Mental disease patient restraint system capable of adjusting tightness based on dynamic sensing monitoring

Through dynamic sensing monitoring technology, the tightness of the constraint belt is automatically adjusted through real-time analysis of EEG signals and moving image data, which solves the problem that existing constraint systems cannot achieve automated intelligent constraints, and improves the efficiency and humanization of constraint management. , saving nursing resources.

CN119055430APending Publication Date: 2024-12-03ZHEJIANG UNIV
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202411324684.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-23
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing restraint system for mental patients cannot realize automated intelligent constraints. The restraint belt requires human remote control operation and cannot be adjusted in real time according to the patient's instantaneous changes, resulting in delayed constraints and consumed a lot of human resources.

Method used

Adopt a mentally ill patient constraint system based on dynamic sensing monitoring, monitor the EEG signal through electrodes and upload it to the backend server to analyze the EEG. If abnormal situations occur, the constraint control command will be issued, and the control constraint belt winding component will automatically restrain it. ; At the same time, the motion camera collects moving image data for posture recognition, judges abnormal motion postures and issues constraint control instructions.

Benefits of technology

It has achieved more meticulous and humane constraint management for mentally ill patients, reduced long-term constraints, increased patients' freedom of movement, and saved medical human resources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119055430A_ABST
    Figure CN119055430A_ABST
Patent Text Reader

Abstract

The invention relates to a mental patient restraint system capable of adjusting tightness based on dynamic sensing monitoring, which adopts equipment for monitoring electroencephalogram signals of mental patients to sense and monitor the electroencephalogram signals of the mental patients and upload the electroencephalogram signals to a background, and a background server analyzes the electroencephalogram signals to generate corresponding electroencephalogram (EEG). If the electroencephalogram of the patient is monitored and found to have abnormal brain wave conditions, the background server issues a corresponding first constraint control instruction, the first constraint control instruction is issued to a signal receiving unit of the mental patient constraint equipment through the network system and then forwarded to the controller through the signal receiving unit, and the controller executes the constraint control instruction and controls the restraint strap winding assembly to work; and the patient is restrained, tightened and limited. The condition and change of the grabbed patient can be evaluated more comprehensively and meticulously, constraint management can be carried out on the mental disease patient in a more humanized mode, long-time constraint is avoided, a certain degree of freedom of movement is increased, and meanwhile distribution of nursing resources can be optimized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of intelligent medical systems, and in particular to a restraint system for patients with mental illnesses that performs tension adjustment based on dynamic sensor monitoring, and an application method and electronic system thereof. Background Art

[0002] The necessity of implementing protective restraints on mentally ill patients is mainly reflected in: protecting the safety of patients and others, ensuring the implementation of patients' treatment and emotional control. For some patients with impaired cognitive function or lack of disease self-awareness, impulsiveness, irritability or violent behavior, appropriate restraint measures are necessary to ensure the continuity and effectiveness of treatment.

[0003] Existing constraint schemes include:

[0004] 1. Physical restraint: Use physical tools such as restraint belts or straitjackets to limit the patient's physical activities to prevent the patient from engaging in unsafe behaviors such as self-harm or harming others during the onset of the disease.

[0005] 2. Chemical restraint: Control the patient's symptoms by using antipsychotic drugs so that the patient can better cooperate with treatment under the influence of drugs.

[0006] 3. Environmental constraints: Create a safe and orderly environment, such as a closed ward, to reduce the patient's risk index.

[0007] 4. Psychological restraint: Through psychotherapy and communication skills, enhance the patient's identification and compliance with treatment and improve the patient's cooperation.

[0008] 5. Legal constraints: Provide necessary treatment and constraints to mentally ill patients in accordance with relevant laws and regulations to ensure the safety of patients and the public.

[0009] When implementing restraint measures, medical institutions and nursing staff should follow the principle of minimum necessity, that is, to minimize restrictions on the patient's freedom while ensuring the patient's safety and treatment effectiveness. At the same time, the necessity and effectiveness of restraint measures should be regularly evaluated and adjusted in a timely manner to meet the best interests of the patient.

[0010] The existing clinical restraints for mentally ill patients are mostly restraint belts, which restrain the patient's body parts such as thighs and arms to the bed to prevent the patient from moving around. For example, the invention patent with publication number CN117883230A discloses a knee restraint device for nursing mentally ill patients, as shown in the attached Figure 1 As shown, it includes a main restraint kneepad, a secondary restraint kneepad, a restraint connecting belt and a remote control; the upper and lower ends of the main restraint kneepad and the secondary restraint kneepad are both provided with anti-slip ring belts, and are connected as a whole through the restraint connecting belt; as shown in the attached Figure 2As shown, the main restraint kneepad body is provided with a controller module, a restraint belt reeling assembly and a restraint belt locking assembly; the controller module controls the restraint belt reeling assembly to execute the restraint connecting belt reeling action, and controls the restraint belt locking assembly to execute the restraint connecting belt locking action. Although this invention can effectively restrain the actions of mentally ill patients by remote control when necessary, and restrict fast walking, it requires human remote control for restraint control, so it cannot achieve automated intelligent restraint, allowing the restraint belt to automatically restrain according to the condition of the mentally ill patient; at the same time, it cannot be adjusted in real time according to the patient's instantaneous changes, so that the restraint has a certain lag. It is also more labor-intensive and cannot achieve the effect of saving nursing resources. Summary of the invention

[0011] In order to solve the above problems, the present application proposes a restraint system for patients with mental illness that performs tension adjustment based on dynamic sensor monitoring, and an application method and electronic system thereof.

[0012] On the one hand, the present application proposes a mentally ill patient restraint system for adjusting tightness based on dynamic sensor monitoring, including a mentally ill patient restraint device consisting of a wireless signal receiving unit, a restraint belt winding component and a controller module, and the mentally ill patient restraint device also includes:

[0013] Electrode sheets, used for sensing and monitoring brain electrical signals of patients with mental illness and providing real-time feedback to the controller module;

[0014] The controller module is also used to: after processing the EEG signal, upload it to the background server through the wireless signal receiving unit;

[0015] The backend server is used to: perform signal analysis on the EEG signal and generate an EEG of a patient with a mental illness; and monitor whether a preset abnormal brain wave condition appears on the EEG of the patient with a mental illness:

[0016] If it occurs, a corresponding first restraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; the controller module executes the first restraint control instruction, controls the action of the restraint belt reeling component, and starts to restrain the mentally ill patient;

[0017] If it does not appear, it is abandoned;

[0018] The electrode sheet is electrically connected to the controller module;

[0019] The mentally ill patient restraint device is communicatively connected to the background server.

[0020] As an optional implementation scheme of the present application, optionally, it also includes:

[0021] An in-hospital gateway, used for routing communications between the mentally ill patient restraint device and the backend server;

[0022] The mental patient restraint device is communicatively connected to the backend server via the in-hospital gateway.

[0023] As an optional implementation scheme of the present application, optionally, the abnormal brain wave condition includes:

[0024] The electroencephalogram shows waveform characteristics of sharp waves, spike waves or low-amplitude fast waves;

[0025] as well as,

[0026] A peak exceeding a preset electroencephalogram signal value appears on the electroencephalogram.

[0027] As an optional embodiment of the present application, optionally, the mentally ill patient restraint device further comprises:

[0028] A motion camera, deployed in the corresponding ward, for collecting motion image data of patients with mental illness and feeding it back to the controller module in real time;

[0029] The motion camera is electrically connected to the controller module.

[0030] As an optional implementation scheme of the present application, optionally, the controller module is further used for:

[0031] After the motion image data is processed, it is uploaded to the background server through the wireless signal receiving unit.

[0032] As an optional implementation scheme of the present application, optionally, the background server is also used for:

[0033] Performing frame image processing on the motion image data to obtain motion frame images of several mental illness patients; and performing motion posture recognition on each of the motion frame images to determine whether a preset abnormal motion posture occurs:

[0034] If it occurs, a corresponding second restraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; the controller module executes the second restraint control instruction, controls the action of the restraint belt reeling component, and starts to restrain the mentally ill patient;

[0035] If it does not appear, give up.

[0036] As an optional implementation scheme of the present application, optionally, the background server includes:

[0037] EEG processing system for providing EEG monitoring services;

[0038] A motion tracking monitoring system, used to provide frame image processing of the motion image data and a judgment service on whether a preset abnormal motion posture occurs;

[0039] Backend database, used to store data.

[0040] On the other hand, the present application proposes an application method of a mental illness patient restraint system for adjusting the tightness based on dynamic sensor monitoring, comprising the following steps:

[0041] Provide mental illness patients with restraint belt retractors and electrodes, and deploy motion cameras;

[0042] The backend server sends instructions to activate the system's electrodes and motion cameras;

[0043] Dynamic sensor monitoring of restraints:

[0044] (1) The electrode sheet senses and monitors the EEG signals of patients with mental illness and feeds them back to the controller module in real time; after the controller module processes the EEG signals, it uploads them to the backend server through the wireless signal receiving unit;

[0045] The backend server performs signal analysis on the EEG signal and generates an EEG of the mentally ill patient; and monitors whether a preset abnormal brain wave condition appears on the EEG of the mentally ill patient:

[0046] If it occurs, a corresponding first restraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; the controller module executes the first restraint control instruction, controls the action of the restraint belt reeling component, and starts to restrain the mentally ill patient;

[0047] If it does not appear, it is abandoned;

[0048] (2) The motion camera collects motion image data of the mental illness patient and feeds it back to the controller module in real time; after the controller module processes the motion image data, it uploads it to the background server through the wireless signal receiving unit;

[0049] The backend server performs frame image processing on the motion image data to obtain motion frame images of several mental illness patients; and performs motion posture recognition on each of the motion frame images, and determines whether a preset abnormal motion posture appears:

[0050] If it occurs, a corresponding second restraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; the controller module executes the second restraint control instruction, controls the action of the restraint belt reeling component, and starts to restrain the mentally ill patient;

[0051] If it does not appear, give up.

[0052] In another aspect, the present application further provides an electronic system, comprising:

[0053] processor;

[0054] a memory for storing processor-executable instructions;

[0055] Wherein, the processor is configured to implement the application method when executing the executable instructions.

[0056] Technical effects of the present invention:

[0057] This application uses a device for monitoring the EEG signals of mentally ill patients (such as an electrode sheet, an EEG electrode sheet) to sense and monitor the EEG signals of mentally ill patients, and uploads them to the background server through the configured gateway and the communication system composed of the wireless signal receiving unit, and the background server analyzes the EEG signals to generate the corresponding electroencephalogram (EEG). If the monitoring finds that the patient's EEG shows abnormal brain waves, the background server issues the corresponding first constraint control instruction, and the network system issues it to the signal receiving unit of the mental patient's restraint device, which is then forwarded to the controller, and the controller executes the constraint control instruction to control the restraint belt winding component to restrain, tighten and restrict the patient. It can evaluate the situation and changes of the captured patient more comprehensively and meticulously, and can more humanely manage the restraint of patients with mental illness, avoid long-term restraint, increase a certain degree of freedom of movement, and save medical human resources.

[0058] The present invention can optimize the constraint process and tools and save nursing resources.

[0059] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0061] Figure 1 A schematic diagram of a restraint device for an existing mentally ill patient is shown;

[0062] Figure 2A schematic diagram of the control system components of an existing restraint device for a mentally ill patient is shown;

[0063] Figure 3 A schematic diagram showing the composition of the application system of the mental illness patient restraint system of the present invention is shown;

[0064] Figure 4 It is a functional service schematic diagram of the background server of the present invention;

[0065] Figure 5 It is a schematic diagram showing the application of the electronic system of the present invention. DETAILED DESCRIPTION

[0066] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0067] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0068] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0069] Example 1

[0070] like Figure 3 As shown, the present application provides a mental illness patient restraint system based on dynamic sensor monitoring for tension adjustment, including a wireless signal receiving unit, a restraint belt winding component and a controller module as shown in the attached Figure 2 The mentally ill patient restraint device shown in the figure further comprises:

[0071] Electrode sheets, used for sensing and monitoring brain electrical signals of patients with mental illness and providing real-time feedback to the controller module;

[0072] The controller module is also used to: after processing the EEG signal, upload it to the background server through the wireless signal receiving unit;

[0073] The backend server is used to: perform signal analysis on the EEG signal and generate an EEG of a patient with a mental illness; and monitor whether a preset abnormal brain wave condition appears on the EEG of the patient with a mental illness:

[0074] If it occurs, a corresponding first restraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; the controller module executes the first restraint control instruction, controls the action of the restraint belt reeling component, and starts to restrain the mentally ill patient;

[0075] If it does not appear, it is abandoned;

[0076] The electrode sheet is electrically connected to the controller module;

[0077] The mentally ill patient restraint device is communicatively connected to the background server.

[0078] The control system of the mentally ill patient restraint device is as follows Figure 2 As shown, the specific working principle of its constraint can refer to the public patent in the background technology.

[0079] Among them, its wireless signal receiving unit can adopt a wireless module such as a Bluetooth module or a 5G module, etc., and communicate with the background by networking with the in-hospital gateway.

[0080] In this embodiment, the architecture of the wireless module communicating with the backend through the gateway generally includes the following key components:

[0081] 1. Wireless module: This is a hardware module connected to the device, responsible for sending and receiving wireless signals. It usually supports specific wireless communication protocols such as Wi-Fi, Bluetooth, LoRa, NB-IoT, etc.

[0082] 2. Gateway device: The gateway is the bridge connecting the wireless module and the backend server. It is responsible for collecting data from the wireless module and forwarding the data to the backend system. At the same time, the gateway is also responsible for sending instructions or data from the backend system to the wireless module.

[0083] 3. Backend server: This is the core of the entire communication architecture, usually including databases and applications. The backend server processes data from the wireless module, executes necessary business logic, and stores data for further analysis or recording. It is also responsible for sending control instructions to the wireless module.

[0084] 4. Communication protocol: The communication between the wireless module and the gateway, and between the gateway and the backend server needs to follow certain protocols. These protocols define the data format, transmission method, encryption method, etc. to ensure the accuracy and security of data transmission.

[0085] 5. Network connection: The connection between the wireless module and the gateway is usually achieved through wireless signals, while the connection between the gateway and the backend server may be achieved through a wired or wireless network, such as Ethernet, Wi-Fi, 4G / 5G, etc.

[0086] In actual applications, the data collected by the wireless module is first sent to the gateway, which then packages the data and sends it to the backend server through the network. After the backend server processes the data, it can send the results or instructions back to the gateway, which then forwards the instructions to the corresponding wireless module. This architecture makes applications such as remote monitoring, data collection, and equipment control possible.

[0087] In this embodiment, the administrator specifically configures the channel for each device to communicate with the background through the gateway.

[0088] In order to overcome the defect of manual remote control and waste of nursing resources, avoid the disadvantage that medical staff need to conduct clinical monitoring of mentally ill patients for a long time and cannot do other nursing work, and at the same time increase the humane way of patient restraint, the present invention adopts an intelligent restraint system, which can control the automatic operation of the restraint belt winding component by identifying the dynamic state information of the mentally ill patient, so as to complete the automatic restraint of the mentally ill patient.

[0089] In this solution, firstly, a device that can monitor the EEG signals of mentally ill patients (such as electrode sheets, EEG electrode sheets) is used to sense and monitor the EEG signals of mentally ill patients, and the signals are uploaded to the background server through the communication system composed of the configured gateway and the wireless signal receiving unit. The background server analyzes the EEG signals and generates the corresponding electroencephalogram (EEG). If the monitoring finds that the patient's EEG has abnormal brain waves, the background server sends the corresponding first restraint control instruction, which is sent by the network system to the signal receiving unit of the mentally ill patient restraint device, and then forwarded to the controller by the controller, which executes the restraint control instruction to control the restraint belt winding component to restrain, tighten and limit the patient.

[0090] In this solution, after the background server identifies the patient's corresponding abnormal brain waves based on the EEG signal, it can issue first constraint control instructions of different degrees according to the type of abnormal brain waves. For example, if it is a slight abnormal fluctuation, a first constraint control instruction of mild constraint can be issued. Mild constraint, for example, can make the restraint belt winding component reel in 1 / 4 circle or half a circle. If it is a moderate constraint, it can be a constraint control instruction to reel in 2 / 3 circle or one circle. Let the controller control the motor of the restraint belt winding component to rotate the corresponding number of circles, so as to achieve the tightening and restriction adjustment of the corresponding restraint belt.

[0091] The specific tightening and restriction degrees corresponding to different types can be pre-set in the corresponding mapping table (constraint instructions corresponding to different constraint types) on the background server. The background server will automatically match and issue the corresponding degree of constraint control instructions according to the degree, level, type, etc. of the identified brain wave abnormalities.

[0092] As an optional implementation scheme of the present application, optionally, it also includes:

[0093] An in-hospital gateway, used for routing communications between the mentally ill patient restraint device and the backend server;

[0094] The mental patient restraint device is communicatively connected to the backend server via the in-hospital gateway.

[0095] The in-hospital gateway is deployed by the administrator, who configures the communication channels between it and various devices.

[0096] As an optional implementation scheme of the present application, optionally, the abnormal brain wave condition includes:

[0097] The electroencephalogram shows waveform characteristics of sharp waves, spike waves or low-amplitude fast waves;

[0098] as well as,

[0099] A peak exceeding a preset electroencephalogram signal value appears on the electroencephalogram.

[0100] Sharp waves and spikes: may be associated with epileptic seizures.

[0101] High-amplitude rhythmic activity: May be associated with certain types of brain lesions or drug effects.

[0102] Low-amplitude fast wave activity: may be associated with metabolic encephalopathy or certain drug intoxication.

[0103] These different types of waveform features can be monitored on the EEG, and the EEG software can also monitor these waveform features based on the configured monitoring information and issue an alarm when these waveform features are found. The specific understanding and operation can be combined with the EEG application software. The administrator can set the type of waveform feature of the alarm in the EEG application software in advance.

[0104] In addition, the peak monitoring can be used to determine whether the patient is in an abnormal condition. If the patient is too intense, a peak exceeding the preset EEG signal value will appear on the EEG, which can be used as one of the constraints. The peak alarm value can also be set on the EEG application software.

[0105] Therefore, combined with the monitoring of EEG abnormalities, preventive restraint of violence on patients is carried out to avoid the lag of restraint caused by restraint after violence occurs.

[0106] In this embodiment, restraint control is also performed by monitoring whether the patient's posture shows any violent or other actions. If the background finds that the patient's posture meets the preset violent posture, the restraint control condition is triggered, and the background issues the corresponding second restraint control instruction, which is executed by the controller of the device. For details, refer to the above-mentioned first restraint control instruction.

[0107] Combined with Figure 3 As shown, the present invention can also first send the restraint control instruction to the PDA terminal of each corresponding medical staff after the background server generates the corresponding restraint control instruction, so that the corresponding medical staff can clinically confirm the restraint control instruction. The medical staff will then determine whether the patient needs to be restrained based on the clinical situation. If so, the confirmation information will be fed back to the background server, and then the background server will send the corresponding restraint control instruction. In this way, it is ensured that the nurse can confirm the restraint.

[0108] As an optional embodiment of the present application, optionally, the mentally ill patient restraint device further comprises:

[0109] A motion camera, deployed in the ward, for collecting motion image data of patients with mental illness and feeding it back to the controller module in real time;

[0110] The motion camera is electrically connected to the controller module.

[0111] An action camera is a video device designed to capture dynamic scenes. It is usually small and lightweight, impact-resistant, waterproof and dustproof, making it very suitable for outdoor and extreme sports enthusiasts. An action camera can record every detail of the movement at a high frame rate and high resolution, providing users with clear and smooth motion images. In addition, action cameras are often equipped with various fixing devices and accessories, allowing users to fix them on sports equipment such as helmets, bicycles, skateboards, etc., so as to capture unique sports images from different perspectives.

[0112] Motion cameras can be deployed in wards to collect motion images of patients. They can be electrically connected to the controller through wires, etc., and the controller can uniformly control and activate them. The collected image data can be processed by the controller and then reported to the background server.

[0113] As an optional implementation scheme of the present application, optionally, the controller module is further used for:

[0114] After the motion image data is processed, it is uploaded to the background server through the wireless signal receiving unit.

[0115] The controller pre-processes the received motion image, which usually includes the following steps:

[0116] 1. Image acquisition: First, the controller needs to obtain raw image data from the image sensor or other input device.

[0117] 2. Noise removal: Since the image may be affected by various noises during the acquisition process, the first step of preprocessing is usually to apply a filtering algorithm to remove noise, such as Gaussian filtering, median filtering, etc.

[0118] 3. Contrast enhancement: By adjusting the contrast of the image, the details of the image are made clearer and easier to process. This can be achieved through techniques such as histogram equalization.

[0119] 4. Edge detection: In order to identify objects in an image, it is necessary to detect the edges in the image. Commonly used edge detection algorithms include Sobel operator, Canny edge detection, etc.

[0120] 5. Image Scaling: Depending on the needs, the image may need to be scaled to a specific resolution for easier processing or display.

[0121] 6. Image format conversion: Convert image data into a format that the controller can handle, such as converting from RGB to YUV format, or converting color space.

[0122] 7. Image enhancement: Improve image quality through enhancement algorithms, such as sharpening, to highlight the details of the image.

[0123] 8. Image segmentation: Divide the image into multiple regions or objects to facilitate target recognition and tracking.

[0124] 9. Other preprocessing: Depending on the requirements of specific applications, other preprocessing steps may be required, such as image correction, distortion correction, etc.

[0125] After completing these preprocessing steps, the controller can use the processed image data for further analysis and processing, such as motion detection, object tracking, behavior analysis, etc.

[0126] In this embodiment, the motion image enhancement processing and segmentation can be executed in the program of the controller chip, and the motion images of multiple patients can be segmented, so as to acquire the motion images of multiple patients in the ward. After the controller numbers each patient, the motion image of each patient can be uploaded separately.

[0127] As an optional implementation scheme of the present application, optionally, the background server is also used for:

[0128] Performing frame image processing on the motion image data to obtain motion frame images of several mental illness patients; and performing motion posture recognition on each of the motion frame images to determine whether a preset abnormal motion posture occurs:

[0129] If it occurs, a corresponding second restraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; the controller module executes the second restraint control instruction, controls the action of the restraint belt reeling component, and starts to restrain the mentally ill patient;

[0130] If it does not appear, give up.

[0131] When processing motion images in the background, the video stream must first be decomposed into a series of individual frame images.

[0132] This typically involves the following steps:

[0133] 1. Read video files or real-time video streams.

[0134] 2. Use a video decoder to decode the video data into frame images.

[0135] 3. Store continuous frame images in memory for further processing.

[0136] 4. Perform required image processing operations on each frame of image, such as filtering, edge detection, feature extraction, etc.

[0137] 5. After processing, the frame images can be reassembled into a video stream or saved as image files separately.

[0138] Ensure that performance and resource management are considered during processing to efficiently handle large amounts of data.

[0139] The model recognition scheme for motion posture recognition of frame images and determining whether abnormal motion posture occurs can be divided into the following steps:

[0140] 1. Feature extraction: Use deep learning models such as convolutional neural networks (CNN) to extract key features from the image. Pre-trained models such as ResNet and Inception can be used as feature extractors.

[0141] 2. Model design: Design a classification model, such as a fully connected neural network, to determine whether the motion posture is abnormal based on the extracted features. The model can adopt a multi-layer structure to improve the accuracy of recognition.

[0142] 3. Training and validation: Use labeled data sets to train the model and verify the performance of the model through methods such as cross-validation. Adjust model parameters and structure to optimize recognition results.

[0143] 4. Abnormal posture determination: Set a threshold. When the probability of the model output is lower than the threshold, it is determined to be an abnormal motion posture. The threshold setting should be adjusted based on the performance of the model on the validation set.

[0144] An abnormal motion posture classification model trained by various abnormal motion posture data sets of patients can be deployed on the background to recognize the motion posture of each motion frame image, determine whether the preset abnormal motion posture appears in the motion frame image, and output the corresponding results, so as to quickly identify the patient's abnormal movement posture.

[0145] The training set of the model can capture a large number of patients' motion images from the background database and classify them to obtain a training set consisting of abnormal motion images.

[0146] Next, we can use deep learning models such as CNN to train the training set to obtain an abnormal motion posture classification model. The following is one way:

[0147] First, collect and prepare an abnormal motion image dataset. Make sure the dataset contains a variety of normal and abnormal motion posture images and annotate the data.

[0148] Secondly, the dataset is preprocessed, including image resizing, normalization, and enhancement, to improve the efficiency and effectiveness of model training.

[0149] Then, a suitable deep learning architecture, such as a convolutional neural network (CNN), is selected as the basis for the abnormal motion posture classification model.

[0150] Next, divide the dataset into training set, validation set, and test set. Use the training set to train the model, and use the validation set to adjust the model parameters and prevent overfitting.

[0151] After that, the model is trained, through multiple iterations, using optimization techniques such as back-propagation and gradient descent to adjust the network weights.

[0152] After training is completed, the test set is used to evaluate the model performance, and the classification effect of the model is measured by indicators such as accuracy, recall, and F1 score.

[0153] Finally, the model is fine-tuned based on the evaluation results to optimize the model structure or parameters to achieve better classification results. After the model training is completed, it can be deployed in practical applications for real-time or offline classification of abnormal motion postures.

[0154] As attached Figure 4 As shown, as an optional implementation scheme of the present application, optionally, the background server includes:

[0155] EEG processing system for providing EEG monitoring services;

[0156] A motion tracking monitoring system, used to provide frame image processing of the motion image data and a judgment service on whether a preset abnormal motion posture occurs;

[0157] Backend database, used to store data.

[0158] The specific background service functions can be combined with the above description and will not be repeated here.

[0159] Obviously, those skilled in the art should understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated: HDD) or a solid-state drive (Solid-State Drive, SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0160] Example 2

[0161] Based on the implementation principle of Example 1, the present application, on the other hand, proposes an application method of a mental illness patient restraint system for adjusting tightness based on dynamic sensor monitoring, comprising the following steps:

[0162] Provide mental illness patients with restraint belt retractors and electrodes, and deploy motion cameras;

[0163] The backend server sends instructions to activate the system's electrodes and motion cameras;

[0164] Dynamic sensor monitoring of restraints:

[0165] (1) The electrode sheet senses and monitors the EEG signals of patients with mental illness and feeds them back to the controller module in real time; after the controller module processes the EEG signals, it uploads them to the backend server through the wireless signal receiving unit;

[0166] The backend server performs signal analysis on the EEG signal and generates an EEG of the mentally ill patient; and monitors whether a preset abnormal brain wave condition appears on the EEG of the mentally ill patient:

[0167] If it occurs, a corresponding first restraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; the controller module executes the first restraint control instruction, controls the action of the restraint belt reeling component, and starts to restrain the mentally ill patient;

[0168] If it does not appear, it is abandoned;

[0169] (2) The motion camera collects motion image data of the mental illness patient and feeds it back to the controller module in real time; after the controller module processes the motion image data, it uploads it to the background server through the wireless signal receiving unit;

[0170] The backend server performs frame image processing on the motion image data to obtain motion frame images of several mental illness patients; and performs motion posture recognition on each of the motion frame images, and determines whether a preset abnormal motion posture appears:

[0171] If it occurs, a corresponding second restraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; the controller module executes the second restraint control instruction, controls the action of the restraint belt reeling component, and starts to restrain the mentally ill patient;

[0172] If it does not appear, give up.

[0173] The above-mentioned two monitoring modes, electrode sheet and motion camera, can be carried out simultaneously. As long as an abnormal alarm occurs in one of the monitoring modes, the background server will send the corresponding restraint control instruction, which will be sent to the wireless signal receiving unit through the in-hospital gateway, and then forwarded by the wireless signal receiving unit to the controller module for execution, controlling the movement of the restraint belt winding component to start restraining the mentally ill patient.

[0174] Please understand the principle of Example 1 for details.

[0175] The modules or steps of the present invention described above can be implemented by a general-purpose computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by a program code executable by a computing system, so that they can be stored in a storage system and executed by the computing system, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0176] Example 3

[0177] Furthermore, in another aspect, the present application also proposes an electronic system, comprising:

[0178] processor;

[0179] a memory for storing processor-executable instructions;

[0180] Wherein, the processor is configured to implement the application method described in Example 2 when executing the executable instructions.

[0181] The electronic system of the embodiment of the present disclosure includes a processor and a memory for storing processor executable instructions, wherein the processor is configured to implement the application method described in the above embodiment 2 when executing the executable instructions.

[0182] Here, it should be noted that the number of processors may be one or more. At the same time, the electronic system of the embodiment of the present disclosure may also include an input system and an output system. The processor, memory, input system, and output system may be connected via a bus or in other ways, which are not specifically limited here.

[0183] The memory, as a computer-readable storage medium, can be used to store software programs, computer executable programs and various modules, such as the program or module corresponding to the application method of the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic system by running the software programs or modules stored in the memory.

[0184] The input system can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the system / terminal / server. The output system can include a display system such as a display screen.

[0185] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A mentally ill patient restraint system for adjusting tightness based on dynamic sensor monitoring, comprising a mentally ill patient restraint device consisting of a wireless signal receiving unit, a restraint belt winding component and a controller module, characterized in that: The mentally ill patient restraint device also includes: Electrode sheets, used for sensing and monitoring brain electrical signals of patients with mental illness and providing real-time feedback to the controller module; The controller module is also used to: after processing the EEG signal, upload it to the background server through the wireless signal receiving unit; The backend server is used to: perform signal analysis on the EEG signal and generate an EEG of a patient with a mental illness; and monitor whether a preset abnormal brain wave condition appears on the EEG of the patient with a mental illness: If it occurs, a corresponding first restraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; the controller module executes the first restraint control instruction, controls the action of the restraint belt reeling component, and starts to restrain the mentally ill patient; If it does not appear, it is abandoned; The electrode sheet is electrically connected to the controller module; The mentally ill patient restraint device is communicatively connected to the background server.

2. The mental illness patient restraint system for adjusting tightness based on dynamic sensor monitoring according to claim 1 is characterized in that: Also includes: An in-hospital gateway, used for routing communications between the mentally ill patient restraint device and the backend server; The mental patient restraint device is communicatively connected to the backend server via the in-hospital gateway.

3. The mental illness patient restraint system for adjusting tightness based on dynamic sensor monitoring according to claim 1 is characterized in that: The abnormal brain waves include: The electroencephalogram shows waveform characteristics of sharp waves, spike waves or low-amplitude fast waves; as well as, A peak exceeding a preset electroencephalogram signal value appears on the electroencephalogram.

4. The mental illness patient restraint system for adjusting tightness based on dynamic sensor monitoring according to claim 1 is characterized in that: The mentally ill patient restraint device also includes: A motion camera, deployed in the corresponding ward, for collecting motion image data of patients with mental illness and feeding it back to the controller module in real time; The motion camera is electrically connected to the controller module.

5. The mental illness patient restraint system for adjusting tightness based on dynamic sensor monitoring according to claim 4 is characterized in that: The controller module is further used for: After the motion image data is processed, it is uploaded to the background server through the wireless signal receiving unit.

6. The mental illness patient restraint system for adjusting tightness based on dynamic sensor monitoring according to claim 5 is characterized in that: The backend server is also used for: Performing frame image processing on the motion image data to obtain motion frame images of several mental illness patients; and performing motion posture recognition on each of the motion frame images to determine whether a preset abnormal motion posture occurs: If it occurs, a corresponding second constraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; The controller module executes the second restraint control instruction to control the restraint belt reeling component to start restraining the mental illness patient; If it does not appear, give up.

7. The mental illness patient restraint system for adjusting tightness based on dynamic sensor monitoring according to claim 6 is characterized in that: The backend server comprises: EEG processing system for providing EEG monitoring services; A motion tracking monitoring system, used to provide frame image processing of the motion image data and a judgment service on whether a preset abnormal motion posture occurs; Backend database, used to store data.

8. An application method of the mental illness patient restraint system for adjusting tightness based on dynamic sensor monitoring as described in any one of claims 1 to 7, characterized in that: The steps include: Provide mental illness patients with restraint belt retractors and electrodes, and deploy motion cameras; The backend server sends instructions to activate the system's electrodes and motion cameras; Dynamic sensor monitoring of restraints: (1) The electrode sheet senses and monitors the EEG signals of patients with mental illness and feeds them back to the controller module in real time; after the controller module processes the EEG signals, it uploads them to the background server through the wireless signal receiving unit; The backend server performs signal analysis on the electroencephalogram signal and generates an electroencephalogram of a patient with a mental illness; And, monitoring whether the EEG of the mental illness patient shows a preset abnormal brain wave condition: If it occurs, a corresponding first constraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; The controller module executes the first restraint control instruction to control the restraint belt reeling component to start restraining the mental illness patient; If it does not appear, it is abandoned; (2) The motion camera collects motion image data of the patient with mental illness and feeds it back to the controller module in real time; after the controller module processes the motion image data, it uploads it to the background server through the wireless signal receiving unit; The backend server performs frame image processing on the motion image data to obtain motion frame images of several mental illness patients; and performs motion posture recognition on each of the motion frame images, and determines whether a preset abnormal motion posture appears: If it occurs, a corresponding second constraint control instruction is generated and sent to the wireless signal receiving unit, which is then forwarded to the controller module by the wireless signal receiving unit; The controller module executes the second restraint control instruction to control the restraint belt reeling component to start restraining the mental illness patient; If it does not appear, give up.

9. An electronic system, characterized in that include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the application method described in claim 8 when executing the executable instructions.

Citation Information

Patent Citations

  • Shoulder restraint strap having monitoring and alarming functions and capable of preventing bed falling and tube pulling

    CN110974519A

  • Monitoring system for epilepsy abnormality

    CN114027856A

  • Home-based interactive intelligent monitoring system and method for epileptic seizure

    CN114145755A

  • Body constraint decision-making system

    CN114842959A

  • Restraint device and method for dysphoria patient

    CN114983657A