Pressure damage monitoring method, device and system based on multiple sensors

Abstract

The invention relates to the technical field of health care, in particular to a pressure injury monitoring method, device and system based on multiple sensors. The system comprises an intelligent mattress and an upper computer server, the intelligent mattress comprises a sensing layer, and the sensing layer comprises a multimode sensor array, a microprocessor unit, a data bus and a wireless transmission module; the multimode sensor array is composed of a plurality of sensor units; the sensor unit is integrated with a plurality of sensors and piezoelectric micromechanical ultrasonic transducer array elements; the sensing layer further comprises a flexible wire and a lock catch. According to the intelligent mattress, monitoring-physical therapy integration based on the PMUT array is achieved, the problems that an existing intelligent mattress is subjected to monitoring surface layer, physical therapy is not targeted, body type adaptability is poor, function expansion is limited and the like are solved, precise health monitoring and targeted physical therapy of people with different body types are achieved, and an innovative and efficient integrated solution is provided for the field of health care and healthy home furnishing.

Description

Technical Field

[0001] This application relates to the field of healthcare technology, and in particular to methods, devices, and systems for monitoring pressure injuries based on multiple sensors. Background Technology

[0002] With the aging population and the increasing prevalence of sub-health issues, the demand for home-based and intelligent health management continues to rise. Currently, people who are bedridden for extended periods are highly susceptible to complications such as pressure injuries and muscle atrophy due to poor local blood circulation and insufficient muscle activity. Post-operative recovery patients require continuous monitoring of their physiological status and gentle physical therapy interventions, while the sub-healthy population has a strong demand for convenient health monitoring and soothing physical therapy. Against this backdrop, the smart mattress, as a core home furnishing device that occupies one-third of a person's daily time, has become a key device for integrating health monitoring and physical therapy functions.

[0003] Traditional health and wellness mattresses and health monitoring equipment have significant technical shortcomings: First, their monitoring functions are superficial, relying mostly on single pressure or temperature and humidity sensors. They can only acquire data on the body's surface condition and cannot collect deep physiological information such as muscles and subcutaneous tissues, making it difficult to predict early health risks. Second, their therapeutic functions lack targeting. Existing products mostly use whole-body vibration or electromagnetic heat therapy, which cannot provide precise therapy to areas prone to pressure injuries or stiff muscles. Furthermore, the intensity and frequency of therapy are not adjustable, resulting in poor adaptability. Summary of the Invention

[0004] In view of this, this application provides a method, device, and system for monitoring pressure injuries based on multiple sensors, in order to solve the problems of related technologies that can only acquire data on the surface of the human body, cannot collect deep physiological information such as muscles and subcutaneous tissues, are difficult to predict early health risks, cannot provide precise physiotherapy for high-incidence areas of pressure injuries and areas of muscle stiffness, and have poor adaptability due to the inability to adjust the intensity and frequency of physiotherapy.

[0005] Firstly, this application provides a method for monitoring pressure-induced injuries based on multiple sensors. This method is applied to a host computer server and includes: Given the first working mode of the smart mattress selected by the user, data from multiple preset sensors located under each physiological zone of the human body are acquired based on the first working mode. The preset sensor data is mapped to multiple preset scoring dimensions to obtain the score values ​​of each preset scoring dimension corresponding to each human physiological zone. Pre-defined risk areas are determined based on the scoring values; Given that the user has selected the second working mode of the smart mattress, the spatial coordinates of the preset risk area are obtained based on the second working mode. Based on spatial coordinates, the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element participating in focusing relative to the reference array element is determined, and the phase delay time is sent to the smart mattress. The reference array element is the array element closest to the spatial coordinates.

[0006] Furthermore, based on the scoring values, preset risk areas are determined, including: Obtain the region weight corresponding to each human physiological region; Based on the score values ​​and regional weights, preset risk areas are determined.

[0007] Furthermore, obtain the region weights corresponding to each physiological region of the human body, including: Obtain the initial weights of the regions corresponding to each human physiological region; Adjust the initial weight of the region to fit the user's body shape to obtain the region weight.

[0008] Furthermore, based on spatial coordinates, the phase delay time of each piezoelectric micromechanical ultrasonic transducer element participating in focusing relative to the reference element is determined, including: All piezoelectric micromechanical ultrasonic transducer array elements involved in focusing are obtained based on spatial coordinates; The array element layout is obtained based on all the piezoelectric micromechanical ultrasonic transducer elements involved in focusing. Based on the array element layout and spatial coordinates, the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element relative to the reference array element is obtained.

[0009] Secondly, this application provides a monitoring device for pressure-related injuries based on multiple sensors. This device is a host computer server and includes: The first acquisition module is used to acquire data from multiple preset sensors located under each human physiological zone based on the first working mode of the smart mattress selected by the user, when the first working mode of the smart mattress is determined. The module is used to map preset sensor data to multiple preset scoring dimensions to obtain the score values ​​of each preset scoring dimension corresponding to each human physiological zone. The first determination module is used to determine the preset risk area based on the score value; The second acquisition module is used to acquire the spatial coordinates of a preset risk area based on the second working mode when the user selects the second working mode of the smart mattress. The second determining module is used to determine the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element participating in focusing relative to the reference array element based on spatial coordinates, and send the phase delay time to the smart mattress, wherein the reference array element is the array element closest to the spatial coordinates.

[0010] Thirdly, this application provides a monitoring system for pressure injuries based on multiple sensors, the system comprising: a smart mattress and a host computer server, the host computer server being used to execute the method of the first aspect; The smart mattress includes a sensing layer, which comprises a multi-mode sensor array, a microprocessor unit, a data bus, and a wireless transmission module. The multi-mode sensor array consists of multiple sensor units. Each sensor unit integrates multiple sensors and a piezoelectric micromechanical ultrasonic transducer array element. The microprocessor unit is used to initialize the sensor, read sensor data in real time, and drive and control the piezoelectric micromechanical ultrasonic transducer array elements. The microprocessor unit is used to send sensor data to the wireless transmission module via the data bus after confirming that the sensor initialization is successful. The wireless transmission module is used to upload the received sensor data to the host computer server. The host computer server is used to analyze the received sensor data, obtain the phase delay duration, and send the phase delay duration to the microprocessor unit through the wireless transmission module and data bus. The microprocessor unit is used to calculate the transmission time of each piezoelectric micromechanical ultrasonic transducer element based on the phase delay duration, and convert the transmission time into an analog timing signal to be sent to the piezoelectric micromechanical ultrasonic transducer element.

[0011] Furthermore, the sensing layer also includes flexible wires and latches; Flexible conductors are used to move the multi-mode sensor array to a target monitoring area that is adapted to the user's body shape; The locking mechanism is used to secure the length of the flexible wire, ensuring that the sensor unit is aligned with the target monitoring area.

[0012] Furthermore, the sensor units in the multimode sensor array adopt a row-column scalable architecture.

[0013] Fourthly, this application provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the pressure injury monitoring method based on multiple sensors described in the first aspect or any corresponding embodiment.

[0014] Fifthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to perform the pressure injury monitoring method based on multiple sensors described in the first aspect or any corresponding embodiment.

[0015] In this embodiment, when the user selects the smart mattress to be in the first working mode, multiple preset sensor data corresponding to each human physiological zone are collected according to the human physiological structure zones. These preset sensor data may include body surface microenvironment data, body position dynamic data, pressure distribution data, and deep tissue physiological data. The multi-dimensional sensing system supports daily monitoring. At the same time, based on these preset sensor data, the score values ​​of each preset scoring dimension corresponding to each human physiological zone can be obtained to determine the current preset risk area. Then, when the user selects the smart mattress to be in the second working mode, relying on the wideband response characteristics of the piezoelectric micromechanical ultrasonic transducer array element, based on the spatial coordinates of the preset risk area, the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element participating in focusing relative to the reference array element can be obtained. This enables subsequent targeted ultrasound therapy, forming a complete closed loop of "data acquisition - intelligent analysis - targeted intervention", realizing the synergy of health status monitoring and targeted intervention. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of a pressure injury monitoring system based on multiple sensors according to an embodiment of this application; Figure 2 This is an overall structural diagram of the smart mattress according to an embodiment of this application; Figure 3 This is a structural diagram of the sensing layer of a smart mattress according to an embodiment of this application; Figure 4 This is a structural diagram of a multimode sensor unit according to an embodiment of this application; Figure 5 This is a schematic flowchart of a method for monitoring pressure-induced damage based on multiple sensors according to an embodiment of this application; Figure 6 This is a complete flowchart of a method for monitoring pressure-induced injuries based on multiple sensors according to an embodiment of this application; Figure 7 This is a device block diagram of a host server according to an embodiment of this application; Figure 8 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of this application; The list of components represented by each number in the above figures is as follows: 1: Smart mattress assembly; 2: Upper breathable sponge pad; 3: Sensing layer; 4: Bottom rubber pad; 3.3: Multimode sensor array; 3.1: Flexible wire; 3.2: Locking mechanism; 3.4: Microprocessor unit for reading and caching data from each sensor row; 3.5: RS485 data bus; 3.6: Wireless transmission module; 5: Multimode sensor unit; 5.1: Connecting cable interface; 5.2: I2C address interface; 5.3: I2C multiplexer chip; 5.4: MEMS temperature and humidity sensor chip; 5.5: Piezoresistive pressure sensor; 5.6: MEMS array PMUT chip; 5.7: MEMS inertial sensor chip. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0020] With the increasing aging of the global population and the growing prevalence of sub-health issues, the demand for home-based and intelligent health management continues to rise. Currently, the number of disabled and semi-disabled elderly is surging, and those who are bedridden for extended periods are highly susceptible to complications such as pressure injuries and muscle atrophy due to poor local blood circulation and insufficient muscle activity. Post-operative rehabilitation patients require continuous monitoring of their physiological status and gentle physical therapy interventions, while the sub-healthy population has a strong demand for convenient health monitoring and soothing physical therapy. Against this backdrop, the smart mattress, as a core home furnishing device that occupies one-third of a person's daily time, has become a key device integrating health monitoring and physical therapy functions.

[0021] Traditional health and wellness mattresses and health monitoring equipment have significant technical shortcomings: First, their monitoring functions are superficial, relying mostly on single pressure or temperature and humidity sensors, which can only acquire data on the body's surface and cannot collect deep physiological information such as muscles and subcutaneous tissues, making it difficult to predict early health risks; Second, their therapeutic functions lack targeting, with existing products mostly using whole-body vibration or electromagnetic heat therapy, which cannot provide precise therapy to areas prone to pressure injuries or stiff muscles, and the intensity and frequency of therapy are not adjustable, resulting in poor adaptability.

[0022] PMUT (Piezoelectric Micromachined Ultrasonic Transducer), as a core device of novel MEMS (Micro-Electromechanical Systems), overcomes the limitations of traditional ultrasonic devices—large size, high power consumption, and difficulty in flexible integration—thanks to its miniaturization, low power consumption, wide bandwidth response, and array integration advantages. Numerous studies have confirmed that ultrasonic stimulation can influence the metabolic activities of human tissue cells through energy transfer at specific frequencies and intensities, promoting anabolism and inhibiting catabolism. Simultaneously, it can activate autophagy mechanisms to reduce cell apoptosis and maintain the biomechanical properties and activity of tissues. This characteristic has been verified in medical scenarios such as bone and cartilage tissue preservation. It can achieve deep tissue physiotherapy (such as promoting blood circulation and relieving muscle spasms) by emitting specific frequency ultrasound waves, and it can also invert deep physiological parameters of the human body by receiving echo signals, providing technical support for the functional integration of intelligent health and wellness equipment. Currently, PMUT technology has been initially applied in medical ultrasound imaging and portable physiotherapy devices, but its integrated application in intelligent mattress scenarios remains unexplored.

[0023] Existing ultrasonic physiotherapy solutions have significant technical bottlenecks: solutions relying on electromagnetic ultrasonic probes can achieve non-contact detection, but the devices are large and lack flexibility, making it difficult to adapt to the deformation requirements of mattresses, and the physiotherapy is not targeted enough; solutions based on a single pressure sensor array can only achieve sleep posture recognition and pressure distribution monitoring, lacking deep data acquisition and physiotherapy functions; traditional ultrasonic physiotherapy equipment requires professional operation and relies on coupling agents, making it impossible to achieve unmanned and continuous application in home scenarios.

[0024] Based on the above, this application proposes a multi-sensor system for monitoring pressure-induced injuries, such as... Figure 1 The system includes a smart mattress and a host computer server. The host computer server communicates wirelessly with the smart mattress. Details are as follows: like Figure 2As shown, the smart mattress consists of an upper breathable sponge pad, a sensing layer, and a lower rubber pad. The upper breathable sponge pad and the lower rubber pad are merely components of the smart mattress and do not have any special functions. In this embodiment, the sensing layer is given the function of monitoring pressure injuries. Figure 3 As shown, the sensing layer includes a multi-mode sensor array (the number of sensors can be expanded by increasing row / column density), a microprocessor unit (for reading and caching data from each row of sensors), a data bus (such as an RS485 data bus for polling and transmitting array data), and a wireless transmission module (for polling the microprocessor unit and sending the acquired data to the host server via Wi-Fi / Bluetooth). The multi-mode sensor array consists of multiple sensor units. Figure 4 As shown, the sensor unit consists of a single PCB and multiple sensor chips, integrating multiple sensors and piezoelectric micromechanical ultrasonic transducer array elements. Figure 4 The sensor unit includes: a connection cable interface with power supply, analog data, and digital data transmission capabilities; an I2C address interface that uses resistors to encode multiple I / O pins to determine the chip's specific location in the array; an I2C multiplexer chip with a digital I2C interface for enabling chip selection in the array; a MEMS temperature and humidity sensor chip with a digital I2C interface for single-point temperature and humidity data acquisition; a piezoresistive pressure sensor with an analog interface for single-point pressure data acquisition; a MEMS array PMUT chip with an analog interface for acquiring deep tissue data and active physiotherapy via ultrasound; and a MEMS inertial sensor chip with a digital I2C interface for single-point motion data acquisition.

[0025] Functionally, it achieves the following: by collecting data on the body surface microenvironment, body position, pressure, and deep tissues through multiple sensors, the data is transmitted to the host computer server via a data bus and wireless module. Relying on the broadband characteristics of the PMUT array, targeted ultrasound therapy is carried out simultaneously, forming a synergistic effect of precise monitoring and targeted intervention.

[0026] Specifically, after the user lies down, the system initiates a hardware self-test process: each row of microprocessor units sequentially initializes the MEMS temperature and humidity sensor, MEMS inertial sensor, piezoresistive pressure sensor, and PMUT array chip. Communication between the microprocessor and sensors is divided into two categories: digital communication and analog acquisition. For the MEMS temperature and humidity sensor and the MEMS inertial sensor, the microprocessor addresses and enables each column of I2C multiplexers via the I2C bus. After enabling the target column multiplexer, the corresponding sensor data can be read. For the piezoresistive pressure sensor and the PMUT array chip, the microprocessor completes data reading and drive control through multiple independent analog lines.

[0027] Each microprocessor unit confirms the successful initialization status of each sensor in that row. If a certain percentage, such as 90%, is successfully initialized, the data from each sensor is sent to the wireless transmission module via the RS485 data bus.

[0028] Additionally, when sending sensor data to the wireless transmission module, if a large number of errors are found in the microprocessor unit (e.g., the wireless transmission module only receives...), Figure 4 If the sensor data sent by 3 out of 5 microprocessor units contained in the 5 lines is detected, a fault is considered to have been detected, an error log is output, and the system enters standby mode.

[0029] After confirming that all microprocessor units in all rows are initialized normally, the wireless transmission module starts the WIFI / Bluetooth connection and establishes communication with the host computer server.

[0030] The wireless transmission module automatically searches for and connects to the host computer server. If a connection timeout is detected, a retry is performed using an exponential backoff algorithm. After successfully connecting to the host computer, the wireless transmission module polls the microprocessor unit according to its Modbus communication protocol via the RS485 data bus, based on the device address of each microprocessor unit. Upon receiving the polling message, each microprocessor immediately reads all sensor data and returns the sensor data according to the read operation. The wireless transmission module receives the sensor data and caches it locally. After collecting all sensor data, it packages and uploads it to the host computer server according to the protocol.

[0031] The host computer server calibrates the received sensor data, then obtains the user-selected operating mode, analyzes the received sensor data to obtain the phase delay duration, and sends the phase delay duration to the microprocessor unit through the wireless transmission module and data bus. The microprocessor unit receives the operating mode command and the distance between each pair of sensor units from the host computer server through the wireless transmission module, calculates the transmission time of each piezoelectric micromechanical ultrasonic transducer element based on the phase delay duration, and converts the transmission time into an analog timing signal to drive the corresponding piezoelectric micromechanical ultrasonic transducer element to operate.

[0032] In addition to the two significant technical shortcomings mentioned in the above embodiments, traditional health and wellness mattresses and health monitoring equipment also suffer from: insufficient body shape adaptability, fixed sensor array layout, difficulty in matching the body curves of users with different heights and body types, and easy occurrence of monitoring blind spots or physiotherapy misalignment.

[0033] Furthermore, existing ultrasound therapy technologies primarily focus on in vitro tissue preservation or targeted clinical treatment, but have not yet developed optimized solutions for daily home-based therapy, nor have they been integrated with the flexible structure and body shape adaptation needs of smart mattresses. Current technologies generally neglect body shape adaptation design, with sensor arrays often featuring a fixed density layout. For users of different heights and body types, this can easily lead to incomplete coverage of key areas or sensor redundancy.

[0034] To address the issue of mattresses not fitting the user's body shape, such as Figure 3 The sensing layer also includes flexible wires, which are stretched according to the user's body shape before the user lies down, moving the multi-mode sensor array to the target monitoring area adapted to the user's body shape, such as the head, shoulders, waist, hips, and legs. The wires can be made of polyurethane elastic material. The sensing layer also includes latches, which are used to manually lock the wires after the multi-mode sensor array is moved into place, ensuring that the sensor units are accurately aligned with the target monitoring areas such as the head, shoulders, waist, hips, and legs, and fit the body surface without monitoring blind spots. If the user's body shape exceeds the coverage of the basic array, the sensor units adopt a row and column expandable architecture to add more sensor units.

[0035] Functionally, the system combines locking mechanisms and flexible guide wires to adapt to different user body shapes and mattress sizes, enabling adaptation for people of different heights and weights and for different mattress sizes. It also supports on-demand expansion of functional modules. After body shape adaptation is complete, the system initiates a hardware self-test process, as described in the above embodiments, which will not be repeated here.

[0036] In this embodiment, by integrating a PMUT array with multiple types of MEMS sensors, the user's body is partitioned and arranged to collect multi-dimensional human and environmental data in real time. Combined with the array's ultrasound therapy function, this achieves synergy between health status monitoring and targeted intervention. A "sliding latch + flexible wire" structure is adopted to adapt to different body types, and an expandable row and column architecture is compatible with multiple scenario requirements, simplifying the redundant structure of traditional solutions and enhancing the stability and adaptability of core functions. Ultimately, this achieves more precise health monitoring, targeted therapy intervention, and diversified usage scenarios, improving the user's health and wellness experience, reducing the burden of care, and promoting the technological upgrade and scenario expansion of intelligent health and wellness equipment.

[0037] This application provides a method for monitoring pressure-related injuries based on multiple sensors, such as... Figure 5 As shown in the flowchart in the accompanying drawings, the steps illustrated can be performed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in a different order than that shown here.

[0038] Figure 5This is a flowchart of a method for monitoring pressure-induced injuries based on multiple sensors according to an embodiment of this application. The execution entity of this method can be a host computer server, and the method flow includes the following steps: Step S501: If the user selects the first working mode of the smart mattress, data from multiple preset sensors located under each physiological zone of the human body are acquired based on the first working mode.

[0039] Step S502: Map the preset sensor data to multiple preset scoring dimensions to obtain the score values ​​of each preset scoring dimension corresponding to each human physiological zone.

[0040] Step S503: Determine the preset risk area based on the score value.

[0041] Step S504: If the user selects the second working mode of the smart mattress, obtain the spatial coordinates of the preset risk area based on the second working mode.

[0042] Step S505: Based on spatial coordinates, determine the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element participating in focusing relative to the reference array element, and send the phase delay time to the smart mattress, wherein the reference array element is the array element closest to the spatial coordinates.

[0043] Optionally, if the host computer server obtains that the user selects the first working mode for the smart mattress, such as the sensor detection mode, the microprocessor unit drives multiple preset sensors corresponding to each physiological zone of the human body, such as driving MEMS inertial sensors and piezoresistive pressure sensors to synchronously collect dynamic body position and pressure distribution data, and drives the PMUT array to emit ultrasonic waves in low-power mode to assist in detecting muscle tension; after all the collected sensor data is cached by the microprocessor unit, it is transmitted to the wireless transmission module via RS485 bus for polling, and then uploaded to the host computer server.

[0044] The host computer server uses a multi-dimensional data fusion algorithm combined with an ergonomic model and incorporates the Braden scoring algorithm with multi-sensor fusion to comprehensively analyze postural dynamics, pressure distribution, muscle tension and environmental baseline data. It obtains the score values ​​of each preset scoring dimension (such as humidity, activity, movement, friction / shear force) under each human physiological zone and generates a pressure distribution and postural assessment report.

[0045] Specifically, objective data is collected through integrated digital I2C interface MEMS temperature and humidity sensors, MEMS inertial sensors, and analog interface piezoresistive pressure sensors, and mapped to the scoring dimensions of humidity, activity, movement, and friction / shear force, respectively.

[0046] For example, MEMS temperature and humidity sensors can be used to collect the humidity value of the microenvironment on the body surface under each physiological zone and map it to the humidity score dimension. Among them, humidity value > preset threshold (e.g., 60%) → high humidity risk → score decreases; humidity value < preset threshold → low humidity risk → score increases.

[0047] MEMS inertial sensors were used to collect angular velocity, acceleration, and postural holding time in each physiological zone of the human body, and these data were mapped to the activity score dimension. Frequent activity (e.g., turning over once every 30 minutes → frequent changes in angular velocity / acceleration) → strong activity ability → higher score; prolonged stillness → lower score.

[0048] MEMS inertial sensors are used to collect angular velocity, acceleration, and postural duration under each physiological zone of the human body, and these are mapped to the movement score dimension. Among them, flexible postural movement (such as voluntary adjustment of sitting posture → change in acceleration) → strong movement ability → higher score; inability to move voluntarily → lower score.

[0049] Piezoresistive pressure sensors are used to collect the peak pressure and duration of pressure in each physiological zone of the human body, and these values ​​are mapped to the friction / shear force scoring dimension. Among them, a peak pressure > safety threshold (e.g., 30 kPa) and duration > 1 hour → high risk of friction / shear force → score decreases; uniform pressure distribution → score increases.

[0050] It should be noted that the thresholds mentioned above, such as humidity 60% and pressure 30kPa, are values ​​optimized based on the clinical Braden scoring criteria and home-based health care scenarios, and are different from the subjective judgment of traditional manual scoring.

[0051] Obtain the score value corresponding to each preset scoring dimension under each human physiological zone, and select the area with the highest value as the preset risk area, which is the high-risk area for pressure ulcers.

[0052] If the host computer server receives a message from the user selecting the second working mode for the smart mattress, such as the ultrasound intervention mode, the microprocessor unit drives the PMUT array to start according to the spatial coordinates of the high-risk pressure ulcer area determined by the host computer server based on the Braden score, the distance between each pair of sensor units, and the PMUT transmission power. Because the spatial distances from each PMUT element to the high-risk pressure ulcer area are different (e.g., the target point in the buttock area is 3cm from element A and 4cm from element B), if all elements "emit" ultrasound waves "simultaneously," the waves from elements with longer propagation distances will arrive at the target point later, resulting in a phase difference (asynchronous vibration) between the waves and beam dispersion. Therefore, "active adjustment" is needed to bring the phase difference of the waves from each element at the target point to zero, achieving focusing. In this embodiment of the application, the phase delay algorithm is used to determine the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element participating in focusing in the high-risk area of ​​pressure ulcers relative to the reference array element (i.e. the array element closest to the spatial coordinates in the PMUT array), and the emission timing of each array element in the PMUT array is adjusted to achieve ultrasonic focusing. The focused ultrasonic waves are emitted according to the 1-5MHz frequency and focusing parameters set by the host computer server to carry out physiotherapy.

[0053] The following method is used to determine the phase delay time of each piezoelectric micromechanical ultrasonic transducer element participating in focusing relative to the reference element: The system acquires the array elements of all piezoelectric micromechanical ultrasonic transducers involved in focusing within the high-risk area for pressure ulcers, along with their array element layout. Based on the array element layout, the distance from each element to its spatial coordinates is obtained. For example, the distance from the reference array element A to the target area is d1 = 3cm = 0.03m, and the distance from array element B to the target area is d2 = 4cm = 0.04m. Additionally, the propagation speed of ultrasound in the mattress and human tissue is obtained as v = 1500m / s.

[0054] Calculate the propagation time difference: the time it takes for the wave of reference element A to reach the target point is t1 = d1 / v = 0.03 / 1500 = 20μs; The time it takes for the wave of array element B to reach the target point is t2 = d2 / v = 0.04 / 1500 ≈ 26.67 μs; The propagation time difference Δt is approximately 6.67 μs (meaning that the wave of array element B arrives at the target point 6.67 μs later than that of the reference array element A). Therefore, the phase delay of array element B relative to the reference array element is 6.67 μs.

[0055] After receiving the phase delay durations calculated by the host computer server, the microprocessor unit converts the "transmission time" into an analog timing signal (such as high-level trigger transmission) and transmits it to the corresponding PMUT array element through an independent analog line. Each PMUT array element receives the analog timing command and triggers transmission at the specified time. The ultrasonic waves from all array elements arrive at the target area synchronously according to the preset phase difference, forming a focused beam.

[0056] Simultaneously, the MEMS temperature and humidity sensor collects real-time temperature data of the body surface microenvironment, which is then uploaded to the host server via the microprocessor unit and wireless transmission module. The host server uses a temperature monitoring algorithm to determine whether the temperature exceeds a threshold (e.g., 38°C). If it does, a power adjustment command is issued, and the microprocessor unit executes the command to reduce the PMUT transmission power until the host server detects that the temperature has returned to a safe range. After the preset treatment time is reached, the host server issues a stop command, and the microprocessor unit drives the PMUT array to stop working and records the treatment parameters, which are then uploaded to the host server via the wireless transmission module.

[0057] After receiving all the data, the host computer server generates a health report that includes stress risk warnings and physiotherapy effect assessments through a physiological state evaluation algorithm. If the analysis finds abnormal pressure distribution, it issues a sensor position adjustment command, which is then manually adjusted. All raw data, analysis results, and operation records are synchronously stored by the host computer to complete a single workflow.

[0058] In addition, it adapts to the row-column expandable architecture designed in this application, automatically identifies the I2C address encoding of newly added PMUT array elements, updates the spatial mapping model and phase calculation matrix, and is compatible with hardware structure and functional expansion requirements.

[0059] In this embodiment, an expandable PMUT array and multiple types of MEMS sensors are integrated to simultaneously collect data on the body surface microenvironment, body position, pressure, and deep tissues. It also has targeted ultrasound therapy functions, realizing the integrated functions of deep physiological monitoring, targeted therapy, and body shape adaptation, filling the gap in the application of PMUT technology in smart mattress scenarios.

[0060] As an optional embodiment, step S503 above includes: Step S5031: Obtain the region weight corresponding to each human physiological partition.

[0061] Step S5032: Determine the preset risk area based on the score value and regional weight.

[0062] Optionally, weights can be assigned to each physiological region of the human body. It should be noted that these weights can be fixed values ​​set in advance, such as assigning higher weights to areas with a high incidence of pressure sores (e.g., the buttocks and waist) and lower weights to areas with a low incidence (e.g., the head and legs).

[0063] Alternatively, you can set an initial weight for only one region, such as setting the hip region (weight 0.3) > waist region (weight 0.25) > shoulder region (weight 0.2) > leg region (weight 0.15) > head region (weight 0.1).

[0064] The initial weight of the body shape adjustment area is adjusted as follows: If the user is obese, the coverage area of ​​the hip area sensor is expanded (e.g., 2 new hip area sensor units are added), and the weight of the hip area is increased to 0.35; if the user is slender, the coverage area of ​​the waist area is expanded, and the weight of the waist area is increased to 0.3.

[0065] The Braden scoring system is used to weight and fuse the data with regional weights to obtain a comprehensive score for each physiological zone. The comprehensive score for each physiological zone is then calculated as follows: (score value of "humidity" in the current zone × regional weight) + (score value of "activity" in the current zone × regional weight) + (score value of "movement" in the current zone × regional weight) + (score value of "friction / shear force" in the current zone × regional weight).

[0066] For example: if the weight of the buttock area is 0.25, and the scores of each preset scoring dimension of the buttock area are "humidity 0.625, activity 0.3, movement 0.2, friction / shear force 0.7", then the comprehensive score of the buttock area = (0.625×0.25) + (0.3×0.25) + (0.2×0.25) + (0.7×0.25).

[0067] The comprehensive score of all human physiological zones will be compared with a preset threshold (such as 0.5). Zones below the preset threshold will be identified as preset risk areas, namely "high-risk areas for pressure ulcers". The precise coordinates will be determined by the sensor I2C address encoding to provide location information for subsequent PMUT array targeted physiotherapy.

[0068] As an alternative embodiment, such as Figure 6 , Figure 6 This is a complete flowchart of a method for monitoring pressure-induced injuries based on multiple sensors according to an embodiment of this application. The specific process is as follows: Mattress body shape fit; System initialization (initialization of multiple sensors); If initialization succeeds, connect to the host server; otherwise, output an error log. If the connection to the host computer server fails, an exponential backoff wait will be executed; otherwise, a polling mode will be started.

[0069] If the polling is successful, the Braden sensor, which integrates multimodal sensing, is used to predict the location of pressure sores; otherwise, the system enters a waiting state. When predicting the location of pressure ulcers, the system determines the current mode selection. If the user selects the multi-mode sensor monitoring mode, the polling mode is activated. If the user selects the ultrasound intervention mode, the PMUT phased-array ultrasound is executed, and it is determined whether the physical therapy is completed. If the physical therapy is completed, the system enters a waiting state; otherwise, the PMUT phased-array ultrasound continues to be executed.

[0070] This embodiment also provides a monitoring device for pressure-induced injuries based on multiple sensors. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0071] This embodiment provides a pressure injury monitoring device based on multiple sensors, such as... Figure 7 As shown, it includes: The first acquisition module 701 is used to acquire multiple preset sensor data corresponding to each human physiological zone based on the first working mode when the user selects the first working mode of the smart mattress. The module 702 is used to map preset sensor data to multiple preset scoring dimensions to obtain the score values ​​of each preset scoring dimension corresponding to each human physiological partition. The first determining module 703 is used to determine a preset risk area based on the scoring value; The second acquisition module 704 is used to acquire the spatial coordinates of a preset risk area based on the second working mode when the user selects the second working mode of the smart mattress. The second determining module 705 is used to determine the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element participating in focusing relative to the reference array element based on spatial coordinates, and send the phase delay time to the smart mattress, wherein the reference array element is the array element closest to the spatial coordinates.

[0072] In this embodiment, when the user selects the smart mattress to be in the first working mode, multiple preset sensor data corresponding to each human physiological zone are collected according to the human physiological structure zones. These preset sensor data may include body surface microenvironment data, body position dynamic data, pressure distribution data, and deep tissue physiological data. The multi-dimensional sensing system supports daily monitoring. At the same time, based on these preset sensor data, the score values ​​of each preset scoring dimension corresponding to each human physiological zone can be obtained to determine the current preset risk area. Then, when the user selects the smart mattress to be in the second working mode, relying on the wideband response characteristics of the piezoelectric micromechanical ultrasonic transducer array element, based on the spatial coordinates of the preset risk area, the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element participating in focusing relative to the reference array element can be obtained. This enables subsequent targeted ultrasound therapy, forming a complete closed loop of "data acquisition - intelligent analysis - targeted intervention", realizing the synergy of health status monitoring and targeted intervention.

[0073] In some optional implementations, the first determining module 703 is used to obtain the regional weight corresponding to each human physiological partition; and to determine the preset risk area based on the score value and the regional weight.

[0074] In some optional implementations, the first determining module 703 is used to obtain the initial weight of the region corresponding to each human physiological partition; adjust the initial weight of the region according to the user's body shape to obtain the region weight.

[0075] In some optional implementations, the second determining module 705 is used to obtain all piezoelectric micromechanical ultrasonic transducer array elements participating in focusing based on spatial coordinates; obtain the array element layout based on all piezoelectric micromechanical ultrasonic transducer array elements participating in focusing; and obtain the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element relative to the reference array element based on the array element layout and spatial coordinates.

[0076] In this embodiment, the pressure injury monitoring device based on multiple sensors is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0077] This application also provides a computer device having the above-described features. Figure 7 The device shown is a pressure injury monitoring device based on multiple sensors.

[0078] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of this application, such as... Figure 8As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 Take a processor 10 as an example.

[0079] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GPA), or any combination thereof.

[0080] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0081] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0082] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0083] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0084] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0085] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for monitoring pressure-induced damage based on multiple sensors, characterized in that, The method is applied to a host computer server, and the method includes: When the user selects the first working mode of the smart mattress, data from multiple preset sensors located under each physiological zone of the human body are acquired based on the first working mode. The preset sensor data is mapped to multiple preset scoring dimensions to obtain the score values ​​of each preset scoring dimension corresponding to each human physiological zone. A preset risk area is determined based on the scoring values; If the user selects a second working mode for the smart mattress, the spatial coordinates of the preset risk area are obtained based on the second working mode. Based on the spatial coordinates, the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element participating in focusing relative to the reference array element is determined, and the phase delay time is sent to the smart mattress, wherein the reference array element is the array element closest to the spatial coordinates.

2. The method according to claim 1, characterized in that, The step of determining the preset risk area based on the score value includes: Obtain the region weight corresponding to each human physiological region; The preset risk area is determined based on the score value and the regional weight.

3. The method according to claim 1, characterized in that, The process of obtaining the region weights corresponding to each human physiological region includes: Obtain the initial weights of the regions corresponding to each human physiological region; The initial weight of the region is adjusted to suit the user's body shape, thus obtaining the region weight.

4. The method according to claim 1, characterized in that, The determination of the phase delay time of each piezoelectric micromechanical ultrasonic transducer element participating in focusing relative to the reference element, based on the spatial coordinates, includes: All piezoelectric micromechanical ultrasonic transducer array elements participating in focusing are obtained based on the aforementioned spatial coordinates; The array element layout is obtained based on all the piezoelectric micromechanical ultrasonic transducer elements participating in focusing. Based on the array element layout and the spatial coordinates, the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element relative to the reference array element is obtained.

5. A monitoring device for pressure-induced damage based on multiple sensors, characterized in that, The device is a host computer server, and the device includes: The first acquisition module is used to acquire multiple preset sensor data corresponding to each human physiological zone based on the first working mode when the user selects the first working mode of the smart mattress. The module is used to map the preset sensor data to multiple preset scoring dimensions to obtain the score values ​​of each preset scoring dimension corresponding to each human physiological partition. The first determining module is used to determine a preset risk area based on the scoring value; The second acquisition module is used to acquire the spatial coordinates of the preset risk area based on the second working mode when the user selects the second working mode of the smart mattress. The second determining module is used to determine the phase delay time of each piezoelectric micromechanical ultrasonic transducer array element participating in focusing relative to the reference array element based on the spatial coordinates, and send the phase delay time to the smart mattress, wherein the reference array element is the array element closest to the spatial coordinates.

6. A monitoring system for pressure-induced injuries based on multiple sensors, characterized in that, The system includes: a smart mattress and a host computer server, wherein the host computer server is used to execute the method of claim 1; The smart mattress includes a sensing layer, which comprises a multi-mode sensor array, a microprocessor unit, a data bus, and a wireless transmission module. The multi-mode sensor array consists of multiple sensor units, and each sensor unit integrates multiple sensors and a piezoelectric micromechanical ultrasonic transducer array element. The microprocessor unit is used to initialize the sensor, read sensor data in real time, and drive and control the piezoelectric micromechanical ultrasonic transducer array elements. The microprocessor unit is used to send the sensor data to the wireless transmission module via the data bus after determining that the sensor initialization is successful. The wireless transmission module is used to upload the received sensor data to the host computer server; The host computer server is used to analyze the received sensor data, obtain the phase delay duration, and send the phase delay duration to the microprocessor unit through the wireless transmission module and the data bus. The microprocessor unit is used to calculate the emission time of each piezoelectric micromechanical ultrasonic transducer element based on the phase delay duration, and convert the emission time into an analog timing signal to be sent to the piezoelectric micromechanical ultrasonic transducer element.

7. The system according to claim 6, characterized in that, The sensing layer also includes flexible wires and latches; The flexible conductor is used to move the multi-mode sensor array to a target monitoring range that is adapted to the user's body shape; The latch is used to fix the length of the flexible wire so that the sensor unit is aligned with the target monitoring area.

8. The system according to claim 6, characterized in that, The sensor units in the multimode sensor array adopt a row-column expandable architecture.

9. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for monitoring pressure injuries based on multiple sensors as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method for monitoring pressure injuries based on multiple sensors as described in any one of claims 1 to 4.

Images