Data uplink transmission method and system of intelligent hospital Internet of Things medical terminal equipment

Abstract

The invention discloses a data uplink transmission method and system for intelligent hospital Internet of Things medical terminal equipment, and relates to the technical field of Internet of Things medical terminals, and the method comprises the following steps: obtaining various parameter information generated in the uploading process of an electrocardiograph monitor data packet, including data processing capability and network reliability; by acquiring data processing capacity and network reliability parameters in the uploading process of the electrocardiograph monitor, the system accurately analyzes buffer overflow and packet loss retransmission mechanism failure, and a transmission quality coefficient is generated in combination with machine learning. The intelligent mechanism detects the high-risk uploading process in real time, data packet error sequence or loss is reduced, the integrity of electrocardiogram (ECG) data is ensured, and misdiagnosis is effectively avoided. The high-risk uploading process is divided into an unstable type, a continuous type and a burst type, and corresponding early warning measures are taken respectively, so that timely processing of critical data is ensured, the safety and stability of data transmission are improved, and the safety of a patient is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things medical terminals, and in particular to a data uplink transmission method and system for Internet of Things medical terminal equipment in a smart hospital. Background Art

[0002] The data uplink transmission method of IoT medical terminal devices in smart hospitals refers to uploading patient physiological data, equipment operating status and other information collected by various medical terminal devices to the hospital's central server or cloud platform through the network for medical staff to analyze and process. This process usually relies on Internet of Things (IoT) technology. The terminal device connects to the data center through a wireless network (such as Wi-Fi, Bluetooth, and cellular networks) to complete real-time data transmission. Its core goal is to ensure that data can be uploaded accurately, timely, and securely to support remote diagnosis and treatment, health monitoring, and intelligent management of equipment status.

[0003] Specifically, the uplink data transmission of medical terminal devices must first be pre-processed by the data acquisition module. For example, the ECG monitor will filter and integrate the collected raw data, and then package the data for transmission through the adapted communication protocol. Encryption and data verification technology are usually used to ensure the security and integrity of the data during transmission. The uploaded data will be further analyzed according to different medical needs, such as remote monitoring of the patient's health status or prediction of the operation and maintenance of medical equipment. In addition, the efficiency and stability of uplink transmission are crucial to the operation of smart hospitals, especially in high-concurrency situations, to ensure the rapid response of the system and ensure that medical staff can obtain key medical information in real time.

[0004] The prior art has the following deficiencies: If the ECG monitor uploads data packets in the wrong order and the system fails to correctly perceive and process them, serious consequences may occur. First, these data contain the patient's ECG information, which is crucial for doctors to judge heart health. The disordered order may cause the system to be unable to reconstruct the complete ECG, affecting the doctor's accurate analysis and diagnosis, thereby delaying treatment decisions. Secondly, the wrong order may lead to data processing errors or loss of ECG event records, affecting the identification of abnormal events and arrhythmias, and delaying the response to critical situations. In addition, the disordered order may also cause data analysis and storage problems, affecting subsequent medical records and medical record compilation. In terms of legal liability, data transmission errors may lead to medical errors or patient damage, and hospitals and medical personnel may face legal proceedings and accountability, seriously affecting the reputation and trust of medical institutions.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a data uplink transmission method and system for medical terminal equipment of the Internet of Things in a smart hospital. By obtaining the data processing capacity and network reliability parameters in the upload process of the electrocardiogram monitor, the system can accurately analyze the buffer overflow and the failure of the packet loss and retransmission mechanism, and generate a transmission quality coefficient in combination with a machine learning model. This intelligent perception mechanism detects high-risk upload processes in real time, significantly reduces the misordering or loss of data packets, ensures the integrity and correct order of electrocardiogram (ECG) data, and effectively avoids misdiagnosis or missed diagnosis due to data anomalies. The high-risk upload process is divided into unstable, continuous and sudden types in the scheme, and corresponding early warning measures are taken for different types. Unstable and continuous processes issue a first or second level serious warning to prompt medical personnel to check, while the sudden type is recorded for subsequent maintenance to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: comprising the following steps: Obtain various parameter information generated during the ECG monitor data packet upload process, including data processing capability and network reliability; Under the detection window, the acquired data processing capacity and network reliability are analyzed, and the analyzed data processing capacity and network reliability are input into the pre-learned machine model. The transmission quality coefficient is generated through the learning model, and the data packet upload process of the ECG monitor is intelligently sensed based on the transmission quality coefficient. Based on the results of machine learning output, the ECG monitor data packet upload process is divided into a high-risk upload process or a low-risk upload process, and an intelligent evaluation is performed on the abnormal upload process of the ECG monitor data packet upload process; For the high-risk upload process of the output, continuously obtain the upload process information of the ECG monitor data packet, and classify the high-risk upload process into an accidental state or a non-accidental state; Different early warning measures are taken for different high-risk upload processes.

[0008] Preferably, the data processing capability includes buffer overflow information, which is used to measure the effectiveness and carrying capacity of the buffer when the system processes data, and reflects the processing capability of the device when facing the input data stream. The network reliability includes packet loss and retransmission mechanism failure information, which measures the network's ability to handle lost data packets during data transmission and reflects the reliability of the network.

[0009] Preferably, under the detection window, after performing abnormal analysis on the hedge area overflow information and the packet loss retransmission mechanism failure information, a hedge area overflow index and a packet loss retransmission mechanism failure index are generated respectively, and the hedge area overflow index and the packet loss retransmission mechanism failure index are input into a pre-learned machine model, and a transmission quality coefficient is generated through the learning model, and the ECG monitor data packet upload process is intelligently perceived based on the transmission quality coefficient.

[0010] Preferably, in the detection window, after performing abnormal analysis on the hedge area overflow information, the specific steps of generating the hedge area overflow index are as follows: In the detection window, data is collected in real time. The collected data includes data arrival rate, data processing capacity, buffer capacity and current buffer usage. The data arrival rate is calibrated as , the data processing capability is calibrated as , the buffer capacity is marked as B capacity And the current buffer usage is marked as ; According to the collected parameters, the data inflow rate is calculated to determine whether there is an overflow risk. The calculation expression is as follows: , where R in Indicates the data inflow rate; Considering the limitation of buffer capacity, the buffer conflict index is calculated. The calculation expression is as follows: , where C index represents the buffer conflict index; By combining the data inflow rate and the buffer conflict index, the hedge area overflow index is generated. The calculation expression is as follows: index =(R in ·(1-C index )) α ·(1+C index ) β , where O index represents the hedge overflow index, α is the data inflow rate weight, and β is the buffer conflict index weight.

[0011] Preferably, in the detection window, after performing abnormal analysis on the packet loss retransmission mechanism failure information, the specific steps of generating the packet loss retransmission mechanism failure index are as follows: In the detection window, various data parameters are collected, including the total number of data packets sent N s , the number of successfully received data packets N r And the number of retransmissions N t ; Calculate the packet loss rate. The calculation expression is as follows: , where P lossIndicates the packet loss rate, which is used to evaluate the loss of data packets during transmission; Calculate the retransmission efficiency index. The calculation expression is as follows: , where R eff Represents the retransmission efficiency index, which is used to reflect the effectiveness of the retransmission mechanism; The packet loss rate and retransmission efficiency are combined to generate the packet loss retransmission mechanism failure index. The calculation expression is as follows: R fail =(P loss ·(1-R eff )) θ , where R fail represents the failure index of packet loss and retransmission mechanism, and θ is the weight factor, which is used to adjust the relative importance of packet loss rate and retransmission efficiency.

[0012] Preferably, the hedge area overflow index O index and packet loss retransmission mechanism failure index R fail Input into the pre-learned machine model, and generate the transmission quality coefficient TQ through the machine model according to the following formula: , where h1 and h2 are the overflow index of the hedge area O index and packet loss retransmission mechanism failure index R fail Pre-set proportional coefficient, and h1 and h2 are both greater than 0.

[0013] Preferably, the generated transmission quality coefficient is compared with a preset transmission quality coefficient reference threshold, and the comparison result is as follows: If the transmission quality coefficient is greater than or equal to a preset transmission quality coefficient reference threshold, the ECG monitor data packet upload process is classified as a high-risk upload process; If the transmission quality coefficient is less than a preset transmission quality coefficient reference threshold, the ECG monitor data packet upload process is classified as a low-risk upload process.

[0014] Preferably, for the high-risk uploading process of the output, a plurality of transmission quality coefficients generated during the uploading process of the ECG monitor data packet are continuously obtained to establish a data set for comprehensive analysis; The average value and standard deviation of several mass transfer coefficients in the data set are calculated, and the calculated average value and standard deviation of the mass transfer coefficient are compared and analyzed with the preset mass transfer coefficient average value reference threshold and the preset mass transfer coefficient standard deviation reference threshold, respectively. The analysis results are as follows; If the mass transfer coefficient average value is greater than or equal to a preset mass transfer coefficient average value reference threshold and the mass transfer coefficient standard deviation is less than a preset mass transfer coefficient standard deviation reference threshold, the high-risk upload process is classified as unstable; If the average value of the mass transfer coefficient is greater than a preset reference threshold value of the average value of the mass transfer coefficient, the high-risk uploading process is classified as continuous; If the mass transfer coefficient average value is less than a preset mass transfer coefficient average value reference threshold and the mass transfer coefficient standard deviation is less than a preset mass transfer coefficient standard deviation reference threshold, the high-risk upload process is classified as a burst type.

[0015] The data uplink transmission system of the IoT medical terminal equipment in smart hospitals includes parameter acquisition module, data analysis and model input module, intelligent risk assessment module, high-risk status monitoring module, and early warning module: The parameter acquisition module obtains various parameter information generated during the upload of ECG monitor data packets, including data processing capability and network reliability; The data analysis and model input module analyzes the acquired data processing capability and network reliability in the detection window, inputs the analyzed data processing capability and network reliability into the pre-learned machine model, generates the transmission quality coefficient through the learning model, and performs intelligent perception of the ECG monitor data packet upload process based on the transmission quality coefficient; The intelligent risk assessment module divides the ECG monitor data packet upload process into a high-risk upload process or a low-risk upload process based on the results of machine learning output, and performs intelligent assessment on abnormal upload processes in the ECG monitor data packet upload process; The high-risk state monitoring module continuously obtains the upload process information of the ECG monitor data packet for the output high-risk upload process, and divides the high-risk upload process into an accidental state or a non-accidental state; The early warning module takes different early warning measures for different high-risk upload processes.

[0016] In the above technical solution, the technical effects and advantages provided by the present invention are: By acquiring the data processing capacity and network reliability parameters during the upload process of the ECG monitor, the system can accurately analyze the buffer overflow and the failure of the packet loss and retransmission mechanism, and generate the transmission quality coefficient in combination with the machine learning model. This intelligent perception mechanism ensures that when potential problems occur during the data packet upload process, the system can detect and identify high-risk upload processes in real time, greatly reducing the situation of misordering or loss of data packets. Through continuous monitoring and dynamic adjustment, the integrity and correct order of electrocardiogram (ECG) data are ensured, effectively avoiding misdiagnosis or missed diagnosis caused by abnormal data. This provides doctors and automatic analysis systems with more reliable ECG data, ensuring accurate analysis and judgment of patients' heart health status.

[0017] Through intelligent evaluation, the present invention further divides high-risk upload processes into unstable, continuous and sudden types, and takes corresponding early warning measures according to different risk types. For unstable and continuous upload processes, a level one or level two serious warning is issued to prompt relevant medical personnel to conduct inspections and interventions to ensure the reliability of data transmission. For sudden types, records are kept to avoid excessive intervention but provide a reference for subsequent maintenance. This hierarchical early warning mechanism can effectively avoid potential risks in transmission, ensure that critical data can be processed in a timely manner, reduce the risk of medical errors, and improve the security and stability of data transmission, thereby protecting the lives of patients and improving the hospital's operational efficiency and reputation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0019] Figure 1 The present invention is a flow chart of the method.

[0020] Figure 2 It is a schematic diagram of the modules of the present invention. DETAILED DESCRIPTION

[0021] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0022] The present invention provides Figure 1 The data uplink transmission method of the smart hospital IoT medical terminal device shown includes the following steps: Obtain various parameter information generated during the ECG monitor data packet upload process, including data processing capability and network reliability; Data processing capability includes buffer overflow information, which is used to measure the effectiveness and carrying capacity of the buffer when the system processes data, and reflects the processing capability of the device when facing input data streams. Network reliability includes packet loss retransmission mechanism failure information, which measures the network's ability to handle lost data packets during data transmission and reflects the reliability of the network. Under the detection window, the acquired data processing capacity and network reliability are analyzed, and the analyzed data processing capacity and network reliability are input into the pre-learned machine model. The transmission quality coefficient is generated through the learning model, and the data packet upload process of the ECG monitor is intelligently sensed based on the transmission quality coefficient. Under the detection window, after abnormal analysis of the hedge area overflow information and the packet loss retransmission mechanism failure information, the hedge area overflow index and the packet loss retransmission mechanism failure index are generated respectively, and the hedge area overflow index and the packet loss retransmission mechanism failure index are input into the pre-learned machine model, and the transmission quality coefficient is generated through the learning model. Based on the transmission quality coefficient, the ECG monitor data packet upload process is intelligently perceived; During the upload of ECG monitor data packets, changes in the buffer overflow index will indeed affect the judgment of doctors or automatic analysis systems, and may lead to misdiagnosis or missed diagnosis; the buffer overflow index reflects the system's ability to process data, especially under high data traffic or processing load; buffer overflow will cause some ECG data to be lost or transmitted in a wrong order, making the ECG waveform incomplete or distorted, and key cardiac signals (such as P waves, QRS waves, T waves, etc.) may not be accurately captured or arranged incorrectly; such data abnormalities will directly affect the diagnosis of acute conditions such as arrhythmias, myocardial ischemia, and cardiac arrest, because the identification of these conditions depends on complete, continuous and accurate ECG data; if doctors or automatic analysis systems receive erroneous or missing ECG data, they may misjudge it as normal, or fail to make a correct diagnosis and intervention in time in actual critical situations; therefore, data loss and misordering caused by buffer overflow greatly increase the risk of misdiagnosis or missed diagnosis, which may delay the patient's treatment and even endanger his life; In the detection window, after performing an abnormal analysis on the hedge area overflow information, the specific steps to generate the hedge area overflow index are as follows: In the detection window, data is collected in real time. The collected data includes data arrival rate, data processing capacity, buffer capacity and current buffer usage. The data arrival rate is calibrated as , the data processing capability is calibrated as , the buffer capacity is marked as B capacity And the current buffer usage is marked as , data arrival rate Indicates the number of data packets arriving within T time, data processing capacity Indicates the number of packets that can be processed within T time, and the buffer capacity B capacity Indicates the maximum number of packets that can be stored in the buffer zone and the current buffer usage Indicates the number of packets currently used by the buffer; It should be noted that the above T time is selected as a relatively short time period. The time within the time period is not specifically limited here and can be set according to actual conditions. Its purpose is to monitor the situation during the network operation within the T time, so as to monitor the situation in different time periods (within the T time) during the network operation in this way; According to the collected parameters, the data inflow rate is calculated to determine whether there is an overflow risk. The calculation expression is as follows: , where R in Indicates the data inflow rate; It should be noted that overflow risk refers to the risk of data loss or system performance degradation during data transmission and processing due to the inability of the buffer to process the received data in a timely manner; this risk usually occurs in high data traffic environments, especially when the data arrival speed exceeds the system processing capacity; overflow may result in incomplete information, affecting data accuracy and system stability; Types of spillover risks include: 1. Data loss risk: When the buffer is full, newly arrived data packets may be discarded, resulting in the loss of important information; this is particularly dangerous in critical applications such as medical monitoring and financial transactions; 2. System performance degradation: Frequent overflow events may cause the system to respond more slowly and increase latency, thus affecting user experience and real-time decision-making capabilities; 3. Abnormal behavior risk: Overflow may cause system errors or crashes, resulting in device restarts or service interruptions, affecting normal operation; 4. Data inconsistency risk: When the buffer overflows and data is retransmitted, data inconsistency may occur, affecting subsequent data analysis and processing; 5. Legal liability risk: In some industries, such as healthcare or finance, data overflow may lead to compliance issues, which in turn may lead to legal liability and compensation; 6. Security risks: Overflows may be exploited by attackers, leading to system vulnerabilities, such as denial of service attacks (DoS), thus affecting system security; By identifying and assessing these overflow risks, the system can take measures to monitor and optimize them to ensure the reliability and stability of data processing; Considering the limitation of buffer capacity, the buffer conflict index is calculated. The calculation expression is as follows: , where C index represents the buffer conflict index; By combining the data inflow rate and the buffer conflict index, the hedge area overflow index is generated, and the calculation expression is as follows: index =(R in ·(1-C index ))α ·(1+C index ) β , where O index represents the overflow index of the hedge area, α is the data inflow rate weight, and β is the buffer conflict index weight; Under the detection window, the calculation expression of the buffer overflow index shows that the larger the performance value of the buffer overflow index generated during the ECG monitor data packet upload process, the greater the pressure on the ECG monitor buffer during the data packet upload process, the less processing capacity, and the data may be lost or misordered due to processing delay or overflow, resulting in an increased probability of abnormalities in the upload process; on the contrary, the smaller the performance value of the buffer overflow index, the more efficient the system is in processing data, the more stable the buffer is, the lower the risk of data loss or misordering is, and the lower the probability of abnormalities in the upload process; During the data packet upload process of the ECG monitor, changes in the packet loss and retransmission mechanism failure index will directly affect the judgment of doctors or automatic analysis systems, and may lead to misdiagnosis or missed diagnosis; the packet loss and retransmission mechanism failure index reflects the system's ability to handle lost data packets during data transmission; if the retransmission mechanism fails, the lost data packets cannot be retransmitted in time or correctly, resulting in incomplete or disordered electrocardiogram (ECG) data; the continuity and integrity of ECG data are the key basis for identifying acute diseases such as arrhythmia, myocardial ischemia, and cardiac arrest; the early identification of these diseases usually relies on accurate analysis of subtle changes in the ECG waveform, and the loss or misorder of data packets will cause key waveform information (such as P wave, QRS wave, T wave, etc.) to be missing or chaotic, thereby affecting the doctor or system's correct judgment of the heart condition; if cardiac abnormalities cannot be identified in a timely and accurate manner, patients may miss the opportunity for treatment, their condition may worsen, or even endanger their lives; therefore, the increase in the packet loss and retransmission mechanism failure index will greatly increase the unreliability in data transmission, and thus significantly increase the risk of misdiagnosis or missed diagnosis, which is crucial for the real-time and accuracy of ECG monitoring; In the detection window, after abnormal analysis of packet loss and retransmission mechanism failure information, the specific steps for generating a packet loss and retransmission mechanism failure index are as follows: In the detection window, various data parameters are collected, including the total number of data packets sent N s , the number of successfully received data packets N r And the number of retransmissions N t , where the total number of packets sent is N s Indicates the total number of packets sent within the detection window and the number of packets successfully received N r Indicates the number of packets successfully received within the detection window and the number of retransmissions N t Indicates the number of retransmissions triggered by packet loss; It should be noted that the method for obtaining the total number of data packets sent, the number of data packets successfully received, and the number of retransmission parameters is as follows: 1. Total number of packets sent Network monitoring tools: Use network monitoring tools such as Wireshark, NetFlow, etc. for real-time traffic analysis. These tools can record the number of packets sent within a specified time window. Application logs: At the application level, you can add logging functionality to your code to count the number of packets sent; for example, increment a counter when each packet is sent. 2. Number of packets successfully received ACK mechanism: In the TCP protocol, the receiver will send an ACK confirmation signal, and the sender can count the number of successfully received data packets based on the number of ACKs received; Network monitoring tools: You can also use network monitoring tools to count the number of successfully received packets through captured network traffic data; analyze inbound packets and confirm their integrity; 3. Number of retransmissions TCP retransmission: In the TCP protocol, the number of retransmissions can be obtained by monitoring the number of retransmission packets; network monitoring tools can provide detailed retransmission packet information; Application layer logging: At the application layer, you can set up retransmission logic after a packet is sent and log the count at each retransmission; for example, after sending a packet, if no ACK is received, increase the retransmission counter; Through these methods, the total number of data packets sent, the number of successful receptions, and the number of retransmissions can be systematically obtained, providing basic data for subsequent network reliability analysis; Calculate the packet loss rate. The calculation expression is as follows: , where P loss Indicates the packet loss rate, which is used to evaluate the loss of data packets during transmission; Calculate the retransmission efficiency index. The calculation expression is as follows: , where R eff Represents the retransmission efficiency index, which is used to reflect the effectiveness of the retransmission mechanism; The packet loss rate and retransmission efficiency are combined to generate the packet loss retransmission mechanism failure index. The calculation expression is as follows: R fail =(P loss ·(1-R eff )) θ , where R fail represents the failure index of packet loss retransmission mechanism, θ is the weight factor, which is used to adjust the relative importance of packet loss rate and retransmission efficiency; Under the detection window, the packet loss and retransmission mechanism failure index calculation expression shows that the larger the performance value of the packet loss and retransmission mechanism failure index generated during the ECG monitor data packet upload process, the worse the network reliability in processing data loss and retransmission, and the higher the possibility that the data packet loss is not timely or correctly retransmitted, thereby increasing the probability of abnormalities in the ECG monitor data packet upload process; conversely, the smaller the performance value of the packet loss and retransmission mechanism failure index, it means that the network retransmission mechanism works normally, the data packet can be retransmitted smoothly, the risk of data loss and misordering during the upload process is reduced, and the probability of abnormalities is also reduced; The hedge area overflow index O index and packet loss retransmission mechanism failure index R fail Input into the pre-learned machine model, and generate the transmission quality coefficient TQ through the machine model according to the following formula: , where h1 and h2 are the overflow index of the hedge area O index and packet loss retransmission mechanism failure index R fail Pre-set proportional coefficient, and h1 and h2 are both greater than 0; In the detection creation window, it can be seen from the transmission quality coefficient calculation expression that the greater the performance value of the hedge area overflow index generated during the uploading of the ECG monitor data packet, the greater the performance value of the packet loss retransmission mechanism failure index, the greater the performance value of the transmission quality coefficient, indicating that the probability of abnormality in the uploading of the ECG monitor data packet is greater; conversely, the smaller the performance value of the hedge area overflow index generated during the uploading of the ECG monitor data packet, the smaller the performance value of the packet loss retransmission mechanism failure index, the smaller the performance value of the transmission quality coefficient, indicating that the probability of abnormality in the uploading of the ECG monitor data packet is smaller; Based on the results of machine learning output, the ECG monitor data packet upload process is divided into a high-risk upload process or a low-risk upload process, and an intelligent evaluation is performed on the abnormal upload process of the ECG monitor data packet upload process; The generated transmission quality coefficient is compared with the preset transmission quality coefficient reference threshold, and the comparison results are as follows: If the transmission quality coefficient is greater than or equal to a preset transmission quality coefficient reference threshold, the ECG monitor data packet upload process is classified as a high-risk upload process; If the transmission quality coefficient is less than a preset transmission quality coefficient reference threshold, the ECG monitor data packet upload process is classified as a low-risk upload process; For the high-risk upload process of the output, continuously obtain the upload process information of the ECG monitor data packet, and divide the high-risk upload process into sudden, unstable and continuous types; For the high-risk uploading process of the output, several transmission quality coefficients generated during several uploading processes of the ECG monitor data packets are continuously obtained to establish a data set for comprehensive analysis; The average value and standard deviation of several mass transfer coefficients in the data set are calculated, and the calculated average value and standard deviation of the mass transfer coefficient are compared and analyzed with the preset mass transfer coefficient average value reference threshold and the preset mass transfer coefficient standard deviation reference threshold, respectively. The analysis results are as follows; If the mass transfer coefficient average value is greater than or equal to a preset mass transfer coefficient average value reference threshold and the mass transfer coefficient standard deviation is less than a preset mass transfer coefficient standard deviation reference threshold, the high-risk upload process is classified as unstable; If the average value of the mass transfer coefficient is greater than a preset reference threshold value of the average value of the mass transfer coefficient, the high-risk uploading process is classified as continuous; If the average value of the mass transfer coefficient is less than a preset reference threshold value of the average value of the mass transfer coefficient and the standard deviation of the mass transfer coefficient is less than a preset reference threshold value of the standard deviation of the mass transfer coefficient, the high-risk upload process is classified as a burst type; Take different early warning measures for different high-risk upload processes; Different early warning measures are taken for different high-risk upload processes. Level 1 warnings (serious warnings) and level 2 warnings (more serious warnings) are issued for persistent and unstable types, prompting relevant staff to check the data upload process. For sudden types, no warnings are issued in view of the possibility that they may return to normal in a short time, but they need to be recorded for reference during subsequent maintenance.

[0023] By acquiring the data processing capacity and network reliability parameters during the upload process of the ECG monitor, the system can accurately analyze the buffer overflow and the failure of the packet loss and retransmission mechanism, and generate the transmission quality coefficient in combination with the machine learning model. This intelligent perception mechanism ensures that when potential problems occur during the data packet upload process, the system can detect and identify high-risk upload processes in real time, greatly reducing the situation of misordering or loss of data packets. Through continuous monitoring and dynamic adjustment, the integrity and correct order of electrocardiogram (ECG) data are ensured, effectively avoiding misdiagnosis or missed diagnosis caused by abnormal data. This provides doctors and automatic analysis systems with more reliable ECG data, ensuring accurate analysis and judgment of patients' heart health status.

[0024] Through intelligent evaluation, the present invention further divides high-risk upload processes into unstable, continuous and sudden types, and takes corresponding early warning measures according to different risk types. For unstable and continuous upload processes, a level one or level two serious warning is issued to prompt relevant medical personnel to conduct inspections and interventions to ensure the reliability of data transmission. For sudden types, records are kept to avoid excessive intervention but provide a reference for subsequent maintenance. This hierarchical early warning mechanism can effectively avoid potential risks in transmission, ensure that critical data can be processed in a timely manner, reduce the risk of medical errors, and improve the security and stability of data transmission, thereby protecting the lives of patients and improving the hospital's operational efficiency and reputation.

[0025] The present invention provides Figure 2 The data uplink transmission system of the smart hospital IoT medical terminal device shown is characterized by including a parameter acquisition module, a data analysis and model input module, an intelligent risk assessment module, a high-risk state monitoring module, and an early warning module; The parameter acquisition module obtains various parameter information generated during the upload of ECG monitor data packets, including data processing capability and network reliability; The data analysis and model input module analyzes the acquired data processing capability and network reliability in the detection window, inputs the analyzed data processing capability and network reliability into the pre-learned machine model, generates the transmission quality coefficient through the learning model, and performs intelligent perception of the ECG monitor data packet upload process based on the transmission quality coefficient; The intelligent risk assessment module divides the ECG monitor data packet upload process into a high-risk upload process or a low-risk upload process based on the results of machine learning output, and performs intelligent assessment on abnormal upload processes in the ECG monitor data packet upload process; The high-risk state monitoring module continuously obtains the upload process information of the ECG monitor data packet for the output high-risk upload process, and divides the high-risk upload process into an accidental state or a non-accidental state; The early warning module takes different early warning measures for different high-risk upload processes.

[0026] The data uplink transmission method for the smart hospital Internet of Things medical terminal equipment provided in the embodiment of the present invention is realized by the data uplink transmission system for the smart hospital Internet of Things medical terminal equipment mentioned above. The specific method and process of the data uplink transmission system for the smart hospital Internet of Things medical terminal equipment are detailed in the embodiment of the data uplink transmission method for the smart hospital Internet of Things medical terminal equipment mentioned above, which will not be repeated here.

[0027] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for uplink transmission of data of a medical terminal device of the Internet of Things in a smart hospital, comprising the following steps: Obtain various parameter information generated during the ECG monitor data packet upload process, including data processing capability and network reliability; Under the detection window, the acquired data processing capacity and network reliability are analyzed, and the analyzed data processing capacity and network reliability are input into the pre-learned machine model. The transmission quality coefficient is generated through the learning model, and the data packet upload process of the ECG monitor is intelligently sensed based on the transmission quality coefficient. Based on the results of machine learning output, the ECG monitor data packet upload process is divided into a high-risk upload process or a low-risk upload process, and an intelligent evaluation is performed on the abnormal upload process of the ECG monitor data packet upload process; For the high-risk upload process of the output, continuously obtain the upload process information of the ECG monitor data packet, and classify the high-risk upload process into an accidental state or a non-accidental state; Different early warning measures are taken for different high-risk upload processes.

2. The method for uplink data transmission of a smart hospital IoT medical terminal device according to claim 1, characterized in that: Data processing capability includes buffer overflow information, which is used to measure the effectiveness and carrying capacity of the buffer when the system processes data, and reflects the processing capability of the device when facing input data streams. Network reliability includes packet loss and retransmission mechanism failure information, which measures the network's ability to handle lost data packets during data transmission and reflects the reliability of the network.

3. The method for uplink data transmission of a smart hospital IoT medical terminal device according to claim 2, characterized in that: In the detection window, after abnormal analysis of the hedge area overflow information and the packet loss retransmission mechanism failure information, the hedge area overflow index and the packet loss retransmission mechanism failure index are generated respectively, and the hedge area overflow index and the packet loss retransmission mechanism failure index are input into the pre-learned machine model. The transmission quality coefficient is generated through the learning model, and the ECG monitor data packet upload process is intelligently perceived based on the transmission quality coefficient.

4. The method for uplink data transmission of a smart hospital IoT medical terminal device according to claim 3 is characterized in that: In the detection window, after performing an abnormal analysis on the hedge area overflow information, the specific steps to generate the hedge area overflow index are as follows: In the detection window, data is collected in real time. The collected data includes data arrival rate, data processing capacity, buffer capacity and current buffer usage. The data arrival rate is calibrated as , the data processing capability is calibrated as , the buffer capacity is marked as B capacity And the current buffer usage is marked as ; According to the collected parameters, the data inflow rate is calculated to determine whether there is an overflow risk. The calculation expression is as follows: , where R in Indicates the data inflow rate; Considering the limitation of buffer capacity, the buffer conflict index is calculated. The calculation expression is as follows: , where C index represents the buffer conflict index; By combining the data inflow rate and the buffer conflict index, the hedge area overflow index is generated, and the calculation expression is as follows: index =(R in ·(1-C index )) α ·(1+C index ) β , where O index represents the hedge overflow index, α is the data inflow rate weight, and β is the buffer conflict index weight.

5. The method for uplink data transmission of a smart hospital IoT medical terminal device according to claim 3 is characterized in that: In the detection window, after abnormal analysis of packet loss and retransmission mechanism failure information, the specific steps for generating a packet loss and retransmission mechanism failure index are as follows: In the detection window, various data parameters are collected, including the total number of data packets sent N s , the number of successfully received data packets N r And the number of retransmissions N t ; Calculate the packet loss rate. The calculation expression is as follows: , where P loss Indicates the packet loss rate, which is used to evaluate the loss of data packets during transmission; Calculate the retransmission efficiency index. The calculation expression is as follows: , where R eff Represents the retransmission efficiency index, which is used to reflect the effectiveness of the retransmission mechanism; The packet loss rate and retransmission efficiency are combined to generate the packet loss retransmission mechanism failure index. The calculation expression is as follows: R fail =(P loss ·(1-R eff )) θ , where R fail represents the failure index of packet loss and retransmission mechanism, and θ is the weight factor, which is used to adjust the relative importance of packet loss rate and retransmission efficiency.

6. The method for uplink data transmission of a smart hospital IoT medical terminal device according to claim 3, characterized in that: The hedge area overflow index O index and packet loss retransmission mechanism failure index R fail Input into the pre-learned machine model, and generate the transmission quality coefficient TQ through the machine model according to the following formula: ; Where h1 and h2 are the overflow index of the hedge area, respectively. index and packet loss retransmission mechanism failure index R fail Pre-set proportional coefficient, and h1 and h2 are both greater than 0.

7. The method for uplink data transmission of a smart hospital IoT medical terminal device according to claim 6, characterized in that: The generated transmission quality coefficient is compared with the preset transmission quality coefficient reference threshold, and the comparison results are as follows: If the transmission quality coefficient is greater than or equal to a preset transmission quality coefficient reference threshold, the ECG monitor data packet upload process is classified as a high-risk upload process; If the transmission quality coefficient is less than a preset transmission quality coefficient reference threshold, the ECG monitor data packet upload process is classified as a low-risk upload process.

8. The method for uplink data transmission of a smart hospital IoT medical terminal device according to claim 7, characterized in that: For the high-risk uploading process of the output, several transmission quality coefficients generated during several uploading processes of the ECG monitor data packets are continuously obtained to establish a data set for comprehensive analysis; The average value and standard deviation of several mass transfer coefficients in the data set are calculated, and the calculated average value and standard deviation of the mass transfer coefficient are compared and analyzed with the preset mass transfer coefficient average value reference threshold and the preset mass transfer coefficient standard deviation reference threshold, respectively. The analysis results are as follows; If the mass transfer coefficient average value is greater than or equal to a preset mass transfer coefficient average value reference threshold and the mass transfer coefficient standard deviation is less than a preset mass transfer coefficient standard deviation reference threshold, the high-risk upload process is classified as unstable; If the average value of the mass transfer coefficient is greater than a preset reference threshold value of the average value of the mass transfer coefficient, the high-risk uploading process is classified as continuous; If the mass transfer coefficient average value is less than a preset mass transfer coefficient average value reference threshold and the mass transfer coefficient standard deviation is less than a preset mass transfer coefficient standard deviation reference threshold, the high-risk upload process is classified as a burst type.

9. A data uplink transmission system for a smart hospital Internet of Things medical terminal device, used to implement the data uplink transmission method for a smart hospital Internet of Things medical terminal device as described in any one of claims 1 to 8, characterized in that: Including parameter acquisition module, data analysis and model input module, intelligent risk assessment module, high-risk status monitoring module, and early warning module: The parameter acquisition module obtains various parameter information generated during the upload of ECG monitor data packets, including data processing capability and network reliability; The data analysis and model input module analyzes the acquired data processing capability and network reliability in the detection window, inputs the analyzed data processing capability and network reliability into the pre-learned machine model, generates the transmission quality coefficient through the learning model, and performs intelligent perception of the ECG monitor data packet upload process based on the transmission quality coefficient; The intelligent risk assessment module divides the ECG monitor data packet upload process into a high-risk upload process or a low-risk upload process based on the results of machine learning output, and performs intelligent assessment on abnormal upload processes in the ECG monitor data packet upload process; The high-risk state monitoring module continuously obtains the upload process information of the ECG monitor data packet for the output high-risk upload process, and divides the high-risk upload process into an accidental state or a non-accidental state; The early warning module takes different early warning measures for different high-risk upload processes.

Images