CN117315885B - A remote shared alarm system for monitoring urine bag urine volume and ECG monitor - Google Patents

Abstract

The invention discloses a remote shared alarm system for monitoring urine volume of a urine bag and an Electrocardiograph (ECG) monitor, which relates to the technical field of medical monitoring, and is used for respectively detecting the urine bag and heartbeat of a patient, respectively constructing a urine bag detection data set and a heartbeat detection data set according to acquired detection sub-data, respectively generating a urine bag coefficient Ld and a heartbeat coefficient Xt when the urine bag coefficient Ld and the heartbeat coefficient Xt do not exceed corresponding thresholds, and respectively generating predicted values; generating abnormal characteristics when the predicted value is higher than a corresponding threshold value, sending early warning information to medical staff, and summarizing to generate a corresponding scheme library; matching the corresponding solutions from the corresponding solution library by using abnormal characteristics, outputting the corresponding solutions, carrying out data sharing and remote consultation of organization, and giving out a treatment solution; adding the corrected treatment plan into the treatment plan library, and when the patient is not treated by medical staff. The remote consultation is organized and the scheme is revised, so that when the abnormal condition of the patient occurs, a more accurate coping scheme can be obtained, and the safety of the patient is ensured.

Description

A remote shared alarm system for monitoring urine bag urine volume and ECG monitor

Technical Field

The invention relates to the technical field of medical monitoring, and in particular to a remote shared alarm system for monitoring urine volume in a urine bag and an electrocardiogram monitor.

Background technique

The remote shared alarm system is a system that can remotely monitor and share alarm information. In the medical field, the remote shared alarm system can be used to monitor the patient's vital signs, such as electrocardiogram, blood oxygen, respiration, etc. Once an abnormal situation occurs, the system can immediately alert medical staff and initiate emergency procedures when necessary.

Critically ill patients are usually equipped with urine bags and have their heartbeats monitored by electrocardiogram monitors. They are usually cared for by dedicated personnel. However, at night, the medical staff or accompanying personnel who take care of them also need to rest. Besides resting, they can only do regular rounds at best, and may not be able to rush to the ward immediately when the patient's condition becomes abnormal; or the medical staff may rush to the ward in time, but cannot solve the current prominent abnormality in time.

In order to solve the above problems, the present invention provides a remote shared alarm system for monitoring urine volume in a urine bag and an electrocardiogram monitor.

Summary of the invention

1. Technical issues to be solved

In view of the deficiencies of the prior art, the present invention provides a remote shared alarm system for monitoring urine bag urine volume and electrocardiogram monitor, which detects the patient's urine bag and heartbeat respectively, and constructs a urine bag detection data set and a heartbeat detection data set with the acquired detection sub-data, and generates a urine bag coefficient Ld and a heartbeat coefficient Xt respectively. When both do not exceed the corresponding threshold, a predicted value is generated respectively; when the predicted value is higher than the corresponding threshold, an abnormal feature is generated, and an early warning message is sent to medical staff, and a response plan library is generated in summary; the response plan is matched from the response plan library with the abnormal feature and output, and data sharing and remote consultation are organized to provide a treatment plan; the revised response plan is added to the response plan library, and when the patient does not receive treatment from medical staff. Organize a remote consultation and revise the plan, when the patient is in an abnormal condition, a more accurate response plan can be obtained to ensure the safety of the patient, and solve the problems in the background technology.

(II) Technical solution

To achieve the above objectives, the present invention is implemented through the following technical solutions: a remote shared alarm system for monitoring urine bag urine volume and electrocardiogram monitor, comprising a detection unit, a first processing unit, a control unit, a communication unit, a scheme summary unit, a second processing unit, a third processing unit, and an alarm unit, wherein after entering the night, when there is still a patient on the current bed, the detection unit first identifies whether there is a medical staff in the ward where the patient is located, and if not, the urine bag and heartbeat of the patient are detected respectively, and a urine bag detection data set and a heartbeat detection data set are respectively constructed with the acquired detection sub-data; after the urine bag detection data set and the heartbeat detection data set are sent to the first processing unit, a urine bag coefficient Ld and a heartbeat coefficient Xt are respectively generated; when the current urine bag coefficient Ld and the heartbeat coefficient Xt do not exceed the corresponding threshold value, the trained prediction model is used to predict the urine bag coefficient Ld and the heartbeat coefficient Xt and generate prediction values respectively; when the urine bag coefficient Ld or the heartbeat coefficient Xt is When the predicted value of t is higher than the corresponding threshold, the abnormal sub-data and its number are determined, and the abnormal features are generated in combination with the abnormal degree. When the number of abnormal sub-data exceeds the corresponding threshold, the control unit forms a control instruction, firstly enables the communication unit to send an early warning message to the medical staff, and then enables the solution summary unit to collect the corresponding response plan according to the abnormal features, and summarize and generate a response plan library; after the medical staff receives the early warning message, the second processing unit matches the response plan from the response plan library with the abnormal features and outputs it, combines the current urine bag detection data set, heartbeat detection data set and response plan library for data sharing, organizes remote consultation when there are no medical staff around the bed, and provides a treatment plan for the patient; the third processing unit corrects the output response plan and adds the corrected response plan to the response plan library. If the patient does not receive treatment from the medical staff within the scheduled time after obtaining the corrected response plan or treatment plan, the alarm unit sends an alarm to the outside.

Furthermore, the detection unit includes an environment recognition module, a urine volume detection module and a heartbeat detection module, wherein, after entering night, the environment recognition module recognizes the environment of the patient's ward to determine whether there are medical staff in the ward. If not, the environment recognition module first detects the urine bag at fixed time intervals, and obtains at least the urine volume Nv, pH Sj and transparency Tm from the generated detection data, and then summarizes them to establish a urine bag detection data set; then the heartbeat detection module monitors the patient's heartbeat data in real time at fixed time intervals, and obtains at least the heartbeat frequency Xp and R-R interval Xw from the generated monitoring data, and summarizes them to form a heartbeat detection data set.

Furthermore, the first processing unit includes an evaluation module, a prediction module, an analysis module and a model training module, wherein the urine bag detection data set and the heartbeat detection data set are sent to the evaluation module respectively, and based on the current sub-data, the evaluation module generates the urine bag coefficient Ld and the heartbeat coefficient Xt respectively.

Furthermore, the urine bag coefficient Ld is generated as follows: the urine volume Nv, pH Sj and transparency Tm are obtained, and after dimensionless processing, according to the following formula:

Among them, α and β are changeable constant parameters, 0.51≤α≤0.76, 0.61≤β≤0.93, and users can adjust them according to actual conditions; the heart rate coefficient Xt is generated as follows: obtain the heart rate Xp and R-R interval Xw, and after dimensionless processing, according to the following formula:

Among them, γ is a changeable constant parameter, 0.91≤γ≤1.36, 0.68≤θ≤1.46, the user can adjust it according to the actual situation, R is the correlation coefficient between the heart rate Xp and the R-R interval Xw, R is obtained by correlation analysis, and D is a constant correction parameter.

Furthermore, a neural network algorithm is used to select sample data from the urine bag detection data set and the heartbeat detection data set. Through the sample data, a coefficient prediction model is established by the model training module after training and testing. When the urine bag coefficient Ld and the heartbeat coefficient Xt do not exceed the corresponding threshold values, the coefficient prediction model is used, and the sub-data in the urine bag detection data set and the heartbeat detection data set are used as input data. The prediction module predicts the sub-data in the urine bag detection data set and the heartbeat detection data set to generate predicted values of the corresponding sub-data, and then generates predicted values of the urine bag coefficient Ld and the heartbeat coefficient Xt.

Furthermore, when at least one of the predicted values of the urine bag coefficient Ld and the heartbeat coefficient Xt is higher than the corresponding threshold, the analysis module determines the part of several sub-data in the urine bag detection data set and the heartbeat detection data set that exceeds the corresponding threshold, and marks it as abnormal data; determines the number of abnormal data, and determines the abnormality degree of the sub-data based on the proportion of the sub-data exceeding the corresponding threshold, and generates abnormal features by combining the abnormal data and its abnormality degree.

Furthermore, when the predicted values of the urine bag coefficient Ld and the heartbeat coefficient Xt do not exceed the corresponding thresholds, the monitoring coefficient Jxs is generated in association, wherein the monitoring coefficient Jxs is generated as follows:

Wherein, 0≤F ₁ ≤1, 0≤F ₂ ≤1, and 0.74≤F ₁ +F ₂ ≤1.69, the specific value of which is adjusted and set by the user, and C is a constant correction coefficient.

Furthermore, when the monitoring coefficient Jxs exceeds the corresponding threshold, the control unit generates a control instruction, firstly causing the communication unit to send a warning message to the medical staff, and then causing the solution summary unit to select the corresponding response plan from the existing cases and treatment plans based on the abnormal characteristics, and summarize and output the response plan library.

Furthermore, the second processing unit includes a remote consultation module, a data sharing module and a matching module, wherein when the medical staff who are not in the ward receive the early warning information, the abnormal characteristics and the response plan are used as sample data, and a matching model is constructed using a similarity algorithm. The matching model is output after training and testing the sample data. The matching module uses the matching model to match and output the response plan from the response plan library based on the abnormal characteristics; after summarizing the urine bag detection data set, heartbeat detection data set and response plan containing historical data and predicted data, the data sharing module shares the data with the medical staff or doctor team responsible for the patient. Under the data sharing conditions, the remote consultation module organizes a remote consultation and provides a treatment plan for the patient.

Furthermore, the third processing unit includes a judgment module, a correction module and an output module, wherein:

Obtain the response plan and the treatment plan, use the trained similarity model, and let the judgment module judge the similarity of the response plan and the treatment plan. When the similarity is lower than the threshold, mark the part that causes the similarity to be lower than the threshold, determine it as the abnormal area and output it; send the response plan with the abnormal area to the correction module, so that the correction module corrects the abnormal area, and send the corrected response plan to the remote consultation module for verification. If the verification is correct, add the corrected response plan to the response plan library.

(III) Beneficial effects

The present invention provides a remote shared alarm system for monitoring urine bag urine volume and electrocardiogram monitor, which has the following beneficial effects:

1. By generating the urine bag coefficient Ld and the heart rate coefficient Xt and their predicted values, when there are no medical staff in the patient's ward, the patient's condition can be predicted and monitored. When necessary, notifications and reminders can be sent to the medical staff who are not in the ward in time, so that the medical staff can deal with abnormal situations in time and ensure the patient's health.

2. By obtaining the number of abnormal data and the monitoring coefficient Jxs, the patient's condition is further evaluated. When the patient's physical condition is not good, the response plan library is used to output the response plan in a timely manner for emergency treatment, thereby ensuring the patient's health status.

3. When medical staff cannot enter the ward in time, by organizing remote consultation, medical staff outside the ward can diagnose the patient in time based on the generated test data, especially at night, by sending early warning information to medical staff who are not in the ward, remote consultation can be carried out to ensure the safety of patients.

4. After organizing a remote consultation, use the output treatment plan to revise the response plan, thereby forming a new response plan, replacing and updating the response plan library, so that when the patient encounters an abnormal condition, a more accurate response plan can be obtained to ensure the patient's safety.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of a first process of a remote shared alarm system according to the present invention;

FIG2 is a schematic diagram of a second process flow of the remote shared alarm system of the present invention;

In the figure:

10. Detection unit; 11. Environment recognition module; 12. Urine volume detection module; 13. Heartbeat detection module;

20. First processing unit; 21. Evaluation module; 22. Prediction module; 23. Analysis module; 24. Model training module; 30. Control unit; 40. Communication unit; 50. Solution summary unit;

60. Second processing unit; 61. Remote consultation module; 62. Data sharing module; 63. Matching module;

70. The third processing unit; 71. The judging module; 72. The correcting module; 73. The output module; 80. The alarm unit.

Detailed ways

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.

Please refer to Figures 1 and 2. The present invention provides a remote shared alarm system for monitoring urine bag urine volume and electrocardiogram monitor, including a detection unit 10, a first processing unit 20, a control unit 30, a communication unit 40, a solution summary unit 50, a second processing unit 60, a third processing unit 70, and an alarm unit 80, wherein:

After entering the night, if there is still a patient in the current bed, the detection unit 10 first identifies whether there is a medical staff in the ward where the patient is located. If not, the patient's urine bag and heartbeat are detected respectively, and the obtained detection sub-data are used to construct a urine bag detection data set and a heartbeat detection data set respectively;

After the urine bag detection data set and the heartbeat detection data set are sent to the first processing unit 20, a urine bag coefficient Ld and a heartbeat coefficient Xt are generated respectively. When the current urine bag coefficient Ld and the heartbeat coefficient Xt do not exceed the corresponding thresholds, the trained prediction model is used to predict the urine bag coefficient Ld and the heartbeat coefficient Xt and generate prediction values respectively;

When the predicted value of the urine bag coefficient L or the heart rate coefficient Xt is higher than the corresponding threshold, the abnormal sub-data and its quantity are determined, and the abnormal characteristics are generated in combination with the abnormal degree. When the number of abnormal sub-data exceeds the corresponding threshold, the control unit 30 generates a control instruction, firstly enables the communication unit 40 to send an early warning message to the medical staff, and then enables the solution summary unit 50 to collect the corresponding response solutions according to the abnormal characteristics, and summarize and generate a response solution library;

After the medical staff receives the warning information, the second processing unit 60 matches the response plan from the response plan library with the abnormal characteristics and outputs it, combines the current urine bag detection data set, the heartbeat detection data set and the response plan library for data sharing, organizes remote consultation when there are no medical staff around the bed, and provides a treatment plan for the patient;

The third processing unit 70 corrects the output response plan and adds the corrected response plan to the response plan library. If the patient does not receive treatment from medical staff within a predetermined time after obtaining the corrected response plan or treatment plan, the alarm unit 80 sends an alarm to the outside.

1 and 2 , the detection unit 10 includes an environment recognition module 11, a urine volume detection module 12 and a heartbeat detection module 13, wherein, after entering night, the environment recognition module 11 recognizes the environment of the patient's ward to determine whether there are medical staff or accompanying personnel in the ward. If not, the environment recognition module 11 first detects the urine bag at fixed time intervals, and obtains at least the urine volume Nv, pH Sj and transparency Tm from the generated detection data, and then summarizes them to establish a urine bag detection data set; then, the heartbeat detection module 13 monitors the patient's heartbeat data in real time at fixed time intervals, and obtains at least the heartbeat frequency Xp and R-R interval Xw from the generated monitoring data, and summarizes them to form a heartbeat detection data set.

When in use, when there are no medical staff around the patient, a urine bag detection data set and a heartbeat detection data set are generated respectively. By detecting and generating sub-data at fixed time intervals, the patient's physical condition is monitored, and the patient's physical condition can be monitored based on the generated detection data.

1 and 2, the first processing unit 20 includes an evaluation module 21, a prediction module 22, an analysis module 23 and a model training module 24, wherein the urine bag detection data set and the heartbeat detection data set are respectively sent to the evaluation module 21, and based on the current sub-data, the evaluation module 21 generates a urine bag coefficient Ld and a heartbeat coefficient Xt respectively.

The urine bag coefficient Ld is generated as follows: the urine volume Nv, pH Sj and transparency Tm are obtained, and after dimensionless processing, they are calculated according to the following formula:

Among them, α and β are changeable constant parameters, 0.51≤α≤0.76, 0.61≤β≤0.93, and users can adjust them according to actual conditions. Among them, the heart rate coefficient Xt is generated as follows: obtain the heart rate Xp and R-R interval Xw, and after dimensionless processing, according to the following formula:

Among them, γ is a changeable constant parameter, 0.91≤γ≤1.36, 0.68≤θ≤1.46, the user can adjust it according to the actual situation, R is the correlation coefficient between the heart rate Xp and the R-R interval Xw, R is obtained by correlation analysis, and D is a constant correction parameter.

When in use, the patient's physical condition can be evaluated by forming the heart rate coefficient Xt and the urine bag coefficient Ld. When necessary, medical staff can take corresponding measures for the patient or issue an external warning based on the changes in the values of the heart rate coefficient Xt and the urine bag coefficient Ld.

1 and 2 , a neural network algorithm is used to select sample data from the urine bag detection data set and the heartbeat detection data set, and a coefficient prediction model is established by the model training module 24 after training and testing based on the sample data;

When the urine bag coefficient Ld and the heartbeat coefficient Xt do not exceed the corresponding threshold value, the coefficient prediction model is used, and the sub-data in the urine bag detection data set and the heartbeat detection data set are used as input data. The prediction module 22 predicts the sub-data in the urine bag detection data set and the heartbeat detection data set to generate the prediction value of the corresponding sub-data, and then generates the prediction value of the urine bag coefficient Ld and the heartbeat coefficient Xt;

When at least one of the predicted values of the urine bag coefficient Ld and the heartbeat coefficient Xt is higher than the corresponding threshold, the analysis module 23 determines the part of several sub-data in the urine bag detection data set and the heartbeat detection data set that exceeds the corresponding threshold, and marks it as abnormal data; determines the number of abnormal data, and determines the abnormal degree of the sub-data based on the proportion of the sub-data exceeding the corresponding threshold, and generates abnormal features by combining the abnormal data and its abnormal degree.

When in use, after establishing the coefficient prediction model, the changes in the urine bag coefficient Ld, the heart rate coefficient Xt and the corresponding sub-data are predicted and a predicted value is generated. When the predicted value is higher than the corresponding threshold, the abnormal sub-data is screened out, and the abnormal data and abnormal features are determined. The prediction results can be described based on the generated abnormal features. By obtaining the abnormal features, medical staff can quickly understand the patient's current status.

Referring to FIG1 and FIG2 , when the predicted values of the urine bag coefficient Ld and the heart rate coefficient Xt do not exceed the corresponding threshold values, the monitoring coefficient Jxs is generated in association, wherein the monitoring coefficient Jxs is generated as follows:

Wherein, 0≤F ₁ ≤1, 0≤F ₂ ≤1, and 0.74≤F ₁ +F ₂ ≤1.69, the specific value of which is adjusted and set by the user, and C is a constant correction coefficient.

When the monitoring coefficient Jxs exceeds the corresponding threshold, the control unit 30 generates a control instruction, firstly causing the communication unit 40 to send a warning message to the medical staff, and then causing the solution summary unit 50 to select the corresponding response plan from the existing cases and treatment plans based on the abnormal characteristics, and summarize and output the response plan library.

When in use, when the predicted values of the urine bag coefficient Ld and the heart rate coefficient Xt both show normal, the monitoring coefficient Jxs is further formed, which can make a more comprehensive judgment and warning on the patient's next state. When the medical staff is not in the room, if the monitoring coefficient Jxs shows that the patient's current state is not good, a response plan library can be quickly established according to the abnormal characteristics. When the medical staff is too late to deal with it, the response plan library can be used for emergency.

1 and 2, the second processing unit 60 includes a remote consultation module 61, a data sharing module 62 and a matching module 63, wherein:

When the medical staff who are not in the ward receive the warning information, the abnormal characteristics and the response plan are used as sample data, and the matching model is constructed using the similarity algorithm. After training and testing the sample data, the matching model is output, and the matching module 63 uses the matching model to match the response plan from the response plan library according to the abnormal characteristics and outputs it;

After summarizing the urine bag detection data set, heartbeat detection data set and response plan containing historical data and predicted data, the data sharing module 62 shares the data with the medical staff or doctor team responsible for the patient. Under the data sharing conditions, the remote consultation module 61 organizes a remote consultation and provides a treatment plan for the patient.

When in use, through the matching model generated by training, when there are abnormal features, a response plan can be quickly selected from the response plan library, so that when there are no medical staff in the ward, emergency treatment can be carried out by quickly selecting a response plan; further, by building a remote consultation system, based on the detection data and the corresponding prediction data, after notifying the medical staff who are not in the ward, a treatment plan can be given to the patient through remote consultation, thus completing the remote treatment process and improving treatment efficiency.

Referring to FIG. 1 and FIG. 2 , the third processing unit 70 includes a judgment module 71, a correction module 72 and an output module 73, wherein the coping plan and the treatment plan are obtained, and the similarity between the coping plan and the treatment plan is judged by the judgment module 71 using the trained similarity model. When the similarity is lower than a threshold, the part causing the similarity to be lower than the threshold is marked, determined as an abnormal area and output;

The response plan carrying the abnormal area is sent to the correction module 72, so that the correction module 72 corrects the abnormal area, and the corrected response plan is sent to the remote consultation module 61 for verification by the remote consultation module 61. If the verification is correct, the corrected response plan is added to the response plan library.

When in use, after obtaining the response plan and treatment plan, the output response plan is modified to form a new response plan, and the response plan library is replaced and updated, so that when the patient has an abnormal condition, a more accurate response plan can be obtained.

To sum up the above content:

By generating the urine bag coefficient Ld and the heart rate coefficient Xt and their predicted values, when there are no medical staff in the patient's ward, the patient's condition can be predicted and monitored. When necessary, timely notifications and reminders can be sent to the medical staff who are not in the ward, so that the medical staff can deal with abnormal situations in time and ensure the patient's health.

By obtaining the number of abnormal data and the monitoring coefficient Jxs, the patient's condition is further evaluated. When the patient's physical condition is not good, the response plan library is used to output the response plan in a timely manner for emergency treatment, thereby ensuring the patient's health status.

When medical staff cannot enter the ward in time, by organizing remote consultation, medical staff outside the ward can diagnose the patient in time based on the generated test data, especially at night, by sending early warning information to medical staff who are not in the ward, remote consultation can be carried out to ensure the safety of patients.

After organizing a remote consultation, the output treatment plan is used to revise the response plan, thereby forming a new response plan, replacing and updating the response plan library. When the patient encounters an abnormal condition, a more accurate response plan can be obtained to ensure the patient's safety.

The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

The above description is only a specific implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims (8)

1. A remote shared alarm system for monitoring urine volume in a urine bag and an electrocardiogram monitor, characterized in that it comprises a detection unit (10), a first processing unit (20), a control unit (30), a communication unit (40), a solution summary unit (50), a second processing unit (60), a third processing unit (70), and an alarm unit (80), wherein: After entering the night, if there is still a patient on the current bed, the detection unit (10) first identifies whether there is a medical staff in the ward where the patient is located. If not, the urine bag and heartbeat of the patient are detected respectively, and the obtained detection sub-data are used to construct a urine bag detection data set and a heartbeat detection data set respectively; After the urine bag detection data set and the heartbeat detection data set are sent to the first processing unit (20), a urine bag coefficient Ld and a heartbeat coefficient Xt are generated respectively, and when the current urine bag coefficient Ld and the heartbeat coefficient Xt do not exceed the corresponding thresholds, the trained prediction model is used to predict the urine bag coefficient Ld and the heartbeat coefficient Xt and generate prediction values respectively; When the predicted value of the urine bag coefficient Ld or the heartbeat coefficient Xt is higher than the corresponding threshold value, the abnormal sub-data and the number thereof are determined, and abnormal features are generated in combination with the abnormal degree; when the number of abnormal sub-data exceeds the corresponding threshold value, the control unit (30) generates a control instruction, firstly causing the communication unit (40) to send an early warning message to the medical staff, and then causing the solution summary unit (50) to collect corresponding response solutions according to the abnormal features, and summarize and generate a response solution library; After the medical staff receives the warning information, the second processing unit (60) matches the response plan from the response plan library with the abnormal characteristics and outputs it, combines the current urine bag detection data set, the heartbeat detection data set and the response plan library for data sharing, organizes a remote consultation when there are no medical staff around the bed, and provides a treatment plan for the patient; The third processing unit (70) amends the output response plan and adds the amended response plan to the response plan library. If the patient does not receive treatment from the medical staff within a predetermined time after the amended response plan or treatment plan is obtained, the alarm unit (80) sends an alarm to the outside. The detection unit (10) comprises an environment recognition module (11), a urine volume detection module (12) and a heartbeat detection module (13), wherein at night, the environment recognition module (11) recognizes the environment of the patient's ward to determine whether there are medical staff in the ward; if not, the environment recognition module (11) first detects the urine bag at fixed time intervals, and obtains at least the urine volume Nv, pH Sj and transparency Tm from the generated detection data, and then summarizes them to establish a urine bag detection data set; then, the heartbeat detection module (13) monitors the patient's heartbeat data in real time at fixed time intervals, and obtains at least the heartbeat frequency Xp and the R-R interval Xw from the generated monitoring data, and then summarizes them to form a heartbeat detection data set; Using a neural network algorithm, sample data is selected from a urine bag detection data set and a heartbeat detection data set, and a coefficient prediction model is established by a model training module (24) after training and testing based on the sample data; When the urine bag coefficient Ld and the heartbeat coefficient Xt do not exceed the corresponding threshold values, the coefficient prediction model is used, and the sub-data in the urine bag detection data set and the heartbeat detection data set are used as input data. The prediction module (22) predicts the sub-data in the urine bag detection data set and the heartbeat detection data set to generate prediction values of the corresponding sub-data, and then generates prediction values of the urine bag coefficient Ld and the heartbeat coefficient Xt. 2. The remote shared alarm system for monitoring urine bag urine volume and electrocardiogram monitor according to claim 1, characterized in that: the first processing unit (20) comprises an evaluation module (21), a prediction module (22), an analysis module (23) and a model training module (24), wherein the urine bag detection data set and the heartbeat detection data set are respectively sent to the evaluation module (21), and based on the current sub-data, the evaluation module (21) generates a urine bag coefficient Ld and a heartbeat coefficient Xt respectively. 3. The remote shared alarm system for monitoring urine bag urine volume and ECG monitor according to claim 2 is characterized in that: the urine bag coefficient Ld is generated as follows: the urine volume Nv, pH Sj and transparency Tm are obtained, and after dimensionless processing, according to the following formula: ; Among them, α and β are variable constant parameters. ,/> , users can adjust according to actual conditions; the heart rate coefficient Xt is generated as follows: obtain the heart rate Xp and RR interval Xw, and after dimensionless processing, according to the following formula: ; Among them, γ is a variable constant parameter, ,/> , the user can adjust it according to the actual situation, R is the correlation coefficient between the heart rate Xp and the RR interval Xw, R is obtained by correlation analysis, and D is the constant correction parameter. 4. The remote shared alarm system for monitoring urine bag urine volume and electrocardiogram monitor according to claim 3 is characterized in that: when at least one of the predicted values of the urine bag coefficient Ld and the heartbeat coefficient Xt is higher than the corresponding threshold, the analysis module (23) determines the part of several sub-data in the urine bag detection data set and the heartbeat detection data set that exceeds the corresponding threshold, and marks it as abnormal data; determines the number of abnormal data, and determines the abnormal degree of the sub-data based on the proportion of the sub-data exceeding the corresponding threshold, and generates abnormal features by combining the abnormal data and the abnormal degree. 5. The remote shared alarm system for monitoring urine bag urine volume and electrocardiogram monitor according to claim 4 is characterized in that: when the predicted values of the urine bag coefficient Ld and the heart rate coefficient Xt do not exceed the corresponding threshold value, the monitoring coefficient Jxs is generated in association, wherein the monitoring coefficient Jxs is generated as follows: ; in, ,/> , and/> , its specific value is adjusted and set by the user, and C is the constant correction coefficient. 6. The remote shared alarm system for monitoring urine bag urine volume and electrocardiogram monitor according to claim 5 is characterized in that: when the monitoring coefficient Jxs exceeds the corresponding threshold value, the control unit (30) forms a control instruction, firstly causing the communication unit (40) to send an early warning message to the medical staff, and then causing the solution summary unit (50) to select the corresponding response plan from the existing cases and treatment plans according to the abnormal characteristics, and summarize and output the response plan library. 7. The remote shared alarm system for monitoring urine bag urine volume and electrocardiogram monitor according to claim 6, characterized in that: the second processing unit (60) comprises a remote consultation module (61), a data sharing module (62) and a matching module (63), wherein: When the medical staff who are not in the ward receive the warning information, the abnormal characteristics and the response plan are used as sample data, and a matching model is constructed using a similarity algorithm. After training and testing the sample data, the matching model is output, and the matching module (63) uses the matching model to match the response plan from the response plan library according to the abnormal characteristics and outputs it; After summarizing the urine bag detection data set, heartbeat detection data set and response plan containing historical data and predicted data, the data sharing module (62) shares the data with the medical staff or doctor team responsible for the patient. Under the data sharing conditions, the remote consultation module (61) organizes a remote consultation and provides a treatment plan for the patient. 8. The remote shared alarm system for monitoring urine bag urine volume and electrocardiogram monitor according to claim 7, characterized in that: the third processing unit (70) comprises a judgment module (71), a correction module (72) and an output module (73), wherein: Obtaining a response plan and a treatment plan, using the trained similarity model, the judgment module (71) judges the similarity between the response plan and the treatment plan, and when the similarity is lower than a threshold, marking the part that causes the similarity to be lower than the threshold, determining it as an abnormal area and outputting it; The response plan containing the abnormal area is sent to the correction module (72), so that the correction module (72) corrects the abnormal area, and the corrected response plan is sent to the remote consultation module (61), which verifies it. If the verification is correct, the corrected response plan is added to the response plan library.