight accordingly to ensure that the sum of the two remains constant.

[0014] Furthermore, the present application also proposes that the step of generating a back adjustment strategy for preventing pressure sores and skin injuries based on the acquired data in combination with the user's rehabilitation stage and historical rehabilitation data includes: when receiving rehabilitation safety limit parameters including the maximum allowable continuous pressure time Tmax_pressure(t), the pressure threshold Pmax(t), and the temperature change range [Tmin(t), Tmax(t)] input by medical staff, based on the acquired pressure distribution data pi(t), temperature data ti(t) and physiological index data, in combination with the user's rehabilitation stage and historical rehabilitation data, constructing a dynamic multi-objective optimization model; the objective function of the dynamic multi-objective optimization model is: min F(x, t) = [w1(t)f1(x, t), w2(t)f2(x, t), w3(t)f3(x, t)] wherein x(t) = [p1(t), p2(t), ..., pn(t), t1(t), t2(t), ..., tn(t)] is a decision variable, which represents the pressure and temperature values ​​of each point at time t; f1(x, t) is a dynamic pressure sore risk function, which is used to evaluate the risk of pressure sores caused by the current pressure distribution; f2(x, t) is a dynamic blood circulation status function, which is used to evaluate the impact of the current regulation strategy on blood circulation; f3(x, t) is a dynamic muscle function recovery function, which is used to evaluate the degree of promotion of the current regulation strategy on muscle function recovery; wi(t) is a time-varying weight coefficient, which is dynamically adjusted with the rehabilitation stage; the constraints of the dynamic multi-objective optimization model include: 0 ≤ pi(t) ≤ Pmax(t), i = 1, 2, ...,n Tmin(t) ≤ ti(t) ≤ Tmax(t), i = 1, 2, ..., n T(pi, t) ≤ Tmax_pressure(t),i = 1, 2, ..., n |dpi(t) / dt| ≤ Rmax_p, |dti(t) / dt| ≤ Rmax_t, where T(pi, t) represents the duration of pressure pi at time t, Rmax_p and Rmax_t are the maximum adjustment rates of pressure and temperature, respectively; when a change in the user's physiological state is detected, based on the user's physiological tolerance function g(x, t) and rehabilitation progress function h(x, t), constructed based on historical rehabilitation data, a weight adjustment mechanism is adopted: dwi(t) / dt = α(g(x, t), h(x, t)), i =1, 2, 3, where α is the weight adjustment function, which is used to dynamically adjust the weight of each objective according to the user's state; by solving the dynamic multi-objective optimization model, the optimal pressure and temperature distribution schemes at each back-resting point at different times are obtained, and a back-resting adjustment strategy for preventing pressure sores and skin injuries is generated.

[0015] Furthermore, the present application also proposes an electric wheelchair backrest adjustment device, which includes: an acquisition module, which is used to obtain pressure distribution data, temperature data and physiological indicator data including skin temperature and local blood flow conditions of the contact surface between the user and the wheelchair backrest based on a multi-point sensor network; a generation module, which is used to generate a backrest adjustment strategy for preventing pressure sores and skin injuries based on the acquired data in combination with the user's rehabilitation stage and historical rehabilitation data; an adjustment module, which is used to adjust the pressure and temperature of each backrest point at a preset adjustment speed when the generated adjustment strategy meets the smooth transition requirements; a monitoring module, which is used to continuously monitor the changes in the user's physiological indicators and discomfort feedback signals during the adjustment process; an optimization module, which is used to optimize the adjustment strategy in real time according to the monitoring results and user feedback when abnormal changes are detected, and store the optimized adjustment parameters in the user rehabilitation database.

[0016] Furthermore, the present application also proposes an electronic device, including a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the above method are executed.

[0017] Furthermore, the present application also proposes a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method are executed.

[0018] From the above, it can be seen that the electric wheelchair backrest adjustment method, device, electronic device and storage medium provided by the present application solve the problem of lack of precise multi-point adjustment and real-time response capabilities in the prior art by real-time monitoring of the user's physiological condition and dynamically adjusting the backrest pressure and temperature distribution. It has the advantages of being able to perform precise multi-point pressure and temperature adjustment according to the user's real-time physiological condition, effectively preventing pressure sores and skin injuries, and supporting progressive rehabilitation training. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flow chart of a method for adjusting the backrest of an electric wheelchair provided in this application.

[0020] Figure 2 This is a schematic structural diagram of an electric wheelchair backrest adjustment device provided in this application.

[0021] In the figure: 210, acquisition module; 220, generation module; 230, adjustment module; 240, monitoring module; 250, optimization module. DETAILED DESCRIPTION

[0022] The technical solutions in the present application will be clearly and completely described below in conjunction with the drawings in the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0023] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0024] During the adjustment of the backrest of an electric wheelchair for users recovering from serious illnesses, preventing pressure sores and skin injuries while taking into account the user's rehabilitation needs is a complex technical challenge. Existing electric wheelchair backrest systems usually adopt fixed adjustment strategies and lack the ability to dynamically respond to the user's real-time physiological condition. This approach cannot meet the changing physical needs of users during rehabilitation, and may cause excessive local pressure or prolonged duration, increasing the risk of pressure sores and skin injuries. In addition, it is difficult for existing systems to provide personalized adjustment strategies based on the user's rehabilitation stage and individual differences, which may affect the rehabilitation effect and even cause secondary injuries.

[0025] In this regard, refer to Figure 1 , the present application proposes a method for adjusting the backrest of an electric wheelchair, the method comprising: S110, obtaining pressure distribution data, temperature data, and physiological index data including skin temperature and local blood flow status on the contact surface between the user and the wheelchair backrest based on a multi-point sensor network; S120, generating a back-support adjustment strategy for preventing pressure sores and skin injuries based on the acquired data and in combination with the user's rehabilitation stage and historical rehabilitation data; S130, when the generated adjustment strategy meets the requirement of smooth transition, adjusting the pressure and temperature of each back point at a preset adjustment speed; S140, during the adjustment process, continuously monitoring the user's physiological index changes and discomfort feedback signals; S150: When an abnormal change is detected, the adjustment strategy is optimized in real time according to the monitoring results and user feedback, and the optimized adjustment parameters are stored in the user rehabilitation database.

[0026] Among them, the multi-point sensor network refers to a network system composed of multiple pressure sensors, temperature sensors and physiological indicator sensors, which can be specifically implemented by using a flexible pressure sensor array, an infrared temperature sensor and a photoelectric volumetric pulse wave sensor.

[0027] Among them, the rehabilitation stage refers to the current rehabilitation process of the user, which can be achieved by using medical records, rehabilitation assessment scales and daily activity ability scores. At different rehabilitation stages, the user's physical condition, pressure ulcer risk and rehabilitation goals are different, for example: In the early stages of rehabilitation, the user is weak and at high risk of pressure sores. The adjustment strategy at this time should be based on the principles of extremely low pressure, even distribution, and frequent adjustments, giving priority to safety and preventing pressure sores.

[0028] In the middle stage of rehabilitation, the user's physical condition gradually improves, and the pressure can be gradually increased. According to the results of the rehabilitation assessment, local pressure / temperature adjustments can be made in a targeted manner to promote blood circulation and muscle function recovery.

[0029] In the later stages of rehabilitation, the user's physical functions are further restored, and more personalized adjustments can be made based on the user's daily activity ability and comfort, taking into account both comfort and functionality.

[0030] Among them, historical rehabilitation data includes pressure distribution data, temperature data, physiological index data, adjustment strategies, user feedback, and rehabilitation evaluation results (such as pressure sore healing, pain score, etc.) every time the user used the wheelchair in the past. These data are used to build a personalized model. By analyzing the user's historical data, a personalized model that reflects their individual physiological characteristics and rehabilitation progress can be established. The general model can more accurately predict the user's response to different pressures / temperatures. By analyzing the trends in historical data, the user's future risk of pressure sores can be predicted and intervention can be made in advance. For example, if historical data shows that the pressure tolerance of a certain part of the user is gradually decreasing, the system can reduce the pressure in that part in advance. By comparing the effects of different adjustment strategies, the adjustment algorithm can be continuously optimized to make it more in line with the individual needs of users.

[0031] Among them, the backrest adjustment strategy refers to the backrest pressure and temperature adjustment strategy generated according to the user's real-time status and rehabilitation needs, which can be implemented by a multi-objective optimization algorithm.

[0032] Among them, the smooth transition requirement refers to the rate and amplitude limit of pressure and temperature changes during the adjustment process, which can be achieved by using a progressive adjustment algorithm. The smooth transition requirement is to avoid drastic changes in pressure and temperature causing discomfort to the user or even causing new injuries. Rapid pressure changes may cause local tissue ischemia, while sudden increases or decreases in temperature may irritate the skin and aggravate inflammatory responses. By limiting the adjustment rate and amplitude, the smoothness and safety of the adjustment process can be ensured, especially when the user is weak or has sensory impairments. The progressive adjustment algorithm breaks down large adjustment targets into multiple small adjustment steps and gradually achieves the target, thereby meeting the smooth transition requirement.

[0033] Among them, changes in physiological indicators refer to the dynamic changes in physiological parameters such as skin temperature and local blood flow conditions, which can be achieved by real-time data analysis and anomaly detection algorithms.

[0034] The core innovation of this application is to obtain the pressure distribution, temperature and physiological index data of the contact surface between the user and the wheelchair backrest in real time through a multi-point sensor network, and generate a personalized backrest adjustment strategy based on the user's rehabilitation stage and historical rehabilitation data. During the adjustment process, the system continuously monitors the user's physiological index changes and discomfort feedback, and optimizes the adjustment strategy in real time based on the monitoring results. This closed-loop feedback mechanism can effectively prevent pressure sores and skin injuries while taking into account the user's rehabilitation needs.

[0035] The working principle of this application can be described in detail as follows: First, a multi-point sensor network is arranged on the surface of the electric wheelchair backrest. The pressure sensor array can be evenly distributed in a matrix form, with a spacing of 5-10cm between each sensor to ensure full coverage of the contact surface between the user and the backrest. Temperature sensors and physiological indicator sensors are arranged in key locations according to the usual human body structure, such as on both sides of the spine and under the shoulder blades.

[0036] Based on a multi-point sensor network, the pressure sensor collects pressure data of each contact point in real time. The temperature sensor monitors the local skin temperature. The physiological indicator sensor collects local blood flow conditions, such as blood oxygen saturation and pulse waveform.

[0037] The pressure distribution data obtained directly reflects the pressure size and distribution of the contact surface between the user's back and the wheelchair backrest. Excessive pressure or prolonged duration is the main cause of pressure sores. Skin temperature can reflect the local blood circulation status. Low skin temperature may mean poor blood circulation, increasing the risk of tissue ischemia and pressure sores. Physiological indicator data, such as local blood flow status (blood oxygen saturation, pulse waveform), more directly reflects the blood and oxygen supply of tissues, and is a key indicator for assessing the risk of pressure sores. These data together form the basis for assessing the user's real-time pressure sore risk.

[0038] The data acquisition frequency can be set to 10 times per second to ensure that rapid physiological changes can be captured. The collected data is transmitted to the central processing unit in real time via a low-power wireless transmission module.

[0039] The central processing unit first preprocesses the received data, including denoising, standardization, and feature extraction. The preprocessed data, including pressure distribution, temperature distribution, and physiological indicators (blood oxygen saturation, pulse wave, etc.), are integrated into a comprehensive description of the user's status. These data are closely related to pressure sores and skin injuries, including: Pressure distribution: High-pressure areas mean that tissues are under severe pressure. Long-term pressure can lead to local blood circulation disorders, which in turn causes tissue ischemia and necrosis, and eventually forms pressure sores.

[0040] Physiological indicators: Blood oxygen saturation directly reflects the oxygenation status of tissues. Low blood oxygen saturation means tissue hypoxia, which is a high-risk signal for the occurrence of pressure sores. Changes in pulse waveforms can reflect the elasticity of blood vessels, blood flow resistance, etc., which helps to assess the overall blood circulation status. Skin temperature is an important indicator reflecting local blood circulation. Too low a temperature usually indicates poor blood circulation and an increased risk of tissue hypoxia.

[0041] Based on the connection between this data and pressure sores / skin injuries, the pressure and temperature are adjusted according to the real-time data to minimize the risk of pressure sores and promote the repair of damaged tissue. Then, combined with the user's rehabilitation stage and historical rehabilitation data, it is input into a pre-trained machine learning model. Based on a multi-objective optimization algorithm, the model considers the three goals of minimizing the risk of pressure sores, improving blood circulation, and restoring muscle function, and generates a back-to-back adjustment strategy.

[0042] The generated regulation strategy includes the target pressure and temperature values ​​for each regulation point, as well as the regulation speed. The system will evaluate whether the strategy meets the smooth transition requirements, that is, the pressure change rate and temperature change rate do not exceed the set value.

[0043] After the smooth transition requirements are met, the electric actuator begins to adjust the pressure and temperature of each point on the back at the preset speed. During the adjustment process, the system continuously monitors the user's physiological index changes and discomfort feedback signals. If abnormal changes are detected, such as a sudden increase in local pressure of more than 20% or an increase in skin temperature of more than 1.5°C, the system will immediately suspend the adjustment and trigger the optimization algorithm.

[0044] In order to achieve precise pressure and temperature regulation, an array of micro airbags (or liquid bags) can be integrated inside the backrest, and each airbag is connected to an independent micro air pump and valve (or hydraulic pump and valve). The central processing unit accurately controls the opening and closing of each air pump / valve and the air / liquid flow rate based on the generated regulation strategy to achieve independent increase and decrease of the pressure at the corresponding contact point. At the same time, constant temperature liquid circulates in the airbag, and the water temperature is adjusted through an independent temperature control system to achieve precise control of the contact point temperature.

[0045] The optimization algorithm will quickly generate new adjustment strategies based on abnormal data and user feedback. For example, if the blood flow condition in a certain area is detected to be deteriorating, the algorithm will reduce the pressure in that area and adjust the pressure distribution in the surrounding areas accordingly. The optimized adjustment parameters will be stored in the user rehabilitation database for subsequent strategy generation and long-term effect evaluation.

[0046] This working principle ensures the safety and effectiveness of the adjustment process. Through real-time data collection and analysis, the system can quickly respond to changes in the user's status and prevent the occurrence of pressure sores and skin injuries. At the same time, combined with the rehabilitation stage and historical data, the system can provide users with personalized support and promote the rehabilitation process.

[0047] As a preferred implementation, the electric wheelchair backrest adjustment method of the present application can be specifically implemented as follows: A 16×16 flexible pressure sensor array is arranged on the backrest surface of the electric wheelchair, with each sensor measuring 1cm×1cm and 5cm apart. Eight high-precision temperature sensors and four photoelectric volumetric pulse wave sensors are additionally arranged at key locations, such as both sides of the spine, below the shoulder blades, and the sacrum.

[0048] A multi-point sensor network is started to collect data. In some embodiments, the pressure data range is 0-200 mmHg with an accuracy of 0.1 mmHg; the temperature data range is 30-40°C with an accuracy of 0.1°C; and the blood flow data includes blood oxygen saturation (SpO2) and pulse waveform.

[0049] After preprocessing, the collected data is input into a multi-objective optimization model. The input of the model includes: pressure data, temperature data, blood flow data, rehabilitation stage (such as the 4th week) and historical rehabilitation data of the past 7 days. The output of the model is the pressure regulation target value and the temperature regulation target value.

[0050] The objective function of the optimization model includes three parts: pressure ulcer risk index (weight 0.5), local blood flow improvement index (weight 0.3) and muscle function recovery index (weight 0.2). Through iterative calculation, the model can quickly generate the optimal adjustment strategy in a short time.

[0051] The generated adjustment strategy will be evaluated to see if it meets the smooth transition requirements. For example, the pressure change rate at any point must not exceed 0.5 mmHg / s, and the temperature change rate must not exceed 0.3°C / min. If the requirements are not met, the system will automatically adjust the change rate and extend the adjustment time.

[0052] After the regulation starts, the system checks the changes in physiological indicators every 0.1 seconds. If an abnormality is detected, such as a sudden increase of more than 10 mmHg in pressure at a certain point or a temperature increase of more than 0.5°C, the system will immediately suspend regulation and recalculate the regulation strategy within 1 second.

[0053] The optimized adjustment parameters will be recorded in the user rehabilitation database, including the pressure distribution map, temperature distribution map, blood flow status data before and after adjustment, and the user's subjective feedback. These data will be used for subsequent strategy optimization and long-term effect evaluation.

[0054] Through this implementation, the system is able to provide precise, safe and personalized back adjustment according to the user's real-time status and rehabilitation stage, effectively preventing pressure sores and skin injuries while promoting the rehabilitation process.

[0055] In some of the above embodiments of the present application, it is proposed to generate a back adjustment strategy for preventing pressure sores and skin injuries based on the acquired data, combined with the user's rehabilitation stage and historical rehabilitation data, so as to provide a personalized back adjustment strategy for electric wheelchair users. However, in this process, how to ensure that the generated adjustment strategy can not only meet the user's immediate needs, but also meet the long-term rehabilitation goals, while also considering medical safety restrictions, is a complex multi-objective optimization problem. In addition, how to effectively integrate the professional knowledge and experience of medical staff into the generation process of the adjustment strategy is also a problem that needs to be solved urgently.

[0056] In this regard, the present application further proposes the steps of generating a back-rest adjustment strategy for preventing pressure sores and skin injuries based on the acquired data in combination with the user's rehabilitation stage and historical rehabilitation data, including: receiving rehabilitation safety limit parameters input by medical staff, including the maximum allowable continuous pressure time, pressure threshold, and temperature change range, and based on the acquired pressure distribution data, temperature data, and physiological indicator data, in combination with the user's rehabilitation stage and historical rehabilitation data, constructing a multi-objective optimization model with the prevention of pressure sores as the main goal and the maintenance of blood circulation and muscle function recovery as secondary goals; when the constructed multi-objective optimization model meets the safety limit parameters set by the medical staff, a back-rest adjustment strategy that balances the immediate pressure release needs and the progressive rehabilitation training requirements is calculated.

[0057] The technical solution of the present application achieves precise control of the backrest adjustment strategy by introducing rehabilitation safety limit parameters input by medical staff and combining multiple data sources to build a multi-objective optimization model. Specifically, the safety limit parameters input by medical staff provide a clear medical safety boundary for the adjustment strategy, ensuring that the generated strategy does not exceed the safety range. The construction of the multi-objective optimization model takes into account multiple goals such as preventing pressure sores, maintaining blood circulation, and promoting muscle function recovery, and reflects the priority of these goals through weight setting. By combining the user's rehabilitation stage and historical rehabilitation data, the model can generate personalized adjustment strategies to adapt to the user's changing needs during the rehabilitation process. The calculated backrest adjustment strategy not only meets the immediate pressure relief needs, but also takes into account the requirements of progressive rehabilitation training, achieving a balance between short-term comfort and long-term rehabilitation goals.

[0058] In the technical solution of the present application, the rehabilitation safety limit parameters input by the medical staff may include the maximum allowable continuous pressure time, pressure threshold and temperature range. These parameters provide a clear safety boundary for the back-to-back adjustment strategy to ensure that the generated strategy does not cause potential harm to the user. For example, the maximum allowable continuous pressure time can be set to 2 hours, the pressure threshold can be set to 32 mmHg, and the temperature range can be set to 35°C to 38°C.

[0059] The construction of a multi-objective optimization model is one of the core features of this application. The model comprehensively considers multiple goals such as preventing the occurrence of pressure sores, maintaining blood circulation, and promoting muscle function recovery. Preventing the occurrence of pressure sores is set as the main goal and can be given a higher weight, such as 0.6; while maintaining blood circulation and promoting muscle function recovery as secondary goals can be given lower weights, such as 0.2 and 0.2 respectively. This weight setting reflects the priority of different goals and ensures that the generated regulation strategy first meets the needs of pressure sore prevention.

[0060] When constructing the multi-objective optimization model, this application also takes into account the user's rehabilitation stage and historical rehabilitation data. For example, for users in the early stages of rehabilitation, the model may be more inclined to generate a strategy of frequently changing postures to prevent long-term stress; while for users in the late stages of rehabilitation, the model may gradually increase the time to maintain a certain posture to promote muscle function recovery. This dynamic adjustment mechanism enables the generated adjustment strategy to adapt to the changing needs of users during the rehabilitation process.

[0061] When the constructed multi-objective optimization model meets the safety limit parameters set by medical staff, the technical solution of this application will calculate a backrest adjustment strategy that balances the immediate pressure release needs and the requirements of progressive rehabilitation training. This step reflects the innovation of this application in seeking a balance between short-term comfort and long-term rehabilitation goals. For example, for a user who has just started rehabilitation training, the adjustment strategy may slightly adjust the backrest angle or pressure distribution every 15 minutes to meet the immediate pressure release needs; at the same time, the strategy will gradually increase the time the user maintains a certain posture, from the initial 5 minutes to 10 minutes and 15 minutes, to meet the requirements of progressive rehabilitation training.

[0062] The technical solution of this application builds a dynamic, multi-objective optimization system by combining medical expertise, real-time data and historical data. This approach not only improves the accuracy and safety of the adjustment strategy, but also better supports the user's long-term rehabilitation process. By introducing the professional knowledge of medical staff, this application effectively solves the problem of how to integrate medical experience into the automated adjustment system. At the same time, the application of the multi-objective optimization model solves the problem of how to strike a balance between meeting immediate needs and long-term rehabilitation goals.

[0063] Specifically, the technical solution of the present application can be implemented through the following steps: First, medical staff input rehabilitation safety limit parameters through the user interface, for example, setting the maximum allowable continuous pressure time to 90 minutes, the pressure threshold to 30 mmHg, and the temperature range to 36°C to 37.5°C.

[0064] Next, the system obtains real-time data about the contact surface between the user and the wheelchair backrest based on a multi-point sensor network. The pressure distribution data may show that the pressure on the user's buttocks is 25 mmHg and the pressure on the center of the back is 20 mmHg; the temperature data may show that the average temperature of the contact surface is 36.5°C; the physiological index data may include a skin surface temperature of 36.8°C and a local blood flow velocity of 3.5 cm / s.

[0065] The system then builds a multi-objective optimization model based on the user's rehabilitation stage (for example, in the middle of rehabilitation) and historical rehabilitation data (such as the pressure tolerance time increased from 30 minutes to 45 minutes in the past week). In the model, the weight of preventing pressure sores may be set to 0.6, the weight of maintaining blood circulation is 0.25, and the weight of promoting muscle function recovery is 0.15.

[0066] Based on this model, the system calculates a balanced backrest adjustment strategy. For example, every 40 minutes, the backrest angle is slightly adjusted by 2-3 degrees, and the pressure distribution is fine-tuned to reduce the hip pressure by 2 mmHg and increase the back pressure by 1 mmHg. This strategy not only meets the needs of immediate pressure relief, but also meets the requirements of progressive rehabilitation training by gradually increasing the holding time (starting from 40 minutes, and may gradually increase to 45 minutes and 50 minutes in the next few days).

[0067] Finally, the system will continuously monitor the user's physiological index changes and discomfort feedback signals. If abnormal changes are detected, such as the local blood flow velocity drops to 3.0 cm / s, the system will optimize the adjustment strategy in real time, and may make the next angle adjustment in advance or increase the adjustment range.

[0068] In this way, the technical solution of the present application can provide electric wheelchair users with a highly personalized, safe and effective back adjustment strategy, significantly improving the user's comfort and safety during the rehabilitation process, while also providing medical staff with a more precise and effective patient management tool.

[0069] In some of the above embodiments of the present application, it is proposed to construct a multi-objective optimization model with the prevention of pressure sores as the main goal and the maintenance of blood circulation and muscle function recovery as the secondary goals to generate a back adjustment strategy. However, in this process, how to accurately determine the weight coefficients of each goal and how to effectively integrate multiple goals into an optimization model still remain challenges. In addition, how to ensure that the model can adapt to changes in the user's rehabilitation stage and how to incorporate the professional knowledge of medical staff into the model are also key issues that need to be addressed.

[0070] In this regard, the present application further proposes to determine the main weight coefficient for preventing the occurrence of pressure sores and the secondary weight coefficient for maintaining blood circulation and muscle function recovery based on the user's rehabilitation stage and historical rehabilitation data, combined with the acquired pressure distribution data, temperature data and physiological indicator data; according to the determined weight coefficients, construct a multidimensional objective function including a pressure distribution function, a temperature distribution function and a physiological indicator function, wherein the pressure distribution function is used to quantify the impact of continuous pressure on the risk of pressure sores, the temperature distribution function is used to evaluate the local blood circulation status, and the physiological indicator function is used to characterize the degree of muscle function recovery; the constructed multidimensional objective function is combined with the rehabilitation safety limit parameters to form a multi-objective optimization model with the prevention of pressure sores as the main goal and the maintenance of blood circulation and muscle function recovery as the secondary goals.

[0071] The technical solution of this application effectively solves the key problems in the construction of multi-objective optimization models through a dynamic weight allocation mechanism, the construction of a multi-dimensional objective function, and the combination with rehabilitation safety limit parameters. This method can dynamically balance multiple rehabilitation goals while taking into account individual differences of users and changes in rehabilitation progress, thereby generating a more personalized and adaptable back-to-back adjustment strategy.

[0072] Specifically, the technical solution of the present application first determines the weight coefficients of different targets based on the user's rehabilitation stage and historical rehabilitation data, combined with the real-time acquired pressure distribution, temperature and physiological index data. This dynamic weight allocation mechanism can be implemented in a variety of ways. For example, a fuzzy logic controller can be used to dynamically adjust the weights of each target according to the user's rehabilitation stage and current physiological state. Another method is to use a machine learning algorithm to predict the optimal weight allocation by analyzing the trends of historical data and current data.

[0073] Furthermore, the present application constructs a multidimensional objective function including a pressure distribution function, a temperature distribution function and a physiological index function. The pressure distribution function can use an exponential decay model to reflect the nonlinear effect of continuous pressure on the risk of pressure sores. The temperature distribution function can use a Gaussian distribution model to evaluate the effect of local temperature changes on blood circulation. The physiological index function can use a polynomial regression model to comprehensively consider the effects of multiple physiological parameters on muscle function recovery.

[0074] Therefore, the design of this multidimensional objective function integrates different rehabilitation goals into a unified optimization framework. For example, the pressure distribution function can be defined as: f_pressure(p) = Σ(w_i * exp(-p_i / p_threshold)); Among them, p_i represents the pressure of the i-th point, p_threshold is the pressure threshold, w_i is the weight of the point, and the value of f_temperature(t) reflects the risk level of bedsores (pressure ulcers) under the current pressure distribution.

[0075] The temperature distribution function can be expressed as: f_temperature(t) = Σ(exp(-(t_i - t_optimal)^2 / (2σ^2))); Among them, t_i represents the temperature of the i-th point, t_optimal is the optimal temperature, σ is the standard deviation, and the value of f_physiology(x) evaluates the impact of the current temperature distribution on local blood circulation.

[0076] The physiological index function can be defined as: f_physiology(x) = a_0 + a_1x_1 + a_2x_2 + ... + a_nx_n + b_1x_1^2 +b_2x_2^2 + ... + b_nx_n^2; Among them, x_i represents different physiological indicators, a_i and b_i are regression coefficients, and the value of f_physiology(x) evaluates the recovery of muscle function under the current physiological state.

[0077] Finally, this application combines the multidimensional objective function with the rehabilitation safety limit parameters to form a complete multi-objective optimization model. This step can be achieved by introducing constraints, such as: g_1(x) ≤ 0, g_2(x) ≤ 0, ..., g_m(x) ≤ 0; Among them, g_i(x) represents different safety restrictions, such as maximum allowable pressure, temperature variation range, etc.

[0078] The innovation of this method lies in its ability to dynamically balance multiple rehabilitation goals while taking into account individual differences in users and changes in rehabilitation progress. In this way, the method can generate a more personalized and adaptable backrest adjustment strategy, effectively improving the accuracy and effectiveness of electric wheelchair backrest adjustment.

[0079] In practical applications, the technical solution of the present application can be implemented by the following steps: First, the system collects the pressure distribution, temperature distribution and physiological index data of the contact surface between the user and the wheelchair backrest in real time through a multi-point sensor network. At the same time, the system obtains the user's rehabilitation stage and historical rehabilitation data from the user rehabilitation database.

[0080] The system then uses machine learning algorithms (such as support vector machines or neural networks) to analyze this data and determine the most appropriate weight assignment at the moment. For example, if the system detects that the user is in the early stages of recovery, it may set the weight of preventing pressure sores to 0.6, the weight of maintaining blood circulation to 0.3, and the weight of restoring muscle function to 0.1.

[0081] Then, the system constructs a multidimensional objective function based on the determined weights. Assuming the above-mentioned function form is used, the system will calculate the specific parameter values ​​of each function based on the current pressure distribution, temperature distribution and physiological index data.

[0082] Afterwards, the system will combine the constructed multi-dimensional objective function with the rehabilitation safety limit parameters pre-set by medical staff (such as maximum allowable pressure, temperature variation range, etc.) to form a complete multi-objective optimization model.

[0083] Finally, the system uses an optimization algorithm (such as genetic algorithm or particle swarm optimization algorithm) to solve this multi-objective optimization model and obtain the optimal backrest adjustment strategy. This strategy will guide the electric wheelchair on how to adjust the pressure and temperature of each backrest point to maximize the multiple goals of preventing pressure sores, maintaining blood circulation, and promoting muscle function recovery.

[0084] Through this method, the technical solution of the present application can dynamically adjust the weights of different rehabilitation goals according to the user's real-time status and rehabilitation stage, and effectively integrate multiple goals into an optimization model. This not only ensures that the model can adapt to changes in the user's rehabilitation stage, but also effectively incorporates the professional knowledge of medical staff into the model by introducing rehabilitation safety limit parameters.

[0085] Compared with traditional fixed-weight or single-target adjustment strategies, this approach has higher flexibility and adaptability. It can more accurately balance the need for immediate pressure relief and the requirements for progressive rehabilitation training, thereby providing more personalized and effective rehabilitation support for patients with serious illnesses. At the same time, this approach also reduces the workload of medical staff, because the system can automatically adjust the strategy according to the user's status, and medical staff intervention is only required in special circumstances.

[0086] In some of the above embodiments of the present application, it is proposed that when the constructed multi-objective optimization model meets the safety limit parameters set by the medical staff, a back adjustment strategy that balances the immediate pressure release demand and the progressive rehabilitation training requirements is calculated to generate a back adjustment strategy for preventing pressure sores and skin injuries. However, in this process, since the user is in the early stages of rehabilitation and has low physiological tolerance, it is necessary to dynamically adjust the weights of the immediate pressure release demand and the progressive rehabilitation training requirements according to the user's real-time status to ensure the user's safety while promoting rehabilitation progress. In addition, it is also necessary to consider the user's pressure load index and local blood flow conditions, and adjust the strategy in time to prevent the occurrence of pressure sores and skin injuries.

[0087] In this regard, the present application further proposes that when it is detected that the user is in the early stages of rehabilitation and has a low physiological tolerance, the baseline weight of the immediate pressure release demand is set to be higher than the baseline weight required for progressive rehabilitation training based on the user's muscle atrophy degree and joint mobility data; while continuously monitoring the pressure distribution data and local blood flow conditions of the user's contact surface with the wheelchair backrest, the user's current pressure load index is calculated based on the pressure duration, pressure intensity and blood flow change rate; when the calculated pressure load index exceeds the safety limit parameters set by medical staff and an abnormal local blood flow condition is detected, the weight of the immediate pressure release demand is increased, and the weight of the progressive rehabilitation training requirement is reduced accordingly; the dynamically adjusted weights are substituted into the multi-objective optimization model to generate a backrest adjustment strategy.

[0088] The technical solution of this application mainly involves the following key technical features: setting initial weights based on the physiological state of the user in the early stage of rehabilitation, real-time monitoring and calculation of the pressure load index, dynamic adjustment of weights, and generation of optimized backrest adjustment strategies. These technical features work together to achieve the goal of dynamically adjusting the backrest adjustment strategy according to the user's real-time state while ensuring the user's safety.

[0089] Specifically, when setting the initial weight based on the user's physiological state at the beginning of rehabilitation, a variety of methods can be used to assess the user's degree of muscle atrophy and joint mobility. For example, electromyography (EMG) can be used to measure muscle activity potentials, or a three-dimensional motion capture system can be used to assess the range of joint motion. Based on this data, the system can calculate the initial weight value using a preset algorithm.

[0090] In terms of real-time monitoring and calculation of the pressure load index, a high-precision pressure sensor array can be used to continuously collect pressure distribution data, while near-infrared spectroscopy or laser Doppler blood flowmetry can be used to monitor local blood flow conditions. The calculation of the pressure load index can take into account the weighted average of pressure duration, pressure intensity, and blood flow change rate.

[0091] In the process of dynamically adjusting the weight, the system can set multiple threshold levels and gradually adjust the weight according to the different degrees of abnormality of the pressure load index and blood flow conditions. For example, when the pressure load index exceeds 80% of the safety limit parameter, the system may slightly increase the weight of the immediate pressure release demand; when it exceeds 100% and abnormal blood flow is detected, the weight may be greatly increased.

[0092] When the dynamically adjusted weights are substituted into the multi-objective optimization model, intelligent optimization methods such as genetic algorithms or particle swarm optimization algorithms can be used to quickly solve the optimal back-end adjustment strategy. This process can be carried out in real time in the embedded system to ensure the timeliness and accuracy of the adjustment strategy.

[0093] This dynamic weight adjustment mechanism effectively solves the problem of low physiological tolerance of users in the early stage of rehabilitation and the need to frequently adjust their posture to prevent pressure sores and skin damage. By substituting the adjusted weights into the multi-objective optimization model, it ensures that the backrest adjustment strategy can take into account both immediate safety needs and long-term rehabilitation goals.

[0094] The technical solution of this application realizes a comprehensive assessment and accurate response to the user status through a dynamic weight adjustment mechanism. In practical applications, this method can operate as follows: First, the system sets initial weights based on the user's initial assessment data entered by the medical staff, such as the muscle atrophy score (e.g., using a scale of 0-5) and the joint range of motion score (e.g., expressed as a percentage of the normal range of motion). Assuming that the user's muscle atrophy score is 2 (moderate atrophy) and the joint range of motion score is 60%, the system may set the initial weight of the immediate pressure relief demand to 0.7 and the initial weight of the progressive rehabilitation training demand to 0.3.

[0095] During continuous monitoring, the system uses a pressure sensor array to collect pressure data. At the same time, near-infrared spectroscopy technology is used to monitor local blood flow conditions. The system calculates the pressure load index based on this data, for example, using the following formula: Pressure load index = (P / Pmax) * (T / Tmax) * (1 - BF / BFnormal); Among them, P is the current pressure, Pmax is the maximum allowable pressure set by medical staff, T is the duration, Tmax is the maximum allowable duration, BF is the current blood flow, and BFnormal is the normal blood flow.

[0096] When the system detects that the pressure load index exceeds the preset threshold (for example, 0.8) and the local blood flow is less than 70% of the normal value, the weight adjustment mechanism will be triggered. The adjustment can be made using the following formula: New weight = old weight + α * (pressure load index - threshold) + β * (1 - BF / BFnormal) Among them, α and β are preset adjustment coefficients. For example, if the calculated new weights are 0.8 and 0.2, the system will substitute these new weights into the multi-objective optimization model.

[0097] The optimization model can be expressed as: min F(x) = 0.8 * f1(x) + 0.2 * f2(x); st g1(x) ≤ 0, g2(x) ≤ 0, ...; Among them, f1(x) represents the pressure release objective function, f2(x) represents the rehabilitation training objective function, and g1(x), g2(x), etc. are safety constraints.

[0098] In this way, the technical solution of the present application can accurately adjust the backrest according to the real-time status of the user, maximizing the rehabilitation effect while ensuring safety. Compared with the traditional fixed parameter adjustment method, this dynamic and personalized adjustment method can better adapt to the dynamic changes of the user's status during the rehabilitation process, thereby providing safer and more effective rehabilitation support.

[0099] In some of the above embodiments of the present application, it is proposed to increase the weight of the immediate pressure release requirement and correspondingly reduce the weight of the progressive rehabilitation training requirement to dynamically adjust the user's back adjustment strategy. However, in this process, when the user's local blood flow condition is detected to be abnormal, the existing technology may not be able to adjust the weight in a timely and accurate manner, resulting in the user's physiological needs not being effectively met, which may increase the risk of pressure sores and skin injuries.

[0100] In this regard, the present application further proposes that when the user's local blood flow condition is detected to be abnormal, based on the blood flow abnormality judgment standard and weight adjustment rules preset by the medical staff, the increase in the weight of the immediate pressure release requirement and the decrease in the weight of the progressive rehabilitation training requirement are dynamically calculated. The judgment of the local blood flow condition abnormality includes: when the local blood flow change rate is lower than the preset minimum threshold or the blood flow fluctuation frequency is higher than the preset maximum threshold, it is judged as the local blood flow condition abnormality.

[0101] The technical solution of this application realizes real-time monitoring and rapid response to the user's local blood flow condition by introducing preset blood flow abnormality judgment criteria and weight adjustment rules. This dynamic adjustment mechanism can timely adjust the weights of immediate pressure release requirements and progressive rehabilitation training requirements when abnormal conditions are detected, thereby better meeting the user's physiological needs.

[0102] Specifically, the technical solution of this application includes the following key features: First, a set of blood flow abnormality determination criteria is established. This criterion can be based on a variety of physiological parameters, such as the local blood flow change rate and the blood flow fluctuation frequency. For example, the minimum threshold of the local blood flow change rate can be set to 5% / minute, and the maximum threshold of the blood flow fluctuation frequency can be set to 2Hz. When the detected parameters exceed these thresholds, the system will determine that the local blood flow condition is abnormal.

[0103] Secondly, corresponding weight adjustment rules were formulated. These rules determine how to adjust the weights of the immediate pressure relief requirement and the progressive rehabilitation training requirement when abnormal blood flow is detected. For example, it can be set that when abnormal blood flow is detected, the weight of the immediate pressure relief requirement increases by 5% per minute, while the weight of the progressive rehabilitation training requirement decreases by 5% accordingly.

[0104] Thirdly, a mechanism for dynamically calculating the weight adjustment amount is implemented. The system will dynamically calculate the increase in the weight required for immediate pressure release and the decrease in the weight required for progressive rehabilitation training according to the degree of blood flow abnormality. This dynamic calculation ensures the accuracy and adaptability of weight adjustment.

[0105] These features are closely related to each other, forming a closed-loop monitoring-judgment-adjustment system. The blood flow abnormality judgment criteria provide clear trigger conditions for the system, the weight adjustment rules determine the system's response, and the dynamic calculation mechanism ensures the accuracy and flexibility of the adjustment. This synergy enables the system to respond more sensitively and accurately to changes in the user's physiological state.

[0106] The technical solution of the present application plays an important role in solving the problem that the weight cannot be adjusted in time when the user's local blood flow condition is abnormal. Through the preset blood flow abnormality judgment criteria, the system can quickly identify abnormal situations. Based on the weight adjustment rules, the system can respond immediately, increase the weight of the immediate pressure release demand, and reduce the weight of the progressive rehabilitation training requirements. This timely adjustment ensures that the user can get more pressure relief when the blood flow is abnormal, reducing the risk of pressure sores and skin damage.

[0107] The mechanism of dynamically calculating the weight adjustment further improves the accuracy and adaptability of the system. The system can not only identify blood flow abnormalities, but also determine the magnitude of weight adjustment based on the degree of abnormality. This refined adjustment ensures that the system can provide the most suitable back-up adjustment strategy based on the actual needs of the user.

[0108] In this way, the technical solution of the present application can better meet the physiological needs of users, especially providing timely and effective adjustments when blood flow conditions are abnormal. This not only improves the user's comfort, but also significantly reduces the risk of pressure sores and skin injuries, providing users with a safer and more effective rehabilitation environment.

[0109] As a preferred implementation, the technical solution of the present application can be implemented through the following steps: First, the system continuously monitors the local blood flow status of the user's contact surface with the wheelchair backrest through a multi-point sensor network. These sensors can use photoplethysmographic sensors to capture the blood flow change rate and blood flow fluctuation frequency in real time.

[0110] Secondly, the system compares the collected data with the preset blood flow abnormality judgment standard. For example, if it detects that the blood flow change rate in a certain area is less than 3% / minute, or the blood flow fluctuation frequency is higher than 2.5Hz, the system will determine that the local blood flow condition in that area is abnormal.

[0111] Next, once abnormal blood flow is detected, the system will immediately start the weight adjustment mechanism. Assume that the current weight of immediate pressure relief demand is 60%, and the weight of progressive rehabilitation training requirement is 40%. The system will calculate the new weight distribution according to the preset weight adjustment rules.

[0112] For example, if abnormal blood flow persists for 2 minutes, the system might increase the weight of the immediate pressure relief request to 70% while decreasing the weight of the progressive rehabilitation request to 30%. This adjustment is dynamic and continuously updated as blood flow conditions change.

[0113] Finally, the system recalculates the backrest adjustment strategy based on the new weight distribution. This may include reducing pressure in abnormal areas, adjusting the backrest angle, or changing the temperature setting. The system performs these adjustments at a steady pace to ensure user comfort.

[0114] Through this implementation, the technical solution of the present application can respond as soon as local blood flow abnormalities are detected, effectively preventing the occurrence of pressure sores and skin injuries, while providing users with more personalized and dynamic rehabilitation support. This not only improves the accuracy and effectiveness of the electric wheelchair backrest adjustment, but also greatly enhances the safety and comfort of users during the rehabilitation process.

[0115] In some of the above embodiments of the present application, a step is proposed to set the baseline weight of the immediate pressure release demand to be higher than the baseline weight of the progressive rehabilitation training requirement based on the user's muscle atrophy degree and joint mobility data, so as to balance the immediate pressure release demand and the progressive rehabilitation training requirement. However, in this process, how to accurately set the weight according to the user's specific physiological condition and how to ensure that the baseline weight of the immediate pressure release demand is not lower than the safety threshold become key issues that need to be solved.

[0116] In this regard, the present application further proposes that when the user's muscle atrophy degree and joint mobility data are received from the medical staff through the user interface, the user's comprehensive physiological condition index is calculated based on the preset scoring weights; based on the calculated comprehensive physiological condition index, the immediate pressure release demand benchmark weight and the progressive rehabilitation training demand benchmark weight are determined from the preset weight configuration model; when the determined immediate pressure release demand benchmark weight is lower than the system preset safety threshold, the immediate pressure release demand benchmark weight is adjusted to a value not lower than the safety threshold, and the progressive rehabilitation training demand benchmark weight is adjusted accordingly to ensure that the sum of the two remains constant.

[0117] The technical solution of this application realizes accurate weight setting based on the user's specific physiological condition by introducing a comprehensive physiological condition index and a preset weight configuration model. At the same time, through the safety threshold mechanism and dynamic weight adjustment, the priority of immediate pressure release needs is ensured while taking into account the needs of progressive rehabilitation training. This method not only improves the accuracy and personalization of weight setting, but also enhances the security and adaptability of the system, effectively solving the problems of inaccurate weight setting and insufficient security in the original solution.

[0118] The innovation of this technical solution is to combine the professional evaluation of medical staff, objective quantification of physiological indicators and intelligent weight configuration model to achieve a more accurate, safe and personalized back adjustment strategy. This method can not only better balance the needs of immediate pressure relief and progressive rehabilitation training, but also make real-time adjustments according to the dynamic changes of the user's rehabilitation process, thereby improving the effect of electric wheelchair back adjustment and user experience.

[0119] The technical solution of this application involves multiple key features, which can be implemented in a variety of ways. First, the medical staff can use a variety of scoring standards to input the user's muscle atrophy degree and joint mobility data, such as a 0-10 point system or a 1-5 point system. The scoring can be based on the professional judgment of the medical staff, or it can be combined with objective measurement tools, such as electromyography or joint angle measurement instrument data.

[0120] When calculating the comprehensive physiological condition index based on the preset score weights, a linear weighted model or a nonlinear model can be used. For example, a linear weighted model can be expressed as: Comprehensive physiological status index = w1 * muscle atrophy score + w2 * joint range of motion score; Among them, w1 and w2 are preset weights, which can be adjusted according to the focus of different rehabilitation stages.

[0121] The preset weight configuration model can be a model trained based on a machine learning algorithm, such as a support vector machine (SVM) or a neural network model. These models can learn the relationship between the comprehensive physiological condition index and the optimal weight configuration based on a large amount of historical data.

[0122] The safety threshold mechanism can be set as a dynamic threshold that automatically adjusts according to the user's recovery progress and physiological tolerance. For example, a safety threshold function can be defined: Safety threshold = basic threshold + f(recovery time, physiological tolerance); Where f is a function that increases with the recovery time and physiological tolerance.

[0123] During the dynamic weight adjustment process, a smoothing factor α (0<α<1) can be introduced to ensure the smoothness of the weight adjustment: New weight = α * calculated weight + (1-α) * original weight; The scores input by medical staff provide the initial data for the entire system, and the calculation of the comprehensive physiological condition index integrates these scores into a single indicator for subsequent processing. The preset weight configuration model is based on this index, combined with historical data and expert knowledge, to give preliminary weight configuration suggestions. The safety threshold mechanism and dynamic weight adjustment are further optimized and protected on this basis to ensure that the system does not ignore user safety while pursuing rehabilitation effects.

[0124] Specifically, when medical staff input the user's muscle atrophy score and joint range of motion score through the user interface, the system first calculates the user's comprehensive physiological condition index based on the preset score weights. This step converts the multi-dimensional score information into a single quantitative indicator, which is convenient for subsequent processing and decision-making.

[0125] Next, the system determines the baseline weights for immediate pressure relief and progressive rehabilitation training from the preset weight configuration model based on the calculated comprehensive physiological condition index. This step uses machine learning or expert system methods to associate the user's physiological condition with the optimal weight configuration, thus achieving personalized weight settings.

[0126] After determining the weight, the system will conduct a safety check. If the determined baseline weight of the immediate pressure relief demand is lower than the system preset safety threshold, the system will automatically adjust it to a value not lower than the safety threshold. This mechanism ensures that the immediate pressure relief demand is always given sufficient attention and prevents safety risks caused by improper weight setting.

[0127] At the same time, in order to maintain the balance of the system, when adjusting the baseline weight of the immediate pressure relief demand, the system will adjust the baseline weight of the progressive rehabilitation training demand accordingly to ensure that the sum of the two remains constant. This balancing mechanism ensures that while ensuring safety, the need for rehabilitation training will not be completely sacrificed.

[0128] Through this method, the technical solution of the present application can accurately set the weight according to the specific physiological condition of the user, and at the same time ensure that the baseline weight of the immediate pressure release demand is not lower than the safety threshold through the safety threshold mechanism. This not only improves the accuracy and safety of backrest adjustment, but also can make real-time adjustments according to the dynamic changes of the user's rehabilitation process, thereby improving the effect of electric wheelchair backrest adjustment and user experience.

[0129] In some of the above embodiments of the present application, steps are proposed for generating a back adjustment strategy for preventing pressure sores and skin injuries based on the acquired data in combination with the user's rehabilitation stage and historical rehabilitation data, so as to generate a back adjustment strategy suitable for the user's current state. However, in this process, since the user's rehabilitation state is dynamically changing and each user's situation is unique, relying solely on static data and fixed models may not be able to fully adapt to the user's real-time demand changes during the rehabilitation process. In addition, how to ensure the safety of the user while taking into account multiple goals such as pressure sore prevention, blood circulation maintenance, and muscle function recovery, and being able to dynamically adjust the strategy according to the user's real-time state, is a complex challenge.

[0130] In this regard, the present application further proposes to construct a dynamic multi-objective optimization model based on the acquired pressure distribution data pi(t), temperature data ti(t) and physiological index data, combined with the user's rehabilitation stage and historical rehabilitation data, when receiving rehabilitation safety limit parameters including the maximum allowable continuous pressure time Tmax_pressure(t), pressure threshold Pmax(t), and temperature range [Tmin(t), Tmax(t)] input by medical staff. The objective function of the model is min F(x, t) =[w1(t)f1(x, t), w2(t)f2(x, t), w3(t)f3(x, t)], where x(t) is a decision variable, representing the pressure and temperature values ​​of each point at time t; f1(x, t), f2(x, t) and f3(x, t) are dynamic pressure sore risk function, dynamic blood circulation status function and dynamic muscle function recovery function respectively; wi(t) is a time-varying weight coefficient. The model also contains multiple constraints to ensure that the pressure and temperature are within a safe range. When changes in the user's physiological state are detected, the weight adjustment mechanism dwi(t) / dt = α(g(x,t), h(x, t)) is used to dynamically adjust the weights of each objective based on the user's physiological tolerance function g(x, t) and rehabilitation progress function h(x, t). By solving the dynamic multi-objective optimization model, the optimal pressure and temperature distribution schemes at each backrest point at different times are obtained, and a backrest adjustment strategy for preventing pressure sores and skin damage is generated.

[0131] The dynamic multi-objective optimization model proposed in this application comprehensively considers the three main objectives of pressure sore risk, blood circulation status and muscle function recovery. By using the time-varying weight coefficient wi(t), the model can dynamically adjust the importance of each objective according to the user's rehabilitation stage. The decision variable x(t) contains the pressure and temperature values ​​of each point of the backrest at different times, enabling the model to accurately control the adjustment of the backrest. f1(x, t), f2(x, t) and f3(x, t) in the objective function respectively evaluate the risk of pressure sores, blood circulation status and muscle function recovery, ensuring the comprehensiveness of the adjustment strategy. The constraints take into account the safety limit parameters set by medical staff, including the range limit of pressure and temperature, as well as the limit of pressure duration, to ensure the safety of the adjustment strategy. At the same time, by limiting the adjustment rate of pressure and temperature, the smoothness of the adjustment process is ensured. The weight adjustment mechanism dwi(t) / dt = α(g(x, t), h(x, t)) is an innovation of this application. The weights of each target are adjusted in real time through the physiological tolerance function g(x, t) and the rehabilitation progress function h(x, t), so that the model can dynamically adjust the strategy according to the user's real-time status and rehabilitation progress.

[0132] The dynamic multi-objective optimization model of the present application can be implemented in a variety of ways. For example, the dynamic pressure sore risk function f1(x, t) can be constructed based on pressure distribution and duration, taking into account the pressure sensitivity of different parts. Specifically, an exponential function can be used to represent the impact of pressure duration on pressure sore risk, such as f1(x, t) = Σ(ai * exp(bi * pi(t) * T(pi, t))), where ai and bi are the sensitivity coefficients of different parts. The dynamic blood circulation status function f2(x, t) can be constructed based on temperature distribution and pressure change rate, for example f2(x, t) = Σ(ci * (ti(t) - Topt)^2+ di * (dpi(t) / dt)^2), where Topt is the optimal blood circulation temperature, and ci and di are weight coefficients. The dynamic muscle function recovery function f3(x, t) can take into account the frequency and amplitude of pressure changes, such as f3(x, t) = Σ(ei * sin(ωi *t) * pi(t)), where ei is the importance coefficient of the muscle group and ωi is the frequency of pressure change.

[0133] The weight adjustment mechanism is one of the core innovations of this application. The physiological tolerance function g(x, t) can be constructed based on the user's physiological indicators (such as heart rate, blood pressure, skin resistance, etc.), for example, g(x, t) = 1 / (1 + exp(-k * (V(t) - V0))), where V(t) is the physiological indicator vector, V0 is the baseline value, and k is the adjustment coefficient. The rehabilitation progress function h(x, t) can be constructed based on the user's rehabilitation stage and historical data, such as h(x, t) = log(1 + R(t) / R0), where R(t) is the rehabilitation progress indicator and R0 is the initial value. The weight adjustment function α can be designed as α(g, h) = λ * g + (1-λ) * h, where λ is the balance coefficient.

[0134] This dynamic multi-objective optimization method solves the problem that static models cannot adapt to the changing needs of users during rehabilitation. It can dynamically balance multiple goals such as pressure sore prevention, blood circulation maintenance, and muscle function recovery based on the user's real-time status and rehabilitation progress while ensuring the user's safety, and generate the optimal backrest adjustment strategy. The innovation of this method lies in its ability to achieve personalized and dynamic adjustment strategies, which significantly improves the accuracy and adaptability of electric wheelchair backrest adjustment and provides users with safer and more effective rehabilitation support.

[0135] Specifically, the dynamic multi-objective optimization model of the present application can be implemented by the following steps: First, based on the multi-point sensor network, the pressure distribution data pi(t) and temperature data ti(t) of the contact surface between the user and the wheelchair backrest, as well as physiological index data including skin temperature and local blood flow status, are obtained. These data are used as the input of the model.

[0136] Next, the medical staff input the rehabilitation safety limit parameters, including the maximum allowable continuous pressure time Tmax_pressure(t), the pressure threshold Pmax(t), and the temperature change range [Tmin(t), Tmax(t)]. These parameters serve as constraints for the model.

[0137] Then, a dynamic multi-objective optimization model is constructed. The objective function contains three sub-functions: f1(x, t), f2(x, t) and f3(x, t), which correspond to the risk of pressure sores, blood circulation status and muscle function recovery, respectively. Each sub-function has a time-varying weight coefficient wi(t).

[0138] The constraints of the model include: pressure and temperature range limits, pressure duration limits, and pressure and temperature adjustment rate limits. These constraints ensure the safety and stability of the regulation strategy.

[0139] During the operation of the model, the system continuously monitors the user's physiological state. When changes are detected, the weight adjustment is calculated through the physiological tolerance function g(x, t) and the rehabilitation progress function h(x, t). The weight adjustment mechanism dwi(t) / dt = α(g(x, t), h(x, t)) ensures that the model can dynamically adjust the importance of each goal according to the user's real-time state.

[0140] Finally, the dynamic multi-objective optimization model is solved by numerical optimization methods (such as gradient descent, genetic algorithm, etc.) to obtain the optimal pressure and temperature distribution scheme at each backrest point at different times. This scheme is the backrest adjustment strategy for preventing pressure sores and skin damage.

[0141] The technical solution of this application achieves accurate response to the complex needs of users during rehabilitation by introducing a dynamic multi-objective optimization model. This method can dynamically adjust the weights of multiple goals such as pressure sore prevention, blood circulation maintenance, and muscle function recovery according to the user's real-time physiological state and rehabilitation progress, thereby generating the optimal backrest adjustment strategy. This dynamic adjustment mechanism ensures that the adjustment strategy always adapts to the user's current needs, significantly improving the accuracy and personalization of the electric wheelchair backrest adjustment.

[0142] In addition, the technical solution of the present application ensures the safety and smoothness of the adjustment process by introducing multiple constraints. By limiting the range of pressure and temperature and the adjustment rate, discomfort or injury that may be caused by sudden changes is avoided. This design is particularly suitable for users who are highly sensitive to external pressure and can provide a more comfortable and safer rehabilitation environment.

[0143] The technical solution of the present application is also highly adaptable and extensible. By adjusting the objective function and constraints, the method can adapt to different types of rehabilitation needs and different stages of rehabilitation processes. For example, the objective function can be added or modified according to the specific situation of the user to consider more rehabilitation factors.

[0144] Second, refer to Figure 2 The present application also proposes an electric wheelchair backrest adjustment device, which comprises: An acquisition module 210 is used to acquire pressure distribution data, temperature data, and physiological index data including skin temperature and local blood flow status of the contact surface between the user and the wheelchair backrest based on a multi-point sensor network; A generating module 220, for generating a back-support adjustment strategy for preventing pressure sores and skin injuries based on the acquired data in combination with the user's rehabilitation stage and historical rehabilitation data; The adjustment module 230 is used to adjust the pressure and temperature of each point at a preset adjustment speed when the generated adjustment strategy meets the smooth transition requirement; The monitoring module 240 is used to continuously monitor the changes in the user's physiological indicators and discomfort feedback signals during the adjustment process; The optimization module 250 is used to optimize the adjustment strategy in real time according to the monitoring results and user feedback when abnormal changes are detected, and store the optimized adjustment parameters in the user rehabilitation database.

[0145] The pressure distribution, temperature and physiological index data of the contact surface between the user and the wheelchair backrest are obtained through a multi-point sensor network, and an adjustment strategy is generated in combination with the user's rehabilitation stage and historical rehabilitation data. Continuous monitoring and optimization are carried out during the adjustment process, which solves the problem of lack of accurate multi-point pressure and temperature adjustment in the existing technology and inability to dynamically adjust according to the user's real-time physiological condition. The system has the advantages of accurate multi-point pressure and temperature adjustment, dynamic adjustment according to the user's real-time physiological condition, adaptation to the changing needs during the rehabilitation process, and automatic optimization of support strategies based on long-term rehabilitation data.

[0146] In addition, in some preferred embodiments, an electric wheelchair backrest adjustment device proposed in the present application can perform any one of the steps in the above method.

[0147] In a third aspect, the present application also provides an electronic device, including a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the above method are executed.

[0148] Through the above technical solution, the processor and the memory are interconnected and communicate with each other through a communication bus and / or other forms of connection mechanisms. The memory stores computer-readable instructions executable by the processor. When the electronic device is running, the processor executes the computer-readable instructions to execute the method in any optional implementation method of the above embodiment to achieve the following functions: based on a multi-point sensor network, the pressure distribution data, temperature data and physiological index data including skin temperature and local blood flow status of the user and the wheelchair back contact surface are obtained; based on the acquired data, combined with the user's rehabilitation stage and historical rehabilitation data, a back adjustment strategy for preventing pressure sores and skin injuries is generated; when the generated adjustment strategy meets the smooth transition requirements, the pressure and temperature of each back point are adjusted at a preset adjustment speed; during the adjustment process, the user's physiological index changes and discomfort feedback signals are continuously monitored; when abnormal changes are detected, the adjustment strategy is optimized in real time according to the monitoring results and user feedback, and the optimized adjustment parameters are stored in the user rehabilitation database.

[0149] In a fourth aspect, the present application also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method are executed.

[0150] Through the above technical solution, when the computer program is executed by the processor, the method in any optional implementation method of the above embodiment is executed to achieve the following functions: based on a multi-point sensor network, the pressure distribution data, temperature data and physiological index data including skin temperature and local blood flow status of the contact surface between the user and the wheelchair backrest are obtained; according to the acquired data, combined with the user's rehabilitation stage and historical rehabilitation data, a backrest adjustment strategy for preventing pressure sores and skin injuries is generated; when the generated adjustment strategy meets the requirements of smooth transition, the pressure and temperature of each backrest point are adjusted at a preset adjustment speed; during the adjustment process, the user's physiological index changes and discomfort feedback signals are continuously monitored; when abnormal changes are detected, the adjustment strategy is optimized in real time according to the monitoring results and user feedback, and the optimized adjustment parameters are stored in the user rehabilitation database.

[0151] Among them, the computer-readable storage medium 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 red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0152] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for adjusting the backrest of an electric wheelchair, characterized in that: The method includes: Based on a multi-point sensor network, the pressure distribution data, temperature data and physiological index data including skin temperature and local blood flow status of the contact surface between the user and the wheelchair backrest are obtained; Based on the acquired data, combined with the user's rehabilitation stage and historical rehabilitation data, a back-rest adjustment strategy for preventing pressure sores and skin injuries is generated; When the generated regulation strategy meets the requirement of smooth transition, the pressure and temperature of each point are regulated at a preset regulation speed; During the adjustment process, the user's physiological index changes and discomfort feedback signals are continuously monitored; When abnormal changes are detected, the adjustment strategy is optimized in real time according to the monitoring results and user feedback, and the optimized adjustment parameters are stored in the user rehabilitation database.

2. The method for adjusting the backrest of an electric wheelchair according to claim 1, characterized in that: The step of generating a back-support adjustment strategy for preventing pressure sores and skin injuries based on the acquired data and in combination with the user's rehabilitation stage and historical rehabilitation data includes: Receive rehabilitation safety limit parameters input by medical staff, including maximum allowable continuous pressure time, pressure threshold, and temperature range, and build a multi-objective optimization model based on the acquired pressure distribution data, temperature data, and physiological index data, combined with the user's rehabilitation stage and historical rehabilitation data, with the primary goal of preventing pressure sores and the secondary goals of maintaining blood circulation and muscle function recovery; When the constructed multi-objective optimization model meets the safety limit parameters set by medical staff, the back-support adjustment strategy that balances the needs of immediate pressure relief and progressive rehabilitation training requirements is calculated.

3. The method for adjusting the backrest of an electric wheelchair according to claim 2, characterized in that: The steps of constructing a multi-objective optimization model with the primary goal of preventing the occurrence of pressure sores and the secondary goals of maintaining blood circulation and muscle function recovery include: Based on the user's rehabilitation stage and historical rehabilitation data, combined with the acquired pressure distribution data, temperature data and physiological index data, determine the main weight coefficient for preventing the occurrence of pressure sores and the secondary weight coefficient for maintaining blood circulation and muscle function recovery; According to the determined weight coefficients, a multidimensional objective function including a pressure distribution function, a temperature distribution function and a physiological index function is constructed, wherein the pressure distribution function is used to quantify the impact of continuous pressure on the risk of pressure sores, the temperature distribution function is used to evaluate the local blood circulation status, and the physiological index function is used to characterize the degree of muscle function recovery; The constructed multidimensional objective function is combined with the rehabilitation safety limit parameters to form a multi-objective optimization model with the prevention of pressure ulcers as the main goal and the maintenance of blood circulation and muscle function recovery as the secondary goals.

4. The method for adjusting the backrest of an electric wheelchair according to claim 2, characterized in that: When the constructed multi-objective optimization model meets the safety limit parameters set by the medical staff, the step of calculating the back-support adjustment strategy that balances the immediate pressure release demand and the progressive rehabilitation training requirement includes: When it is detected that the user is in the early stage of rehabilitation and has low physiological tolerance, the baseline weight of the immediate pressure release requirement is set to be higher than the baseline weight of the progressive rehabilitation training requirement based on the user's muscle atrophy degree and joint mobility data; While continuously monitoring the pressure distribution data and local blood flow status of the contact surface between the user and the wheelchair backrest, the user's current pressure load index is calculated based on the pressure duration, pressure intensity and blood flow change rate; When the calculated pressure load index exceeds the safety limit parameters set by medical staff and abnormal local blood flow conditions are detected, the weight of the immediate pressure relief requirement is increased, while the weight of the progressive rehabilitation training requirement is reduced accordingly; Substitute the dynamically adjusted weights into the multi-objective optimization model to generate a back-end adjustment strategy.

5. The method for adjusting the backrest of an electric wheelchair according to claim 4, characterized in that: The step of increasing the weight of the immediate pressure release requirement and correspondingly decreasing the weight of the progressive rehabilitation training requirement comprises: When the user's local blood flow condition is detected to be abnormal, the increase in the weight of the immediate pressure release requirement and the decrease in the weight of the progressive rehabilitation training requirement are dynamically calculated based on the blood flow abnormality judgment criteria and weight adjustment rules preset by the medical staff; Wherein, the determination of the abnormal local blood flow condition includes: When the local blood flow change rate is lower than a preset minimum threshold or the blood flow fluctuation frequency is higher than a preset maximum threshold, it is determined that the local blood flow condition is abnormal.

6. The method for adjusting the backrest of an electric wheelchair according to claim 4, characterized in that: The step of setting the baseline weight of the immediate pressure release requirement to be higher than the baseline weight of the progressive rehabilitation training requirement based on the user's muscle atrophy degree and joint mobility data includes: When receiving the user's muscle atrophy degree and joint mobility data input by the medical staff through the user interface, calculating the user's comprehensive physiological condition index based on the preset scoring weight; According to the calculated comprehensive physiological status index, determining the immediate pressure release demand baseline weight and the progressive rehabilitation training demand baseline weight from a preset weight configuration model; When the determined immediate pressure relief demand benchmark weight is lower than the system preset safety threshold, the immediate pressure relief demand benchmark weight is adjusted to a value not lower than the safety threshold, and the progressive rehabilitation training demand benchmark weight is adjusted accordingly to ensure that the sum of the two remains constant.

7. The method for adjusting the backrest of an electric wheelchair according to claim 2, characterized in that: The step of generating a back-support adjustment strategy for preventing pressure sores and skin injuries based on the acquired data and in combination with the user's rehabilitation stage and historical rehabilitation data includes: When receiving the rehabilitation safety limit parameters input by medical staff, including the maximum allowable continuous pressure time Tmax_pressure(t), pressure threshold Pmax(t), and temperature change range [Tmin(t), Tmax(t)], a dynamic multi-objective optimization model is constructed based on the acquired pressure distribution data pi(t), temperature data ti(t) and physiological index data, combined with the user's rehabilitation stage and historical rehabilitation data; The objective function of the dynamic multi-objective optimization model is: min F(x, t) = [w1(t)f1(x, t), w2(t)f2(x, t), w3(t)f3(x, t)] in, x(t) = [p1(t), p2(t), ..., pn(t), t1(t), t2(t), ..., tn(t)] is the decision variable, which represents the pressure and temperature values ​​of each point at time t; f1(x, t) is the dynamic pressure ulcer risk function, which is used to assess the risk level of pressure ulcers caused by the current pressure distribution; f2(x, t) is the dynamic blood circulation status function, which is used to evaluate the impact of the current regulation strategy on blood circulation; f3(x, t) is the dynamic muscle function recovery function, which is used to evaluate the degree to which the current regulation strategy promotes muscle function recovery; wi(t) is the time-varying weight coefficient, which is dynamically adjusted with the rehabilitation stage; The constraints of the dynamic multi-objective optimization model include: 0 ≤ pi(t) ≤ Pmax(t), i = 1, 2, ..., n; Tmin(t) ≤ ti(t) ≤ Tmax(t), i = 1, 2, ..., n; T(pi, t) ≤ Tmax_pressure(t), i = 1, 2, ..., n; |dpi(t) / dt| ≤ Rmax_p, |dti(t) / dt| ≤ Rmax_t; Where T(pi, t) represents the duration of pressure pi at time t, Rmax_p and Rmax_t are the maximum adjustment rates of pressure and temperature, respectively; When a change in the user's physiological state is detected, a weight adjustment mechanism is adopted based on the user's physiological tolerance function g(x, t) and rehabilitation progress function h(x, t), which are constructed based on historical rehabilitation data: dwi(t) / dt = α(g(x, t), h(x, t)), i = 1, 2, 3; Among them, α is the weight adjustment function, which is used to dynamically adjust the weight of each target according to the user status; By solving the dynamic multi-objective optimization model, the optimal pressure and temperature distribution schemes at each back-rest point at different times are obtained, and a back-rest adjustment strategy for preventing pressure sores and skin injuries is generated.

8. An electric wheelchair backrest adjustment device, characterized in that: The device includes: An acquisition module is used to acquire pressure distribution data, temperature data, and physiological index data including skin temperature and local blood flow status on the contact surface between the user and the wheelchair backrest based on a multi-point sensor network; A generation module, for generating a back-rest adjustment strategy for preventing pressure sores and skin injuries based on the acquired data and in combination with the user's rehabilitation stage and historical rehabilitation data; A regulating module, used for regulating the pressure and temperature of each back point at a preset regulating speed when the generated regulating strategy meets the requirement of smooth transition; A monitoring module is used to continuously monitor the user's physiological index changes and discomfort feedback signals during the adjustment process; The optimization module is used to optimize the adjustment strategy in real time according to the monitoring results and user feedback when abnormal changes are detected, and store the optimized adjustment parameters in the user rehabilitation database.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 7 are executed.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are executed.

Images