Method, system, medium and equipment of portable, multi-scene and multifunctional first-aid pressing guide device

Abstract

The invention discloses a method, a system, a medium and equipment of a portable, multi-scene and multifunctional first-aid pressing guide device. The device comprises a sensor flexible consumable and a split host; the sensor flexible consumable is of a pressing piece type packaging structure and used for being arranged on a rescued person and a rescuer to detect action characteristic data and temperature data in the rescuing process and conducting calibration through a Kalman filtering model with multiple temperature excursions, and an intelligent guidance processing unit is arranged on the split type host. And the intelligent guidance processing unit is used for analyzing the calibrated action characteristic data of the monitoring position by adopting a deep neural network analysis model to obtain action guidance data. According to the invention, intelligent, efficient and precise treatment guidance in the emergency scene is realized, the condition feedback of the patient is received in the process of monitoring the rescue action, the action guidance content is adjusted in time according to the feedback, and meanwhile, the monitoring data is calibrated, so that the accuracy of the monitoring guidance data is improved.

Description

Technical Field

[0001] The present invention relates to the fields of medical auxiliary products, wearable devices, sensor technology, human-computer interaction, robotics technology, and more specifically to a method, system, medium, and device for a portable, multi-scenario, multi-functional first aid compression guidance device. Background Art

[0002] In scenarios such as battlefields, ordinary communities, field emergencies, and disaster rescue, there is often a situation where professional first aid personnel are not on site or the number of professional personnel is insufficient. People who do not have professional first aid knowledge are needed to participate in the rescue. However, due to the lack of knowledge, experience, and emergency preparation of ordinary personnel, there are often situations when the rescue is provided, such as manual operation failure, first aid failure, and operational errors causing secondary injuries. Therefore, professional auxiliary equipment is needed to guide non-professionals in implementing emergency rescue.

[0003] The mainstream emergency compression guidance device on the market has a single function and generally adopts a CPR compression feedback device. It can only perform CPR on adults. The module device is placed on the human chest. The rescuer presses the module, and the pressing force is transmitted to the patient's chest through the device. At the same time, the device has a displacement sensor and a pressure change sensor to detect CPR real-time parameters and display and feedback alarms through the host computer. The structure is as follows Figure 1 As shown. The above scheme has the following problems: (1) Single function: It is only for cardiopulmonary resuscitation emergency treatment. At the same time, the cardiopulmonary resuscitation CPR compression feedback device is large in size and can only be used for cardiopulmonary resuscitation emergency treatment for adults, not for infants and young children. In addition, the monitoring parameters are single and it is impossible to intelligently adjust the rescue action according to the real-time physical condition of the rescued person; (2) The structural design is inadequate: It can only be placed on the patient's chest. When used on other patients, it must first be disinfected and then the fixed double-sided tape on the device must be replaced. It is not suitable for the rescue of multiple patients and is prone to cross infection; (3) When the sensor device and structural parts are pressed at high intensity, data drift and structural wear will cause feedback data errors, affecting the monitoring of real-time rescue indicators and causing patient damage.

[0004] The Chinese invention patent with announcement number CN116019443B discloses a system and method for detecting compliance of multi-dimensional indicators of chest compression. The system includes a device housing, a rubber strap, a voice interaction module, an inertial measurement unit module, a microcontroller module, a communication module, a storage module, a touch and display module, and a power module. The method includes a compression depth detection method, a compression frequency detection method, an arm compression verticality detection method, and an elbow bend detection method, which can realize the evaluation of the rescuer's compression depth, frequency, and arm and elbow posture standardization. Through the voice interaction method, the rescuer triggers and guides the startup and working status of the system through voice information, and the system guides the rescuer through voice information. The above-mentioned system and method only monitor and guide the actions of the rescuer, and cannot monitor the status of various indicators of the rescued person in real time, nor can it dynamically adjust the rescuer's actions according to the status of the rescued person, and cannot achieve the expected auxiliary rescue. Furthermore, the above-mentioned system and method measures the three-axis inertial data of the attachment of the inertial measurement module, including acceleration, angular velocity, and attitude quaternion, and transmits the real-time collected inertial data to the central control processing module via a data transmission bus. However, the data measured by the inertial measurement module is not calibrated, and data errors such as data drift caused by temperature changes under high-intensity compression are ignored, thereby affecting the monitoring of real-time rescue indicators and affecting the monitoring quality. Therefore, the first aid compression guidance device not only needs to monitor the rescuer's action compliance while monitoring the status of the rescued person, but also needs to improve the accuracy of the monitoring data, thereby reducing monitoring errors and improving the quality and efficiency of first aid guidance. Summary of the Invention

[0005] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art. For scenarios such as cardiopulmonary resuscitation, Heimlich first aid, and expectoration, the present invention receives patient condition feedback during the process of monitoring rescue actions, promptly adjusts the action guidance content based on the feedback, and calibrates the monitoring data to improve the accuracy of the monitoring data. The present invention provides a method, system, medium and equipment for a portable, multi-scenario, multi-functional first aid compression guidance device.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A portable, multi-scenario, multi-functional first aid compression guidance device, including a sensor flexible consumable and a split host;

[0008] The flexible sensor consumable is used to be set at the monitoring position on the rescued person and the rescuer. The flexible sensor consumable includes a flexible sensor module and a medical silicone layer. The flexible sensor module adopts a pressed-sheet packaging structure. The medical silicone layer is arranged on the outer layer of the flexible sensor module. An adhesive layer is provided on the medical silicone layer. The adhesive layer is used to bond the monitoring position. The flexible sensor module includes a flexible sensor acquisition module and an acquisition data processing unit. The flexible sensor acquisition module is connected to the acquisition data processing unit. The flexible sensor acquisition module is used to collect motion characteristic data and temperature data of the monitoring position. The acquisition data processing unit is used to calibrate the motion characteristic data of the monitoring position according to the collected temperature data. The acquisition data processing unit is also connected to the split host.

[0009] The split host is used to be worn on the rescuer. The split host is provided with an intelligent guidance processing unit and a display and voice module. The intelligent guidance processing unit is respectively connected to the collection data processing unit and the display and voice module. The intelligent guidance processing unit is used to analyze the motion feature data of the calibrated monitoring position to obtain motion guidance data.

[0010] Preferably, the flexible sensor module also includes a flexible battery, the flexible sensor acquisition module includes an inertial measurement unit, a pressed-type flexible pressure sensor and a flexible temperature sensor, and the acquisition data processing unit is respectively connected to the inertial measurement unit, the pressed-type flexible pressure sensor, the flexible temperature sensor and the flexible battery; the motion characteristic data includes speed and pressure data.

[0011] Preferably, the split host adopts a smart bracelet and / or smart glasses, a first opening is provided on the medical silicone layer, and an acquisition and transmission interface is provided at the first opening, the acquisition and transmission interface is connected to the acquisition data processing unit, the acquisition and transmission interface is used for an external monitoring device or power supply, and the intelligent guidance processing unit is also connected to a data transmission interface, the data transmission interface is used for an external monitoring device, or is connected to the acquisition and transmission interface to power the flexible sensor module.

[0012] Preferably, S1: acquiring motion characteristic data and temperature data of the monitoring position collected in real time, wherein the motion characteristic data includes acceleration, angular velocity and pressure;

[0013] S2: performing local weighted regression filtering on the motion feature data collected in real time; constructing a Kalman filter model with multiple temperature drifts, and calibrating the motion feature data after the local weighted regression filtering using the Kalman filter model with multiple temperature drifts according to the temperature data to obtain calibrated motion feature data;

[0014] S3: Build a deep neural network analysis model and train it based on historical data;

[0015] S4: The patient's body data and the calibrated motion feature data are subjected to shaping preprocessing and then input into the trained deep neural network analysis model as body parameters and motion feature parameters respectively. After analysis by the deep neural network analysis model, motion parameter indicators are obtained, and the motion parameter indicators are output and displayed. The motion parameter indicators are used to reflect standard rescue action parameters;

[0016] The steps of constructing the Kalman filter model with multiple temperature drifts in step S2 are as follows:

[0017] S2.1: Set the temperature range and divide the set temperature range into multiple temperature intervals.

[0018] S2.2: Take the acceleration, angular velocity, and pressure data in each temperature range as input, and the displacement, pressure, and velocity in each temperature range as output, and construct a Kalman filter model in each temperature range. The specific formula is:

[0019] (depth, pressure, speed) k =α·a k-1 +β·w k-1 +γ·p k-1 ;

[0020] speed k =speed k-1 +α·a k ;

[0021] pressure k =α·a k-1 +γ·p k-1 ;

[0022] Where α = (α1, α2, α3), β = (β1, β2, β3), and γ = (γ1, γ2, γ3) are the Kalman filter model matrix coefficients corresponding to acceleration a, angular velocity w, and pressure p, respectively. a, w, and p are the input acceleration, angular velocity, and pressure, respectively. depth, speed, and pressure are the output displacement, pressure, and velocity, respectively. k is the current prediction period, and k-1 is the previous prediction period.

[0023] S2.3: Based on historical data, the Kalman filter model in each temperature range is trained to obtain a Kalman filter model with multiple temperature drifts.

[0024] Preferably, the method for training the Kalman filter model in each temperature interval in step S2.3 is: performing iterative training using nonlinear regression fitting based on the Gauss-Newton iterative method, and the formula used in the iterative training is:

[0025]

[0026] Among them, L T () is the target residual function of a single temperature interval T, i is the iterative data number, and M is the total number of data.

[0027] Preferably, the method for constructing the deep neural network analysis model in step S3 includes:

[0028] The deep neural network analysis model includes an input layer, three hidden layers and an output layer. The input layer vector includes body parameters and motion feature parameters, and the output layer vector includes motion parameter indicators.

[0029] The hidden layer includes a first hidden layer, a second hidden layer and a batch normalization layer arranged in sequence. The batch normalization layer is connected to the output layer. The activation functions of the first hidden layer, the second hidden layer and the batch normalization layer all adopt the Leaky ReLU activation function. The activation function of the output layer adopts the Sigmoid activation function for parameter regression output. The output layer also maps the output to the target level interval [a, b] by scaling and translating.

[0030] Preferably, the shaping preprocessing in step S4 adopts single-precision floating-point shaping, and the action parameter indicators include a compression force guidance level, a compression depth guidance level, a chest rebound guidance level, a ventilation rate guidance level, and a compression frequency guidance level;

[0031] The method further includes step S5: classifying the calibrated motion feature data into different levels, obtaining the motion parameter implementation level of the rescuer, comparing the motion parameter implementation level with the motion parameter index to obtain motion adjustment information, and outputting and displaying the motion adjustment information;

[0032] The action parameter implementation levels include a compression force implementation level, a compression depth implementation level, a chest rebound implementation level, a ventilation frequency implementation level, and a compression frequency implementation level.

[0033] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the device where the computer-readable storage medium is located executes the portable, multi-scenario, multi-functional first aid compression guidance method.

[0034] An electronic device includes: a memory and a processor, wherein the memory stores a program that can be run on the processor, and when the processor executes the program, it implements the portable, multi-scenario, multi-functional first aid compression guidance method.

[0035] A portable, multi-scenario, multi-functional first aid compression guidance system comprises a first aid compression guidance device and the electronic device.

[0036] Beneficial effects of the present invention:

[0037] The device of the present invention detects the vital signs and motion information of the monitoring positions of the rescuer and the rescued through a flexible sensor module, calibrates the motion characteristic data of the monitoring position according to the collected temperature data through the data acquisition processing unit, analyzes the calibrated motion characteristic data of the monitoring position through the first intelligent guidance processing unit and the second intelligent guidance processing unit on the smart bracelet and the smart glasses to obtain motion guidance data, and performs visual and voice display through the display and voice modules to guide the rescuer to adjust the motion, thereby realizing first aid compression guidance in multiple scenarios such as cardiopulmonary resuscitation, Heimlich maneuver and percussion expectoration. At the same time, the independent design of the sensor flexible consumables and the split host makes it easy to stick or wear, and can realize a one-to-many first aid rescue plan to prevent cross infection of patients in treatment situations.

[0038] The device of the present invention is small and thin by setting the flexible sensor consumable material into a pressed-sheet packaging structure, and can be attached to patients of different ages and body shapes, not limited to infants and adults; and can be easily attached to different monitoring positions of the rescuer and multiple rescued persons respectively, realizing a one-to-many first aid rescue plan and preventing cross-infection among patients in certain treatment situations.

[0039] The method of the present invention realizes intelligent, efficient and precise treatment guidance in emergency scenarios. By receiving feedback on the patient's condition during the process of monitoring the rescue action, the action guidance content is adjusted in a timely manner according to the feedback, and the monitoring data is calibrated at the same time to improve the accuracy of the monitoring guidance data. The data of the acquired monitoring position is calibrated by a Kalman filter model with multiple temperature drifts to reduce the error caused by temperature drift, improve the accuracy of data acquisition, and ensure the validity of the data in complex temperature scenarios. The calibrated data is intelligently analyzed using a deep neural network analysis model to realize the intelligent implementation and adjustment of the rescuer's rescue action. The accuracy and success rate of the action guidance are improved by training the deep neural network analysis model with clinical big data. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The present invention is described in further detail below with reference to the accompanying drawings:

[0041] Figure 1This is a schematic diagram of the installation of a traditional first aid compression guidance device during testing;

[0042] Figure 2 Schematic diagram of the flexible sensor consumable of the device of the present invention when it is placed on the chest of a human body;

[0043] Figure 3 Schematic diagram of the flexible sensor consumable of the device of the present invention when it is placed at the base of a human palm;

[0044] Figure 4 Schematic diagram of the flexible sensor consumable of the device of the present invention when it is placed on a human finger;

[0045] Figure 5 Schematic diagram of the flexible sensor consumable of the device of the present invention when it is placed at the base of the human body;

[0046] Figure 6 It is a schematic structural diagram of the flexible consumable sensor of the device of the present invention;

[0047] Figure 7 It is an exploded schematic diagram of the flexible consumable sensor material of the device of the present invention;

[0048] Figure 8 Schematic diagram of the composition of the flexible sensor module of the device of the present invention;

[0049] Figure 9 It is a schematic structural diagram of the smart wristband of the device of the present invention;

[0050] Figure 10 It is a schematic cross-sectional structural diagram of the rotating shaft device of the smart wristband of the device of the present invention;

[0051] Figure 11 It is a schematic diagram of the structure of the smart glasses of the device of the present invention;

[0052] Figure 12 is a flow chart of the method of the present invention for obtaining calibrated motion feature data;

[0053] Figure 13 is a flow chart of the deep neural network analysis model of the method of the present invention;

[0054] Figure 14 It is a training effect curve diagram of the deep neural network analysis model of the method of the present invention;

[0055] Figure 15 It is a display effect diagram of the action parameter indicators of the method of the present invention.

[0056] Description of reference numerals:

[0057] 1-Sensor flexible consumables, 101-Flexible sensor module, 102-Medical silicone layer, 103-Adhesive layer; 1011-Acquisition data processing unit, 1012-Flexible battery, 1013-Inertial measurement unit, 1014-Press-type flexible pressure sensor, 1015-Flexible temperature sensor, 104-Acquisition transmission interface, 201-Display housing, 202-Dial, 203-Display, 204-First speaker, 205-Watch strap, 2061-Hinge, 2062-Semi-arc base, 207-First data transmission interface, 301-Spectacle lens, 302-Second speaker, 303-Second intelligent guidance processing unit, 304-Second data transmission interface, 305-On / Off switch. DETAILED DESCRIPTION

[0058] The present invention provides a portable, multi-scenario, multi-functional first aid compression guidance device, which includes a sensor flexible consumable 1 and a split host.

[0059] like Figure 2-5 As shown, the sensor flexible consumable 1 is used to set the monitoring position on the rescued person and the rescuer. The monitoring position includes the vital sign monitoring position of the rescued person and the action monitoring position of the rescuer. The vital sign monitoring position of the rescued person is the patient's emergency part, including the chest, abdomen or back. The action monitoring position of the rescuer includes the palm, fingers and base of the tiger. Figure 6 and Figure 7 As shown, the flexible sensor consumable 1 includes a flexible sensor module 101 and a medical silicone layer 102. The flexible sensor module 101 adopts a pressed-sheet packaging structure, and the medical silicone layer 102 is provided on the outer layer of the flexible sensor module 101. An adhesive layer 103 is provided on the medical silicone layer 102. The adhesive layer 103 is used to adhere to the monitoring position. In this embodiment, the adhesive layer 103 is made of medical double-sided tape.

[0060] In this embodiment, the sensor flexible consumable 1 is pasted on the emergency part of the rescued person according to the actual rescue scenario. For example, when performing cardiopulmonary resuscitation, the sensor flexible consumable 1 is pasted on the chest of the rescued person; when performing the Heimlich maneuver, the sensor flexible consumable 1 is pasted on the abdomen of the rescued person; when performing the percussion expectoration method, the sensor flexible consumable 1 is pasted on the back of the rescued person, realizing multi-scenario and portable rescue.

[0061] like Figure 8As shown, the flexible sensor module 101 includes a flexible sensor acquisition module, an acquisition data processing unit 1011, and a flexible battery 1012. The flexible sensor acquisition module is connected to the acquisition data processing unit 1011. The flexible sensor acquisition module is used to collect motion characteristic data and temperature data of the monitoring position. The acquisition data processing unit 1011 is used to calibrate the motion characteristic data of the monitoring position based on the collected temperature data. The acquisition data processing unit 1011 is also connected to the split host. The flexible sensor acquisition module includes an inertial measurement unit 1013, a pressed sheet flexible pressure sensor 1014, and a flexible temperature sensor 1015. The acquisition data processing unit 1011 is connected to the inertial measurement unit 1013, the pressed sheet flexible pressure sensor 1014, the flexible temperature sensor 1015, and the flexible battery 1012, respectively. The motion characteristic data includes speed and pressure data. In this embodiment, the flexible battery 1012 uses a rechargeable thin-film battery to prevent battery failure caused by squeezing and bending during the treatment process. A first opening is provided on the medical silicone layer 102, and a collection and transmission interface 104 is provided at the first opening. The collection and transmission interface 104 is connected to the collection data processing unit 1011. The collection and transmission interface 104 is used for external monitoring equipment or power supply. The monitoring equipment can use a third-party oximeter and ventilation oxygen concentration meter.

[0062] In this embodiment, the data acquisition processing unit 1011 uses a flexible substrate to encapsulate the MCU module based on chip scale package technology (CSP). The MCU contains a Bluetooth module, a wireless transmission module and a wired transmission module, which are suitable for application scenarios that require bending, folding and squeezing, and can provide better mechanical strength and electronic functional stability. At the same time, the flexible sensor module 101 is encapsulated in combination with the medical silicone layer 102, so that it can be attached to the emergency site and the rescuer's rescue site without a foreign body feeling. At the same time, during the rescue compression measurement process, the pressing force is effectively transmitted without hindering the rescue process.

[0063] In this embodiment, the sensor flexible consumable 1 adopts a pressed sheet packaging structure, which is small and thin, and can be attached to patients of different ages and body shapes, not limited to infants and adults; and it is convenient to attach it to different monitoring positions of the rescuer and multiple rescued persons respectively, to realize a one-to-many first aid rescue plan; when the equipment needs to be reused, it is only necessary to replace the sensor flexible consumable 1, which not only buys more time for rescue, but also prevents cross-infection of patients in certain treatment situations. By adopting a flexible material, the rescuer and the rescued person will not be harmed in the process of rescue. At the same time, the pressed sheet structure does not affect the rescuer's wearing of protective gloves. As a disposable consumable, there is no need to place the same sensor module on the body of different patients, thus effectively rescuing while protecting the rescuer and the rescued person.

[0064] In this embodiment, the split host is used to be worn by the rescuer, and the split host is a smart bracelet and smart glasses.

[0065] In this embodiment, Figure 9 As shown, the smart bracelet is provided with a first intelligent guidance processing unit and a first display and voice module. The first intelligent guidance processing unit is connected to the collection data processing unit 1011 and the first display and voice module respectively. The first intelligent guidance processing unit is used to analyze the motion feature data of the calibrated monitoring position to obtain motion guidance data. In this embodiment, the first display and voice module includes a first display device, a first speaker 204 and a first power module. The first display device adopts a display screen 203. The display screen 203, the first speaker 204 and the first power module are all connected to the first intelligent guidance processing unit. The first display and voice device realizes visual and voice control dual feedback reminders. The first intelligent guidance processing unit is also connected to a first data transmission interface 207. The first data transmission interface 207 is used for external monitoring equipment, connected to the collection and transmission interface 104 for powering the flexible sensor module 101, or connected to the host computer for data transmission. The collection data processing unit 1011 and the first intelligent guidance processing unit adopt wireless connection to collect data transmission.

[0066] like Figure 10 As shown, the smart bracelet includes a display housing 201 and a dial 202 rotatably connected by a hinge mechanism. A display 203 is provided on the front of the display housing 201. A first speaker 204 and a first data transmission interface 207 are both located on the side of the display housing 201. The smart bracelet also includes a strap 205 connected to the dial 202, and the strap 205 uses a Velcro assembly. The use of the Velcro assembly makes it easy for people of different body shapes to wear and can be quickly put on and taken off, which helps shorten the preparation time before rescue and gain more golden rescue time. The hinge mechanism includes a shaft 2061 and a semi-arc-shaped base 2062. The first end of the shaft 2061 is provided with a ball, and the second end of the shaft 2061 is provided with a cylindrical boss. A first circular hole is formed in the center of the semi-arc-shaped base 2062, and a second circular hole is formed in the center of the dial 202 at a position corresponding to the semi-arc-shaped base 2062. A rotating shaft 2061 is inserted into the first and second circular holes. The ball at the first end of the rotating shaft 2061 is tangential to the spherical hole provided at the bottom of the display housing 201, and the cylindrical boss at the second end of the rotating shaft 2061 is in contact with the bottom surface of the dial 202. The rotating shaft assembly allows the display screen 203 on the display housing 201 to rotate freely on the dial 202, making it easier for rescuers to view the display screen.

[0067] In this embodiment, Figure 11As shown, the smart glasses are provided with a second intelligent guidance processing unit 303 and a second display and voice module. The second intelligent guidance processing unit 303 is connected to the data collection processing unit 1011 and the second display and voice module respectively. The second intelligent guidance processing unit 303 is used to analyze the calibrated monitoring position motion feature data to obtain motion guidance data. In this embodiment, the second display and voice module includes a second display device, a second speaker 302, and a second power module. The second display device, the second speaker 302, and the second power module are all connected to the second intelligent guidance processing unit 303. The second display and voice device realizes dual feedback reminders of visual and voice control. The second intelligent guidance processing unit 303 is also connected to a second data transmission interface 304, which is used to connect to an external monitoring device, or to connect to the data collection and transmission interface 104 for powering the flexible sensor module 101, or to connect to a host computer for data transmission. The data collection processing unit 1011 and the second intelligent guidance processing unit 303 use a wireless connection to collect and transmit data.

[0068] In this embodiment, in certain emergency scenarios, when it is inconvenient for the rescuer to wear a wristband, or when the display of the wristband is not clear enough, the rescuer can simultaneously use smart glasses to collect and display data. The smart glasses include a glasses frame and a lens 301. The second display device is integrated with the lens 301. The second speaker 302, the second intelligent guidance processing unit 303, and the second data transmission interface 304 are provided on the glasses frame. The glasses frame is also provided with an on / off key 305, which is connected to the second intelligent guidance processing unit 303 and is used to turn the smart glasses on and off.

[0069] This embodiment also includes a protection module for safety protection. The protection module includes insulating gloves. The insulating gloves are used to protect the rescuer during AED first aid, preventing the rescuer from accidentally being shocked by the AED during CPR. At the same time, CPR can also be performed while the AED is discharging, thereby improving the success rate of cardiopulmonary resuscitation.

[0070] In this embodiment, the flexible sensor module 101 is used to detect the vital signs and motion information of the monitoring positions of the rescuer and the rescued, the data acquisition processing unit 1011 is used to calibrate the motion characteristic data of the monitoring position according to the collected temperature data, the first intelligent guidance processing unit and the second intelligent guidance processing unit on the smart bracelet and the smart glasses are used to analyze the calibrated motion characteristic data of the monitoring position to obtain motion guidance data, and the display and voice modules are used for visual and voice display to guide the rescuer to adjust the motion, thereby realizing first aid compression guidance in multiple scenarios such as cardiopulmonary resuscitation, Heimlich maneuver and percussion expectoration method. At the same time, the independent design of the sensor flexible consumable 1 and the split host is convenient for pasting or wearing, which can realize one-to-many first aid rescue plan and prevent cross infection of patients in treatment situations.

[0071] In this embodiment, the specific process is as follows: First, the sensor flexible consumable 1 is attached to the emergency site of the rescued person according to the actual rescue scenario. For example, when performing cardiopulmonary resuscitation, the sensor flexible consumable 1 is attached to the rescued person's chest; when performing the Heimlich maneuver, the sensor flexible consumable 1 is attached to the rescued person's abdomen; when performing the percussion expectoration maneuver, the sensor flexible consumable 1 is attached to the rescued person's back. At the same time, the sensor flexible consumable 1 is attached to the rescuer's palm, fingers, tiger's mouth, etc. The rescuer wears a smart bracelet and smart glasses and then begins rescue. During the rescue process, the vital signs and movement information of the rescuer and the rescued person's monitoring positions detected by multiple flexible sensor modules 101 are calibrated by the data collection processing unit 1011. The calibrated data is transmitted to the first intelligent guidance processing unit and the second intelligent guidance processing unit. After analysis, the action guidance data is output to the display screen 203 or the second display device, and voice prompts are provided. The rescuer adjusts the rescue action according to the displayed action guidance data and voice broadcast information until the rescue is completed.

[0072] The device of the present invention realizes rescue action guidance in various rescue scenarios. The independent design of the disposable sensor flexible consumable 1 is suitable for monitoring people of different body shapes, ages, and positions, which facilitates and quickly carries out rescue. At the same time, it can avoid cross infection, protect the rescuer and the rescued while effectively providing rescue, and provide safety protection for emergency treatment.

[0073] The present invention provides a portable, multi-scenario, multi-functional first aid compression guidance method, comprising the following steps:

[0074] S1: Acquire the motion characteristic data and temperature data of the monitoring position collected in real time. The motion characteristic data includes acceleration, angular velocity and pressure;

[0075] S2: Perform local weighted regression filtering on the real-time collected motion feature data; construct a multiple temperature drift Kalman filter model, and calibrate the motion feature data after local weighted regression filtering using the multiple temperature drift Kalman filter model according to the temperature data to obtain the calibrated motion feature data. Figure 12 As shown in Figure 2, the steps for constructing a Kalman filter model with multiple temperature drifts are:

[0076] S2.1: Set the temperature range and divide the set temperature range into multiple temperature intervals. In this embodiment, the set temperature range is 4-40°C, and the multiple temperature intervals are [4,5), [5,6), ..., [40,41).

[0077] S2.2: Take the acceleration, angular velocity, and pressure data in each temperature interval as input, and the displacement, pressure, and velocity in each temperature interval as output, and construct a Kalman filter model in each temperature interval, such as a 4°C Kalman filter model, a 5°C Kalman filter model, ..., a 40°C Kalman filter model, which are used to process data with temperatures in [4,5), [5,6), ..., [40,41), respectively.

[0078] The specific formula of the Kalman filter model in each temperature range is:

[0079] (depth, pressure, speed) k =α·a k-1 +β·w k-1 +γ·p k-1 ;

[0080] speed k =speed k-1 +α·a k ;

[0081] pressure k =α·a k-1 +γ·p k-1 ;

[0082] Among them, α=(α1,α2,α3), β=(β1,β2,β3), γ=(γ1,γ2,γ3) are the Kalman filter model matrix coefficients corresponding to acceleration a, angular velocity w, and pressure p, respectively. a, w, and p are the input acceleration, angular velocity, and pressure, respectively. Depth, pressure, and speed are the output displacement, pressure, and velocity, respectively. k is the current prediction period, and k-1 is the previous prediction period.

[0083] S2.3: Based on historical data, the Kalman filter model in each temperature range is trained to obtain a Kalman filter model with multiple temperature drifts.

[0084] The method for training the Kalman filter model in each temperature range in step S2.3 is: iterative training is performed using nonlinear regression fitting based on the Gauss-Newton iterative method. The formula used in the iterative training is:

[0085]

[0086] Among them, L T () is the target residual function of a single temperature interval T, i is the iterative data number, and M is the total number of data.

[0087] S3: If Figure 13 As shown, a deep neural network analysis model is constructed and trained based on historical data; the method for constructing the deep neural network analysis model in step S3 includes:

[0088] The deep neural network analysis model includes an input layer, three hidden layers, and an output layer. The input layer vector includes body parameters and motion feature parameters. The body parameters include the patient's height, weight, and gender, and the motion feature parameters include displacement, pressure, and velocity. The output layer vector includes motion parameter indicators, which include compression force guidance level, compression depth guidance level, chest recoil guidance level, ventilation rate guidance level, and compression rate guidance level. In this embodiment, the input layer vector also includes the SPO2 concentration detected by a third-party oximeter and the FiO2 concentration detected by a third-party expiratory oximeter. When the third-party oximeter and the third-party expiratory oximeter are not connected, the SPO2 concentration and FiO2 concentration are both set to default values, for example, the SPO2 concentration is set to 80% and the FiO2 concentration is set to 17%.

[0089] The hidden layer includes the first hidden layer, the second hidden layer and the batch normalization layer, which are set in sequence. The batch normalization layer is connected to the output layer. The first hidden layer, the second hidden layer and the batch normalization layer are all set with 16 neurons. The activation functions of the first hidden layer, the second hidden layer and the batch normalization layer all use the Leaky ReLU activation function. The activation function of the output layer uses the Sigmoid activation function for parameter regression output. The output layer also maps the output to the target level interval [a, b] by scaling and translation, where a is the minimum value in the target level interval and b is the maximum value in the target level interval.

[0090] In this embodiment, the formula of the Leaky ReLU activation function is:

[0091]

[0092] Among them, x j is the input variable; j is the output variable; a jis a fixed parameter in the interval (1,+∞).

[0093] In this embodiment, the output layer uses scaling to map the output to the target level range [a, b] as follows:

[0094] y scaled =S(x)×(ba)+a;

[0095] Among them, y scaled is the scaled action parameter index, and S(x) is the Sigmoid activation function.

[0096] In this embodiment, the training data set collected from the preclinical experiment is close to 5,000 data points, which can effectively train a high-precision flow estimation model. At the same time, during the subsequent use of the device, the historical data stored in the split host can be exported for secondary processing training. The training process model converges and can achieve good prediction results. Figure 14 From the model training results shown, it can be seen that after 200 iterations, the deep neural network analysis model has better learned the above-mentioned nonlinear factors, and the average cost function value of the training set data is calculated to be within 0.6171, indicating that the deep neural network analysis model has good predictive performance.

[0097] S4: The patient's body data and calibrated motion feature data are shaped and pre-processed and then input into the trained deep neural network analysis model as body parameters and motion feature parameters respectively. After analysis by the deep neural network analysis model, the motion parameter index is obtained and the motion parameter index is output and displayed. The motion parameter index is used to reflect the standard rescue action parameters.

[0098] In this embodiment, the shaping preprocessing adopts single-precision floating-point shaping, which is expressed as:

[0099]

[0100] Among them, value is the number before the integer preprocessing, sign represents the 1-bit sign bit, e represents the 8-bit exponent bit, b0~b 22 Represents a 23-bit mantissa, n is the index of the mantissa, and * is a multiplication operation.

[0101] Step S5: The calibrated motion feature data is graded to obtain the rescuer's motion parameter implementation level. The motion parameter implementation levels include compression force implementation level, compression depth implementation level, chest recoil implementation level, ventilation rate implementation level, and compression frequency implementation level. In this embodiment, the compression force implementation level, compression depth implementation level, and chest recoil implementation level are each divided into 10 levels to accommodate the physical signs of infants, young children, adults, and the elderly. The ventilation rate implementation level and compression frequency implementation level are each divided into 5 levels.

[0102] The action parameter implementation level and the action parameter index are compared to obtain action adjustment information, and the action adjustment information is output and displayed. In the present embodiment, the key action parameter index and the key action parameter implementation level are screened according to the importance of the action feature, and the key action adjustment information is output. When the key action parameter implementation level is less than the key action parameter index, the key action adjustment information includes information on increasing force, depth, rebound and frequency; when the key action parameter implementation level is greater than the key action parameter index, the key action adjustment information includes information on reducing force, depth, rebound and frequency; when the key action parameter implementation level is equal to the key action parameter index, the key action adjustment information includes information on maintaining the current information force, depth, rebound and frequency.

[0103] In this embodiment, quality evaluation is performed based on the action parameter implementation level and the action parameter index according to the evaluation mechanism, and the emergency evaluation quality is displayed through the first display device and the second display device.

[0104] like Figure 15 As shown, the action parameter implementation level, action parameter index, and action adjustment information obtained through the above method are displayed on a display screen or a second display device of smart glasses. The emergency evaluation quality and key action adjustment information are displayed, guiding the rescuer with simple instructions. This instructs the rescuer to immediately adjust the action characteristic parameters. Simultaneously, the split host records relevant real-time data for subsequent analysis and secondary training of the deep neural network analysis model based on historical data.

[0105] The method of the present invention realizes intelligent, efficient and precise treatment guidance in emergency scenarios. By receiving feedback on the patient's condition during the process of monitoring the rescue action, the action guidance content is adjusted in a timely manner according to the feedback, and the monitoring data is calibrated at the same time to improve the accuracy of the monitoring guidance data. The data of the acquired monitoring position is calibrated by a Kalman filter model with multiple temperature drifts to reduce the error caused by temperature drift, improve the accuracy of data acquisition, and ensure the validity of the data in complex temperature scenarios. The calibrated data is intelligently analyzed using a deep neural network analysis model to realize the intelligent implementation and adjustment of the rescuer's rescue action. The accuracy and success rate of the action guidance are improved by training the deep neural network analysis model with clinical big data.

[0106] The present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the device where the computer-readable storage medium is located executes the above-mentioned portable, multi-scenario, multi-functional first aid compression guidance method. The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory and other memories.

[0107] The present invention provides an electronic device comprising: a memory and a processor, wherein the memory stores a program that can be run on the processor, and when the processor executes the program, the portable, multi-scenario, multi-functional first aid compression guidance method is implemented.

[0108] If the modules / units integrated in the electronic device described in this application are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the processes in the above-mentioned embodiment methods by instructing the relevant hardware devices to complete them through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned various method embodiments.

[0109] The present invention provides a portable, multi-scenario, multi-functional first aid compression guidance system, which includes a first aid compression guidance device and the above-mentioned electronic device.

[0110] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0111] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection defined by the claims.

Claims

1. A portable, multi-scenario, multi-functional first aid compression guidance device, characterized in that: Including sensor flexible consumables and split host; The flexible sensor consumable is used to be set at the monitoring position on the rescued person and the rescuer. The flexible sensor consumable includes a flexible sensor module and a medical silicone layer. The flexible sensor module adopts a pressed-sheet packaging structure. The medical silicone layer is arranged on the outer layer of the flexible sensor module. An adhesive layer is provided on the medical silicone layer. The adhesive layer is used to bond the monitoring position. The flexible sensor module includes a flexible sensor acquisition module and an acquisition data processing unit. The flexible sensor acquisition module is connected to the acquisition data processing unit. The flexible sensor acquisition module is used to collect motion characteristic data and temperature data of the monitoring position. The acquisition data processing unit is used to calibrate the motion characteristic data of the monitoring position according to the collected temperature data. The acquisition data processing unit is also connected to the split host. The split host is used to be worn on the rescuer. The split host is provided with an intelligent guidance processing unit and a display and voice module. The intelligent guidance processing unit is respectively connected to the collection data processing unit and the display and voice module. The intelligent guidance processing unit is used to analyze the motion feature data of the calibrated monitoring position to obtain motion guidance data.

2. The portable, multi-scenario, multi-functional first aid compression guidance device according to claim 1 is characterized in that: The flexible sensor module also includes a flexible battery, the flexible sensor acquisition module includes an inertial measurement unit, a pressed-type flexible pressure sensor and a flexible temperature sensor, and the acquisition data processing unit is respectively connected to the inertial measurement unit, the pressed-type flexible pressure sensor, the flexible temperature sensor and the flexible battery; the motion characteristic data includes speed and pressure data.

3. The portable, multi-scenario, multi-functional first aid compression guidance device according to claim 1 is characterized in that: The split host adopts a smart bracelet and / or smart glasses, and a first opening is provided on the medical silicone layer. A collection and transmission interface is provided at the first opening, and the collection and transmission interface is connected to the collection data processing unit. The collection and transmission interface is used for an external monitoring device or a power supply. The intelligent guidance processing unit is also connected to a data transmission interface, and the data transmission interface is used for an external monitoring device, or is connected to the collection and transmission interface to power the flexible sensor module.

4. A portable, multi-scenario, multi-functional first aid compression guidance method, characterized in that: The following steps are involved: S1: Acquire motion characteristic data and temperature data of the monitoring position collected in real time, wherein the motion characteristic data includes acceleration, angular velocity and pressure; S2: performing local weighted regression filtering on the motion feature data collected in real time; constructing a Kalman filter model with multiple temperature drifts, and calibrating the motion feature data after the local weighted regression filtering using the Kalman filter model with multiple temperature drifts according to the temperature data to obtain calibrated motion feature data; S3: Build a deep neural network analysis model and train it based on historical data; S4: The patient's body data and the calibrated motion feature data are subjected to shaping preprocessing and then input into the trained deep neural network analysis model as body parameters and motion feature parameters respectively. After analysis by the deep neural network analysis model, motion parameter indicators are obtained, and the motion parameter indicators are output and displayed. The motion parameter indicators are used to reflect standard rescue action parameters; The steps of constructing the Kalman filter model with multiple temperature drifts in step S2 are as follows: S2.1: Set the temperature range and divide the set temperature range into multiple temperature intervals. S2.2: Take the acceleration, angular velocity, and pressure data in each temperature range as input, and the displacement, pressure, and velocity in each temperature range as output, and construct a Kalman filter model in each temperature range. The specific formula is: (depth, pressure, speed) k =a·a k-1 +β·w k-1 +γ·p k-1 ; speed k =speed k-1 +α·a k ; pressure k =a·a k-1 +γ·p k-1 ; Where α = (α1, α2, α3), β = (β1, β2, β3), and γ = (γ1, γ2, γ3) are the Kalman filter model matrix coefficients corresponding to acceleration a, angular velocity w, and pressure p, respectively. a, w, and p are the input acceleration, angular velocity, and pressure, respectively. depth, speed, and pressure are the output displacement, pressure, and velocity, respectively. k is the current prediction period, and k-1 is the previous prediction period. S2.3: Based on historical data, the Kalman filter model in each temperature range is trained to obtain a Kalman filter model with multiple temperature drifts.

5. The portable, multi-scenario, multi-functional first aid compression guidance method according to claim 4 is characterized in that: The method for training the Kalman filter model in each temperature interval in step S2.3 is: iterative training is performed using nonlinear regression fitting based on the Gauss-Newton iterative method. The formula used in the iterative training is: Among them, L T () is the target residual function of a single temperature interval T, i is the iterative data number, and M is the total number of data.

6. The portable, multi-scenario, multi-functional first aid compression guidance method according to claim 4 is characterized in that: The method for constructing the deep neural network analysis model in step S3 includes: The deep neural network analysis model includes an input layer, three hidden layers and an output layer. The input layer vector includes body parameters and motion feature parameters, and the output layer vector includes motion parameter indicators. The hidden layer includes a first hidden layer, a second hidden layer and a batch normalization layer arranged in sequence. The batch normalization layer is connected to the output layer. The activation functions of the first hidden layer, the second hidden layer and the batch normalization layer all adopt the LeakyReLU activation function. The activation function of the output layer adopts the Sigmoid activation function for parameter regression output. The output layer also maps the output to the target level interval [a, b] by scaling and translating.

7. The portable, multi-scenario, multi-functional first aid compression guidance method according to claim 4 is characterized in that: The shaping preprocessing in step S4 adopts single-precision floating-point shaping, and the action parameter indicators include a compression force guidance level, a compression depth guidance level, a chest rebound guidance level, a ventilation rate guidance level, and a compression frequency guidance level; The method further includes step S5: classifying the calibrated motion feature data into different levels, obtaining the motion parameter implementation level of the rescuer, comparing the motion parameter implementation level with the motion parameter index to obtain motion adjustment information, and outputting and displaying the motion adjustment information; The action parameter implementation levels include a compression force implementation level, a compression depth implementation level, a chest rebound implementation level, a ventilation frequency implementation level, and a compression frequency implementation level.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the device where the computer-readable storage medium is located executes the portable, multi-scenario, multi-functional first aid compression guidance method described in any one of claims 4-7.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a program that can be run on the processor, and when the processor executes the program, it implements the portable, multi-scenario, multi-functional first aid compression guidance method as described in any one of claims 4-7.

10. A portable, multi-scenario, multi-functional first aid compression guidance system, characterized in that: The invention comprises a first aid compression instruction device and the electronic device according to claim 9.

Images