A method and system for intelligent management of medical restraint belts

Abstract

The present invention discloses a medical restraint belt intelligent management method and system, which relates to the field of intelligent control technology of restraint belts, including installing sensors on the restraint belt to collect biological information of the restrainer for preliminary restraint and transmitting the collected biological information to the central platform; the central platform defines the personal restraint strength classification according to the restrainer's biological information, and adjusts the restraint strength in real time; the central platform receives voice commands from medical staff to control the restraint belt, and detects abnormal behavior of the restrainer and automatically warns; the medical staff remotely connects to the central platform for restraint monitoring; the central platform classifies and stores the restrainer's biological information and personal restraint strength classification. The present invention collects the restrainer's biological information by installing sensors on the medical restraint belt, calculates the restrainer's personal restraint strength classification based on the biological information, and simultaneously adjusts the restrainer's restraint strength in real time, so that the use of the restraint belt is more suitable for the restrainer.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of restraint belts, and in particular to an intelligent management method and system for medical restraint belts. Background Art

[0002] In recent years, with the continuous advancement of medical technology and the intelligent development of medical facilities, medical restraints have been used more and more widely in medical institutions. Traditional medical restraints are mainly used to restrict patients' activities to prevent self-injury or harm to others. However, the use of traditional restraints often lacks intelligent management and relies on manual adjustment and monitoring by medical staff. Medical staff usually need to check the patient's condition regularly and manually adjust the tightness of the restraint to ensure the patient's safety and comfort. This manual operation is not only time-consuming and manpower-consuming, but also prone to human negligence or misjudgment, resulting in excessive or insufficient restraint. Therefore, it is necessary to propose a solution to the problem that traditional restraints are not intelligent and convenient enough in use. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing medical restraint belt intelligent management method and system, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is to solve the problem that the traditional restraint belt is not intelligent and convenient enough during use.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a method for intelligent management of medical restraint belts, comprising: installing sensors on the restraint belts to collect biological information of the restrainer for preliminary restraint and transmitting the collected biological information to a central platform; the central platform defines personal restraint strength classification according to the restrainer's biological information and adjusts the restraint strength in real time; the central platform receives voice commands from medical staff to control the restraint belts, and automatically warns the restrainer's abnormal behavior through the restraint belts; the medical staff remotely connects to the central platform for restraint monitoring; the central platform classifies and stores the restrainer's biological information and personal restraint strength classification.

[0006] As a preferred solution of the intelligent management method of the medical restraint belt described in the present invention, wherein: the installation of sensors on the restraint belt to collect biological information of the restrained person for preliminary restraint and transmitting the collected biological information to the central platform refers to installing a bio-information sensor on the restraint belt to collect the biological information of the restrained person, including heart rate, skin electrical response, blood oxygen saturation, skin pressure, body shape and activity posture information, and preliminarily restraining and fixing the restrained person according to the biological information until the restraint belt adapts to the restrained person's body shape and generates skin pressure, and the bio-information sensor transmits the collected biological information of the restrained person to the central platform through the network for pre-processing.

[0007] As a preferred solution of the medical restraint belt intelligent management method of the present invention, wherein: the central platform defines the personal restraint strength classification according to the restrainer's biological information, and the real-time adjustment of the restraint strength means that the central platform extracts the mean, standard deviation, minimum value, maximum value, skewness and kurtosis as features according to the collected restrainer's biological information, and normalizes each feature to form a feature F n , for feature F n Perform principal component analysis, including,

[0008] Compute the covariance matrix:

[0009]

[0010] Where ∑ is the covariance matrix, m is the total number of features, μ F is the mean of the feature, is the i-th feature, T is the transposition operation;

[0011] Decompose the covariance matrix to obtain the matrix eigenvalues ​​λ and matrix eigenvectors v:

[0012] Select the matrix eigenvectors corresponding to the first k matrix eigenvalues ​​and construct the matrix eigenvector matrix V:

[0013] Project the features into the matrix feature vector matrix V to obtain the reduced-dimensional feature vector Z:

[0014] Construct a multi-layer perceptron model, including an input layer, a hidden layer, and an output layer, wherein the input layer format is a dimension-reduced feature vector, and the output layer format is a biological information index BI, with a value range of 0 to 1;

[0015] Use the training set to iteratively train the multi-layer perceptron model, use the loss function and Adam optimizer to optimize the model parameters, and input the dimension-reduced feature vector Z into the multi-layer perceptron model to obtain the bioinformatics index BI of the constrainer;

[0016] The skin pressure is used as the constraint strength classification standard. The difference between each constraint strength level is the same. The maximum skin pressure of the restraint belt is set to P. max , the minimum skin pressure is P min , the number of grades is b, and the skin pressure value ΔP of each restraint intensity level of the restrainer is calculated:

[0017]

[0018] Define fuzzy sets and rules based on the calculated constraint bioinformatics index BI, map the bioinformatics index BI to the fuzzy set and define the fuzzy membership function, and calculate the membership x of each fuzzy set i , calculate the constraint strength level S of the constrainer according to the fuzzy set membership:

[0019]

[0020] Calculate the skin pressure value of the restraint intensity based on the restraint intensity level of the restrainer:

[0021] P e =P min +(S-1)*ΔP;

[0022] Where P e is the skin pressure value for the constraint strength.

[0023] As a preferred solution of the medical restraint belt intelligent management method of the present invention, wherein: the central platform receives voice commands from medical staff to control the restraint belt, which means that the central platform collects the voice of medical staff through a microphone array for denoising and filtering, uses a convolutional neural network model and trains through the voice of medical staff, and generates a unique identification signal according to the voice of medical staff. When the microphone array collects the voice, the convolutional neural network first generates an identification signal. When the identification signals are consistent, the central platform starts voice analysis and converts the voice into a text command to control the restraint belt. When the identification signals are inconsistent, the voice analysis is refused.

[0024] The restraint belt control includes restraint, tightening, loosening and releasing the restraint, wherein:

[0025] Restraint means that the restraint belt automatically restrains the restrained person until skin pressure is generated;

[0026] Tightening means that the restraint belt increases the restraint strength of the restrainer by one level. When the skin pressure value of the restraint strength of the restrainer reaches the maximum skin pressure, the tightening command will no longer take effect;

[0027] Relaxation means that the restraint belt reduces the restraint strength of the restrainer by one level. When the skin pressure value of the restraint strength of the restrainer reaches the minimum skin pressure, the relaxation command will no longer take effect;

[0028] Release of restraint refers to the state where the restraint belt is released from restraint.

[0029] As a preferred embodiment of the intelligent management method of the medical restraint belt of the present invention, the automatic warning by detecting abnormal behavior of the restrained person through the restraint belt refers to that the restraint belt automatically detects the activity posture of the restrained person through the sensor, and when it is detected that the restrained person is frequently active and the skin pressure is constantly changing, it is judged that the restrained person is in a struggling state, and the central platform automatically increases the restraint strength by one level, and notifies the staff to check on the restrained person; when it is detected that the restraint strength skin pressure value becomes 0 without receiving the restraint release command, it is judged that the restrained person has escaped, and the central platform automatically sends an alarm to notify the staff.

[0030] As a preferred solution of the intelligent management method of medical restraint belts described in the present invention, wherein: the medical staff remotely connects to the central platform for restraint monitoring, which means that the medical staff remotely connects to the central platform through a mobile terminal to view the restrainer and the restraint strength, and receives notifications from the central platform through the mobile terminal. After receiving the voice control command of the restraint belt from the medical staff, the central platform automatically generates a restraint belt control record and sends it to the mobile terminal of the medical staff.

[0031] As a preferred solution of the medical restraint belt intelligent management method described in the present invention, wherein: the central platform classifies and stores the restrainer's biological information and personal restraint strength grades, which means that the central platform generates a restrainer classification based on the collected restrainer's biological information, and stores the personal restraint strength grades in the restrainer classification as a preset scheme. When the central platform detects the same restrainer's biological information again through the restraint belt, the stored personal restraint strength grades of the restrainer are automatically called.

[0032] Another object of the present invention is to provide a medical restraint belt intelligent management system, which comprises:

[0033] An information collection module, used to collect biological information of the restrained person through sensors and transmit it to the central platform;

[0034] The central processing module is used to receive and pre-process the restrainer's biological information, define the individual restraint intensity classification according to the restrainer's biological information, adjust the restraint intensity in real time, and receive voice commands from medical staff to control the restraint belt;

[0035] Remote monitoring module, used to remotely connect to the medical staff's mobile terminal and send information to the mobile terminal for medical staff to view;

[0036] The storage module is used to generate a restrainer classification based on the restrainer's biological information, and store the restrainer's personal restraint intensity levels in the restrainer classification as a preset solution call.

[0037] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned medical restraint belt intelligent management method when executing the computer program.

[0038] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the medical restraint belt intelligent management method.

[0039] The beneficial effects of the present invention are as follows: the present invention collects biological information of the restrained person through the installation of sensors on the medical restraint belt, calculates the restraint strength grade of the restrained person based on the biological information, and simultaneously adjusts the restraint strength of the restrained person in real time, so that the use of the restraint belt is more suitable for the restrained person, and can assist medical staff in controlling the restraint belt and monitoring the restrained person through voice control and abnormal behavior detection, thereby improving the applicability of the restraint belt and ensuring the safety of the restrained person and medical staff. Finally, by storing the restrained person's constraint grade preset scheme, computing resources are saved and the working efficiency of the restraint belt is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0041] Figure 1 A flowchart of an intelligent management method for medical restraints is shown.

[0042] Figure 2 Schematic diagram of the process flow of medical restraint belt control.

[0043] Figure 3 This is a schematic diagram of the structure of the medical restraint belt intelligent management system. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0045] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0047] Example 1

[0048] Reference Figure 1 and Figure 2, which is the first embodiment of the present invention, and provides a medical restraint belt intelligent management method, the medical restraint belt intelligent management method includes,

[0049] S1. Install sensors on the restraint belt to collect the restrainer's biometric information for preliminary restraint and transmit the collected biometric information to the central platform;

[0050] Specifically, installing sensors on the restraint belt to collect biometric information of the restrained person for preliminary restraint and transmitting the collected biometric information to the central platform means installing a biometric information sensor on the restraint belt to collect biometric information of the restrained person, including heart rate, skin electrical response, blood oxygen saturation, skin pressure, body shape and activity posture information, and preliminarily restraining and fixing the restrained person according to the biometric information until the restraint belt adapts to the restrained person's body shape and generates skin pressure, and the biometric information sensor transmits the collected biometric information of the restrained person to the central platform through the network for preprocessing.

[0051] By installing a variety of biometric sensors on the restraint belt, the patient's heart rate, skin electrical response, blood oxygen saturation, skin pressure, body shape and activity posture information can be collected in real time. This information can provide the patient with a comprehensive physiological state, helping doctors and nurses to more accurately assess and manage the patient's health status. The initial restraint process ensures that the restraint belt adapts to the patient's body shape, generates appropriate skin pressure, improves the effectiveness and comfort of the restraint, and reduces the patient's discomfort and skin injury risk. The biometric sensor transmits the collected patient biometric information to the central platform in real time through the network for preprocessing. This real-time data transmission and processing mechanism improves the timeliness and accuracy of medical monitoring and reduces the risk of emergencies.

[0052] S2. The central platform defines individual restraint intensity levels based on the restrainer’s biometric information and adjusts the restraint intensity in real time;

[0053] Specifically, the central platform defines the individual restraint intensity classification according to the restrainer's biometric information, and real-time adjustment of the restraint intensity means that the central platform extracts the mean, standard deviation, minimum value, maximum value, skewness and kurtosis as features according to the heart rate, skin galvanic response and blood oxygen saturation in the restrainer's biometric information collected;

[0054] The calculation formulas for skewness sk and kurtosis ku are:

[0055]

[0056] Where q is the total number of heart rate, skin galvanic response and blood oxygen saturation data, L i is the i-th data, μ L is the data mean, σ L is the data standard deviation;

[0057] Each feature is normalized to form feature F n , for feature F n Perform principal component analysis, including,

[0058] Compute the covariance matrix:

[0059]

[0060] Where ∑ is the covariance matrix, m is the total number of features, μ F is the mean of the feature, is the i-th feature, T is the transposition operation;

[0061] Decompose the covariance matrix to obtain the matrix eigenvalues ​​λ and matrix eigenvectors v:

[0062] ∑v=λv;

[0063] det(∑-λI)=0;

[0064] Where v is the matrix eigenvector, det is the determinant, λ is the matrix eigenvalue, and I is the identity matrix;

[0065] Select the matrix eigenvectors corresponding to the first k matrix eigenvalues ​​and construct the matrix eigenvector matrix V:

[0066] V=[v1,v2,……,v k ];

[0067] Project the features into the matrix feature vector matrix V to obtain the reduced-dimensional feature vector Z:

[0068]

[0069] Where Z i is the i-th reduced dimension feature vector;

[0070] Construct a multi-layer perceptron model, including an input layer, a hidden layer and an output layer, wherein the input layer format is a reduced-dimensional feature vector, the hidden layer has multiple layers, each layer uses a sigmoid function as an activation function, and the output layer format is a biological information index BI, with a value range of 0 to 1;

[0071] Use the training set to iteratively train the multi-layer perceptron model, use the loss function and Adam optimizer to iteratively optimize the model parameters until the loss no longer decreases significantly during the continuous iteration process, stop iterating, output the model parameters, update the multi-layer perceptron model, and input the dimension-reduced feature vector Z into the multi-layer perceptron model to obtain the bioinformatics index BI of the constrainer;

[0072] The skin pressure is used as the constraint strength classification standard. The difference between each constraint strength level is the same. The maximum skin pressure of the restraint belt is set to P.max , the minimum skin pressure is P min , the number of grades is b, and the skin pressure value ΔP of each restraint intensity level of the restrainer is calculated:

[0073]

[0074] According to the calculated constraint bioinformatics index BI, fuzzy sets and rules are defined, the bioinformatics index BI is mapped to the fuzzy set and the fuzzy membership function is defined:

[0075]

[0076]

[0077] where x low 、x me and x hi are the membership functions of fuzzy sets, a, d and c are the thresholds of fuzzy sets;

[0078] Calculate the membership degree x of each fuzzy set i , membership degree x i Include x low 、x me and x hi , calculate the constraint strength level S of the constrainer according to the fuzzy set membership:

[0079]

[0080] Calculate the skin pressure value of the restraint intensity based on the restraint intensity level of the restrainer:

[0081] P e =P min +(S-1)*ΔP;

[0082] Where P e is the skin pressure value for the constraint strength.

[0083] The sensors installed on the restraint belt can collect the restrainer's heart rate, skin galvanic response, blood oxygen saturation and other biological information in real time. By extracting the mean, standard deviation, minimum, maximum, skewness and kurtosis of these data, the restrainer's physiological state can be comprehensively analyzed. These features can provide a more detailed and accurate assessment of individual health status and help to formulate a more appropriate restraint strength. By normalizing the extracted features, the dimensional differences between different features can be eliminated, so that the data can be compared and analyzed on the same scale. Using principal component analysis (PCA) to reduce the dimensionality of the normalized features can reduce data redundancy and retain the main information, thereby improving the efficiency and accuracy of subsequent analysis and processing. By constructing a multi-layer perceptron (MLP) model and training it with bioinformatics features, the restrainer's bioinformatics index can be realized. The MLP model has a strong nonlinear mapping capability and can capture the relationship between complex physiological characteristics and constraint strength, thereby providing a more accurate constraint strength adjustment scheme. By defining fuzzy sets and fuzzy membership functions, the bioinformatics index (BI) can be mapped to fuzzy sets to process uncertainty and fuzzy information. This fuzzy logic processing method can provide a more flexible and accurate constraint strength adjustment scheme to adapt to the individual differences of different patients. By calculating the membership of each fuzzy set and calculating the constraint strength level of the constrainer based on the fuzzy set membership, the accurate adjustment of the constraint strength can be achieved. Using the fuzzy set defined by the bioinformatics index (BI), complex physiological information can be converted into specific constraint strength adjustment parameters to ensure that the constraint strength matches the physiological state of the constrainer.

[0084] S3. The central platform receives voice commands from medical staff to control the restraint belt, and automatically warns the restrainer of abnormal behavior through the restraint belt;

[0085] Specifically, the central platform receives voice commands from medical staff to control the constraint band, which means that the central platform collects the voice of medical staff through a microphone array for denoising and filtering, uses a convolutional neural network model and trains through the voice of medical staff, and generates a unique identification signal based on the voice of medical staff. When the microphone array collects the voice, it first generates an identification signal through the convolutional neural network. When the identification signals are consistent, the central platform starts voice analysis and converts the voice into text commands for constraint band control. When the identification signals are inconsistent, the voice analysis is refused.

[0086] The restraint belt control includes restraint, tightening, loosening and releasing the restraint, wherein:

[0087] Restraint means that the restraint belt automatically restrains the restrained person until skin pressure is generated;

[0088] Tightening means that the restraint belt increases the restraint strength of the restrainer by one level. When the skin pressure value of the restraint strength of the restrainer reaches the maximum skin pressure, the tightening command will no longer take effect;

[0089] Relaxation means that the restraint belt reduces the restraint strength of the restrainer by one level. When the skin pressure value of the restraint strength of the restrainer reaches the minimum skin pressure, the relaxation command will no longer take effect;

[0090] Release of restraint refers to the state where the restraint belt is released from restraint.

[0091] The central platform collects the voice signals of medical staff through microphone arrays and performs denoising and filtering. The microphone array can improve the capture quality of voice signals, and denoising and filtering can remove background noise and irrelevant signals to ensure the clarity and accuracy of voice signals. This step ensures the basic data quality for subsequent voice recognition and analysis. The medical staff's voice is trained using a convolutional neural network (CNN) to generate a unique recognition signal. The CNN model can generate a unique voice recognition signal for each medical staff member by learning the voice characteristics of the medical staff. This method not only improves the accuracy of voice recognition, but also effectively prevents unauthorized personnel from passing through the voice control restraint belt, thereby enhancing the security of the system. When the microphone array collects voice, a recognition signal is first generated through a convolutional neural network. If the recognition signals are consistent, the central platform will perform voice analysis and convert the voice into text commands for restraint belt control. This step ensures that only verified voice signals can trigger restraint belt control commands, avoiding the possibility of misidentification and misoperation. Voice analysis converts natural language commands into machine-executable instructions, improving the intelligence and ease of use of the system. Through precise restraint strength control, it can improve patient comfort and safety and reduce medical risks caused by improper restraints.

[0092] Furthermore, the restraint belt detects abnormal behavior of the restrained person and issues an automatic warning. The restraint belt automatically detects the restrained person's activity posture through sensors. When the restrained person is detected to be frequently active and the skin pressure is constantly changing, it is determined that the restrained person is in a struggling state. The central platform automatically increases the restraint strength by one level and notifies the staff to check on the restrained person. When the restraint strength skin pressure value becomes 0 without receiving a restraint release command, it is determined that the restrained person has escaped, and the central platform automatically issues an alarm to notify the staff.

[0093] The restraint belt uses sensors to monitor the restrainer's movements in real time and can capture subtle changes in posture. The data collected by the sensors include the frequency, amplitude and direction of movement. These data can be used to determine the restrainer's activity status. By analyzing the activity posture data, it is possible to understand in real time whether the restrainer is in a normal state and promptly detect abnormal behaviors, such as struggling or escaping. When the sensor detects that the restrainer is frequently active and the skin pressure is constantly changing, the central platform determines that the restrainer is struggling. This automated judgment mechanism reduces reliance on manual monitoring and improves monitoring efficiency and accuracy. The system automatically increases the restraint strength by one level to ensure that the restrainer will not be injured due to struggling. At the same time, it notifies medical staff to check to prevent accidents. When the system detects that the skin pressure value of the restraint strength becomes 0 without receiving a release command, the central platform determines that the restrainer may have escaped. At this time, the system automatically issues an alarm. The staff will be informed to handle it. This automatic early warning mechanism can discover and respond to the escape behavior of the restrainer in the first time, and prevent potential risks and safety hazards caused by escape. When a struggling state is detected, the central platform automatically increases the restraint intensity by one level to ensure the safety of the restrainer. At the same time, the system will notify medical staff to check and make necessary interventions. This automated processing method not only improves the response speed, but also ensures that measures are taken in the first time to reduce the risk of injury caused by the restrainer's struggle. When the restrainer's escape behavior is detected, the central platform automatically issues an alarm to notify medical staff to take action. This automatic alarm system can remind medical staff in the first time to prevent the safety hazards caused by escape behavior. Through timely early warning, the consequences caused by escape behavior can be effectively reduced, and the safety and order of the medical environment can be maintained.

[0094] S4, medical staff remotely connect to the central platform for restraint monitoring;

[0095] Specifically, medical staff remotely connect to the central platform for restraint monitoring, which means that medical staff remotely connect to the central platform through a mobile terminal to check the restrainer and the strength of the restraint, and receive notifications from the central platform through the mobile terminal. After receiving the medical staff's voice control command for the restraint belt, the central platform automatically generates a restraint belt control record and sends it to the medical staff's mobile terminal.

[0096] Medical staff can remotely connect to the central platform through mobile terminals and view the physiological information and restraint strength of the restrainer in real time. This remote connection method allows medical staff to no longer be restricted to fixed monitoring locations and can monitor and manage anytime and anywhere, improving work flexibility and efficiency. In addition, the portability of mobile terminals enables medical staff to respond and handle emergencies quickly. Through mobile terminals, medical staff can view the physiological information and current restraint strength of the restrainer in real time, including heart rate, skin galvanic response, blood oxygen saturation, skin pressure and other data. The real-time display of these data can help medical staff quickly understand the status of the restrainer, make timely adjustments and interventions, and ensure the safety and comfort of the restrainer. When the central platform detects an abnormal situation or requires medical staff to intervene, it will send notifications through the mobile terminal. Medical staff can receive these notifications in time and handle them accordingly, improving the timeliness and accuracy of monitoring and management. Through this real-time notification mechanism, emergencies can be effectively prevented and the safety of restrainers can be guaranteed.

[0097] S5. The central platform stores the restrainer's biometric information and individual restraint intensity levels in a classified manner;

[0098] Specifically, the central platform classifies and stores the restrainer's biometric information and personal restraint strength grades, which means that the central platform generates a restrainer classification based on the collected restrainer's biometric information, and stores the personal restraint strength grades in the restrainer classification as a preset scheme. When the central platform detects the same restrainer's biometric information again through the restraint belt, the stored personal restraint strength grades of the restrainer are automatically called.

[0099] The central platform generates detailed classification information by analyzing the collected biological information of the restrainers. This classification information includes the physiological characteristics and health status of the restrainers, which can help the system identify and manage different restrainers more accurately. The generation of classification information is conducive to personalized management, improving the adaptability and accuracy of the system, and ensuring that the use of restraints is more scientific and reasonable. The central platform classifies and stores individual restraint intensity levels based on the restrainers' biological information and the generated classification information. These preset plans can be quickly called when needed in the future, reducing the time and resource consumption of repeated calculations. Classification storage not only improves the efficiency of data management, but also ensures the accuracy and traceability of the data, facilitating subsequent analysis and optimization.

[0100] Example 2

[0101] Reference Figure 3 , which is the second embodiment of the present invention, and which is different from the previous embodiment, provides a medical restraint belt intelligent management system, which includes:

[0102] An information collection module, used to collect the restrainer's biological information through sensors and transmit it to the central platform;

[0103] The central processing module is used to receive and pre-process the restrainer's biological information, define the individual restraint intensity classification according to the restrainer's biological information, adjust the restraint intensity in real time, and receive voice commands from medical staff to control the restraint belt;

[0104] Remote monitoring module, used to remotely connect to the medical staff's mobile terminal and send information to the mobile terminal for medical staff to view;

[0105] The storage module is used to generate a restrainer classification based on the restrainer's biological information, and store the restrainer's personal restraint intensity levels in the restrainer classification as a preset solution call.

[0106] If the functions 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 technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0108] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0109] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0110] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A medical restraint belt intelligent management method, characterized in that: include, Install sensors on the restraint belt to collect the restrainer's biometric information for preliminary restraint and transmit the collected biometric information to the central platform; The central platform defines individual restraint intensity levels based on the restrainer’s biometric information and adjusts restraint intensity in real time; The central platform receives voice commands from medical staff to control the restraint belt, and automatically warns the restrainer of abnormal behavior through the restraint belt; Medical staff remotely connect to the central platform for restraint monitoring; The central platform stores the restrainer’s biometric information and individual restraint intensity levels in a classified manner; The installation of sensors on the restraint belt to collect the restrainer's biometric information for preliminary restraint and transmitting the collected biometric information to the central platform refers to the installation of biometric information sensors on the restraint belt to collect the restrainer's biometric information, including heart rate, skin galvanic response, blood oxygen saturation, skin pressure, body shape and activity posture information, and preliminary restraint and fixation of the restrainer according to the biometric information until the restraint belt adapts to the restrainer's body shape and generates skin pressure, and the biometric information sensor transmits the collected biometric information of the restrainer to the central platform through the network for pre-processing; The central platform defines the personal constraint strength classification according to the biometric information of the constrainer, and real-time adjustment of the constraint strength means that the central platform extracts the mean, standard deviation, minimum, maximum, skewness and kurtosis as features according to the collected biometric information of the constrainer, and normalizes each feature to form a feature F. n , for feature F n Perform principal component analysis, including, Compute the covariance matrix: Where ∑ is the covariance matrix, m is the total number of features, μ F is the mean of the feature, is the i-th feature, T is the transposition operation; Decompose the covariance matrix to obtain the matrix eigenvalues ​​λ and matrix eigenvectors v: Select the matrix eigenvectors corresponding to the first k matrix eigenvalues ​​and construct the matrix eigenvector matrix V: Project the features into the matrix feature vector matrix V to obtain the reduced-dimensional feature vector Z: Construct a multi-layer perceptron model, including an input layer, a hidden layer, and an output layer, wherein the input layer format is a dimension-reduced feature vector, and the output layer format is a biological information index BI, with a value range of 0 to 1; Use the training set to iteratively train the multi-layer perceptron model, use the loss function and Adam optimizer to optimize the model parameters, and input the dimension-reduced feature vector Z into the multi-layer perceptron model to obtain the bioinformatics index BI of the constrainer; The skin pressure is used as the constraint strength classification standard. The difference between each constraint strength level is the same. The maximum skin pressure of the restraint belt is set to P. max , the minimum skin pressure is P min , the number of grades is b, and the skin pressure value ΔP of each restraint intensity level of the restrainer is calculated: Define fuzzy sets and rules based on the calculated constraint bioinformatics index BI, map the bioinformatics index BI to the fuzzy set and define the fuzzy membership function, and calculate the membership x of each fuzzy set i , calculate the constraint strength level S of the constrainer according to the fuzzy set membership: Calculate the skin pressure value of the restraint intensity based on the restraint intensity level of the restrainer: P e =P min +(S-1)*ΔP; Where P e is the skin pressure value for the constraint strength.

2. The medical restraint belt intelligent management method according to claim 1, characterized in that: The central platform receives voice commands from medical staff to control the constraint band, which means that the central platform collects the voice of medical staff through a microphone array for denoising and filtering, uses a convolutional neural network and trains through the voice of medical staff, and generates a unique identification signal based on the voice of medical staff. When the microphone array collects the voice, the convolutional neural network is first used to generate an identification signal. When the identification signals are consistent, the central platform starts voice analysis and converts the voice into a text command for constraint band control. When the identification signals are inconsistent, the voice analysis is refused. The restraint belt control includes restraint, tightening, loosening and releasing the restraint, wherein: Restraint means that the restraint belt automatically restrains the restrained person until skin pressure is generated; Tightening means that the restraint belt increases the restraint strength of the restrainer by one level. When the skin pressure value of the restraint strength of the restrainer reaches the maximum skin pressure, the tightening command will no longer take effect; Relaxation means that the restraint belt reduces the restraint strength of the restrainer by one level. When the skin pressure value of the restraint strength of the restrainer reaches the minimum skin pressure, the relaxation command will no longer take effect; Release of restraint refers to the state where the restraint belt is released from restraint.

3. The medical restraint belt intelligent management method according to claim 2, characterized in that: The automatic warning by detecting abnormal behavior of the restrained person through the restraint belt means that the restraint belt automatically detects the activity posture of the restrained person through the sensor. When the restrained person is found to be frequently moving and the skin pressure is constantly changing, it is judged that the restrained person is in a state of struggle. The central platform automatically increases the restraint strength by one level and notifies the staff to check the restrained person; When the restraint strength skin pressure value is detected to be 0 without receiving the release command, it is judged that the restrained person has escaped, and the central platform automatically sends out an alarm to notify the staff.

4. The medical restraint belt intelligent management method according to claim 3, characterized in that: The medical staff remotely connects to the central platform for restraint monitoring, which means that the medical staff remotely connects to the central platform through a mobile terminal to view the restrainer and the strength of the restraint, and receives notifications from the central platform through the mobile terminal. After receiving the medical staff's voice control command for the restraint belt, the central platform automatically generates a restraint belt control record and sends it to the medical staff's mobile terminal.

5. The medical restraint belt intelligent management method according to claim 4, characterized in that: The central platform classifies and stores the restrainer's biometric information and personal restraint strength grades, which means that the central platform generates a restrainer classification based on the collected restrainer's biometric information, and stores the personal restraint strength grades in the restrainer classification as a preset scheme. When the central platform detects the same restrainer's biometric information again through the restraint belt, the stored restrainer's personal restraint strength grades are automatically called.

6. A medical restraint belt intelligent management system according to any one of claims 1 to 5, characterized in that: include, An information collection module, used to collect biological information of the restrained person through sensors and transmit it to the central platform; The central processing module is used to receive and pre-process the restrainer's biological information, define the individual restraint intensity classification according to the restrainer's biological information, adjust the restraint intensity in real time, and receive voice commands from medical staff to control the restraint belt; Remote monitoring module, used to remotely connect to the medical staff's mobile terminal and send information to the mobile terminal for medical staff to view; The storage module is used to generate a restrainer classification based on the restrainer's biological information, and store the restrainer's personal restraint intensity levels in the restrainer classification as a preset solution call.

7. A computer device comprising: A memory and a processor; the memory stores a computer program, wherein the processor implements the steps of the medical restraint belt intelligent management method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the medical restraint belt intelligent management method according to any one of claims 1 to 5 are implemented.

Images