5G intelligent armpit temperature and vital signs monitoring and early warning system

Abstract

The present invention discloses a 5G intelligent underarm temperature and vital signs monitoring and early warning system, which relates to the field of health monitoring technology, in order to solve the problem that the patient health monitoring process is too cumbersome and the abnormal data early warning is inaccurate. The present invention achieves early warning judgments at different levels by grading the degree of abnormality. This hierarchical early warning method enables doctors to understand the health risks of patients more accurately, monitors respiratory rate through vibration transmission, monitors sleep data through pressure changes, monitors pulse data through photoelectric effects, etc., to ensure the accuracy of the data. The membrane sensor is placed under the patient's armpit, which is more convenient and comfortable than other monitoring equipment, reducing the patient's discomfort. The temperature sensor can monitor the patient's body temperature changes in real time to ensure accurate grasp of the patient's health status. The temperature sensor can obtain the patient's accurate body temperature, avoiding the errors that may exist in traditional thermometers.

Description

Technical Field

[0001] The present invention relates to the field of health monitoring technology, and specifically to a 5G intelligent underarm temperature and vital signs monitoring and early warning system. Background Art

[0002] Axillary health monitoring is usually performed by measuring body temperature under the armpit, which is a common method of measuring body temperature and is widely used in medical and home environments.

[0003] The Chinese patent with publication number CN106473721A discloses a heart rate, respiration and body temperature monitoring system for the armpit, which mainly detects the heart rate, respiration rate and body temperature of the human body in real time through a photoelectric pulse sensor and an infrared thermopile sensor, and then transmits the data to the data processing module through a filter circuit, a signal detection circuit, an A / D analog-to-digital conversion module, a first wireless transceiver module and a second wireless transceiver module in sequence, and displays the final physiological signal image on the recording and display module after processing. Although the above scheme solves the problem of armpit monitoring, there are still the following problems in actual operation:

[0004] 1. The temperature sensor’s usage status was not checked before monitoring the patient’s temperature, and the temperature monitoring process was too complicated.

[0005] 2. The process of monitoring patients’ vital signs used to be cumbersome, which led to an increase in medical manpower.

[0006] 3. After obtaining the patient's body temperature data and vital signs data, no further abnormality determination is made, resulting in an inability to issue specific warnings based on the degree of abnormality. Summary of the invention

[0007] The purpose of the present invention is to provide a 5G intelligent underarm temperature and vital signs monitoring and early warning system, which realizes early warning judgments at different levels by grading the degree of abnormality. This hierarchical early warning method enables doctors to understand the health risks of patients more accurately, monitors respiratory rate through vibration transmission, monitors sleep data through pressure changes, monitors pulse data through photoelectric effect, etc., to ensure the accuracy of data. The membrane sensor is placed under the patient's armpit, which is more convenient and comfortable than other monitoring equipment, reducing the patient's discomfort. The temperature sensor can monitor the patient's body temperature changes in real time to ensure accurate grasp of the patient's health status. The temperature sensor can obtain the patient's accurate body temperature, avoiding the possible errors of traditional thermometers, and can solve the problems in the prior art.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] 5G intelligent underarm temperature and vital signs monitoring and early warning system, including:

[0010] Body temperature data collection unit, used for:

[0011] The patient's body temperature data is monitored in real time, wherein the patient's body temperature data is monitored by a temperature sensor, and the real-time monitored body temperature data is marked as target body temperature data;

[0012] Vital signs data collection unit for:

[0013] Monitor the patient's vital sign data in real time, wherein the patient's vital sign data is monitored by a membrane sensor, and the real-time monitored vital sign data is marked as target vital characteristic data;

[0014] The data collection and analysis early warning unit is used to:

[0015] The target body temperature data and target vital sign data are compared with the standard body temperature data and standard vital sign data respectively, the abnormality of the patient is determined based on the comparison results, and the warning degree is determined based on the abnormality.

[0016] Preferably, the body temperature data acquisition unit comprises:

[0017] The first device detection module is used to:

[0018] Perform equipment inspection before using the temperature sensor for real-time temperature monitoring;

[0019] The historical average usage time data and the full life sensitivity data of the temperature sensor are obtained, wherein the historical average usage time data and the full life sensitivity data are retrieved from the database;

[0020] Compare the historical average usage time data with the full life sensitivity data, and confirm the sensitivity of the historical average usage time data to the full life sensitivity data based on the comparison results;

[0021] Obtain the historical fault records of the temperature sensor and confirm the historical sensitivity data at the time of the historical fault records;

[0022] Compare the sensitivity of the historical average usage time data on the full life sensitivity data with the historical sensitivity data by threshold;

[0023] Based on the comparison results, determine whether the current temperature sensor meets the standard for normal use.

[0024] Preferably, the body temperature data acquisition unit further includes:

[0025] Real-time temperature data monitoring module, used for:

[0026] When the temperature sensor reaches the normal use standard, place the temperature sensor under the patient's armpit;

[0027] The temperature sensor has a built-in thermistor, which acquires the patient's armpit temperature;

[0028] And when the patient's body temperature changes, the temperature sensor changes temperature along with the patient's body temperature;

[0029] At the same time, the temperature sensor records the patient's body temperature within a set preset time range, and the recorded body temperature is marked as target body temperature data.

[0030] Preferably, the vital signs data collection unit comprises:

[0031] The second device detection module is used for:

[0032] Perform equipment testing before using the membrane sensor to monitor vital signs data;

[0033] The equipment inspection process for membrane sensors is the same as that for temperature sensors;

[0034] According to the detection result of the membrane sensor, it is judged whether the current membrane sensor reaches the standard of normal use.

[0035] Preferably, the vital sign data collection unit further includes:

[0036] Vital signs data classification module for:

[0037] When the membrane sensor reaches the normal use standard, place the membrane sensor under the patient's armpit;

[0038] After the membrane sensor is placed, the patient's pulse data, respiratory rate data, sleep data and humidity data are obtained;

[0039] The respiratory rate data is transmitted to the membrane sensor through the vibration generated by the patient's breathing, causing the component parameters inside the membrane sensor to change, thereby generating an electrical signal, and the electrical signal is converted into the patient's respiratory rate data;

[0040] Sleep data uses a membrane sensor to detect the pressure changes caused by heart beats, breathing, and body movements during sleep. After digital signal processing, the heart beat, breathing, and body movement waveforms are separated, and the heart rate, breathing rate, and body movement frequency information are further extracted. The heart rate, breathing rate, and body movement frequency information are statistically analyzed to obtain the patient's sleep data.

[0041] Humidity data is monitored through specific humidity-sensitive materials on the membrane sensor. When the humidity on the skin surface changes, the humidity-sensitive material inside the membrane sensor will sense the change in humidity and generate corresponding electrical signals, which are then converted into humidity data on the body surface.

[0042] Preferably, the vital sign data classification module is further used for:

[0043] Pulse data is monitored through changes in light signals generated when the patient's pulse fluctuates;

[0044] splitting the optical signal generated when the patient's pulse fluctuates into a plurality of sub-signal waves and detecting the power and wavelength of each sub-signal wave;

[0045] Selecting an adaptive phase matching factor according to the phase change of each sub-signal wave;

[0046] The multi-wave mixing efficiency of the optical signal is obtained according to the phase matching factor;

[0047] The peak power of the multi-wave mixing of the optical signal is obtained according to the multi-wave mixing efficiency and the power of each sub-signal wave;

[0048] Setting a conversion parameter of a photoelectric element in a sensor based on the photoelectric effect according to the peak power of the multi-wave mixing of the optical signal;

[0049] Controlling the sensor based on the photoelectric effect to convert the optical signal into an electrical signal output according to the set conversion parameters;

[0050] Obtaining the patient's pulse data according to the output electrical signal;

[0051] And pulse data, respiratory rate data, sleep data and humidity data are uniformly labeled as target life characteristic data.

[0052] Preferably, the data collection, analysis and early warning unit comprises:

[0053] Abnormal data confirmation module, used for:

[0054] Perform curve data conversion on target body temperature data and target vital sign data respectively;

[0055] Retrieving standard body temperature data and standard vital sign data from a database, and converting the curve data after retrieval;

[0056] Perform curve overlap comparison on the curve data of the target body temperature data and the curve data of the standard body temperature data;

[0057] Perform curve overlap comparison between the curve data of the target vital characteristic data and the curve data of the standard vital characteristic data;

[0058] Determine abnormal data according to the curve overlap comparison result, wherein the abnormal data is the part of the target body temperature data and the target vital sign data that does not overlap with the standard body temperature data and the standard vital sign data after the curve overlap;

[0059] The non-overlapping parts are determined as abnormal data, and the monitoring time of the non-overlapping parts is confirmed;

[0060] Confirm the area of ​​the region without overlap, and determine the degree of abnormality of the abnormal data based on the area of ​​the region;

[0061] Among them, the degree of abnormality is divided into first-level abnormality, second-level abnormality and third-level abnormality.

[0062] Preferably, the abnormal data confirmation module includes:

[0063] Coordinate construction submodule, used for:

[0064] A body temperature coordinate system and a life characteristic coordinate system are respectively constructed, and the target body temperature data and the standard body temperature data are imported into the body temperature coordinate system to form a corresponding body temperature curve diagram, and the target body temperature curve and the standard body temperature curve are presented; the target life characteristic data and the standard life characteristic data are imported into the life characteristic coordinate system to form a corresponding life characteristic curve diagram, and the target life characteristic curve and the standard life characteristic curve are presented;

[0065] Function fitting submodule, used for:

[0066] Through fitting technology, a target body temperature function and a standard body temperature function are obtained according to the target body temperature curve and the standard body temperature curve; a target life characteristic function and a standard life characteristic function are obtained according to the target life characteristic curve and the standard life characteristic curve;

[0067] Function operator module, used for:

[0068] Calculate the temperature difference of each corresponding value of the target body temperature function and the standard body temperature function, determine the position of the temperature curve corresponding to the value where the temperature difference is not 0 as the non-overlapping part, and integrate the difference between the target body temperature function and the standard body temperature function to obtain the area of ​​the non-overlapping region of the temperature curve; calculate the life characteristic difference of each corresponding value of the target life characteristic function and the standard life characteristic function, determine the position of the life characteristic curve corresponding to the value where the life characteristic difference is not 0 as the non-overlapping part, and integrate the difference between the target life characteristic function and the standard life characteristic function to obtain the area of ​​the non-overlapping region of the life characteristic curve.

[0069] Preferably, the data collection and analysis early warning unit further includes:

[0070] The abnormal data warning degree confirmation module is used to:

[0071] Make different levels of early warning judgments according to the degree of abnormality;

[0072] Among them, level one anomaly corresponds to level one warning, level two anomaly corresponds to level two warning, and level three anomaly corresponds to level three warning.

[0073] Preferably, the process of the vital sign data collection unit performing statistical analysis on the heart rate, respiratory rate and body movement frequency information is as follows:

[0074] While collecting the patient's heart rate, respiratory rate and body movement information during sleep, the sleeping environment data is collected and recorded. The sleeping environment data includes the sleeping environment temperature, sleeping environment humidity and air cleanliness;

[0075] The sleep environment data is input into a pre-trained sleep environment impact evaluation model, and the sleep environment impact evaluation model outputs a sleep environment impact coefficient;

[0076] The heart rate, breathing rate and body movement information are weighted respectively, and the sleep index is calculated using the following formula:

[0077]

[0078] In the above formula, Indicates the patient's sleep index; represents the sleep environment impact coefficient; Indicates heart rate, breathing rate or body movement information. The data item number for the heart rate, respiratory rate and body movement information; Indicates the standard value of heart rate, respiratory rate or body movement information; Indicates a non-zero constant that is set;

[0079] Obtaining the patient's sleep index, and using the sleep index as the patient's sleep data; if the sleep data is within a predetermined sleep data range, it indicates that the patient's sleep state is good; otherwise, it indicates that the patient's sleep state is poor, and a status warning message is issued;

[0080] Among them, the sleep environment impact assessment model is constructed using a neural network model. After construction, the training data set, verification data set and test data set used to train the neural network model are obtained by screening the experimental monitoring data collected from volunteers.

[0081] Compared with the prior art, the present invention has the following beneficial effects:

[0082] 1. The 5G intelligent underarm temperature and vital signs monitoring and early warning system provided by the present invention can avoid using sensors with poor performance by judging whether the current temperature sensor meets the standard for normal use, thereby improving the overall utilization rate of the equipment. The temperature sensor can monitor the patient's body temperature changes in real time to ensure accurate grasp of the patient's health status. Due to the characteristics of thermistors, the temperature sensor can obtain the patient's accurate body temperature, avoiding possible errors in traditional thermometers.

[0083] 2. The 5G intelligent underarm temperature and vital signs monitoring and early warning system provided by the present invention uses a membrane sensor that can simultaneously monitor multiple vital characteristics data of the patient, including breathing, sleep, pulse and humidity, providing doctors with more comprehensive information on the patient's health status, monitoring the respiratory rate through vibration transmission, monitoring sleep data through pressure changes, and monitoring pulse data through photoelectric effect, etc., to ensure the accuracy of the data. The membrane sensor is placed under the patient's armpit, which is more convenient and comfortable than other monitoring devices, reducing the patient's discomfort.

[0084] 3. The 5G intelligent underarm temperature and vital signs monitoring and early warning system provided by the present invention displays the temperature and vital signs data in a graphical way, so that doctors can more intuitively understand the changing trend of the patient's temperature and vital signs. The curve overlap comparison can directly compare the target data with the standard data, accurately identify the abnormal part that does not match the target data, and realize different levels of early warning judgment by grading the degree of abnormality. This hierarchical early warning method enables doctors to more accurately understand the health risks of patients and take corresponding treatment measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 It is a schematic diagram of the body temperature and vital signs data monitoring module of the present invention;

[0086] Figure 2 It is a schematic diagram of the body temperature and vital sign data monitoring process of the present invention. DETAILED DESCRIPTION

[0087] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0088] In order to solve the problems in the prior art that the use status of the temperature sensor is not detected before the patient's body temperature is monitored, and the body temperature monitoring process is too complicated, please refer to Figure 1 and Figure 2, this embodiment provides the following technical solutions:

[0089] 5G intelligent underarm temperature and vital signs monitoring and early warning system, including:

[0090] Body temperature data collection unit, used for:

[0091] The patient's body temperature data is monitored in real time, wherein the patient's body temperature data is monitored by a temperature sensor, and the real-time monitored body temperature data is marked as target body temperature data;

[0092] Vital signs data collection unit for:

[0093] Monitor the patient's vital sign data in real time, wherein the patient's vital sign data is monitored by a membrane sensor, and the real-time monitored vital sign data is marked as target vital characteristic data;

[0094] The data collection and analysis early warning unit is used to:

[0095] The target body temperature data and target vital sign data are compared with the standard body temperature data and standard vital sign data respectively, the abnormality of the patient is determined based on the comparison results, and the warning degree is determined based on the abnormality.

[0096] Specifically, the temperature data acquisition unit can monitor the patient's temperature changes in real time to ensure accurate understanding of the patient's health status. The temperature sensor can obtain the patient's accurate temperature, avoiding the possible errors of traditional thermometers. The vital sign data acquisition unit can simultaneously monitor multiple vital signs of the patient. The membrane sensor is placed under the patient's armpit, which is more convenient and comfortable than other monitoring equipment, such as electrocardiographs, and reduces the patient's discomfort. The early warning unit can classify the degree of abnormality through data collection and analysis, and realize different levels of early warning judgment. This hierarchical early warning method enables doctors to understand the patient's health risks more accurately and take corresponding treatment measures.

[0097] Body temperature data collection unit, including:

[0098] The first device detection module is used to:

[0099] Perform equipment inspection before using the temperature sensor for real-time temperature monitoring;

[0100] The historical average usage time data and the full life sensitivity data of the temperature sensor are obtained, wherein the historical average usage time data and the full life sensitivity data are retrieved from the database;

[0101] Compare the historical average usage time data with the full life sensitivity data, and confirm the sensitivity of the historical average usage time data to the full life sensitivity data based on the comparison results;

[0102] Obtain the historical fault records of the temperature sensor and confirm the historical sensitivity data at the time of the historical fault records;

[0103] Compare the sensitivity of the historical average usage time data on the full life sensitivity data with the historical sensitivity data by threshold;

[0104] According to the comparison results, determine whether the current temperature sensor meets the standard for normal use;

[0105] Real-time temperature data monitoring module, used for:

[0106] When the temperature sensor reaches the normal use standard, place the temperature sensor under the patient's armpit;

[0107] The temperature sensor has a built-in thermistor, which acquires the patient's armpit temperature;

[0108] And when the patient's body temperature changes, the temperature sensor changes temperature along with the patient's body temperature;

[0109] At the same time, the temperature sensor records the patient's body temperature within a set preset time range, and the recorded body temperature is marked as target body temperature data.

[0110] Specifically, when a patient's body temperature is monitored, the temperature sensor is first detected by the first device detection module. By making full use of historical data and sensitivity analysis, the accuracy and reliability of temperature sensor device detection are improved, which helps to achieve optimized maintenance, fault prevention and data-driven decision-making of the equipment. By comparing the sensitivity of historical average usage time data on full-life sensitivity data with the sensitivity at the time of historical fault records, the current state of the temperature sensor can be judged more accurately, thereby improving the accuracy and reliability of real-time temperature monitoring. By obtaining historical fault records and analyzing the sensitivity data at the time of faults, similar faults can be discovered and prevented from happening again in a timely manner, thereby extending the lifespan. The service life of the sensor can be improved by judging whether the current temperature sensor meets the standard for normal use, avoiding the use of sensors with poor performance, thereby improving the overall utilization of the equipment. When the temperature sensor is qualified, the patient's real-time temperature monitoring module is used to monitor the patient's temperature in real time. The temperature sensor can monitor the patient's temperature changes in real time to ensure accurate understanding of the patient's health status. Due to the characteristics of thermistors, the temperature sensor can obtain the patient's accurate temperature, avoiding the errors that may exist in traditional thermometers. The temperature sensor continuously records the patient's temperature within a set preset time range, generates target temperature data, and provides doctors with continuous and complete temperature change information.

[0111] In order to solve the problem that the process of monitoring patients' vital signs is cumbersome in the prior art, which leads to an increase in medical manpower, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0112] Vital signs data collection unit, including:

[0113] The second device detection module is used for:

[0114] Perform equipment testing before using the membrane sensor to monitor vital signs data;

[0115] The equipment inspection process for membrane sensors is the same as that for temperature sensors;

[0116] According to the detection result of the membrane sensor, it is judged whether the current membrane sensor reaches the standard of normal use.

[0117] Vital signs data classification module for:

[0118] When the membrane sensor reaches the normal use standard, place the membrane sensor under the patient's armpit;

[0119] After the membrane sensor is placed, the patient's pulse data, respiratory rate data, sleep data and humidity data are obtained;

[0120] The respiratory rate data is transmitted to the membrane sensor through the vibration generated by the patient's breathing, causing the component parameters inside the membrane sensor to change, thereby generating an electrical signal, and the electrical signal is converted into the patient's respiratory rate data;

[0121] Sleep data uses a membrane sensor to detect the pressure changes caused by heart beats, breathing, and body movements during sleep. After digital signal processing, the heart beat, breathing, and body movement waveforms are separated, and the heart rate, breathing rate, and body movement frequency information are further extracted. The heart rate, breathing rate, and body movement frequency information are statistically analyzed to obtain the patient's sleep data.

[0122] Humidity data is monitored through specific humidity-sensitive materials on the membrane sensor. When the humidity on the skin surface changes, the humidity-sensitive material inside the membrane sensor will sense the change in humidity and generate corresponding electrical signals, which are then converted into humidity data on the body surface.

[0123] Pulse data is monitored through changes in light signals generated when the patient's pulse fluctuates;

[0124] splitting the optical signal generated when the patient's pulse fluctuates into a plurality of sub-signal waves and detecting the power and wavelength of each sub-signal wave;

[0125] Selecting an adaptive phase matching factor according to the phase change of each sub-signal wave;

[0126] The multi-wave mixing efficiency of the optical signal is obtained according to the phase matching factor;

[0127] The peak power of the multi-wave mixing of the optical signal is obtained according to the multi-wave mixing efficiency and the power of each sub-signal wave;

[0128] Setting a conversion parameter of a photoelectric element in a sensor based on the photoelectric effect according to the peak power of the multi-wave mixing of the optical signal;

[0129] Controlling the sensor based on the photoelectric effect to convert the optical signal into an electrical signal output according to the set conversion parameters;

[0130] Obtaining the patient's pulse data according to the output electrical signal;

[0131] And pulse data, respiratory rate data, sleep data and humidity data are uniformly labeled as target life characteristic data.

[0132] Specifically, when the patient is monitoring vital signs data, the membrane sensor is first tested through the second device detection module. The detection process of the membrane sensor is consistent with that of the temperature sensor. When the membrane sensor is qualified, the patient's vital signs data is monitored through the vital signs data classification module. Among them, the membrane sensor can simultaneously monitor multiple vital signs data of the patient, including breathing, sleep, pulse and humidity, providing doctors with more comprehensive information on the patient's health status. The membrane sensor adopts specific technologies and algorithms, such as monitoring respiratory rate through vibration transmission, monitoring sleep data through pressure changes, and monitoring pulse data through photoelectric effect, etc., to ensure the accuracy of the data. The membrane sensor is placed under the patient's armpit, which is more convenient and comfortable than other monitoring devices, such as electrocardiographs, and reduces the patient's discomfort. By continuously monitoring the patient's vital signs data, doctors can provide patients with more personalized health management suggestions, which helps prevent the occurrence of diseases.

[0133] In order to solve the problem in the prior art that after obtaining the patient's body temperature data and vital signs data, no further abnormality determination is performed, resulting in the inability to issue specific warnings based on the abnormality degree, please refer to Figure 1 and Figure 2 , this embodiment provides the following technical solutions:

[0134] The data collection, analysis and early warning unit includes:

[0135] Abnormal data confirmation module, used for:

[0136] Perform curve data conversion on target body temperature data and target vital sign data respectively;

[0137] Retrieving standard body temperature data and standard vital sign data from a database, and converting the curve data after retrieval;

[0138] Perform curve overlap comparison on the curve data of the target body temperature data and the curve data of the standard body temperature data;

[0139] Perform curve overlap comparison between the curve data of the target vital characteristic data and the curve data of the standard vital characteristic data;

[0140] Determine abnormal data according to the curve overlap comparison result, wherein the abnormal data is the part of the target body temperature data and the target vital sign data that does not overlap with the standard body temperature data and the standard vital sign data after the curve overlap;

[0141] The non-overlapping parts are determined as abnormal data, and the monitoring time of the non-overlapping parts is confirmed;

[0142] Confirm the area of ​​the region without overlap, and determine the degree of abnormality of the abnormal data based on the area of ​​the region;

[0143] Among them, the degree of abnormality is divided into first-level abnormality, second-level abnormality and third-level abnormality.

[0144] Based on the above embodiment, the abnormal data confirmation module includes:

[0145] Coordinate construction submodule, used for:

[0146] A body temperature coordinate system and a life characteristic coordinate system are respectively constructed, and the target body temperature data and the standard body temperature data are imported into the body temperature coordinate system to form a corresponding body temperature curve diagram, and the target body temperature curve and the standard body temperature curve are presented; the target life characteristic data and the standard life characteristic data are imported into the life characteristic coordinate system to form a corresponding life characteristic curve diagram, and the target life characteristic curve and the standard life characteristic curve are presented;

[0147] Function fitting submodule, used for:

[0148] Through fitting technology, a target body temperature function and a standard body temperature function are obtained according to the target body temperature curve and the standard body temperature curve; a target life characteristic function and a standard life characteristic function are obtained according to the target life characteristic curve and the standard life characteristic curve;

[0149] Function operator module, used for:

[0150] Calculate the temperature difference of each corresponding value of the target body temperature function and the standard body temperature function, determine the position of the temperature curve corresponding to the value where the temperature difference is not 0 as the non-overlapping part, and integrate the difference between the target body temperature function and the standard body temperature function to obtain the area of ​​the non-overlapping region of the temperature curve; calculate the life characteristic difference of each corresponding value of the target life characteristic function and the standard life characteristic function, determine the position of the life characteristic curve corresponding to the value where the life characteristic difference is not 0 as the non-overlapping part, and integrate the difference between the target life characteristic function and the standard life characteristic function to obtain the area of ​​the non-overlapping region of the life characteristic curve.

[0151] Specifically, the above scheme provides an adoptable abnormal data analysis method, which refers to coordinate image analysis, combines coordinate curve and function transformation and their corresponding relationship, and judges whether the lines overlap by whether the curve function difference of the corresponding parameter item is 0 at each point on the curve. The area of ​​the non-overlapping region is calculated by function integral operation. On the one hand, the corresponding analysis results can be obtained quantitatively and accurately, and on the other hand, the objectivity and reliability of the analysis are improved.

[0152] The abnormal data warning degree confirmation module is used to:

[0153] Make different levels of early warning judgments according to the degree of abnormality;

[0154] Among them, level one anomaly corresponds to level one warning, level two anomaly corresponds to level two warning, and level three anomaly corresponds to level three warning.

[0155] Specifically, after obtaining the patient's real-time body temperature data and real-time vital sign data, the acquired data is compared with the standard data through the abnormal data confirmation module. Through curve data conversion, the body temperature and vital sign data are displayed in a graphical manner, so that the doctor can more intuitively understand the patient's body temperature and vital sign change trend. The curve overlap comparison can directly compare the target data with the standard data, accurately identify the abnormal part that does not match the target data, and improve the accuracy of abnormal data detection. By judging the non-overlapping part after the curve overlaps, the scheme can accurately identify abnormal data and provide doctors with timely health risk warnings. The abnormal degree of abnormal data is confirmed according to the area, and the abnormality is divided into level one, level two and level three, which helps doctors to quickly evaluate the severity of abnormal data and take corresponding treatment measures. Different levels of warnings are given through the abnormal data warning degree confirmation module, and different levels of warning judgments are achieved by grading the abnormal degree. This hierarchical warning method enables doctors to understand patients' health risks more accurately and take corresponding measures. Since different levels of abnormalities correspond to different warnings, doctors can judge patients' health conditions more accurately and avoid false alarms or missed alarms, thereby improving the accuracy of warnings. Among them, the first-level abnormality is the most abnormal in the abnormal data, the second-level abnormality is the second, and the third-level abnormality is the lowest in the abnormal data. Therefore, the corresponding warnings are: the first-level warning has the strongest alarm level, the second-level warning is the second, and the third-level warning has the weakest alarm level.

[0156] Based on the above-mentioned embodiment, the process of the vital sign data collection unit performing statistical analysis on the heart rate, respiratory rate and body movement information is as follows:

[0157] While collecting the patient's heart rate, respiratory rate and body movement information during sleep, the sleeping environment data is collected and recorded. The sleeping environment data includes the sleeping environment temperature, sleeping environment humidity and air cleanliness;

[0158] The sleep environment data is input into a pre-trained sleep environment impact evaluation model, and the sleep environment impact evaluation model outputs a sleep environment impact coefficient;

[0159] The heart rate, breathing rate and body movement information are weighted respectively, and the sleep index is calculated using the following formula:

[0160]

[0161] In the above formula, Indicates the patient's sleep index; represents the sleep environment impact coefficient; Indicates heart rate, breathing rate or body movement information. The data item number for the heart rate, respiratory rate and body movement information; Indicates the standard value of heart rate, respiratory rate or body movement information; Indicates a non-zero constant that is set;

[0162] Obtaining the patient's sleep index, and using the sleep index as the patient's sleep data; if the sleep data is within a predetermined sleep data range, it indicates that the patient's sleep state is good; otherwise, it indicates that the patient's sleep state is poor, and a status warning message is issued;

[0163] Among them, the sleep environment impact assessment model is constructed using a neural network model. After construction, the training data set, verification data set and test data set used to train the neural network model are obtained by screening the experimental monitoring data collected from volunteers.

[0164] Specifically, the non-zero constant in the above formula can take a value within the range of [0.01, 0.02]. The non-zero constant is mainly to prevent the denominator from being zero in the exponent of the natural constant e. For the predetermined sleep data range, different sleep data ranges can be used according to different age groups. By constructing and training a good sleep environment impact evaluation model and determining the sleep environment impact coefficient based on the sleep environment data, analysis deviations caused by different environmental factors can be avoided and the accuracy of the analysis can be improved. This scheme uses the above formula for quantitative analysis. On the one hand, it improves the objectivity and reliability of the analysis and prevents the adverse effects of human subjective factors. On the other hand, it can automatically and quickly obtain analysis results without human participation, which reduces the requirements for staff, improves the immediacy and efficiency of monitoring, and avoids serious consequences of delays.

[0165] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0166] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. 5G intelligent underarm temperature and vital signs monitoring and early warning system, characterized by: include: Body temperature data collection unit, used for: The patient's body temperature data is monitored in real time, wherein the patient's body temperature data is monitored by a temperature sensor, and the real-time monitored body temperature data is marked as target body temperature data; Vital signs data collection unit for: Monitor the patient's vital sign data in real time, wherein the patient's vital sign data is monitored by a membrane sensor, and the real-time monitored vital sign data is marked as target vital characteristic data; The data collection and analysis early warning unit is used to: Compare the target body temperature data and target vital sign data with the standard body temperature data and standard vital sign data respectively, determine the abnormality of the patient according to the comparison results, and determine the warning degree according to the abnormality; The body temperature data acquisition unit comprises: The first device detection module is used to: Perform equipment inspection before using the temperature sensor for real-time temperature monitoring; The historical average usage time data and the full life sensitivity data of the temperature sensor are obtained, wherein the historical average usage time data and the full life sensitivity data are retrieved from the database; Compare the historical average usage time data with the full life sensitivity data, and confirm the sensitivity of the historical average usage time data to the full life sensitivity data based on the comparison results; Obtain the historical fault records of the temperature sensor and confirm the historical sensitivity data at the time of the historical fault records; Compare the sensitivity of the historical average usage time data on the full life sensitivity data with the historical sensitivity data by threshold; According to the comparison results, determine whether the current temperature sensor meets the standard for normal use; The vital sign data acquisition unit comprises: The second device detection module is used for: Perform equipment testing before using the membrane sensor to monitor vital signs data; The equipment inspection process for membrane sensors is the same as that for temperature sensors; Judging whether the current membrane sensor meets the standard for normal use according to the detection result of the membrane sensor; The vital sign data collection unit further includes: Vital signs data classification module for: When the membrane sensor reaches the normal use standard, place the membrane sensor under the patient's armpit; After the membrane sensor is placed, the patient's pulse data, respiratory rate data, sleep data and humidity data are obtained; The respiratory rate data is transmitted to the membrane sensor through the vibration generated by the patient's breathing, causing the component parameters inside the membrane sensor to change, thereby generating an electrical signal, and the electrical signal is converted into the patient's respiratory rate data; Sleep data is detected by a membrane sensor due to changes in heart rate, breathing and body movements during sleep. After digital signal processing, the heart rate, breathing and body movement waveforms are separated. The heart rate, breathing rate and body movement frequency information are further extracted and statistically analyzed to obtain the patient's sleep data. Humidity data is monitored by the specific humidity sensitive material on the membrane sensor. When the humidity on the skin surface changes, the humidity sensitive material inside the membrane sensor will sense the change in humidity and generate a corresponding electrical signal, which is then converted into humidity data on the body surface. The process of the vital sign data classification module of the vital sign data collection unit performing statistical analysis on the heart rate, respiratory rate and body movement frequency information is as follows: While collecting the patient's heart rate, respiratory rate and body movement information during sleep, the sleeping environment data is collected and recorded. The sleeping environment data includes the sleeping environment temperature, sleeping environment humidity and air cleanliness; The sleep environment data is input into a pre-trained sleep environment impact evaluation model, and the sleep environment impact evaluation model outputs a sleep environment impact coefficient; The heart rate, breathing rate and body movement information are weighted respectively, and the sleep index is calculated using the following formula: In the above formula, Indicates the patient's sleep index; represents the sleep environment impact coefficient; Indicates heart rate, breathing rate or body movement information. The data item number for the heart rate, respiratory rate and body movement information; Indicates the standard value of heart rate, respiratory rate or body movement information; Indicates a non-zero constant that is set; Obtaining the patient's sleep index, and using the sleep index as the patient's sleep data; if the sleep data is within a predetermined sleep data range, it indicates that the patient's sleep state is good; otherwise, it indicates that the patient's sleep state is poor, and a status warning message is issued; Among them, the sleep environment impact assessment model is constructed using a neural network model. After construction, the training data set, validation data set, and test data set used to train the neural network model are obtained by screening the experimental monitoring data collected from volunteers. The non-zero constant takes a value in the range of 0.01-0.

02. The non-zero constant is used to prevent the denominator from being zero in the exponent of the natural constant e; For the predetermined sleep data range, different sleep data ranges are used according to the divisions of different age groups.

2. The 5G intelligent underarm temperature and vital signs monitoring and early warning system according to claim 1 is characterized in that: The body temperature data acquisition unit further includes: Real-time temperature data monitoring module, used for: When the temperature sensor reaches the normal use standard, place the temperature sensor under the patient's armpit; The temperature sensor has a built-in thermistor, which acquires the patient's armpit temperature; And when the patient's body temperature changes, the temperature sensor changes temperature along with the patient's body temperature; At the same time, the temperature sensor records the patient's body temperature within a set preset time range, and the recorded body temperature is marked as target body temperature data.

3. The 5G intelligent underarm temperature and vital signs monitoring and early warning system according to claim 2 is characterized in that: The vital sign data classification module is also used for: Pulse data is monitored through changes in light signals generated when the patient's pulse fluctuates; splitting the optical signal generated when the patient's pulse fluctuates into a plurality of sub-signal waves and detecting the power and wavelength of each sub-signal wave; Selecting an adaptive phase matching factor according to the phase change of each sub-signal wave; The multi-wave mixing efficiency of the optical signal is obtained according to the phase matching factor; The peak power of the multi-wave mixing of the optical signal is obtained according to the multi-wave mixing efficiency and the power of each sub-signal wave; Setting a conversion parameter of a photoelectric element in a sensor based on the photoelectric effect according to the peak power of the multi-wave mixing of the optical signal; Controlling the sensor based on the photoelectric effect to convert the optical signal into an electrical signal output according to the set conversion parameters; Obtaining the patient's pulse data according to the output electrical signal; And pulse data, respiratory rate data, sleep data and humidity data are uniformly labeled as target life characteristic data.

4. The 5G intelligent underarm temperature and vital signs monitoring and early warning system according to claim 3 is characterized by: The data collection, analysis and early warning unit comprises: Abnormal data confirmation module, used for: Perform curve data conversion on target body temperature data and target vital sign data respectively; Retrieving standard body temperature data and standard vital sign data from a database, and converting the curve data after retrieval; Perform curve overlap comparison on the curve data of the target body temperature data and the curve data of the standard body temperature data; Perform curve overlap comparison between the curve data of the target vital characteristic data and the curve data of the standard vital characteristic data; Determine abnormal data according to the curve overlap comparison result, wherein the abnormal data is the part of the target body temperature data and the target vital sign data that does not overlap with the standard body temperature data and the standard vital sign data after the curve overlap; The non-overlapping parts are determined as abnormal data, and the monitoring time of the non-overlapping parts is confirmed; Confirm the area of ​​the region without overlap, and determine the degree of abnormality of the abnormal data based on the area of ​​the region; Among them, the degree of abnormality is divided into first-level abnormality, second-level abnormality and third-level abnormality.

5. The 5G intelligent underarm temperature and vital signs monitoring and early warning system according to claim 4 is characterized in that: The abnormal data confirmation module includes: Coordinate construction submodule, used for: A body temperature coordinate system and a life characteristic coordinate system are respectively constructed, and the target body temperature data and the standard body temperature data are imported into the body temperature coordinate system to form a corresponding body temperature curve diagram, and the target body temperature curve and the standard body temperature curve are presented; the target life characteristic data and the standard life characteristic data are imported into the life characteristic coordinate system to form a corresponding life characteristic curve diagram, and the target life characteristic curve and the standard life characteristic curve are presented; Function fitting submodule, used for: Through fitting technology, a target body temperature function and a standard body temperature function are obtained according to the target body temperature curve and the standard body temperature curve; a target life characteristic function and a standard life characteristic function are obtained according to the target life characteristic curve and the standard life characteristic curve; Function operator module, used for: Calculate the temperature difference of each corresponding value of the target body temperature function and the standard body temperature function, determine the position of the temperature curve corresponding to the value where the temperature difference is not 0 as the non-overlapping part, and integrate the difference between the target body temperature function and the standard body temperature function to obtain the area of ​​the non-overlapping region of the temperature curve; calculate the life characteristic difference of each corresponding value of the target life characteristic function and the standard life characteristic function, determine the position of the life characteristic curve corresponding to the value where the life characteristic difference is not 0 as the non-overlapping part, and integrate the difference between the target life characteristic function and the standard life characteristic function to obtain the area of ​​the non-overlapping region of the life characteristic curve.

6. The 5G intelligent underarm temperature and vital signs monitoring and early warning system according to claim 5 is characterized by: The data collection and analysis early warning unit further includes: The abnormal data warning degree confirmation module is used to: Make different levels of early warning judgments according to the degree of abnormality; Among them, level one anomaly corresponds to level one warning, level two anomaly corresponds to level two warning, and level three anomaly corresponds to level three warning.

Images