Wireless monitoring method and system

Abstract

The invention discloses a wireless monitoring method and system, and the method comprises the steps: collecting the multi-modal physiological data of a patient through a flexible sensor and a wireless electrode according to the physiological state of the patient; according to the collected multi-modal physiological data, an anti-interference algorithm and a wireless communication technology are used for signal processing and transmission; receiving the transmitted multi-modal physiological data, performing real-time analysis by using an intelligent algorithm, and generating an early warning signal; according to the early warning signal, remote medical support is realized by using a cloud platform and an internet of things technology; wherein the cloud platform generates a real-time report and a trend analysis chart of the physiological state of the patient through big data analysis and a visualization technology, and the real-time report and the trend analysis chart are provided for remote monitoring and diagnosis of medical personnel. According to the embodiment of the invention, efficient, continuous and intelligent medical wireless monitoring can be realized, and better monitoring experience is provided for patients.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical monitoring, and particularly relates to a wireless monitoring method and system. Background Art

[0002] With the progress of technology and the increasing attention to health management, the rapid development of medical monitoring technology has become an indispensable part of modern medicine. Traditional hospital monitoring systems usually rely on various fixed devices, which are reliable in performance, but due to their bulkiness and limitations, they can only be used in hospital environments, lacking flexibility and convenience. Especially in the management of chronic diseases, elderly care, and remote monitoring of critically ill patients, the many challenges faced by traditional devices prevent patients from receiving timely and effective monitoring and care. In addition, many patients need to stay in the hospital for a long time during routine monitoring, which not only increases the consumption of medical resources but also causes physical and psychological discomfort to patients. Therefore, it is particularly important to develop a portable and efficient wireless monitoring method. Summary of the Invention

[0003] The purpose of the present invention is to provide a wireless monitoring method and system to solve the deficiencies in the prior art, and to achieve efficient, continuous, and intelligent medical wireless monitoring, providing a better monitoring experience for patients.

[0004] An embodiment of the present application provides a wireless monitoring method, which includes:

[0005] According to the physiological state of the patient, multi-modal physiological data of the patient is collected using a flexible sensor and a wireless electrode. Among them, the multi-modal physiological data includes electrocardiogram, oxygen saturation, and blood pressure data. The flexible sensor uses nanomaterials and microelectromechanical system technology to achieve high-precision data collection, while ensuring wearing comfort and stability for long-term use;

[0006] According to the collected multi-modal physiological data, signal processing and transmission are performed using an anti-interference algorithm and wireless communication technology. Among them, the anti-interference algorithm uses adaptive filtering and spectrum analysis technology to eliminate noise and interference during signal transmission, ensuring the accuracy and stability of the data. The wireless communication technology uses a hybrid network of Bluetooth, ZigBee, and 5G to achieve efficient data transmission;

[0007] The transmitted multi-modal physiological data is received and analyzed in real time using an intelligent algorithm. Among them, the intelligent algorithm uses deep learning and pattern recognition technology to automatically identify electrocardiogram abnormalities, oxygen saturation drops, and / or blood pressure fluctuations, and generate warning signals;

[0008] Based on the warning signals, remote medical support is realized by using cloud platform and Internet of Things technologies; among them, the cloud platform generates real-time reports and trend analysis charts of the patient's physiological state through big data analysis and visualization technologies for medical staff to remotely monitor and diagnose.

[0009] Optionally, according to the patient's physiological state, multi-modal physiological data of the patient is collected by using flexible sensors and wireless electrodes. Among them, the multi-modal physiological data includes electrocardiogram, oxygen saturation and blood pressure data. The flexible sensors achieve high-precision data collection through nanomaterials and microelectromechanical system technologies, while ensuring wearing comfort and stability for long-term use, including:

[0010] According to the patient's physiological state, the flexible sensors and wireless electrodes are deployed at key parts of the patient's body. Among them, the flexible sensors are made of nanomaterials and microelectromechanical system technologies, conform to the skin surface to ensure wearing comfort, and the wireless electrodes are connected to the monitoring and control device through Bluetooth or ZigBee technologies to realize wireless data transmission;

[0011] According to the deployed flexible sensors and wireless electrodes, electrocardiogram data is collected in real time. Among them, the flexible electrocardiogram sensor is used to detect the electrical activity of the heart to generate the original electrocardiogram signal, and the signal amplifier and filter are used to preprocess the original electrocardiogram signal to remove noise and interference to obtain electrocardiogram waveform data;

[0012] The flexible optical sensor is used to collect oxygen saturation data in real time. Among them, red light and infrared light are emitted by the flexible optical sensor to detect the ratio of oxyhemoglobin and deoxyhemoglobin in the blood, and the signal processing algorithm is used to calculate the oxygen saturation data and remove motion artifacts and ambient light interference;

[0013] The flexible pressure sensor module is used to collect blood pressure data in real time. Among them, the flexible pressure sensor is used to detect the pressure change of the arterial wall to generate the original blood pressure signal, and the signal processing algorithm is used to calculate the blood pressure data and remove noise and interference;

[0014] The collected electrocardiogram waveform data, oxygen saturation data and blood pressure data are further filtered and denoised to generate a multi-modal physiological data set.

[0015] Optionally, according to the collected multi-modal physiological data, anti-interference algorithms and wireless communication technologies are used for signal processing and transmission. Among them, the anti-interference algorithms eliminate noise and interference in the signal transmission process through adaptive filtering and spectrum analysis technologies to ensure the accuracy and stability of the data, and the wireless communication technologies realize efficient data transmission through a hybrid network of Bluetooth, ZigBee and 5G, including:

[0016] Based on multimodal physiological data, an adaptive filtering algorithm is used for noise cancellation; among them,

[0017] For electrocardiogram waveform data, an adaptive filter is used to remove baseline drift and high-frequency noise, generating filtered electrocardiogram data; for oxygen saturation data, an adaptive filter is used to remove motion artifacts and ambient light interference, generating filtered oxygen saturation data; for blood pressure data, an adaptive filter is used to remove pressure fluctuation noise, generating filtered blood pressure data;

[0018] Based on the filtered multimodal physiological data, spectrum analysis technology is used for signal enhancement; among them,

[0019] For electrocardiogram waveform data, fast Fourier transform is used to analyze spectral characteristics, enhancing the effective frequency band of the electrocardiogram signal, generating enhanced electrocardiogram waveform data; for oxygen saturation data, spectrum analysis technology is used to identify the effective signal frequency band, enhancing the stability of the oxygen saturation data, generating enhanced oxygen saturation data; for blood pressure data, spectrum analysis technology is used to remove low-frequency interference, enhancing the accuracy of the blood pressure data, generating enhanced blood pressure data;

[0020] Based on the enhanced multimodal physiological data, hybrid networking technology is used for wireless transmission; among them,

[0021] Short-distance data in multimodal physiological data is transmitted through Bluetooth technology to ensure low power consumption and real-time performance; medium-distance data in multimodal physiological data is transmitted through ZigBee technology to ensure stability and anti-interference ability; long-distance data in multimodal physiological data is transmitted through 5G technology to ensure high-speed and large-capacity transmission.

[0022] Optionally, the received and transmitted multimodal physiological data is analyzed in real time using an intelligent algorithm, among which the intelligent algorithm automatically identifies electrocardiogram abnormalities, oxygen saturation drops, and / or blood pressure fluctuations through deep learning and pattern recognition technologies, generating warning signals, including:

[0023] Based on the enhanced electrocardiogram waveform data, a deep learning model is used for electrocardiogram abnormality detection, where a convolutional neural network is used to extract electrocardiogram waveform features, identify abnormal waveforms, and classify abnormal types through pattern recognition technology, generating electrocardiogram abnormality warning signals;

[0024] Based on the enhanced oxygen saturation data, a time series analysis model is used for oxygen saturation drop detection, where a long short-term memory network is used to analyze the oxygen saturation change trend, identify abnormal drops, and generate oxygen saturation drop warning signals through threshold judgment;

[0025] Based on the enhanced blood pressure data, an anomaly detection algorithm is used for blood pressure fluctuation detection. Among them, the Isolation Forest algorithm is used to identify abnormal blood pressure fluctuations, and through pattern recognition technology, a blood pressure fluctuation warning signal is generated;

[0026] According to the generated electrocardiogram anomaly warning signal, oxygen saturation drop warning signal, and blood pressure fluctuation warning signal, a comprehensive warning signal is generated.

[0027] Another embodiment of the present application provides a wireless monitoring system, and the system includes:

[0028] An acquisition module, configured to collect multi-modal physiological data of a patient using a flexible sensor and a wireless electrode according to the physiological state of the patient. Among them, the multi-modal physiological data includes electrocardiogram, oxygen saturation, and blood pressure data. The flexible sensor realizes high-precision data acquisition through nanomaterials and micro-electromechanical system technology, while ensuring wearing comfort and stability for long-term use;

[0029] A processing module, configured to perform signal processing and transmission using an anti-interference algorithm and wireless communication technology according to the collected multi-modal physiological data. Among them, the anti-interference algorithm eliminates noise and interference during signal transmission through adaptive filtering and spectrum analysis technology to ensure the accuracy and stability of the data. The wireless communication technology realizes efficient data transmission through a hybrid network of Bluetooth, ZigBee, and 5G;

[0030] An analysis module, configured to receive the transmitted multi-modal physiological data and perform real-time analysis using an intelligent algorithm. Among them, the intelligent algorithm automatically identifies electrocardiogram anomalies, oxygen saturation drops, and / or blood pressure fluctuations through deep learning and pattern recognition technology, and generates warning signals;

[0031] A monitoring module, configured to provide remote medical support using a cloud platform and Internet of Things technology according to the warning signal; among them, the cloud platform generates real-time reports and trend analysis charts of the patient's physiological state through big data analysis and visualization technology for medical staff to remotely monitor and diagnose.

[0032] Another embodiment of the present application provides a storage medium, in which a computer program is stored. Among them, the computer program is set to execute the method described in any one of the above when running.

[0033] Another embodiment of the present application provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is set to run the computer program to execute the method described in any one of the above.

[0034] Compared with the prior art, a wireless monitoring method provided by the present invention collects multimodal physiological data of a patient according to the patient's physiological state by using a flexible sensor and a wireless electrode; performs signal processing and transmission by using an anti-interference algorithm and a wireless communication technology according to the collected multimodal physiological data; receives the transmitted multimodal physiological data, and performs real-time analysis by using an intelligent algorithm to generate a warning signal; realizes remote medical support by using a cloud platform and Internet of Things technology according to the warning signal; wherein, the cloud platform generates a real-time report and a trend analysis chart of the patient's physiological state through big data analysis and visualization technology for medical staff to remotely monitor and diagnose, so as to realize efficient, continuous, and intelligent medical wireless monitoring and provide a better monitoring experience for patients. Brief Description of the Drawings

[0035] Figure 1 It is a hardware structure block diagram of a computer terminal for a wireless monitoring method provided by an embodiment of the present invention;

[0036] Figure 2 It is a flow schematic diagram of a wireless monitoring method provided by an embodiment of the present invention;

[0037] Figure 3 It is a structure schematic diagram of a wireless monitoring system provided by an embodiment of the present invention. Detailed Embodiment

[0038] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation to the present invention.

[0039] An embodiment of the present invention first provides a wireless monitoring method, which can be applied to an electronic device, such as a computer terminal, specifically, an ordinary computer, etc.

[0040] The following takes running on a computer terminal as an example to describe it in detail. Figure 1 It is a hardware structure block diagram of a computer terminal for a wireless monitoring method provided by an embodiment of the present invention. As Figure 1 shown, the computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the memory may include a non-volatile storage medium and an internal memory.

[0041] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any wireless monitoring method.

[0042] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0043] The internal memory provides an environment for the operation of a computer program in a non-volatile storage medium. When the computer program is executed by a processor, the processor can be caused to execute any one of the wireless monitoring methods.

[0044] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 1 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0045] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0046] See Figure 2 , an embodiment of the present invention provides a wireless monitoring method, which may include the following steps:

[0047] S201, according to the physiological state of the patient, collect multi-modal physiological data of the patient by using a flexible sensor and a wireless electrode, wherein the multi-modal physiological data includes electrocardiogram, oxygen saturation and blood pressure data, and the flexible sensor realizes high-precision data collection through nanomaterials and micro-electromechanical system technology, while ensuring wearing comfort and stability for long-term use;

[0048] The core step of this method is to collect multi-modal physiological data of the patient by using a flexible sensor and a wireless electrode according to the physiological state of the patient, including electrocardiogram, oxygen saturation and blood pressure data. The flexible sensor adopts advanced nanomaterials and micro-electromechanical system (MEMS) technology, which can not only achieve high-precision data collection, but also ensure wearing comfort and stability for long-term use. Due to the flexible characteristics of these sensors, they can closely fit the skin, reduce the discomfort caused by traditional rigid instruments, thereby improving the compliance and user experience of the patient with the monitoring device. The accuracy of this data collection lays a reliable foundation for subsequent real-time analysis and generation of warning signals.

[0049] Collecting multimodal physiological data using flexible sensors and wireless electrodes has important clinical application value. First, comprehensively monitoring multiple physiological indicators such as electrocardiogram, oxygen saturation, and blood pressure helps to comprehensively understand the patient's health status and timely detect potential problems. Second, the comfort design of flexible sensors makes them suitable for long-term wearing and enables continuous monitoring, thereby providing accurate data support for chronic disease management and acute condition monitoring. In addition, the high precision and stability of this method improve the reliability of the data, ensuring that medical staff can formulate scientific treatment plans based on real physiological changes, thus enhancing the safety and quality of life of patients.

[0050] Specifically, according to the patient's physiological state, flexible sensors and wireless electrodes can be deployed at key parts of the patient's body. Among them, the flexible sensors are made by nanomaterials and microelectromechanical system (MEMS) technology, which fit the skin surface to ensure wearing comfort, and the wireless electrodes are connected to the monitoring and control device through Bluetooth or ZigBee technology to achieve wireless data transmission;

[0051] In this step, first, according to the patient's physiological state and monitoring requirements, appropriate sensors and wireless electrodes need to be selected and deployed. Flexible sensors and wireless electrodes are reasonably arranged at key parts such as the patient's electrocardiogram monitoring points, oxygen saturation measurement points, and blood pressure measurement positions. These sensors are manufactured by nanomaterials and MEMS technology, which can achieve excellent conformability while maintaining high-precision data acquisition. Their design takes into account the comfort of patients and can provide a lightweight and soft wearing experience. The wireless electrodes are connected to the monitoring and control device through Bluetooth or ZigBee technology to ensure the stability and real-time nature of data transmission.

[0052] By reasonably deploying flexible sensors and wireless electrodes in this step, not only can the effective acquisition of important physiological signals be achieved, but also the comfort and satisfaction of patients can be significantly improved. By accurately positioning the sensor location, it can ensure higher data quality and enhance the effectiveness of monitoring. This arrangement method is not only applicable to the hospital environment but also convenient for daily monitoring in the home or other non-clinical environments, making telemedicine possible and greatly enhancing the quality of life of patients and the convenience of medical treatment.

[0053] When implementing this step, it is first necessary to evaluate the patient's physiological state to determine the appropriate monitoring site. For example, an electrocardiogram (ECG) monitoring sensor is usually placed on the patient's chest to be close to the electrical activity of the heart and capture ECG signals more effectively. When choosing the location, it is necessary to ensure a tight fit between the sensor and the patient's skin to avoid data loss caused by movement. In addition, nurses or technicians will use skin cleansers for disinfection to ensure that the sensor can be stably attached to the skin. In this process, the design of the flexible sensor takes into account biocompatibility and breathability to ensure that long-term wearing will not cause irritation to the skin.

[0054] Next, the setting of the wireless electrode is also an important part of this process. The selection of the wireless electrode should be based on its communication protocol with the monitoring device. Assuming Bluetooth technology is used, it is necessary to ensure that the working range of the wireless electrode covers the range of the connected device. After the staff places the wireless electrode at the deployment location, a preliminary connection test is carried out to confirm that the signal transmission is stable and without delay. During the test, the battery power also needs to be monitored to ensure that the device can operate continuously and avoid monitoring interruption caused by insufficient power.

[0055] Finally, after the deployment of the sensor and the wireless electrode is completed, the system will start the real-time data monitoring mode. The monitoring device will send the received signal into the data processing module, initially check the quality and stability of the signal through a simple data analysis algorithm, and feedback the results to the nursing staff. If the signal meets the expected standards, the entire monitoring system can enter the normal working state and provide real-time physiological data for medical staff at any time.

[0056] According to the deployed flexible sensor and wireless electrode, electrocardiogram data is collected in real time. Among them, the flexible electrocardiogram sensor is used to detect the electrical activity of the heart and generate the original electrocardiogram signal, and the signal amplifier and filter are used to preprocess the original electrocardiogram signal to remove noise and interference and obtain electrocardiogram waveform data;

[0057] In this step, the deployed flexible electrocardiogram sensor is used to collect electrocardiogram data in real time. The sensor generates the original electrocardiogram signal by detecting the electrical activity of the heart. In this process, the collected original signal is often affected by various factors such as electromagnetic interference and electromyographic noise, so it needs to be preprocessed by a signal amplifier and a filter. The signal amplifier will enhance the weak electrocardiogram signal to make it easier to be processed subsequently, while the filter is responsible for removing interference and noise to make the finally obtained electrocardiogram waveform data clear and of high quality.

[0058] The core of this process lies in ensuring the quality of the collected electrocardiogram (ECG) signals. Clear and accurate ECG waveforms are the basis for cardiac health monitoring, enabling medical staff to detect problems such as arrhythmia and myocardial ischemia in a timely manner. By eliminating noise and interference and improving the accuracy of ECG data, it helps the subsequent analysis and judgment of intelligent algorithms, thus providing a more reliable decision-making basis for the cardiovascular health of patients.

[0059] In this step, the flexible ECG sensor starts to monitor the electrical activity of the patient's heart. The latest nanomaterial technology is adopted inside the sensor, enabling it to capture cardiac electrical signals more sensitively. During the monitoring process, the sensor will generate raw ECG signals, which are initially very weak and thus need to be amplified by a signal amplifier. This amplifier will boost the weak electrical signals to a processable range, enabling subsequent digital processing to proceed smoothly.

[0060] After signal amplification, the raw ECG signals enter the filter for further processing. The filter is mainly designed to deal with possible noise and interference. In clinical applications, ECG signals may be affected by various factors such as muscle movement and external electromagnetic interference. Therefore, high-performance digital filtering algorithms, such as the combination of low-pass and high-pass filtering, are needed to remove interference waves and baseline drift. Suppose the patient experiences muscle tremors during the acquisition process. The system will remove these artifacts through the filter to ensure that the finally obtained ECG signals are clear waveforms.

[0061] Finally, the processed ECG waveform data will be stored and analyzed in real time. The storage technology used by the system can ensure the security and integrity of the data. Medical staff can view the ECG waveforms in real time through the monitoring screen and respond quickly when abnormal waveforms appear. In addition, these data will provide the necessary input for subsequent deep learning algorithms and pattern recognition technologies, further supporting the automatic detection and early warning of arrhythmia.

[0062] The flexible optical sensor is used to collect oxygen saturation data in real time. Among them, the flexible optical sensor emits red light and infrared light, detects the ratio of oxyhemoglobin and deoxyhemoglobin in the blood, calculates the oxygen saturation data using signal processing algorithms, and removes motion artifacts and ambient light interference;

[0063] In this step, the flexible optical sensor is responsible for collecting the patient's oxygen saturation data in real time. This sensor adopts the optical principle, emits red light and infrared light of specific wavelengths, and can effectively judge the ratio of oxyhemoglobin and deoxyhemoglobin by measuring the absorption rates of the two lights after propagating in the blood. Based on these data, the system will use relevant signal processing algorithms to calculate the patient's oxygen saturation. At the same time, to ensure the accuracy of the measurement, it is also necessary to remove data errors caused by motion artifacts or ambient light interference.

[0064] Real-time monitoring of oxygen saturation is crucial for evaluating a patient's respiratory and cardiovascular health. With accurate oxygen saturation data, medical staff can promptly detect potential hypoxia in patients and thus take appropriate treatment measures. The ability to remove motion artifacts and environmental light interference ensures the accuracy of the signal, making the monitoring results more reliable and providing a solid data basis for subsequent medical decisions.

[0065] In this step, a flexible optical sensor will be applied to real-time monitor a patient's oxygen saturation. The sensor works by emitting red light and infrared light at specific wavelengths to detect the ratio of oxyhemoglobin to deoxyhemoglobin in the blood. The sensor will emit red light and infrared light through the skin surface, and the light penetrates and reaches the blood vessels. Subsequently, the oxygen saturation is calculated by detecting the intensity and wavelength changes of the reflected light.

[0066] During the measurement process, the sensor will collect the returned optical signals in real-time and analyze them using signal processing algorithms. The sensor system will perform real-time data correction for different conditions and environments. For example, when a patient moves, it may cause artifacts in the signal, so the system will adopt adaptive filtering technology to effectively remove the data fluctuations caused by motion. At the same time, the interference of environmental light may also affect the measurement results, so the system will design specific filters to ensure that only the optical signals related to blood absorbance are read.

[0067] Finally, the processed oxygen saturation data will be transmitted to the monitoring system in a stable form. The real-time update of this data enables medical staff to quickly understand the patient's oxygenation status and take timely intervention measures when abnormalities occur. At the same time, the generated oxygen saturation indicators can not only be used for clinical analysis but also be integrated into an automated health record system for long-term health tracking and analysis.

[0068] The flexible pressure sensor module is used to collect blood pressure data in real-time. Among them, the pressure change of the arterial wall is detected by the flexible pressure sensor to generate the original blood pressure signal, and signal processing algorithms are used to calculate the blood pressure data and remove noise and interference;

[0069] In this step, a flexible pressure sensor module is adopted to collect blood pressure data in real-time. The sensor is designed to be able to sense the pressure change of the arterial wall to generate the original blood pressure signal. This signal may be affected by various factors during the collection process, including external noise, mechanical interference, etc. Therefore, signal processing algorithms need to be used to process the original blood pressure signal to ensure the accuracy and reliability of the final data.

[0070] Real-time collection of blood pressure data is crucial for monitoring a patient's cardiovascular health status. High-quality blood pressure data can help medical staff detect abnormal conditions such as hypertension or hypotension in a timely manner, thereby adjusting treatment plans and preventing potential health risks. By removing interference and noise, the blood pressure data output by the sensor will be more accurate, providing a reliable reference for medical staff and facilitating better clinical decision-making and patient management.

[0071] In this step, a flexible pressure sensor module will be used to monitor the patient's blood pressure in real time. The sensor is designed to accurately sense the pressure changes in the arterial wall and, using advanced piezoelectric material technology, can accurately convert arterial pressure into an electrical signal. When the patient's heart pumps blood, the pressure changes in the artery will be continuously monitored by the sensor, generating an original blood pressure signal.

[0072] The generated original blood pressure signal will be processed through built-in signal processing algorithms. During this process, the algorithm will analyze the waveform of the signal, extract key features, and calculate the systolic and diastolic blood pressures. At the same time, since the original signal may be affected by body movement, external environment, or other electromagnetic interference, the system will be configured with digital filters to remove this noise. Specifically, the system uses a high-pass filter to remove low-frequency noise and static interference, and a low-pass filter to remove high-frequency fluctuations, making the finally output blood pressure signal more stable and reliable.

[0073] After filtering and processing, the system will transmit the calculated blood pressure data to the monitoring device in real time. These data can not only be used to immediately display the patient's blood pressure situation but also be recorded in the database for subsequent trend analysis and monitoring. This process ensures that medical staff can timely understand the patient's blood pressure changes for timely medical intervention and management.

[0074] The collected electrocardiogram waveform data, oxygen saturation data, and blood pressure data will be further filtered and denoised to generate a multimodal physiological dataset.

[0075] In this step, the collected electrocardiogram waveform data, oxygen saturation data, and blood pressure data will be comprehensively filtered and denoised. This process mainly improves the data quality by selecting appropriate filtering algorithms and technical means. The goal of filtering is to remove the noise that may be introduced during the data collection process and ensure that the data can reflect the patient's true physiological state. After precise signal processing, a multimodal physiological dataset will be finally generated, containing clear and stable electrocardiogram, oxygen saturation, and blood pressure information, which will lay a solid foundation for subsequent signal analysis and intelligent decision-making.

[0076] By filtering and denoising multi-modal physiological data, not only can the accuracy of the data be improved, but also a reliable basis can be provided for subsequent real-time analysis and intelligent diagnosis and treatment. An accurate multi-modal physiological data set will help medical staff understand the patient's health condition more comprehensively and detect potential pathological changes in a timely manner. The completion of this process enables efficient and stable monitoring of physiological data under complex medical conditions, providing a more accurate guarantee for the health and safety of patients.

[0077] In this step, the collected electrocardiogram waveform data, oxygen saturation data, and blood pressure data will be subjected to comprehensive filtering and denoising. This process aims to ensure that all physiological data is as accurate as possible and can truly reflect the patient's health condition. First, the original signals of each type of data will be stored separately, and preprocessing will be performed on them, such as using advanced filtering algorithms like Kalman filtering and mean filtering to remove interference caused by various factors. For electrocardiogram waveform data, the system may adopt adaptive filtering to effectively handle baseline drift and high-frequency noise.

[0078] In the processing of oxygen saturation data, the system will combine ambient light interference data and construct an ambient light standard through comparative experimental settings to correct the oxygen saturation readings and ensure the accuracy of the final oxygen saturation data. For blood pressure data, the system will use low-pass filtering to remove instantaneous fluctuations and further enhance the smoothness of the collected data.

[0079] After completing this step, the processed data will be integrated into a multi-modal physiological data set. This data set will contain clear electrocardiogram waveforms, oxygen saturation, and blood pressure signals, ensuring the consistency and interrelationship of the data. The processed data will be stored in a cloud database for subsequent intelligent analysis and visualization. In this way, a comprehensive patient health condition report can be provided for doctors, supporting clinical decision-making and improving the quality and effect of patient care.

[0080] S202, according to the collected multi-modal physiological data, use anti-interference algorithms and wireless communication technologies for signal processing and transmission. Among them, the anti-interference algorithm eliminates noise and interference in the signal transmission process through adaptive filtering and spectrum analysis technologies to ensure the accuracy and stability of the data, and the wireless communication technology realizes efficient data transmission through a hybrid network of Bluetooth, ZigBee, and 5G;

[0081] In this wireless monitoring method, the collected multimodal physiological data (including electrocardiogram, oxygen saturation, and blood pressure data) need to be processed and transmitted through anti-interference algorithms and wireless communication technologies. The anti-interference algorithms adopt adaptive filtering and spectrum analysis technologies, which can effectively eliminate the noise and interference that may occur during signal transmission, ensuring the accuracy and stability of the transmitted data. Adaptive filtering improves the clarity of the signal by monitoring the changes in the signal in real time and adjusting the filtering parameters, while spectrum analysis can identify the effective components in the signal and enhance specific frequency bands of the signal. This process ensures the high quality and reliability of medical monitoring data, enabling subsequent analysis to be based on accurate data and obtaining more scientific medical decisions.

[0082] The combination of anti-interference algorithms and wireless communication technologies ensures the real-time and reliability of patients' physiological data. This is particularly important for remote medical monitoring because the accuracy of the data directly affects doctors' judgment of the condition and the quality of decision-making. Through Bluetooth, ZigBee, and 5G hybrid networking technologies, efficient transmission of various physiological data can be achieved, supporting stable data transfer in different distances and environments. This flexible wireless transmission method not only reduces the limitations of traditional monitoring devices but also improves patients' comfort and the continuity of monitoring, providing strong technical support for the realization of intelligent medical care and health management.

[0083] Specifically, noise cancellation can be performed on multimodal physiological data using the adaptive filtering algorithm. Among them, for electrocardiogram waveform data, an adaptive filter is used to remove baseline drift and high-frequency noise to generate filtered electrocardiogram data; for oxygen saturation data, an adaptive filter is used to remove motion artifacts and environmental light interference to generate filtered oxygen saturation data; for blood pressure data, an adaptive filter is used to remove pressure fluctuation noise to generate filtered blood pressure data.

[0084] In this link, the system uses the adaptive filtering algorithm to perform noise cancellation on multimodal physiological data to improve the clarity and accuracy of the signal. The core of the adaptive filtering algorithm lies in its ability to dynamically adjust the filtering parameters according to the changes in the input signal and effectively process different types of noise. For electrocardiogram waveform data, the adaptive filter can remove common baseline drift and high-frequency noise to ensure the accuracy of the final output electrocardiogram signal; for oxygen saturation data, it effectively eliminates motion artifacts and environmental light interference to ensure its stability; and in the processing of blood pressure data, the adaptive filter is used to identify and remove the noise caused by pressure fluctuations, thereby generating reliable blood pressure readings.

[0085] Using an adaptive filtering algorithm for noise cancellation can significantly improve the quality of physiological data, laying a solid foundation for subsequent data analysis and processing. The removal of noise ensures the accuracy of important physiological parameters such as electrocardiogram, oxygen saturation, and blood pressure, greatly reducing the risk of misdiagnosis. In clinical applications, clear data is of great significance for medical decision-making, enabling medical staff to quickly identify the health status of patients and intervene in a timely manner.

[0086] In this step, all collected multimodal physiological data will undergo noise cancellation through an adaptive filtering algorithm to ensure the accuracy and stability of the signals. First, the processing of electrocardiogram waveform data will involve using an adaptive filter that can analyze the characteristics of the electrocardiogram in real time and remove baseline drift and high-frequency noise. For example, when the electrocardiogram signal fluctuates due to interference spikes, the adaptive filter will dynamically detect and analyze this signal, reducing or eliminating these fluctuations to obtain a clear electrocardiogram. During this process, the algorithm automatically adjusts its coefficients by comparing the real-time input signal with a preset model, thus achieving the best noise cancellation effect.

[0087] Next, the processing of oxygen saturation data is equally important. Through the adaptive filter, the system can eliminate artifacts caused by patient movement or external light source interference. Suppose a patient makes a small movement during the monitoring process, which may cause the sensor to capture an unstable optical signal. In this case, the adaptive filter will automatically identify these motion artifacts and eliminate them, thereby extracting the true oxygen saturation signal to ensure the stability and accuracy of the data. This filtering process will continue to adapt to changes in the real-time monitoring situation.

[0088] Finally, the processing of blood pressure data also applies the adaptive filtering technique. This process requires special attention to the pressure fluctuation noise caused by pulsation. For example, a patient may cause signal instability due to emotional fluctuations during blood pressure measurement. The adaptive filter will remove the noise caused by emotional changes by dynamically adjusting the captured signal characteristics in real time, ensuring that the final generated blood pressure readings are accurate and reliable. After this series of noise cancellation processes, the system can obtain high-quality multimodal physiological data, providing a solid foundation for subsequent spectral analysis.

[0089] Based on the filtered multimodal physiological data, signal enhancement is performed using spectral analysis techniques. Among them, for electrocardiogram waveform data, fast Fourier transform is used to analyze the spectral characteristics, enhance the effective frequency band of the electrocardiogram signal, and generate enhanced electrocardiogram waveform data; for oxygen saturation data, spectral analysis techniques are used to identify the effective signal frequency band, enhance the stability of the oxygen saturation data, and generate enhanced oxygen saturation data; for blood pressure data, spectral analysis techniques are used to remove low-frequency interference, enhance the accuracy of the blood pressure data, and generate enhanced blood pressure data.

[0090] In this step, the system performs spectral analysis on the filtered multimodal physiological data to enhance the signal. Spectral analysis techniques are particularly suitable for identifying and processing signal features that are difficult to detect in the time domain. For electrocardiogram waveform data, the system uses the Fast Fourier Transform (FFT) technique to analyze its spectral characteristics, thereby enhancing the effective frequency band; for oxygen saturation data, spectral techniques are used to identify the effective signal frequency band and enhance its stability; and for blood pressure data, spectral analysis is also used to remove low-frequency interference and enhance data accuracy, ensuring that the finally generated data is more reliable.

[0091] Enhancing the signal through spectral analysis techniques can accurately extract the effective information of the signal and improve data quality. This process ensures that the subsequent intelligent analysis phase can perform effective physiological state monitoring at a higher level and provides a basis for the timely identification of abnormal signals. Especially in medical monitoring, accurate signals are crucial for accurate diagnosis and timely intervention, so spectral enhancement has an important impact on ensuring medical effects.

[0092] In this stage, the multimodal physiological data after adaptive filtering will be subjected to spectral analysis to extract the effective information in the signal and enhance its quality. First, for electrocardiogram waveform data, the system will apply the Fast Fourier Transform (FFT) technique. FFT can transform the time-domain signal into a frequency-domain signal, making the characteristics of different frequency components appear. In this process, the system will identify the main frequency components of the electrocardiogram signal, such as the QRS waveband, and perform data enhancement based on these frequency components, thereby improving the effectiveness and clarity of the electrocardiogram signal.

[0093] Next, the spectral analysis of oxygen saturation data is equally important. Through spectral analysis, the system can identify the light absorption characteristics of oxyhemoglobin and deoxyhemoglobin, thereby effectively distinguishing light interference from real physiological information. For example, using spectral analysis, signal fluctuations caused by changes in ambient light can be excluded, and the main frequency signals related to oxyhemoglobin can be enhanced. This processing process ensures the reliability of the data in the subsequent stage and makes the oxygen saturation readings during the monitoring process more credible.

[0094] Finally, the blood pressure data is also improved through spectral analysis techniques. The system will analyze the frequency-domain characteristics of the blood pressure signal and remove signal interference caused by low-frequency noise. For example, by identifying and eliminating low-frequency components caused by instrument and environmental changes, the system can output accurate and stable blood pressure readings. These enhanced data will play a crucial role in the subsequent wireless transmission, ensuring the high quality and reliability of data transmission.

[0095] According to the enhanced multimodal physiological data, wireless transmission is carried out using a hybrid networking technology; among them, short-distance data in the multimodal physiological data is transmitted through Bluetooth technology to ensure low power consumption and real-time performance; medium-distance data in the multimodal physiological data is transmitted through ZigBee technology to ensure stability and anti-interference ability; long-distance data in the multimodal physiological data is transmitted through 5G technology to ensure high-speed and large-capacity transmission.

[0096] In this step, the enhanced multimodal physiological data will be wirelessly transmitted using a hybrid networking technology. The system selects a suitable wireless communication protocol according to the data type and transmission distance. Through low-power Bluetooth technology, electrocardiogram waveform data can be transmitted over a short distance to achieve timely data feedback; while oxygen saturation data uses ZigBee technology for medium-distance transmission to ensure transmission stability and anti-interference ability; finally, for blood pressure data, 5G technology will be used for long-distance transmission to ensure high-speed and large-capacity data transfer to meet the needs of clinical monitoring.

[0097] The application of the hybrid networking technology enables wireless transmission to adapt to different environments and requirements, improving the flexibility and reliability of data transmission. Different communication technologies ensure the stable transmission of data under various conditions, which is particularly important for remote medical monitoring as it enables medical staff to keep track of the patient's physiological status at any time and respond promptly to abnormal situations, thereby enhancing patient safety and medical efficiency.

[0098] In this link, the enhanced multimodal physiological data will be wirelessly transmitted using a hybrid networking technology to achieve efficient and stable data transfer. First of all, electrocardiogram waveform data will be transmitted over a short distance through low-power Bluetooth technology. The system will package the processed data and send it to the monitoring device through the Bluetooth module to ensure that the data can be quickly fed back. For example, in the intensive care unit, nurses can receive real-time electrocardiogram fluctuations of patients to help them quickly judge the patient's health status. The low-power consumption feature of this process also ensures that the device will not quickly deplete the battery during long-term monitoring.

[0099] Next, the oxygen saturation data will be transmitted over a medium distance through ZigBee technology. ZigBee has strong anti-interference ability, which is conducive to maintaining transmission stability, especially in a hospital environment where there are often signals interfered by other electronic devices. Suppose a patient is moving around in the ward, ZigBee can intelligently select the optimal signal path to securely transmit the real-time data of oxygen saturation to the monitoring center, providing continuous health monitoring for medical staff. This efficient data transmission method ensures that medical staff can obtain effective data for intervention in a timely manner when necessary.

[0100] Finally, for blood pressure data that needs to be transmitted over long distances, the system will adopt 5G technology. The 5G network has higher bandwidth and lower latency, which can meet the needs of medical staff for fast and large-capacity data transmission in telemedicine. For example, in some remote diagnosis and treatment scenarios, the patient's blood pressure data may need to be transmitted to the specialist's terminal immediately. The 5G technology can ensure that the data is successfully sent within a few milliseconds, enabling doctors to make quick diagnostic decisions. This hierarchical wireless transmission strategy, by carefully selecting relevant technologies, not only improves the efficiency of data transmission but also ensures the accuracy and security of information.

[0101] S203, Receive the transmitted multimodal physiological data and perform real-time analysis using intelligent algorithms. Among them, the intelligent algorithms automatically identify electrocardiogram abnormalities, oxygen saturation drops, and / or blood pressure fluctuations through deep learning and pattern recognition technologies, and generate warning signals.

[0102] In this wireless monitoring method, by receiving the transmitted multimodal physiological data, the system uses intelligent algorithms for real-time analysis. Here, the intelligent algorithms are mainly based on deep learning and pattern recognition technologies, which can automatically process and analyze complex physiological signal data to identify potential health risks. Specifically, key physiological indicators such as electrocardiogram abnormalities, oxygen saturation drops, and blood pressure fluctuations will be automatically monitored. For example, the deep learning model built by the system will process electrocardiogram waveform data, detect abnormal patterns in the electrocardiogram signals by analyzing waveform features and using advanced technologies such as convolutional neural networks (CNNs). This process can timely detect serious diseases such as arrhythmia, thus generating corresponding warning signals.

[0103] The implementation of this method has great clinical application value. Through the real-time analysis of physiological data, it can immediately issue an alarm when the patient's health status is abnormal, providing timely intervention information for medical staff. This intelligent monitoring method not only improves the medical response speed, reduces the risk of potential medical accidents, but also makes telemedicine more feasible and efficient. Especially in the face of sudden diseases or changes in the patient's physical condition, it can rely on instant data analysis to make precise medical decisions and ensure the health and safety of patients.

[0104] Specifically, based on the enhanced electrocardiogram waveform data, a deep learning model can be used to detect electrocardiogram abnormalities. Among them, convolutional neural networks are used to extract electrocardiogram waveform features, identify abnormal waveforms, and classify abnormal types through pattern recognition technologies to generate electrocardiogram abnormality warning signals.

[0105] In this step, the system inputs the enhanced electrocardiogram (ECG) waveform data into a deep learning model, mainly using a Convolutional Neural Network (CNN) for analysis. Convolutional Neural Networks are designed for processing image data, but their powerful feature extraction capabilities are also applicable to ECG waveforms. Through layer-by-layer convolution and pooling, the network can identify important features in the ECG signal, such as QRS complexes, P waves, and T waves, etc., and effectively distinguish normal and abnormal waveforms. During the model training process, the system uses a large amount of labeled ECG data to enhance the learning efficiency, and finally enables the model to automatically identify various abnormal waveforms, such as arrhythmia or ventricular fibrillation, and quickly generate corresponding warning signals.

[0106] The automation and intelligence of this process significantly improve the accuracy and real-time performance of ECG monitoring. Especially in intensive care or emergency scenarios, it can immediately detect and report ECG abnormalities, greatly reducing the risks brought by delays in manual operations. This technology not only helps medical staff grasp the patient's health status but also provides data support for the formulation of subsequent treatment plans, enhancing the scientific nature of clinical decisions.

[0107] In this process, the system first obtains the enhanced ECG waveform data and inputs it into a pre-constructed deep learning model, mainly using a Convolutional Neural Network (CNN). Convolutional Neural Networks are particularly suitable for processing data with spatial structures, such as images and waveforms. When processing ECG waveform data, the system first denoises the waveform data to ensure that the input signal is clear and interference-free. Then, the CNN automatically extracts important features in the ECG signal through multiple layers of convolution and pooling operations. In this way, the model can identify various waveforms in the electrocardiogram, including P waves, QRS complexes, and T waves, and screen out abnormal waveforms. During the training phase of the model, the system needs to use a large number of labeled ECG data sets to ensure that the model can learn the characteristics of normal and abnormal ECG activities. After training, the model will be able to automatically determine whether there are abnormal signals in the input ECG waveform. For example, if the input ECG waveform shows irregular QRS complexes, the model will immediately identify it as arrhythmia through the learned feature library and generate relevant warning signals. This intelligent processing method not only improves the accuracy of diagnosis but also reduces the time required for manual review.

[0108] Finally, when the model identifies an ECG abnormality, it will generate detailed warning signals through the monitoring system to prompt medical staff to pay attention to the status of relevant patients. This process can also combine pattern recognition technology to classify the identified abnormal waveforms and generate different warning types, such as specific types of atrial fibrillation or ventricular premature beats. This classification result helps doctors quickly judge and take necessary medical measures in emergency situations, improving the success rate of patient treatment.

[0109] Based on the enhanced oxygen saturation data, a time series analysis model is used for oxygen saturation decline detection. Among them, a long short-term memory network is used to analyze the change trend of oxygen saturation, identify abnormal declines, and generate an oxygen saturation decline warning signal through threshold judgment;

[0110] In this step, the system applies the enhanced oxygen saturation data to a long short-term memory (LSTM) network model for analysis. LSTM is a recurrent neural network that can effectively process time series data and has strong memory capabilities, making it suitable for analyzing the change trend of oxygen saturation. By analyzing historical data, LSTM can capture the change pattern of oxygen saturation over time and predict future oxygen saturation values. When the oxygen saturation data shows an abnormal decline, the system will make a judgment through a set threshold, thereby generating a warning signal for the decline in oxygen saturation in a timely manner.

[0111] This detection method realizes the real-time monitoring of the patient's oxygen saturation and can quickly identify conditions that may lead to the patient's hypoxia. In emergency rescue, surgery, or other high-risk scenarios, it is crucial to obtain the signal of abnormal oxygen saturation in a timely manner, which can provide information for doctors to support decision-making and ensure the patient's life safety. At the same time, the time series-based analysis method can also help doctors understand the change trend of the patient's oxygen saturation and provide a reference for subsequent medical interventions.

[0112] In this link, the system inputs the enhanced oxygen saturation data into a long short-term memory (LSTM) network model for analysis. LSTM is a special recurrent neural network, especially suitable for processing time series data and capable of memorizing long-term dependencies. The system will use the historical oxygen saturation data as input, and the LSTM network can learn the trend of oxygen saturation changing over time. For example, by analyzing the oxygen saturation fluctuations of a corresponding patient in the past few hours, the model will capture the characteristics within the normal fluctuation range, thereby forming a trend model based on time series.

[0113] During the training process, the system needs to provide a large amount of labeled time series data so that the LSTM network can learn normal and abnormal states. In addition, LSTM will continuously adjust itself to improve the prediction accuracy of oxygen saturation changes. When new data arrives, the LSTM model will monitor the value of oxygen saturation in real time and use the prediction model to determine whether the current value is lower than the normal range. If the system detects a sharp decline in oxygen saturation and this change exceeds the set threshold, the model will immediately generate a warning signal for the decline in oxygen saturation.

[0114] Meanwhile, to improve the accuracy and timeliness of early warnings, the system also combines a threshold judgment algorithm to implement diversified judgment criteria. For example, if the oxygen saturation drops several times in a row and shows a downward trend, the system will consider this phenomenon abnormal and trigger the early warning mechanism. The generated early warning signal will quickly notify medical staff, enabling them to intervene in a timely manner and take appropriate medical measures, such as adjusting oxygen supply or conducting further physiological monitoring, if necessary.

[0115] Based on the enhanced blood pressure data, an anomaly detection algorithm is used to detect blood pressure fluctuations. Among them, the Isolation Forest algorithm is used to identify abnormal blood pressure fluctuations, and through pattern recognition technology, a blood pressure fluctuation early warning signal is generated.

[0116] In this step, the system processes the enhanced blood pressure data, mainly using the Isolation Forest algorithm for anomaly detection. The Isolation Forest algorithm is a tree-based method suitable for anomaly detection of large-scale data, which can effectively identify blood pressure fluctuations significantly different from the normal pattern. When the system receives new blood pressure data, it will compare these data with the previous normal range, and automatically identify outliers by constructing multiple decision trees. If the identified fluctuations exceed the normal blood pressure range, the system will quickly generate an early warning signal for blood pressure fluctuations.

[0117] By using the detection system with the Isolation Forest algorithm, the ability to monitor blood pressure fluctuations can be significantly improved, and changes in patients' blood pressure can be detected and responded to in a timely manner. This not only helps reduce health risks caused by abnormal blood pressure but also provides more accurate clinical information for medical staff, promotes scientific decision-making and intervention, and thus improves the overall medical quality and patient safety.

[0118] In this step, the system inputs the enhanced blood pressure data into the Isolation Forest algorithm for anomaly detection. The Isolation Forest algorithm is an anomaly detection technique based on random forests, especially suitable for processing high-dimensional data. This algorithm identifies and evaluates the anomaly of data by constructing multiple decision trees. First, the system will build a model. By analyzing the normal distribution of historical blood pressure data, the Isolation Forest will learn the characteristics of the normal blood pressure range. When new blood pressure data flows in, the algorithm will evaluate the relative position of the data point to the normal range to determine whether it is an outlier.

[0119] During the analysis process, the Isolation Forest algorithm identifies anomalies by "isolating" data points. That is, the easier a data point is to be isolated, the higher its anomaly level. For example, if the systolic and diastolic blood pressure values of a certain blood pressure measurement are much higher than the normal range, the Isolation Forest algorithm will prove this by constructing multiple trees and finally determine that the value is abnormal. After identifying abnormal fluctuations, the system will generate corresponding early warning signals to prompt medical staff to pay attention to the patient's blood pressure status.

[0120] Finally, the generated blood pressure fluctuation warning signal will be integrated into the hospital's monitoring system and updated in real time. After receiving the signal, medical staff will immediately take necessary intervention measures, such as adjusting the drug dosage, monitoring the patient's condition, or conducting further tests. Through this, the Isolation Forest algorithm ensures real-time monitoring of blood pressure fluctuations, improves the timeliness and effectiveness of medical interventions, and safeguards the health and safety of patients.

[0121] Generate a comprehensive warning signal based on the generated electrocardiogram abnormality warning signal, oxygen saturation drop warning signal, and blood pressure fluctuation warning signal.

[0122] In this final step, the system will generate a comprehensive warning signal through comprehensive processing of multiple generated warning signals (including electrocardiogram abnormality warning signals, oxygen saturation drop warning signals, and blood pressure fluctuation warning signals). The generation process of the comprehensive warning signal will involve signal priority sorting and integration to ensure that important health information can be processed by medical staff first. For example, if a patient has both electrocardiogram abnormalities and blood pressure fluctuations at the same time, the system will give priority to sending an electrocardiogram abnormality alarm so that medical staff can respond in a timely manner.

[0123] By generating a comprehensive warning signal, it can provide medical staff with a more comprehensive summary of the patient's condition, helping them quickly judge the changes in the condition and make corresponding medical decisions. This comprehensive monitoring scheme greatly improves the efficiency of the medical ecosystem, enabling medical staff to coordinate resources more efficiently when facing multiple risks, ensuring patient safety, and thus improving the quality of medical services.

[0124] In this final step, the system integrates the received electrocardiogram abnormality warning signal, oxygen saturation drop warning signal, and blood pressure fluctuation warning signal to generate a comprehensive warning signal. First, the system will sort the priorities according to the severity and type of the warning signal. For example, if both electrocardiogram abnormalities and blood pressure fluctuations are detected at the same time, the system may set the electrocardiogram abnormality warning signal to a higher priority because heart problems usually require more urgent medical attention. Such priority judgments will be based on the set algorithm to ensure that the most urgent signals can be conveyed to medical staff first.

[0125] During the signal integration process, the system will judge and classify various signals through logical algorithms. If a patient has multiple abnormal states at the same time, the system will generate a comprehensive warning signal, integrating all necessary information together to provide a comprehensive overview of the patient's health. This processing mechanism ensures that medical staff can quickly identify and respond to multiple health risks and make corresponding medical decisions quickly.

[0126] Finally, the comprehensive warning signals can also be displayed through a graphical monitoring interface, updating the patient's physiological status in real time and pushing relevant information to the mobile terminals of medical staff. This integrated approach improves the efficiency of information transmission, enabling the medical team to obtain comprehensive health information of the patient in a short time, thereby optimizing the allocation of medical resources and ensuring the best medical outcomes for the patient. Such a comprehensive management method enables the hospital to respond more effectively to emergencies and complex cases, enhancing the overall quality of medical services through efficient communication and intelligent monitoring technologies.

[0127] S204, according to the warning signals, use cloud platform and Internet of Things technologies to achieve remote medical support; wherein, the cloud platform generates real-time reports and trend analysis charts of the patient's physiological status through big data analysis and visualization technologies for medical staff to remotely monitor and diagnose.

[0128] In this link, the system uses the cloud platform and Internet of Things technologies to achieve remote medical support according to the generated warning signals. Specifically, the generation of warning signals means that there are potential health risks in the patient's physiological status, and the system uploads and stores them through the cloud platform. The cloud platform integrates big data analysis and visualization technologies to process the data collected from various monitoring devices in real time to generate detailed reports on the patient's physiological status and trend analysis charts. These reports not only include real-time physiological parameters such as the current values of electrocardiogram, oxygen saturation, and blood pressure, but also the change trends of historical data, providing intuitive visual information support for medical staff. Through this comprehensive information display, doctors can quickly evaluate the patient's health status and make more effective medical decisions.

[0129] This method has important practical significance and application value in medical monitoring. Through the remote medical support of the cloud platform, medical staff can access the patient's health data anytime and anywhere, especially obtaining the dynamic changes of physiological indicators in a timely manner at every critical moment. This real-time remote monitoring ability not only improves the response speed of medical services, but also enables necessary intervention measures to be taken promptly in case of emergencies, reducing the incidence of adverse events in patients. For example, in the face of serious diseases or the postoperative recovery stage, remote monitoring can ensure that the medical team can promptly detect the abnormal changes of the patient and thus take immediate countermeasures to ensure the patient's life safety and recovery.

[0130] In the specific implementation process, the system first transmits the generated warning signals to the cloud platform through Internet of Things technology. When abnormal signals of electrocardiogram, oxygen saturation or blood pressure are detected, the system immediately starts the data upload program. This process relies on efficient wireless communication technologies such as Bluetooth, ZigBee or 5G to transmit the monitoring data and warning information to the cloud server in real time. The uploaded data includes the current physiological parameter values, historical data, and the corresponding warning signals. This Internet of Things-based architecture ensures low latency and high reliability of data transmission, enabling medical staff to quickly obtain the latest health information of patients.

[0131] Next, the cloud platform will process the received patient data using big data analysis technology. Specifically, the system will perform real-time analysis on various physiological indicators and compare them with historical data to identify trend changes. For example, if the electrocardiogram monitoring data shows that the heart rate fluctuates multiple times within a short period, the system will automatically generate a detailed report explaining the change trend, fluctuation range of the heart rate and its possible clinical significance. At the same time, the system will also use data visualization technology to present the analysis results in the form of charts, facilitating doctors and medical staff to quickly understand the patient's health status. Such dynamic reports can be not only simple numerical values but also trend line charts, helping the medical team to clearly grasp the patient's condition changes at a glance.

[0132] Finally, medical staff will access the cloud platform through a computer or mobile device to view the patient's physiological data and analysis reports in real time. At this time, doctors can use the remote monitoring function to view and evaluate the patient's health status at any time. For example, in the case of first aid or intensive care, doctors can quickly obtain the electrocardiogram waveform and oxygen saturation changes of the patient and judge whether immediate intervention measures are needed based on this information. Through this method, the team can better coordinate medical resources, ensure a rapid response in case of emergencies, and make scientific and effective medical decisions. In addition, doctors can also conduct remote consultations on the cloud platform, communicate with other experts in real time, share patient data, and further improve the accuracy and timeliness of clinical decisions. The combination of this cloud platform and Internet of Things technology not only optimizes the medical service process but also improves the overall quality of patient care.

[0133] It can be seen that according to the physiological state of the patient, multi-modal physiological data of the patient is collected using a flexible sensor and a wireless electrode; according to the collected multi-modal physiological data, signal processing and transmission are performed using an anti-interference algorithm and wireless communication technology; the transmitted multi-modal physiological data is received and real-time analysis is performed using an intelligent algorithm to generate a warning signal; according to the warning signal, remote medical support is realized using a cloud platform and Internet of Things technology; wherein, the cloud platform generates a real-time report of the patient's physiological state and a trend analysis chart through big data analysis and visualization technology for medical staff to remotely monitor and diagnose, so as to achieve efficient, continuous, and intelligent medical wireless monitoring and provide a better monitoring experience for the patient.

[0134] Another embodiment of the present invention provides a wireless monitoring system. Refer to Figure 3 , the system may include:

[0135] An acquisition module 301, configured to collect multi-modal physiological data of a patient according to the physiological state of the patient using a flexible sensor and a wireless electrode, wherein the multi-modal physiological data includes electrocardiogram, oxygen saturation, and blood pressure data, and the flexible sensor realizes high-precision data acquisition through nanomaterials and microelectromechanical system technology, while ensuring wearing comfort and stability for long-term use;

[0136] A processing module 302, configured to perform signal processing and transmission on the collected multi-modal physiological data using an anti-interference algorithm and wireless communication technology, wherein the anti-interference algorithm eliminates noise and interference in the signal transmission process through adaptive filtering and spectrum analysis technology to ensure the accuracy and stability of the data, and the wireless communication technology realizes efficient data transmission through a hybrid network of Bluetooth, ZigBee, and 5G;

[0137] An analysis module 303, configured to receive the transmitted multi-modal physiological data and perform real-time analysis using an intelligent algorithm, wherein the intelligent algorithm automatically identifies electrocardiogram abnormalities, oxygen saturation drops, and / or blood pressure fluctuations through deep learning and pattern recognition technology to generate a warning signal;

[0138] A monitoring module 304, configured to realize remote medical support using a cloud platform and Internet of Things technology according to the warning signal; wherein, the cloud platform generates a real-time report of the patient's physiological state and a trend analysis chart through big data analysis and visualization technology for medical staff to remotely monitor and diagnose.

[0139] It can be seen that according to the physiological state of the patient, multi-modal physiological data of the patient is collected by using a flexible sensor and a wireless electrode; according to the collected multi-modal physiological data, signal processing and transmission are carried out by using an anti-interference algorithm and wireless communication technology; the transmitted multi-modal physiological data is received, and real-time analysis is carried out by using an intelligent algorithm to generate a warning signal; according to the warning signal, remote medical support is realized by using a cloud platform and Internet of Things technology; wherein, the cloud platform generates a real-time report of the patient's physiological state and a trend analysis chart through big data analysis and visualization technology for medical staff to remotely monitor and diagnose, so as to realize efficient, continuous, and intelligent medical wireless monitoring and provide a better monitoring experience for patients.

[0140] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, and wherein the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0141] Specifically, in this embodiment, the above storage medium can be configured to store a computer program for executing the following steps:

[0142] S201, according to the physiological state of the patient, use a flexible sensor and a wireless electrode to collect multi-modal physiological data of the patient, wherein the multi-modal physiological data includes electrocardiogram, oxygen saturation, and blood pressure data, and the flexible sensor realizes high-precision data collection through nanomaterials and microelectromechanical system technology, while ensuring wearing comfort and stability for long-term use;

[0143] S202, according to the collected multi-modal physiological data, use an anti-interference algorithm and wireless communication technology for signal processing and transmission, wherein the anti-interference algorithm eliminates noise and interference in the signal transmission process through adaptive filtering and spectrum analysis technology to ensure the accuracy and stability of the data, and the wireless communication technology realizes efficient data transmission through a hybrid network of Bluetooth, ZigBee, and 5G;

[0144] S203, receive the transmitted multi-modal physiological data, and perform real-time analysis by using an intelligent algorithm, wherein the intelligent algorithm automatically identifies electrocardiogram abnormalities, oxygen saturation drops, and / or blood pressure fluctuations through deep learning and pattern recognition technology to generate a warning signal;

[0145] S204, according to the warning signal, use a cloud platform and Internet of Things technology to realize remote medical support; wherein, the cloud platform generates a real-time report of the patient's physiological state and a trend analysis chart through big data analysis and visualization technology for medical staff to remotely monitor and diagnose.

[0146] It can be seen that according to the physiological state of the patient, a flexible sensor and a wireless electrode are used to collect the multi-modal physiological data of the patient; according to the collected multi-modal physiological data, an anti-interference algorithm and wireless communication technology are used for signal processing and transmission; the transmitted multi-modal physiological data is received, and an intelligent algorithm is used for real-time analysis to generate a warning signal; according to the warning signal, a cloud platform and Internet of Things technology are used to achieve remote medical support; wherein, the cloud platform generates a real-time report of the patient's physiological state and a trend analysis chart through big data analysis and visualization technology for medical staff to remotely monitor and diagnose, so as to realize efficient, continuous, and intelligent medical wireless monitoring and provide a better monitoring experience for patients.

[0147] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0148] Specifically, the above electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0149] Specifically, in this embodiment, the above processor may be configured to execute the following steps through a computer program:

[0150] S201, according to the physiological state of the patient, use a flexible sensor and a wireless electrode to collect the multi-modal physiological data of the patient, wherein the multi-modal physiological data includes electrocardiogram, oxygen saturation, and blood pressure data, and the flexible sensor realizes high-precision data collection through nanomaterials and microelectromechanical system technology, while ensuring wearing comfort and stability for long-term use;

[0151] S202, according to the collected multi-modal physiological data, use an anti-interference algorithm and wireless communication technology for signal processing and transmission, wherein the anti-interference algorithm eliminates noise and interference in the signal transmission process through adaptive filtering and spectrum analysis technology to ensure the accuracy and stability of the data, and the wireless communication technology realizes efficient data transmission through a hybrid network of Bluetooth, ZigBee, and 5G;

[0152] S203, receive the transmitted multi-modal physiological data and perform real-time analysis using an intelligent algorithm, wherein the intelligent algorithm automatically identifies electrocardiogram abnormalities, oxygen saturation drops, and / or blood pressure fluctuations through deep learning and pattern recognition technology to generate a warning signal;

[0153] S204. Implement remote medical support based on the warning signal by using the cloud platform and Internet of Things technology. Among them, the cloud platform generates real-time reports and trend analysis charts of the patient's physiological state through big data analysis and visualization technology for medical staff to remotely monitor and diagnose.

[0154] It can be seen that multi-modal physiological data of the patient is collected by using flexible sensors and wireless electrodes according to the patient's physiological state; signal processing and transmission are performed by using anti-interference algorithms and wireless communication technology according to the collected multi-modal physiological data; the received multi-modal physiological data is analyzed in real time by using intelligent algorithms to generate warning signals; remote medical support is implemented by using the cloud platform and Internet of Things technology according to the warning signals. Among them, the cloud platform generates real-time reports and trend analysis charts of the patient's physiological state through big data analysis and visualization technology for medical staff to remotely monitor and diagnose, so as to achieve efficient, continuous, and intelligent medical wireless monitoring and provide a better monitoring experience for patients.

[0155] The structure, features, and function effects of the present invention have been described in detail based on the embodiments shown in the drawings. The above is only the preferred embodiment of the present invention, but the present invention is not limited to the scope defined by the drawings. Any changes made according to the concept of the present invention, or equivalent embodiments modified to equivalent changes, still within the spirit covered by the specification and drawings, should be within the protection scope of the present invention.

Claims

1. A wireless monitoring method, characterized in that, The method includes: According to the physiological state of the patient, multi-modal physiological data of the patient is collected using a flexible sensor and a wireless electrode. Among them, the multi-modal physiological data includes electrocardiogram, oxygen saturation, and blood pressure data. The flexible sensor realizes high-precision data collection through nanomaterials and micro-electromechanical system technology, while ensuring wearing comfort and stability for long-term use. According to the collected multi-modal physiological data, signal processing and transmission are performed using an anti-interference algorithm and wireless communication technology. Among them, the anti-interference algorithm eliminates noise and interference during signal transmission through adaptive filtering and spectrum analysis technology, ensuring the accuracy and stability of the data. The wireless communication technology realizes efficient data transmission through a hybrid network of Bluetooth, ZigBee, and 5G. Receive the transmitted multi-modal physiological data and perform real-time analysis using an intelligent algorithm. Among them, the intelligent algorithm automatically identifies electrocardiogram abnormalities, oxygen saturation drops, and / or blood pressure fluctuations through deep learning and pattern recognition technology, and generates warning signals. According to the warning signals, remote medical support is realized using a cloud platform and Internet of Things technology. Among them, the cloud platform generates real-time reports and trend analysis charts of the patient's physiological state through big data analysis and visualization technology for medical staff to remotely monitor and diagnose.

2. The method according to claim 1, characterized in that, The step of collecting the multi-modal physiological data of the patient according to the physiological state of the patient using a flexible sensor and a wireless electrode, where the multi-modal physiological data includes electrocardiogram, oxygen saturation, and blood pressure data, and the flexible sensor realizes high-precision data collection through nanomaterials and micro-electromechanical system technology, while ensuring wearing comfort and stability for long-term use, includes: According to the physiological state of the patient, the flexible sensor and the wireless electrode are deployed at key parts of the patient's body. The flexible sensor is made of nanomaterials and micro-electromechanical system technology, fits the skin surface, and ensures wearing comfort. The wireless electrode is connected to the monitoring and control device through Bluetooth or ZigBee technology to realize wireless data transmission. According to the deployed flexible sensor and wireless electrode, electrocardiogram data is collected in real time. Among them, the flexible electrocardiogram sensor is used to detect the electrical activity of the heart to generate the original electrocardiogram signal, and the signal amplifier and filter are used to preprocess the original electrocardiogram signal to remove noise and interference to obtain electrocardiogram waveform data. The oxygen saturation data is collected in real time using a flexible optical sensor. Among them, the flexible optical sensor emits red light and infrared light to detect the ratio of oxyhemoglobin and deoxyhemoglobin in the blood, and the signal processing algorithm is used to calculate the oxygen saturation data and remove motion artifacts and ambient light interference. The blood pressure data is collected in real time using a flexible pressure sensor module. Among them, the flexible pressure sensor is used to detect the pressure change of the arterial wall to generate the original blood pressure signal, and the signal processing algorithm is used to calculate the blood pressure data and remove noise and interference. The collected electrocardiogram waveform data, oxygen saturation data, and blood pressure data are further filtered and denoised to generate a multi-modal physiological data set.

3. The method according to claim 2, characterized in that, Based on the collected multimodal physiological data, signal processing and transmission are carried out using anti-interference algorithms and wireless communication technologies. Among them, the anti-interference algorithm eliminates noise and interference during signal transmission through adaptive filtering and spectrum analysis technologies to ensure the accuracy and stability of the data. The wireless communication technology realizes efficient data transmission through a hybrid network of Bluetooth, ZigBee, and 5G, including: Based on the multimodal physiological data, an adaptive filtering algorithm is used to eliminate noise; among them, For electrocardiogram waveform data, an adaptive filter is used to remove baseline drift and high-frequency noise to generate filtered electrocardiogram data; for oxygen saturation data, an adaptive filter is used to remove motion artifacts and ambient light interference to generate filtered oxygen saturation data; for blood pressure data, an adaptive filter is used to remove pressure fluctuation noise to generate filtered blood pressure data; Based on the filtered multimodal physiological data, spectrum analysis technology is used for signal enhancement; among them, For electrocardiogram waveform data, fast Fourier transform is used to analyze the spectral characteristics to enhance the effective frequency band of the electrocardiogram signal and generate enhanced electrocardiogram waveform data; for oxygen saturation data, spectrum analysis technology is used to identify the effective signal frequency band to enhance the stability of the oxygen saturation data and generate enhanced oxygen saturation data; for blood pressure data, spectrum analysis technology is used to remove low-frequency interference to enhance the accuracy of the blood pressure data and generate enhanced blood pressure data; Based on the enhanced multimodal physiological data, a hybrid networking technology is used for wireless transmission; among them, Short-distance data in the multimodal physiological data is transmitted through Bluetooth technology to ensure low power consumption and real-time performance; medium-distance data in the multimodal physiological data is transmitted through ZigBee technology to ensure stability and anti-interference ability; long-distance data in the multimodal physiological data is transmitted through 5G technology to ensure high-speed and large-capacity transmission.

4. The method according to claim 3, wherein The received transmitted multimodal physiological data is analyzed in real time using intelligent algorithms. Among them, the intelligent algorithm automatically identifies electrocardiogram abnormalities, oxygen saturation drops, and / or blood pressure fluctuations through deep learning and pattern recognition technologies to generate warning signals, including: Based on the enhanced electrocardiogram waveform data, a deep learning model is used for electrocardiogram abnormality detection. Among them, a convolutional neural network is used to extract electrocardiogram waveform features, identify abnormal waveforms, and classify abnormal types through pattern recognition technology to generate electrocardiogram abnormality warning signals; Based on the enhanced oxygen saturation data, a time series analysis model is used for oxygen saturation drop detection. Among them, a long short-term memory network is used to analyze the change trend of oxygen saturation, identify abnormal drops, and generate oxygen saturation drop warning signals through threshold judgment; Based on the enhanced blood pressure data, an anomaly detection algorithm is used for blood pressure fluctuation detection. Among them, an isolation forest algorithm is used to identify abnormal blood pressure fluctuations and generate blood pressure fluctuation warning signals through pattern recognition technology; Based on the generated electrocardiogram abnormality warning signals, oxygen saturation drop warning signals, and blood pressure fluctuation warning signals, a comprehensive warning signal is generated.

5. A wireless monitoring system, characterized in that, The system includes: The acquisition module is used to collect multimodal physiological data of patients according to their physiological states by using flexible sensors and wireless electrodes. Among them, the multimodal physiological data includes electrocardiogram (ECG), oxygen saturation, and blood pressure data. The flexible sensors achieve high-precision data acquisition through nanomaterials and microelectromechanical systems technology, while ensuring wearing comfort and stability for long-term use. The processing module is used to perform signal processing and transmission according to the collected multimodal physiological data by using anti-interference algorithms and wireless communication technology. Among them, the anti-interference algorithm eliminates noise and interference during signal transmission through adaptive filtering and spectrum analysis technology to ensure the accuracy and stability of the data. The wireless communication technology realizes efficient data transmission through a hybrid network of Bluetooth, ZigBee, and 5G. The analysis module is used to receive the transmitted multimodal physiological data and perform real-time analysis by using intelligent algorithms. Among them, the intelligent algorithm automatically identifies abnormal ECG, decreased oxygen saturation, and / or blood pressure fluctuations through deep learning and pattern recognition technology to generate warning signals. The monitoring module is used to provide remote medical support according to the warning signals by using cloud platforms and Internet of Things technology. Among them, the cloud platform generates real-time reports and trend analysis charts of the patient's physiological state through big data analysis and visualization technology for medical staff to remotely monitor and diagnose.

6. The system according to claim 5, characterized in that, The acquisition module is specifically used for: According to the patient's physiological state, deploy flexible sensors and wireless electrodes at key parts of the patient's body. Among them, the flexible sensors are made through nanomaterials and microelectromechanical systems technology, conform to the skin surface to ensure wearing comfort, and the wireless electrodes are connected to the monitoring and control device through Bluetooth or ZigBee technology to achieve wireless data transmission. According to the deployed flexible sensors and wireless electrodes, collect ECG data in real time. Among them, use flexible ECG sensors to detect cardiac electrical activities to generate raw ECG signals, and use signal amplifiers and filters to preprocess the raw ECG signals to remove noise and interference to obtain ECG waveform data. Use flexible optical sensors to collect oxygen saturation data in real time. Among them, emit red light and infrared light through the flexible optical sensors to detect the ratio of oxyhemoglobin and deoxyhemoglobin in the blood, use signal processing algorithms to calculate the oxygen saturation data, and remove motion artifacts and ambient light interference. Use the flexible pressure sensor module to collect blood pressure data in real time. Among them, detect the pressure changes in the arterial wall through the flexible pressure sensor to generate raw blood pressure signals, use signal processing algorithms to calculate the blood pressure data, and remove noise and interference. Perform further filtering and denoising on the collected ECG waveform data, oxygen saturation data, and blood pressure data to generate a multimodal physiological data set.

7. The system according to claim 6, characterized in that, The processing module is specifically used for: Perform noise cancellation on the multimodal physiological data by using an adaptive filtering algorithm. Among them, For electrocardiogram waveform data, an adaptive filter is used to remove baseline drift and high-frequency noise, generating filtered electrocardiogram data; for oxygen saturation data, an adaptive filter is used to remove motion artifacts and ambient light interference, generating filtered oxygen saturation data; for blood pressure data, an adaptive filter is used to remove pressure fluctuation noise, generating filtered blood pressure data; According to the filtered multi-modal physiological data, signal enhancement is performed using spectral analysis technology; among them, For electrocardiogram waveform data, fast Fourier transform is used to analyze spectral characteristics, enhance the effective frequency band of the electrocardiogram signal, and generate enhanced electrocardiogram waveform data; for oxygen saturation data, spectral analysis technology is used to identify the effective signal frequency band, enhance the stability of the oxygen saturation data, and generate enhanced oxygen saturation data; for blood pressure data, spectral analysis technology is used to remove low-frequency interference, enhance the accuracy of the blood pressure data, and generate enhanced blood pressure data; According to the enhanced multi-modal physiological data, wireless transmission is performed using a hybrid networking technology; among them, Short-distance data in the multi-modal physiological data is transmitted through Bluetooth technology to ensure low power consumption and real-time performance; medium-distance data in the multi-modal physiological data is transmitted through ZigBee technology to ensure stability and anti-interference ability; long-distance data in the multi-modal physiological data is transmitted through 5G technology to ensure high-speed and large-capacity transmission.

8. The system according to claim 7, wherein The analysis module is specifically used for: According to the enhanced electrocardiogram waveform data, deep learning models are used for electrocardiogram abnormality detection. Among them, convolutional neural networks are used to extract electrocardiogram waveform features, identify abnormal waveforms, and classify abnormal types through pattern recognition technology, generating electrocardiogram abnormality warning signals; According to the enhanced oxygen saturation data, time series analysis models are used for oxygen saturation drop detection. Among them, long short-term memory networks are used to analyze the change trend of oxygen saturation, identify abnormal drops, and generate oxygen saturation drop warning signals through threshold judgment; According to the enhanced blood pressure data, anomaly detection algorithms are used for blood pressure fluctuation detection. Among them, the isolation forest algorithm is used to identify abnormal blood pressure fluctuations, and pattern recognition technology is used to generate blood pressure fluctuation warning signals; According to the generated electrocardiogram abnormality warning signals, oxygen saturation drop warning signals, and blood pressure fluctuation warning signals, a comprehensive warning signal is generated.

9. A storage medium, characterized in that, The computer program is stored in the storage medium, where the computer program is set to execute the method described in any one of claims 1-4 when running.

10. An electronic device, comprising a memory and a processor, characterized in that, The computer program is stored in the memory, and the processor is set to run the computer program to execute the method described in any one of claims 1-4.

Images