A bladder function training guidance and control system and method based on multimodal sensors

Abstract

The application relates to the technical field of medical devices, and particularly discloses a bladder function training guide and control system and method based on a multi-modal sensor, which comprises the following: an integrated sensing module, which monitors the body surface pressure of a bladder area through a pressure sensor array, obtains the geometric parameters of the bladder in combination with an ultrasonic probe, and simultaneously collects the liquid conductivity data in the bladder by using impedance tomography technology; a bladder parameter inference module, which fuses multi-source data to calculate real-time bladder wall tension and limit capacity, and constructs a personalized tension-capacity model; a urination demand evaluation module, which calculates a urination demand value based on real-time tension, model parameters and limit capacity; a training plan optimization module, which dynamically adjusts an initial training scheme according to the urination demand of the day; and a training guide and control module, which executes the optimized plan and performs real-time monitoring, and triggers an audible-light vibration reminder or a catheterization device when the demand value reaches a threshold value. The system realizes intelligent and personalized guide and control of bladder function training through multi-modal data fusion and closed-loop control.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a bladder function training guidance and control system and method based on a multimodal sensor. Background Art

[0002] Bladder dysfunction is a common problem in the treatment and rehabilitation of urinary system diseases, severely impacting patients' quality of life. Bladder function training is crucial for improving bladder function and enhancing patients' ability to urinate independently. However, traditional bladder function training often lacks precise monitoring and scientific guidance, making personalized and effective training difficult. The key to bladder function training lies in accurately and accurately understanding bladder status in real time, enabling the development of an appropriate training plan. In the past, clinical assessment of bladder function relied primarily on subjective patient feedback and limited diagnostic tools. However, subjective patient responses can vary significantly and be inaccurate. While conventional examinations, such as ultrasound, can provide some bladder information, single-modality data cannot fully reflect the complex physiological state of the bladder. With the rapid advancement of sensor technology, multimodal sensor fusion is becoming a trend in the medical field. By combining multiple sensor types, richer and more comprehensive physiological data from different dimensions can be obtained, providing strong support for precision medicine. A bladder function training guidance and control system and method based on multimodal sensors has emerged. It uses multiple sensors such as pressure sensors, ultrasound probes, and impedance tomography to obtain bladder-related information in all directions. It is of great significance to improve the scientificity, accuracy and personalization of bladder function training. It is expected to be widely used in the rehabilitation treatment of urinary system diseases and promote the development of this field towards intelligence and precision.

[0003] Existing technologies for bladder function training have numerous shortcomings. The lack of multimodal data fusion monitoring methods for bladder status monitoring results in an incomplete understanding of bladder status, making it difficult to accurately assess patients' urination needs and provide urination reminders. Furthermore, common universal training programs fail to account for the variations in training effectiveness caused by patients' diverse physiological characteristics.

[0004] Therefore, the present invention proposes a bladder function training guidance and control system and method based on a multimodal sensor. Summary of the Invention

[0005] The present invention provides a bladder function training guidance and control system and method based on a multimodal sensor, for use in:

[0006] The present invention provides a bladder function training guidance and control system based on a multimodal sensor, comprising:

[0007] An integrated sensing module is used to detect the surface pressure of the patient's bladder area based on a pressure sensor array, measure the real-time geometric parameters of the bladder based on an ultrasound probe, and obtain quantitative data on the conductivity of the fluid in the patient's bladder based on impedance tomography;

[0008] The bladder parameter inference module is used to calculate the real-time bladder wall tension and the number of units of the maximum capacity based on the quantitative data of the fluid conductivity in the patient's bladder, the surface pressure of the patient's bladder area, and the real-time geometric parameters of the bladder, and to build a bladder wall tension-bladder capacity model for the patient;

[0009] A urination demand assessment module is used to assess the patient's real-time urination demand value based on the patient's real-time bladder wall tension, bladder wall tension-bladder capacity model, and the number of limit capacity units;

[0010] A training plan optimization module is used to optimize the initial bladder function training plan based on the patient's real-time urination demand value obtained on the day to obtain an optimized bladder function training plan;

[0011] The training guidance module is used to guide the patient's bladder function training based on the optimized bladder function training plan. At the same time, when the urination demand value reaches the urination demand threshold in the optimized bladder function training plan, it triggers sound and light vibration to remind the patient to urinate or start the catheterization device.

[0012] Optionally, it also includes:

[0013] The water drinking reminder module is used to dynamically calculate the current water requirement based on the patient's weight, activity level, ambient temperature and humidity, and the real-time bladder status model, and issue real-time water drinking reminders to the patient based on the current water requirement.

[0014] Optionally, an integrated sensing module includes:

[0015] a pressure sensing submodule, configured to continuously detect a real-time surface pressure distribution value of a patient's bladder area as surface pressure based on a pressure sensor array;

[0016] an ultrasound probe measurement submodule, configured to continuously transmit ultrasound signals to the patient's bladder area and receive ultrasound echo signals reflected from the bladder area based on the ultrasound probe, and determine real-time geometric parameters of the bladder based on the ultrasound echo signals received in real time by the ultrasound probe;

[0017] The bladder impedance detection submodule is used to construct an impedance tomography image of the patient's bladder by applying a weak alternating current to multiple electrodes placed on the patient's bladder area and measuring the potential difference on the patient's bladder area surface, and to determine quantitative data on the fluid conductivity in the patient's bladder based on the continuously acquired impedance tomography image.

[0018] Optionally, the bladder parameter inference module includes:

[0019] a residual urine volume statistics submodule, configured to determine the number of residual urine volume units of the patient based on the quantitative data of the conductivity of the liquid in the patient's bladder;

[0020] a bladder wall tension estimation submodule, configured to estimate real-time bladder wall tension based on the surface pressure of the patient's bladder area and real-time geometric parameters of the bladder;

[0021] The correlation analysis submodule is used to perform correlation analysis between the number of residual urine units of the patient within a preset cycle and the real-time bladder wall tension, introduce the immediate elastic modulus and delayed elastic modulus of the bladder, and use a three-element standard linear solid model to describe the patient's bladder wall tension-bladder capacity model;

[0022] The limit capacity calculation submodule is used to calculate the limit capacity units of the patient's bladder based on the conductivity change data of the bladder liquid and the urination events over a long period of time and the patient's bladder wall tension-bladder capacity model.

[0023] Optionally, the bladder wall tension estimation submodule includes:

[0024] a bladder mechanics model and function establishment unit, for obtaining a surface pressure range of the patient's bladder region and a geometric limit parameter range of the bladder, and establishing the patient's bladder elastic mechanics model and pressure transfer function based on the surface pressure range of the patient's bladder region and the geometric limit parameter range of the bladder;

[0025] a bladder pressure distribution conversion unit, configured to convert body surface pressure into intra-bladder pressure distribution based on a bladder pressure transfer function of the patient;

[0026] The bladder wall tension estimation unit is used to estimate the real-time bladder wall tension based on the patient's bladder elastic mechanical model and the real-time geometric parameters of the bladder.

[0027] Optionally, the limit capacity calculation submodule includes:

[0028] a nonlinear model description unit, used to describe the nonlinear relationship between the conductivity of the bladder fluid and the bladder volume during bladder filling based on an exponential decay model, and obtain an original bladder fluid conductivity-capacity dynamic model;

[0029] A urination event recognition unit is used to identify all conductivity drop features in the conductivity change data of the bladder fluid over a long period of time, and calculate the urination event probability of each conductivity drop feature based on the conductivity change data before and after all conductivity drop features and the hidden Markov model, and screen all urination events from all conductivity drop features based on the urination event probability;

[0030] A model personalization description unit is used to optimize the volume attenuation coefficient and background noise compensation term in the original conductivity-volume dynamic model based on the conductivity change data before and after all urination events and the Markov chain Monte Carlo method to obtain the patient's intra-bladder fluid conductivity-volume dynamic model;

[0031] The limit capacity unit number calculation unit is used to calculate the limit capacity unit number of the patient's bladder based on the patient's bladder fluid conductivity-capacity dynamic model, the patient's bladder fluid conductivity limit value and the patient's bladder wall maximum tension value.

[0032] Optionally, the method for calculating the number of limit capacity units of the patient's bladder based on the patient's bladder fluid conductivity-capacity dynamic model, the patient's bladder fluid conductivity limit value, and the patient's bladder wall maximum tension value includes:

[0033] ;

[0034] Where, is the maximum capacity unit of the patient's bladder, is the patient's maximum bladder wall tension value, is the maximum tension value of the bladder wall of a standard adult. is the Poisson's ratio of bladder tissue, is the natural logarithm function, is the approximate radius of the patient's bladder when not full, is the bladder wall thickness of the patient's bladder when it is not full. is the maximum conductivity of the patient's bladder fluid, is the background noise compensation term in the patient's bladder fluid conductivity-volume dynamic model, is the conductivity of the fluid in the bladder when the patient's bladder is not full. is the volume attenuation coefficient in the patient's bladder fluid conductivity-volume dynamic model.

[0035] Optionally, the urination need assessment module includes:

[0036] A real-time bladder capacity estimation submodule, configured to determine the patient's real-time bladder capacity units based on the patient's real-time bladder wall tension and a bladder wall tension-bladder capacity model;

[0037] The urination demand value quantification submodule is used to calculate the patient's real-time urination demand value based on the patient's real-time bladder capacity unit number, the limit capacity unit number, the patient's real-time bladder wall tension and the patient's bladder wall maximum tension value.

[0038] Optionally, the training plan optimization module includes:

[0039] An initial training plan generation submodule is configured to generate an initial bladder function training plan of the patient based on the physiological sign data of the patient;

[0040] A training plan optimization submodule is configured to optimize adjustable parameters in the initial bladder function training plan by reinforcement learning on the real-time micturition demand value of the patient acquired on the day and all micturition event occurrence times of the patient, to obtain an optimized bladder function training plan.

[0041] The application provides a bladder function training guidance and control method based on a multi-modal sensor, comprising:

[0042] Step 1: detecting the body surface pressure of the bladder region of the patient based on a pressure sensor array, simultaneously, measuring the real-time geometric parameters of the bladder based on an ultrasonic probe, and acquiring the liquid conductivity quantitative data in the bladder of the patient based on impedance tomography;

[0043] Step 2: calculating the real-time bladder wall tension and the limit capacity unit number based on the liquid conductivity quantitative data in the bladder of the patient and the body surface pressure of the bladder region of the patient and the real-time geometric parameters of the bladder, and building a bladder wall tension-bladder capacity model of the patient;

[0044] Step 3: evaluating the real-time micturition demand value of the patient based on the real-time bladder wall tension of the patient, the bladder wall tension-bladder capacity model and the limit capacity unit number;

[0045] Step 4: optimizing the initial bladder function training plan based on the real-time micturition demand value of the patient acquired on the day, to obtain an optimized bladder function training plan;

[0046] Step 5: guiding and controlling the bladder function training of the patient based on the optimized bladder function training plan, and simultaneously, triggering an audible light vibration to remind the patient to urinate or starting a urinary catheterization device when the micturition demand value reaches the micturition demand threshold in the optimized bladder function training plan.

[0047] The application has the following beneficial effects compared with the prior art:

[0048] Other features and advantages of the application will be set forth in the following description of the application, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the application. The objects and other advantages of the application can be realized and attained by the structure particularly pointed out in the written description and claims hereof.

[0049] The technical solutions of the application will be further described in detail below with reference to the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0050] The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application, and do not limit the application. In the drawings:

[0051] Figure 1 4 is a module diagram of a bladder function training guidance and control system based on a multimodal sensor in an embodiment of the present invention;

[0052] Figure 2 This is a logic flow chart of a multimodal sensor-based bladder function training guidance and control method in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0054] Provided is an implementation of a bladder function training guidance and control system based on a multimodal sensor, such as Figure 1 Shown, including:

[0055] The integrated sensing module is used to detect surface pressure in the patient's bladder area using a pressure sensor array. Simultaneously, it measures real-time bladder geometric parameters using an ultrasound probe and obtains quantitative data on the conductivity of the fluid within the patient's bladder using impedance tomography. The pressure sensor array is distributed across the patient's bladder area, detecting surface pressure changes in that area in real time. For example, when the bladder is full, the bladder wall exerts pressure on the body surface. The pressure sensor array accurately senses this pressure change and converts it into an electrical or digital signal.

[0056] At the same time, the ultrasound probe uses the reflection principle of ultrasound to provide real-time X-ray of the bladder, measuring the bladder's real-time geometric parameters, such as the length, width, and height of the bladder, to reflect the morphological changes of the bladder.

[0057] In addition, impedance tomography technology applies a weak current to the human body and obtains quantitative data on the conductivity of the fluid in the patient's bladder based on the different conductivity properties of different tissues and liquids, thereby understanding the electrical properties of the urine in the bladder. The integration of these data provides comprehensive bladder status information for subsequent modules.

[0058] The bladder parameter inference module is used to calculate the real-time bladder wall tension and the number of units of the maximum capacity based on the quantitative data of the fluid conductivity in the patient's bladder, the surface pressure of the patient's bladder area, and the real-time geometric parameters of the bladder. It also builds the patient's bladder wall tension-bladder capacity model, including:

[0059] Based on the quantitative data of the conductivity of the liquid in the bladder, combined with specific algorithms and empirical formulas, the number of units of residual urine volume of the patient can be determined, and the approximate situation of the remaining urine in the bladder can be understood.

[0060] Then, based on the surface pressure in the bladder area and the real-time geometric parameters of the bladder, the real-time bladder wall tension is calculated using mechanical principles and mathematical models. This value reflects the amount of tension the bladder wall is subjected to in the current state.

[0061] The patient's residual urine volume in a preset period (such as a day or a week) is correlated with the real-time bladder wall tension. The immediate elastic modulus and delayed elastic modulus of the bladder are introduced, and a three-element standard linear solid model is used to describe the relationship between them. This allows the patient to develop a personalized bladder wall tension-bladder capacity model, including:

[0062] ;

[0063] Where, is the real-time bladder wall tension (Pa), is the bladder capacity (m³), is the instantaneous elastic modulus (Pa), which is 4.2±1.5kPa. is the delayed elastic modulus (Pa), which is 1.8±0.6kPa. The viscosity coefficient (Pa・s) represents the resistance coefficient of bladder wall tissue to viscous flow under stress, reflecting the dynamic mechanical response characteristics of the bladder when it is filled. Based on clinical research data, the typical viscosity coefficient of a healthy bladder is: ;

[0064] This model can accurately depict the changes in the patient's bladder wall tension under different capacity states, providing a key basis for subsequent assessment of urination needs.

[0065] By analyzing the data on changes in bladder fluid conductivity over a long period of time, combined with urination event records and the established bladder wall tension-bladder capacity model, the patient's bladder's maximum capacity units can be calculated. This value is crucial for judging the functional status of the bladder and formulating a reasonable training plan.

[0066] The urination need assessment module is used to assess the patient's real-time urination need value based on the patient's real-time bladder wall tension, bladder wall tension-bladder capacity model, and the number of limit capacity units, including:

[0067] Based on the patient's real-time bladder wall tension and the bladder wall tension-bladder capacity model, the patient's current real-time bladder capacity units are determined to clarify the actual degree of bladder filling at this moment.

[0068] The urination demand value quantification submodule combines the real-time bladder capacity unit number, the limit capacity unit number, the real-time bladder wall tension of the patient, and the maximum bladder wall tension value, and uses a specific calculation formula to accurately calculate the real-time urination demand value of the patient. For example, if the real-time bladder capacity is close to the limit capacity, and the real-time bladder wall tension is high, close to the maximum bladder wall tension value, then the urination demand value will increase accordingly, indicating that the patient has a strong urination demand at this moment. In this way, the system can dynamically and accurately assess the patient's urination demand at different times, providing an important reference for subsequent training plan optimization and control.

[0069] The training plan optimization module is used to optimize the initial bladder function training plan based on the real-time urination demand value of the patient obtained on the day, and obtain an optimized bladder function training plan. The initial training plan is formulated by the initial training plan generation submodule based on the physiological sign data of the patient (such as age, gender, physical condition, etc.), and is a preliminary and general training framework. The training plan optimization submodule, through reinforcement learning on the real-time urination demand value of the patient obtained on the day and the time of all urination events of the patient, deeply analyzes the urination rules and demand changes of the patient, and then optimizes and adjusts the adjustable parameters (such as urination interval time, bladder filling amount for each training, etc.) in the initial bladder function training plan, to obtain an optimized bladder function training plan that is more suitable for the actual situation of the patient on the day. For example, if the real-time urination demand value of the patient on a certain day shows that the patient's bladder function has recovered well, and the urination interval time is relatively stable and long, the training plan optimization submodule may appropriately lengthen the urination interval time in the initial plan, so that the training plan is more targeted and effective, and the recovery of the patient's bladder function is better promoted.

[0070] The training control module is used to control the bladder function training of the patient based on the optimized bladder function training plan, and when the urination demand value reaches the urination demand threshold in the optimized bladder function training plan, it triggers the sound-light-vibration to remind the patient to urinate or starts the catheterization device. During the training process, it continuously monitors the urination demand value of the patient. Once the urination demand value reaches the pre-set urination demand threshold in the optimized bladder function training plan, the system will immediately trigger the sound-light-vibration to remind the patient to urinate in an intuitive and obvious way. For some patients who cannot urinate independently, the system will also automatically start the catheterization device to ensure that the patient's bladder function training can be carried out smoothly, while ensuring the health and urination safety of the patient, avoiding damage to the bladder due to excessive urine retention or delayed urination, and realizing the intelligent and personalized control of bladder function training.

[0071] In an alternative embodiment, it further comprises:

[0072] A drinking water reminding module is used to dynamically calculate the current water demand based on the patient's body weight, activity level, environmental temperature and humidity, and real-time bladder state model, and to send real-time drinking water reminders to the patient based on the current water demand.

[0073] In this embodiment, the real-time bladder state model integrates the data obtained and analyzed by the integrated sensing module and the bladder parameter inference module, reflecting the current functional state, capacity, and urine generation of the bladder. If the real-time bladder state model shows that the urine generation rate in the bladder is slow or the bladder function is in a specific stage of recovery, the amount of drinking water may need to be adjusted appropriately to promote urine generation and bladder function recovery. For example, in order to maintain the normal filling and emptying cycle of the bladder, in some cases it may be necessary to increase the amount of drinking water to stimulate urine generation, or to appropriately control the amount of drinking water when the risk of bladder overfilling is high.

[0074] The calculation process of the current water demand includes:

[0075] Basic water demand calculation: According to general medical recommendations, the basic water demand per kilogram of body weight per day for an adult is about 30-40 milliliters. Assuming that the patient weighs 70 kilograms, we take the intermediate value of 35 milliliters per kilogram to calculate the basic water demand. So the basic water demand = 70 kg x 35 ml / kg = 2450 ml. This is the basic water requirement per day based on the patient's body weight.

[0076] Activity level adjustment: The activity level can be obtained by wearing a sports bracelet or other device, and it is assumed to be measured by steps and exercise intensity. If the patient's daily steps reach 10,000 steps or more and the exercise intensity is moderate (such as brisk walking), according to the empirical formula, for every additional 1,000 steps, an additional 50 milliliters of water is needed, and for every 30 minutes of moderate intensity exercise, an additional 100 milliliters of water is needed.

[0077] The patient walked 12,000 steps that day, with an additional 2,000 steps, corresponding to an additional water requirement of 2,000 ÷ 1,000 x 50 = 100 milliliters. At the same time, the moderate intensity exercise lasted for 60 minutes, requiring an additional 60 ÷ 30 x 100 = 200 milliliters of water. Therefore, the water requirement due to increased activity is 100 + 200 = 300 milliliters.

[0078] Environmental temperature and humidity adjustment: Assuming that the environmental temperature and humidity sensor obtains an environmental temperature of 30°C and a relative humidity of 40%. According to research, for every 1°C increase in temperature, an additional 5 milliliters of water per kilogram of body weight per day is required; for every 10% decrease in relative humidity, an additional 10 milliliters of water per kilogram of body weight per day is required.

[0079] The temperature is increased by 30-25 = 5 °C from the suitable temperature (assuming 25 °C), and the additional water required due to the temperature increase is 70 kg x 5 °C x 5 ml / kg / °C = 1750 ml. The relative humidity is decreased by 60%-40% = 20% from the suitable humidity (assuming 60%), and the additional water required due to the humidity decrease is 70 kg x 20% ÷ 10% x 10 ml / kg = 1400 ml. Therefore, the water required due to the change in environmental temperature and humidity is 1750 + 1400 = 3150 ml.

[0080] Real-time bladder state model adjustment: The real-time bladder state model is obtained by analyzing the quantitative data of the electrical conductivity of the liquid in the bladder, the body surface pressure of the bladder area, and the real-time parameters of the bladder geometry. Assuming that the model shows that the patient's bladder is currently in a mild dehydration state, in order to promote urine production and recovery of normal bladder function, an additional 500 ml of water intake is required.

[0081] Calculate the current water requirement: Add the above items to get the current water requirement = basal water requirement + activity adjustment water requirement + environmental temperature and humidity adjustment water requirement + bladder real-time state model adjustment water requirement = 2450 + 300 + 3150 + 500 = 6400 ml.

[0082] After dynamically calculating the current water requirement based on the above multiple factors, the drinking water reminder module will send real-time drinking water reminders to the patient according to this calculation result. The reminder methods may include but are not limited to mobile application push messages, vibration prompts of the wearable device, voice reminders, etc. For example, in the afternoon when the patient's activity is large and the environmental temperature is high, the drinking water reminder module calculates that the patient needs to intake 500 ml more water than usual, and then sends a vibration and displays a drinking water prompt information through the smart bracelet worn by the patient, reminding the patient to supplement water in time to maintain normal water metabolism and good conditions for bladder function training. This way of dynamically calculating water requirement based on multiple factors and real-time reminding helps patients maintain reasonable water intake, better cooperate with bladder function training, and promote the rehabilitation process.

[0083] In an alternative embodiment, the integrated sensing module comprises:

[0084] The pressure sensing sub-module is used to continuously detect the real-time body surface pressure distribution value of the patient's bladder area based on the pressure sensor array as the body surface pressure. These data provide an important basis for subsequent analysis of the filling degree of the bladder, the pressure change trend, etc., helping the system to understand the mechanical state of the bladder at different times.

[0085] An ultrasound probe measurement sub-module is configured to continuously emit ultrasound signals to the patient's bladder region and receive ultrasound echo signals reflected from the bladder region, and determine real-time geometric parameters of the bladder based on the ultrasound echo signals received in real time by the ultrasound probe. For example, the length, width, and height of the bladder can be calculated to obtain the volume of the bladder, and the thickness and shape of the bladder wall can also be analyzed. These real-time geometric parameters are crucial for accurately determining the morphological changes of the bladder and evaluating the functional status of the bladder, and provide intuitive morphological information of the bladder for the entire guidance and control system.

[0086] A bladder impedance detection sub-module is configured to apply a weak alternating current to multiple electrodes placed on the surface of the patient's bladder region and measure the potential difference on the surface of the patient's bladder region, construct an impedance tomography of the patient's bladder, and determine quantitative data of the liquid conductivity in the patient's bladder based on the continuously obtained impedance tomography.

[0087] The sub-module takes advantage of the different conductivities of different tissues and liquids. By placing multiple electrodes on the surface of the patient's bladder region and applying a weak alternating current to the human body, a potential difference will be generated on the surface due to the difference in conductivity between the liquid in the bladder (urine) and the surrounding tissues. The bladder impedance detection sub-module measures these potential differences and constructs an impedance tomography of the patient's bladder based on electrical principles and mathematical algorithms. The continuously obtained impedance tomography can reflect the changes in liquid conductivity in the bladder over time, and the sub-module determines quantitative data of the liquid conductivity in the patient's bladder based on these data. For example, by analyzing the impedance tomography data, the composition and concentration of the urine can be understood, as different compositions and concentrations of urine have different conductivities. These quantitative data of the liquid conductivity help to understand the physiological state of the bladder and provide unique electrical dimension information for comprehensive evaluation of bladder function.

[0088] The three sub-modules work together to obtain real-time information of the bladder from multiple dimensions such as pressure, geometric shape, and liquid conductivity, providing a rich and accurate data basis for subsequent bladder parameter inference, urination demand assessment, and other modules, and is a key link for the accurate operation of the bladder function training guidance and control system based on multi-modal sensors.

[0089] In an alternative embodiment, the bladder parameter inference module includes:

[0090] The residual urine volume counting sub-module is configured to determine the residual urine volume of the patient in units based on the liquid conductivity quantitative data of the patient's bladder. The conductivity of urine is related to the components such as electrolytes dissolved therein, and different urine volumes will cause changes in conductivity. Through a mathematical model or an empirical formula established based on a large amount of clinical data, the sub-module can convert the measured liquid conductivity quantitative data into the residual urine volume in units. For example, it is found through research on a large number of patients that under certain conditions, there is a certain functional relationship between the conductivity of urine and the residual urine volume. By substituting the liquid conductivity data of the current patient into the function, the residual urine volume in units can be obtained. Understanding the residual urine volume is of great significance for evaluating the emptying capacity of the bladder and subsequent treatment and training plan. It reflects the amount of urine remaining in the bladder after the last urination, and can assist in determining whether the bladder function is normal.

[0091] The bladder wall tension calculating sub-module is configured to calculate the real-time bladder wall tension based on the body surface pressure of the bladder region of the patient and the real-time geometric parameters of the bladder. The body surface pressure of the bladder region reflects the effect of the internal pressure of the bladder on the body surface, and the real-time geometric parameters (such as shape, size, etc.) of the bladder affect the distribution of pressure on the bladder wall. First, by establishing a mechanical model of the bladder, considering the elastic properties of the bladder and the pressure transmission law, the body surface pressure is converted into the internal pressure of the bladder, and combined with the geometric shape parameters of the bladder, the real-time bladder wall tension is calculated by using mechanical principles and mathematical methods. For example, based on the theory of elasticity, it is assumed that the bladder is approximately a certain geometric shape, and according to the body surface pressure and the parameters of the geometric shape, the tension of the bladder wall under the current state is calculated by a corresponding formula. The real-time bladder wall tension is an important indicator reflecting the functional state of the bladder, and excessive or insufficient tension may indicate a problem with the bladder, providing a key basis for subsequent urination demand assessment and training plan.

[0092] The correlation analysis submodule is configured to perform correlation analysis on the number of residual urine units of the patient in a preset period and the real-time bladder wall tension, and introduce the instantaneous elastic modulus and the delayed elastic modulus of the bladder. The three-element standard linear solid model is used to describe the bladder wall tension-bladder volume model of the patient. The two moduli reflect the elastic response characteristics of the bladder tissue under stress. The instantaneous elastic modulus reflects the elastic change of the bladder under instantaneous stress, and the delayed elastic modulus describes the elastic change of the bladder during continuous stress. The three-element standard linear solid model is used to describe the relationship between the residual urine volume and the bladder wall tension. The model can accurately depict the change rule of the bladder wall tension under different urine volumes. Through analysis and fitting of a large amount of data, the personalized bladder wall tension-bladder volume model of the patient is obtained. The model is crucial for in-depth understanding of the physiological characteristics of the bladder of the patient. It can help the system accurately estimate the bladder volume according to the bladder wall tension, provide an important theoretical basis for urination demand assessment and training plan optimization, and enable the system to more accurately grasp the functional state of the bladder of the patient.

[0093] The limit capacity calculation submodule is configured to calculate the limit capacity of the bladder of the patient based on the change data of the liquid conductivity in the bladder and the urination events in a long period and the bladder wall tension-bladder volume model of the patient. The change of the liquid conductivity in the bladder is closely related to the change of the urine volume in the bladder, and the urination events clearly mark the stage change of the bladder volume. By analyzing the change trend of the liquid conductivity in a long period, combining the sudden change of the conductivity when the urination event occurs, and using the relationship reflected by the bladder wall tension-bladder volume model, the limit capacity of the bladder is calculated. For example, in the process of multiple urinations, the change of the liquid conductivity before and after each urination is observed, and the corresponding relationship between the bladder wall tension and the volume is observed. Through specific algorithms and data analysis methods, the maximum capacity of the bladder in the normal physiological range is determined. Understanding the limit capacity of the bladder is crucial for developing a reasonable bladder function training plan. It can help the system set a suitable urination threshold to avoid damage to the bladder due to excessive filling, and also provides an important reference for evaluating the recovery of the bladder function of the patient.

[0094] In an alternative embodiment, the bladder wall tension calculation submodule comprises:

[0095] A bladder mechanics model and function establishment unit is configured to obtain a body surface pressure range of a bladder region of a patient and a geometric limit parameter range of the bladder, and establish a bladder elastic mechanics model and a pressure transfer function of the patient based on the body surface pressure range of the bladder region of the patient and the geometric limit parameter range of the bladder. The body surface pressure range reflects the change interval of the pressure exerted by the bladder on the body surface under different filling degrees, and the geometric limit parameter range of the bladder covers the shape, size and other parameters of the bladder under extreme states such as maximum and minimum volume. Based on these data, the unit establishes the bladder elastic mechanics model of the patient by using mechanical principles and mathematical methods. This model regards the bladder as a mechanical structure with elastic properties, simulates the deformation and stress distribution of the bladder under different pressure actions. At the same time, the pressure transfer function is established, which describes the relationship between the body surface pressure and the internal pressure of the bladder. For example, considering that the shape of the bladder is approximately an ellipsoid, according to the relationship between the elastic mechanics theory and the actually measured body surface pressure and the geometric parameters of the bladder, the corresponding mathematical model and function expression are constructed. These models and functions are the basis for subsequent accurate calculation of the bladder wall tension and provide a theoretical framework for understanding the internal mechanical state of the bladder.

[0096] A bladder pressure distribution conversion unit is configured to convert the body surface pressure into the bladder internal pressure distribution based on the bladder pressure transfer function of the patient. Since the body surface pressure is not directly equivalent to the bladder internal pressure, and the distribution of the bladder internal pressure is also not uniform at different positions, it is necessary to obtain the real pressure distribution in the bladder through this conversion process. For example, assuming that the pressure transfer function shows that the body surface pressure and the bladder internal pressure have a nonlinear relationship and are related to the specific geometric position of the bladder, the unit will use the pressure transfer function to perform accurate calculation based on the real-time body surface pressure data and the current geometric shape of the bladder, so as to obtain the pressure values of each position in the bladder and draw a detailed atlas of the bladder internal pressure distribution. The accurate bladder internal pressure distribution is crucial for subsequent calculation of the bladder wall tension, because the tension of the bladder wall at different positions is closely related to the pressure of the position.

[0097] a bladder wall tension estimation unit configured to estimate real-time bladder wall tension based on a patient's bladder elastomechanics model and real-time geometric parameters of the bladder. The real-time geometric parameters of the bladder (e.g. current volume, shape change, etc.) determine the force-bearing area and direction of the bladder wall, while the bladder elastomechanics model provides the conversion relationship between pressure and tension. For example, according to the stress-strain relationship in elastomechanics, combined with the material properties of the bladder wall (described by the elastomechanics model) and the current pressure distribution (from the bladder pressure distribution conversion unit) and geometry, through a specific calculation formula, the real-time tension values of the bladder wall at each position are obtained. These real-time bladder wall tension data are of key significance for assessing the functional status of the bladder, determining whether there is abnormal pressure load, and developing targeted treatment and training programs, and are one of the important parameters in the entire bladder function training guidance and control system.

[0098] In an alternative embodiment, the limit capacity estimation sub-module comprises:

[0099] a nonlinear model description unit configured to describe the nonlinear relationship between the electrical conductivity of the liquid in the bladder and the bladder volume during bladder filling based on an exponential decay model to obtain an original liquid conductivity-volume dynamic model in the bladder. During bladder filling, as the urine increases, the bladder volume increases, and the electrical conductivity of the liquid in the bladder will change nonlinearly due to urine dilution and other reasons. The exponential decay model can well describe this relationship. For example, assuming that the electrical conductivity of the liquid in the bladder is σ, and the bladder volume is V, the exponential decay model can be expressed as:

[0100] ;

[0101] wherein, is the real-time electrical conductivity of the liquid in the bladder (S / m), is the electrical conductivity of the liquid in the bladder of the patient in the non-filled state (S / m), is a natural constant, is a volume decay coefficient, is a background noise compensation term (S / m).

[0102] The original liquid conductivity-volume dynamic model in the bladder is obtained. This model provides a basic framework for subsequent analysis, which preliminarily establishes the mathematical relationship between the electrical conductivity of the liquid and the bladder volume, and helps to understand the electrical and volume change law of the bladder during filling.

[0103] The urination event recognition unit is used to identify all conductivity drop features (the moment of the conductivity change and the conductivity change values ​​before and after) in the conductivity change data of the bladder fluid over a long period of time. Based on the conductivity change data before and after all conductivity drop features and the hidden Markov model, the urination event probability of each conductivity drop feature is calculated. Based on the urination event probability, all urination events are screened out from all conductivity drop features, including:

[0104] ;

[0105] Where, For the conductivity drop characteristics The probability of urination events, is the natural exponential function, is the event sensitivity parameter (high value (0.25-0.3) is taken for emergency monitoring, and medium value (0.1-0.15) is taken for routine monitoring), For the conductivity drop characteristics The conductivity change value before and after the conductivity change data before and after, is the total number of conductivity drop features;

[0106] Then, all conductivity drop features with a probability of urination event greater than a preset value are used to determine that a urination event has occurred.

[0107] The model's personalized description unit is used to optimize the volume decay coefficient and background noise compensation term in the original conductivity-volume dynamic model based on pre- and post-micturition conductivity change data from all urination events and the Markov Chain Monte Carlo method, thereby obtaining a patient's bladder fluid conductivity-volume dynamic model. This process prioritizes optimizing the volume decay coefficient and background noise compensation term in the original model. The volume decay coefficient influences the decay rate between bladder volume and fluid conductivity in the model, while the background noise compensation term corrects for noise interference in the measured data. By continuously adjusting these two parameters, the model is tailored to the individual patient's specific circumstances, resulting in a personalized bladder fluid conductivity-volume dynamic model. This personalized model more accurately reflects the true relationship between bladder fluid conductivity and bladder volume, providing a more reliable basis for accurately estimating bladder capacity.

[0108] The limit capacity unit calculation unit is used to calculate the patient's limit bladder capacity unit based on a dynamic model of the patient's intrabladder fluid conductivity and capacity, the patient's intrabladder fluid conductivity limit, and the patient's bladder wall maximum tension value. The intrabladder fluid conductivity limit reflects the maximum or minimum conductivity that the bladder fluid can achieve, while the maximum bladder wall tension value defines the maximum tension that the bladder can withstand within a safe range. By substituting these parameters into a personalized model and applying relevant mathematical calculation methods (which may involve solving specific equations or performing numerical simulations, for example), the patient's limit bladder capacity unit is determined. This limit capacity unit number is important for developing appropriate bladder function training programs and assessing patient bladder function. It provides a key reference for setting an appropriate upper limit for bladder filling during training, helping to avoid bladder damage caused by overfilling.

[0109] In an alternative embodiment, the method for calculating the number of limit capacity units of the patient's bladder based on the patient's intra-bladder fluid conductivity-capacity dynamic model, the patient's intra-bladder fluid conductivity limit value, and the patient's bladder wall maximum tension value by the limit capacity unit calculation unit includes:

[0110] ;

[0111] Where, The number of units of the patient's bladder's maximum capacity reflects the maximum capacity that the patient's bladder can hold under the current physiological state. It is an important indicator for measuring bladder function and is crucial for formulating bladder function training plans and judging bladder health status.

[0112] The maximum tension value of the patient's bladder wall indicates the maximum tensile force that the bladder wall can withstand. During bladder filling, the tension on the bladder wall gradually increases. When this maximum value is reached, the bladder is close to its limit capacity. This parameter limits overfilling of the bladder and ensures that the calculated limit capacity is within the physiological tolerance range of the bladder. For example, if the bladder wall material becomes fragile due to disease or other reasons, Tmax will decrease accordingly, and the calculated limit capacity unit will also decrease;

[0113] It is the maximum tension value of the bladder wall of a standard adult;

[0114] is the Poisson's ratio of bladder tissue, which describes the ratio of transverse strain to longitudinal strain when a material is subjected to unidirectional tension or compression. For bladder tissue, the Poisson's ratio reflects the deformation characteristics of the bladder under stress. For example, when the bladder wall is subjected to longitudinal tension, the Poisson's ratio determines its degree of transverse contraction or expansion.

[0115] is the natural logarithm function;

[0116] is the approximate radius of the patient's bladder in a non-filled state (i.e., the radius of the corresponding sphere obtained by approximately converting the bladder volume to the volume of a sphere);

[0117] The bladder wall thickness of the patient's bladder in a non-filled state (the existing adult bladder wall thickness in a non-filled state can be used);

[0118] The maximum conductivity of the fluid in the patient's bladder provides the electrical boundary condition for calculating the limit capacity;

[0119] The background noise compensation term in the patient's bladder fluid conductivity-capacity dynamic model is used to correct the impact of these noises on the calculation, making the limit capacity calculated based on fluid conductivity more accurate;

[0120] The conductivity of the bladder fluid in the patient's non-filled bladder;

[0121] The volume decay coefficient in the patient's bladder fluid conductivity-capacity dynamic model describes the rate at which fluid conductivity decays with bladder volume. This coefficient reflects the intrinsic relationship between bladder volume and fluid conductivity in the model. By adjusting this coefficient, the model can better fit the individual patient's bladder characteristics, allowing for accurate calculation of the number of limit capacity units.

[0122] In an alternative embodiment, the urination need assessment module comprises:

[0123] The real-time bladder capacity estimation submodule determines the patient's real-time bladder capacity in units based on their real-time bladder wall tension and the bladder wall tension-bladder capacity model. Using this model, the submodule uses real-time bladder wall tension as input and, using the mathematical relationships defined by the model, calculates the patient's real-time bladder capacity in units. This calculation, based on the patient's individual bladder characteristic model, more accurately reflects the patient's current bladder fullness than more general estimation methods.

[0124] The urination demand value quantification submodule is used to calculate the patient's real-time urination demand value based on the patient's real-time bladder capacity unit number, the limit capacity unit number, the patient's real-time bladder wall tension and the patient's bladder wall maximum tension value.

[0125] In this embodiment, the bladder wall tension-bladder capacity model reflects the changing pattern of the patient's bladder wall tension under different capacity states and is a personalized mathematical model.

[0126] In this embodiment, the real-time bladder wall tension is obtained in real time by the bladder wall tension estimation submodule.

[0127] In this embodiment, the real-time bladder capacity units reflect the actual amount of bladder filling at the moment, the limit capacity units represent the maximum amount the bladder can hold, the real-time bladder wall tension reflects the force currently exerted on the bladder wall, and the maximum bladder wall tension value represents the maximum tensile force the bladder wall can withstand. The submodule integrates these factors through a specific calculation formula to quantify the need for urination. For example, the formula that may be used is:

[0128] ;

[0129] Where, is the urination demand value, is the real-time bladder capacity unit number, is the number of units of the maximum capacity, For real-time bladder wall tension, It is the maximum tension value of the bladder wall.

[0130] The closer the bladder is to capacity and the closer the bladder wall tension is to its maximum value, the greater the need to urinate. This quantitative calculation yields a real-time urination need value that more scientifically and accurately reflects the patient's current actual need to urinate, providing a clear basis for decision-making in the training plan optimization and training guidance modules, such as whether to remind the patient to urinate or activate the catheterization device.

[0131] In an alternative embodiment, the training plan optimization module includes:

[0132] The initial training plan generation submodule is used to generate an initial bladder function training plan for the patient based on their physiological sign data. This physiological sign data covers multiple aspects, such as the patient's age, gender, weight, underlying diseases, current physical condition, and previous bladder function test data. This data comprehensively reflects the patient's overall health status and bladder function foundation. For example, for young patients without other serious underlying diseases, their physical recovery ability is relatively good. When formulating a training plan, a relatively short urination interval training time and a higher bladder filling volume target may be set. For elderly patients or those with other diseases that affect bladder function, considering their physical tolerance, the training plan may be more conservative, with longer urination intervals and relatively low bladder filling volumes each time. By analyzing and evaluating these physiological sign data, the submodule uses pre-set rules or algorithms to develop a preliminary bladder function training plan that is suitable for the patient's basic condition. This plan provides a basic framework for subsequent optimization.

[0133] The training plan optimization submodule is used to optimize the adjustable parameters in the initial bladder function training plan by strengthening learning based on the patient's real-time urination demand value and all urination event times of the patient obtained on the day, so as to obtain an optimized bladder function training plan.

[0134] In this scenario, the training plan optimization submodule acts like an intelligent agent. The adjustable parameters of the initial training plan (such as urination interval and bladder filling volume per training session) are its "actions," while information such as the real-time urination need and the time of urination events constitutes "environmental feedback." The submodule continuously adjusts these adjustable parameters, observing "reward signals" such as how well they satisfy the patient's urination needs and whether they improve bladder function. It gradually finds the optimal parameter settings and thus develops an optimized bladder function training plan. For example, if the patient's real-time urination need often increases rapidly towards the end of the interval at the current urination interval, indicating that the urination interval may be too long, the submodule will appropriately shorten the urination interval to better adapt to the patient's bladder function status and improve training effectiveness. This optimization approach, based on real-time data and reinforcement learning, ensures that the training plan is more tailored to the patient's actual needs, enabling personalized and precise bladder function training.

[0135] The present invention provides an embodiment of a bladder function training guidance and control method based on a multimodal sensor, comprising:

[0136] Step 1: Detecting the surface pressure of the patient's bladder area using a pressure sensor array, while simultaneously measuring the real-time geometric parameters of the bladder using an ultrasound probe and obtaining quantitative data on the conductivity of the fluid in the patient's bladder using impedance tomography;

[0137] Step 2: Based on the quantitative data of the patient's bladder fluid conductivity, the surface pressure in the patient's bladder area, and the real-time geometric parameters of the bladder, the real-time bladder wall tension and the number of units of the ultimate capacity are calculated, and a bladder wall tension-bladder capacity model is constructed for the patient;

[0138] Step 3: Estimate the patient's real-time urination need based on the patient's real-time bladder wall tension, bladder wall tension-bladder capacity model, and the number of limit capacity units;

[0139] Step 4: Optimize the initial bladder function training plan based on the patient's real-time urination demand value obtained on the day to obtain an optimized bladder function training plan;

[0140] Step 5: The patient is guided to perform bladder function training based on the optimized bladder function training program. At the same time, when the urination demand value reaches the urination demand threshold in the optimized bladder function training program, the sound and light vibration are triggered to remind the patient to urinate or start the catheterization device.

[0141] The above methods achieve precise control and timely intervention of the patient's bladder function training, ensure the smooth progress of the training process, maintain the patient's physical health, avoid damage to the bladder due to untimely urination or excessive urine holding, and ensure that the entire training process is safe and effective.

[0142] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalents, the present invention is intended to include these modifications and variations.

Claims

1. A bladder function training guidance and control system based on multimodal sensors, characterized in that: include: An integrated sensing module is used to detect the surface pressure of the patient's bladder area based on a pressure sensor array, measure the real-time geometric parameters of the bladder based on an ultrasound probe, and obtain quantitative data on the conductivity of the fluid in the patient's bladder based on impedance tomography; The bladder parameter inference module is used to calculate the real-time bladder wall tension and the number of units of the maximum capacity based on the quantitative data of the fluid conductivity in the patient's bladder, the surface pressure of the patient's bladder area, and the real-time geometric parameters of the bladder, and to build a bladder wall tension-bladder capacity model for the patient; A urination demand assessment module is used to assess the patient's real-time urination demand value based on the patient's real-time bladder wall tension, bladder wall tension-bladder capacity model, and the number of limit capacity units; A training plan optimization module is used to optimize the initial bladder function training plan based on the patient's real-time urination demand value obtained on the day to obtain an optimized bladder function training plan; A training guidance module is used to guide patients in bladder function training based on an optimized bladder function training plan. At the same time, when the urination demand value reaches the urination demand threshold in the optimized bladder function training plan, it triggers sound and light vibration to remind the patient to urinate or start the catheterization device; Among them, the bladder parameter inference module includes: a residual urine volume statistics submodule, configured to determine the number of residual urine volume units of the patient based on the quantitative data of the conductivity of the liquid in the patient's bladder; a bladder wall tension estimation submodule, configured to estimate real-time bladder wall tension based on the surface pressure of the patient's bladder area and real-time geometric parameters of the bladder; The correlation analysis submodule is used to perform correlation analysis between the number of residual urine units of the patient within a preset cycle and the real-time bladder wall tension, introduce the immediate elastic modulus and delayed elastic modulus of the bladder, and use a three-element standard linear solid model to describe the patient's bladder wall tension-bladder capacity model; The limit capacity calculation submodule is used to calculate the limit capacity units of the patient's bladder based on the conductivity change data of the bladder liquid and the urination events over a long period of time and the patient's bladder wall tension-bladder capacity model.

2. The multimodal sensor-based bladder function training guidance and control system according to claim 1, characterized in that: Also includes: The water drinking reminder module is used to dynamically calculate the current water requirement based on the patient's weight, activity level, ambient temperature and humidity, and the real-time bladder status model, and issue real-time water drinking reminders to the patient based on the current water requirement.

3. The multimodal sensor-based bladder function training and control system according to claim 1, characterized in that: Integrated sensing module, including: a pressure sensing submodule, configured to continuously detect a real-time surface pressure distribution value of a patient's bladder area as surface pressure based on a pressure sensor array; an ultrasound probe measurement submodule, configured to continuously transmit ultrasound signals to the patient's bladder area and receive ultrasound echo signals reflected from the bladder area based on the ultrasound probe, and determine real-time geometric parameters of the bladder based on the ultrasound echo signals received in real time by the ultrasound probe; The bladder impedance detection submodule is used to construct an impedance tomography image of the patient's bladder by applying a weak alternating current to multiple electrodes placed on the patient's bladder area and measuring the potential difference on the patient's bladder area surface, and to determine quantitative data on the fluid conductivity in the patient's bladder based on the continuously acquired impedance tomography image.

4. The multimodal sensor-based bladder function training guidance and control system according to claim 1, characterized in that: The bladder wall tension estimation submodule includes: a bladder mechanics model and function establishment unit, for obtaining a surface pressure range of the patient's bladder region and a geometric limit parameter range of the bladder, and establishing the patient's bladder elastic mechanics model and pressure transfer function based on the surface pressure range of the patient's bladder region and the geometric limit parameter range of the bladder; a bladder pressure distribution conversion unit, configured to convert body surface pressure into intra-bladder pressure distribution based on a bladder pressure transfer function of the patient; The bladder wall tension estimation unit is used to estimate the real-time bladder wall tension based on the patient's bladder elastic mechanical model and the real-time geometric parameters of the bladder.

5. The multimodal sensor-based bladder function training guidance and control system according to claim 1, characterized in that: The limit capacity calculation submodule includes: a nonlinear model description unit, used to describe the nonlinear relationship between the conductivity of the bladder fluid and the bladder volume during bladder filling based on an exponential decay model, and obtain an original bladder fluid conductivity-capacity dynamic model; a urination event recognition unit for identifying all conductivity dip features in the conductivity change data of the bladder fluid over a long period, and calculating the urination event probability of each conductivity dip feature based on the before-and-after conductivity change data of all conductivity dip features and a hidden Markov model, and screening out all urination events from all conductivity dip features based on the urination event probability; a model personalization description unit, configured to optimize the volume attenuation coefficient and background noise compensation term in the original conductivity-volume dynamic model based on the conductivity change data before and after all urination events and the Markov chain Monte Carlo method, thereby obtaining a patient's intra-bladder fluid conductivity-volume dynamic model, wherein the volume attenuation coefficient describes the decay rate of fluid conductivity as the bladder volume changes; The limit capacity unit number calculation unit is used to calculate the limit capacity unit number of the patient's bladder based on the patient's bladder fluid conductivity-capacity dynamic model, the patient's bladder fluid conductivity limit value and the patient's bladder wall maximum tension value.

6. The multimodal sensor-based bladder function training guidance and control system according to claim 5, characterized in that: The method for calculating the number of units of the patient's bladder capacity limit by the limit capacity unit calculation unit based on the patient's bladder fluid conductivity-capacity dynamic model, the patient's bladder fluid conductivity limit value, and the patient's bladder wall maximum tension value includes: ； Where, is the maximum capacity unit of the patient's bladder, is the patient's maximum bladder wall tension value, is the maximum tension value of the bladder wall of a standard adult. is the Poisson's ratio of bladder tissue, is the natural logarithm function, is the approximate radius of the patient's bladder when not full, is the bladder wall thickness of the patient's bladder when it is not full. is the maximum conductivity of the patient's bladder fluid, is the background noise compensation term in the patient's bladder fluid conductivity-volume dynamic model, is the conductivity of the fluid in the bladder when the patient's bladder is not full. is the volume attenuation coefficient in the patient's bladder fluid conductivity-volume dynamic model.

7. The multimodal sensor-based bladder function training and control system according to claim 1, characterized in that: Urination Need Assessment Module, including: A real-time bladder capacity estimation submodule, configured to determine the patient's real-time bladder capacity units based on the patient's real-time bladder wall tension and a bladder wall tension-bladder capacity model; The urination demand value quantification submodule is used to calculate the patient's real-time urination demand value based on the patient's real-time bladder capacity unit number, the limit capacity unit number, the patient's real-time bladder wall tension and the patient's bladder wall maximum tension value.

8. The multimodal sensor-based bladder function training guidance and control system according to claim 1, characterized in that: Training plan optimization module, including: an initial training plan generating submodule, for generating an initial bladder function training plan for the patient based on the patient's physiological sign data; The training plan optimization submodule is used to optimize the adjustable parameters in the initial bladder function training plan by strengthening learning based on the patient's real-time urination demand value and all urination event times of the patient obtained on the day, so as to obtain an optimized bladder function training plan.

9. A bladder function training and control method based on a multimodal sensor, characterized in that: The multimodal sensor-based bladder function training guidance and control system applied to any one of claims 1 to 8 comprises: Step 1: Detecting the surface pressure of the patient's bladder area using a pressure sensor array, while simultaneously measuring the real-time geometric parameters of the bladder using an ultrasound probe and obtaining quantitative data on the conductivity of the fluid in the patient's bladder using impedance tomography; Step 2: Based on the quantitative data of the patient's bladder fluid conductivity, the surface pressure in the patient's bladder area, and the real-time geometric parameters of the bladder, the real-time bladder wall tension and the number of units of the ultimate capacity are calculated, and a bladder wall tension-bladder capacity model is constructed for the patient; Step 3: Estimate the patient's real-time urination need based on the patient's real-time bladder wall tension, bladder wall tension-bladder capacity model, and the number of limit capacity units; Step 4: Optimize the initial bladder function training plan based on the patient's real-time urination demand value obtained on the day to obtain an optimized bladder function training plan; Step 5: The patient is guided to perform bladder function training based on the optimized bladder function training program. At the same time, when the urination demand value reaches the urination demand threshold in the optimized bladder function training program, the sound and light vibration are triggered to remind the patient to urinate or start the catheterization device.

Images