Infusion management system based on monitoring data

Abstract

The invention provides an infusion management system based on monitoring data, and belongs to the field of infusion management. The problem of low infusion control efficiency is solved; specifically, the medical record acquisition module constructs a disease identification model and a disease-drug table; the patient diagnosis module determines a medicine name and a medicine dosage of a patient to obtain primary prescription information; the infusion control module is used for feeding the primary prescription information back to a doctor to obtain quasi prescription information; performing fluid infusion on the patient according to the accurate prescription information, and adjusting the injection speed of the medicine in real time; the infusion monitoring module monitors the adverse reaction of the patient in the infusion process; the medical record information of the target hospital is obtained, analyzed and summarized to obtain the treatment medicine and the medicine dosage of each disease, the infusion speed of the patient in the infusion process is adjusted according to the actual body and disease conditions of the patient, and the medical efficiency is improved.

Description

Technical Field

[0001] The invention discloses an infusion management system based on monitoring data and relates to the field of infusion management. Background Art

[0002] The existing infusion management system has the following deficiencies: High requirements for medical staff: Although the existing infusion management system can automatically complete most of the monitoring work and issue early warning signals in a timely manner, medical staff are still required to use the equipment correctly and handle abnormal situations in a timely manner; if the medical staff is not familiar with the use of the equipment or operates it improperly, the equipment may not work properly or produce false alarms.

[0003] Individual differences among patients: There are individual differences among different patients, such as age, gender, physical constitution, etc. These differences will affect the type and dosage of drugs, and the infusion system needs to be personalized according to the patient's physical condition and disease condition; however, some existing infusion management systems cannot fully consider these individual differences and make corresponding adjustments and optimizations, which affects the patient's infusion effect and safety.

[0004] Equipment maintenance and replacement costs: The existing infusion control system needs to be used with a variety of sensors, displays, cameras and other equipment. The maintenance and replacement costs of these devices are too high, increasing the operating costs of medical institutions. Summary of the invention

[0005] In view of the shortcomings of the prior art, the purpose of the present invention is to provide an infusion management system based on monitoring data, aiming to solve the problem of low infusion control efficiency.

[0006] In order to achieve the above object, the present invention is implemented through the following technical solution: an infusion management system based on monitoring data comprises: Medical record acquisition module: used to obtain all medical record information of the target hospital and extract patient information, disease information and medication information from the medical record information; build a disease recognition model based on the disease information, calculate the standard dose of the drug corresponding to each disease based on the patient information and medication information, and build a disease-drug table; Patient diagnosis module: used to obtain the patient's medical examination report, use the medical examination report as the input of the disease recognition model, and determine the patient's disease name; according to the disease name and medical examination report and combined with the disease-drug table, determine the patient's medication name and dosage, and obtain primary prescription information; Infusion control module: used to feed back primary prescription information to the physician to obtain quasi-prescription information; perform intravenous injection for the patient according to the quasi-prescription information, obtain the injection video of the drug intravenous injection and the patient's blood pressure in real time, and adjust the injection speed of the drug in real time according to the injection video to ensure uniform injection of the drug; Infusion monitoring module: used to monitor the patient in real time during the infusion process to see if any adverse reactions occur; if so, notify the physician immediately; if not, continue monitoring until the patient's infusion is completed.

[0007] Furthermore, the workflow of the medical record acquisition module is as follows: Process A1: Obtain all medical records in the target hospital; extract the patient information, disease information and medication information corresponding to each medical record; Patient information includes: patient identity information, gender, age, and BMI index; Disease information includes: disease name, lesion picture and symptoms; Medication information includes: medication name and dosage; Process A2: Construct a medical record table based on patient information, disease information, and medication information. The patient identity information is the primary key of the medical record table. According to the medical record table, count the total number of all symptoms in the medical record information, recorded as bn; Process A3: Summarize all medical record information corresponding to the first disease in the medical record table to obtain medical record table 1'; Based on the medical record table 1', the disease information corresponding to the first disease is counted, and according to the patient information and medication information corresponding to the first disease, the standard dosage of the drug for treating the first disease is calculated; Process A4: repeat the same process of counting the disease information corresponding to the first disease and calculating the standard dose of the therapeutic drug for the first disease, counting the disease information corresponding to the second to bn diseases, and calculating the standard dose of the therapeutic drug corresponding to the second to bn diseases; Construct a disease-drug table in the format of the i-th disease-the standard dosage of the drug for the i-th disease; Process A5: Summarize the disease information corresponding to the 1st to bnth diseases as sample information; use the sample information as the training object, design the model structure of the CNN model, build a disease recognition model, and enter the patient diagnosis module.

[0008] Furthermore, the specific process of process A3 is as follows: Process A31: In the medical record table 1', all lesion images and symptoms corresponding to the first disease are summarized as the first disease symptom set; The name of the medication corresponding to the first disease is used as the target medication; the names and dosages of all target medications are counted; Process A32: Take the patients in medical record table 1` as target patients; count the number of all target patients, recorded as fb; count the number of target medications, recorded as mm; According to the patient's age, the age-weighted dose of the target medication is calculated to obtain qm(1), qm(2) to qm(mm); Process A33: The number of male target patients is recorded as fbm, and the number of female target patients is recorded as fbw; fbm, fbw and fp satisfy: fbm+fbw=fp; According to the patient's gender, the sex-weighted dose of the target medication was calculated to obtain rm(1), rm(2) to rm(mm); Process A34: The number of target patients whose BMI index is not within the normal range is recorded as fpa, and the number of target patients whose BMI index is within the normal range is recorded as fpb; the relationship between fpa, fpb and fp satisfies: fpa+fpb=fp; Repeat the same process of calculating rm(1)~rm(mm), calculate the body-weighted dose of the target medication according to the patient's BMI index, and obtain pm(1), pm(2)~pm(mm); Process A35: Summarize the age-weighted doses of the first to mmth target medications: qm(1), qm(2)~qm(mm); Gender-weighted dose: rm(2), rm(3)~rm(mm); Body weighted dose: pm(1), pm(2)~pm(mm); The standard dose of the first target drug is recorded as bzm(1). The calculation formula of bzm(1) is as follows: ; The standard dose of the second target drug is recorded as bzm(2). The calculation formula of bzm(2) is as follows: ; By analogy, the standard dose of the mmth target drug is recorded as bzm (mm). The calculation formula of bzm (mm) is as follows: ; BZM (1) ~ BZM (mm) are summarized as the standard doses of drugs for the treatment of the first disease.

[0009] Furthermore, the specific process of the process A32 is as follows: Process A321: Count the number of patients corresponding to age groups 1 to 4 in medical record table 1`, and record them as fp1, fp2, fp3 and fp4; fp1, fp2, fp3, fp4 and fb satisfy: fp1+fp2+fp3+fp4=fb; Process A322: Let the ternary formula a-1: m （p） (q, i); the ternary formula a-1 represents the dose of the i-th target drug for the p-th age group, the q-th target patient; where the value range of p is 1 to 4, and the value range of i is: 1 to mm; If p=1, the value range of q is: 1~fp1; if p=2, the value range of q is: 1~fp2; if p=3, the value range of q is: 1~fp3; if p=4, the value range of q is: 1~fp4; Using the ternary formula a-1 to represent the dosage of all target drugs for patients in age groups 1 to 4, we get: m （1） (1,1),m （1） (1,2)~m （1） (1, mm)~m （1） (fp1, mm)~m （4） (fp4, mm); Among them, m （1） (1,1) indicates the first age group, the first target patient, and the first target medication dose; m （1） (1,2) indicates the first age group, the first target patient, and the dose of the second target medication; By analogy, m （1） (1, mm) means the first age group, the first target patient, and the dose of the mmth target drug; m （1） (fp1, mm) indicates the dose of the mmth target drug in the first age group, the fp1th target patient; m （4） (fp4, mm) means the 4th age group, the fp4th target patient, and the mmth target drug dose; Process A323: Calculate the age-weighted dose of the first target drug, denoted as qm(1); Calculate m （1） (1,1)~m （1） The average value of (fp1, 1) is denoted as am(1); Calculate m （2） (1,1)~m （2） The average value of (fp2, 1) is denoted as am(2); Calculate m （3） (1,1)~m （3） The average value of (fp3, 1) is denoted as am(3); Calculate m （4） (1,1)~m （4） The average value of (fp4, 1) is denoted as am(4); The calculation formula of qm (1) is as follows: ; Process A324: Repeat the same process of calculating qm(1) to calculate the age-weighted doses of the 2nd to mmth target drugs, and obtain: qm(2), qm(3)~qm(mm); Among them, qm(2) represents the age-weighted dose of the second target drug; qm(3) represents the age-weighted dose of the third target drug; and so on, qm(mm) represents the age-weighted dose of the mmth target drug.

[0010] Furthermore, the specific process of the process A33 is as follows: Process A331: Let binary formula a-2: mm(x, y); ternary formula a-2 represents the dosage of the yth target medication for the xth male target patient; wherein the value range of x is: 1~fbm, and the value range of y is: 1~mm; Let the binary formula a-3: mw(w, z); the ternary formula a-1 represents the dose of the zth target medication for the wth female target patient; where the value range of w is: 1~fbw, and the value range of z is: 1~mm; Process A332: Using binary formula a-2 to represent the target drug dosage for all male patients, we obtain: mm(1,1), mm(1,2)~mm(1,m)~mm(fbm,m); Among them, mm(1,1) represents the dose of the first target medication for the first male target patient; mm(1,2) indicates the dose of the second target medication for the first male target patient; By analogy, mm(1, m) represents the dose of the mth target medication for the first male target patient; mm(fbm,m) represents the dose of the mth target medication for the fbmth male target patient; Process A333: Use binary formula a-3 to represent the target drug dosage for all female patients, and obtain: mw(1,1), mw(1,2)~mw(1,m)~mw(fbm,m); Among them, mw(1,1) represents the first female target patient and the dose of the first target medication; mw(1,2) represents the first female target patient and the dose of the second target medication; By analogy, mw(1, m) represents the dose of the mth target medication for the first female target patient; mw(fbw,m) represents the dose of the mth target medication for the fbwth female target patient; Process A334: Calculate the sex-weighted dose of the first target drug, denoted as rm(1); Calculate the average value of mm(1,1) to mm(fbm,1), recorded as bm(1); Calculate the average value of mw(1,1) to mw(fbw,1), denoted as bm(2); The calculation formula of rm(1) is as follows: ; Process A335: Repeat the same process of calculating rm(1) to calculate the sex-weighted doses of the second to mmth target drugs, and obtain: rm(2), rm(3)~rm(mm); Among them, rm(2) represents the sex-weighted dose of the second target drug; rm(3) represents the sex-weighted dose of the third target drug; and so on, rm(mm) represents the sex-weighted dose of the mmth target drug.

[0011] Furthermore, the specific process of process A5 is as follows: Process A51: Design the layer structure of the CNN model; Import library: Import the Keras module and use it to create a sequential model; Add layer: Convolutional layer 1: The number of filters is set to 32; the convolution kernel size is set to 3×3; Use ReLU (Rectified Linear Unit) as the activation function; The output shape is set to: 128×128 pixels, 3 color channels; Max pooling layer 1: The pooling window is set to: 2×2; Process A52: Adding layers: Convolutional layer 2: Set the number of filters to 64; the rest of the settings are the same as convolutional layer 1; Max pooling layer 2: The settings are the same as max pooling layer 1; Convolutional layer 3: Set the number of filters to 128; the rest of the settings are the same as convolutional layer 1; Max pooling layer 3: The settings are the same as max pooling layer 1; Process A53: Adding layers: Flatten layer: Use the Flatten() function to flatten the multi-dimensional feature map output by the maximum pooling layer 3 into a one-dimensional array; Fully connected layer: Use the add() function and the Dense() function to add 128 neurons, and use the ReLU function as the activation function to learn high-level features; Dropout layer: Use regularization techniques to randomly drop 50% of neurons to reduce overfitting; Output layer: The number of neurons output is equal to the number of different categories, and the Softmax function is used as the activation function to convert the output into a probability distribution, outputting the name of the disease with the highest probability of the patient suffering from it; Process A54: Back up the sample information three times, and use them as training set, test set and validation set respectively; use the cross entropy loss function as the loss function, use the training set and test set to train the model constructed by processes A51 to A53, and use the validation set to test the model until the output value of the loss function is minimized, thus completing the construction of the disease recognition model.

[0012] Furthermore, the workflow of the patient diagnosis module is as follows: Process B1: Obtain the patient's medical examination report, use the medical examination report as the input of the disease recognition model, and determine the patient's disease name as the disease name; Search the disease-drug table according to the disease name, and use the drug name that has the same disease name as the disease name as the prescription drug; The dosage of the prescribed medication is by default: the standard dosage of the disease name corresponding to the medication name; Process B2: Obtain the patient's MBI index and calculate the reduction ratio of prescribed medication, recorded as cu; Process B21: The MBI index of the patient is recorded as tz, and the normal range of the MBI index is recorded as [tz1, tz2]; determine whether tz is within the interval [tz1, tz2]; If tz is in the interval [tz1,tz2], then cu=0; If tz is not in the interval [tz1,tz2], compare tz with tz1 and tz2, and enter process B22; Process B22: If tz<tz1, the calculation formula of cu is as follows: ; If tz>tz1, the calculation formula of cu is as follows: ; Process B3: The patient's disease name, prescribed medications and the reduction ratio of prescribed medications are sent to the infusion control module as primary prescription information.

[0013] Furthermore, the workflow of the infusion control module is as follows: Process C1: Feedback primary prescription information to physicians to obtain quasi-prescription information; Process C2: before infusion; assuming that the width of the infusion bottle is d1; the width of the infusion tube is d2; Assume that the height of the liquid level in the infusion bottle before infusion is h1; Assume that the longitudinal distance from the mouth of the infusion bottle to the palm is h2; Get the density of the liquid drug in the infusion bottle, denoted as ρ液 ; Process C3: After infusion; after infusion, the volume of the liquid medicine in the infusion bottle is reduced, which is recorded as ΔV; The speed at which the liquid level in the infusion bottle drops is recorded as v1; the speed at which the liquid medicine in the infusion tube is infused is recorded as v2; The time it takes for the liquid level in the infusion bottle to drop is recorded as Δt; Process C4: Assume the patient's blood pressure before infusion is P 血 ; Atmospheric pressure is recorded as P 大气 ; Assuming that the patient's blood pressure remains unchanged during the infusion process, derive the constraint condition 1 of the infusion speed v2; Process C5: Combine constraint 1 to derive constraint 2 of v2; Process C51: During the infusion process, the patient's blood pressure is proportional to the density of the patient's blood after the infusion; Assume that the total volume of human blood is V 血 , the density of blood is ρ 血 ; Assume that the blood density of the patient after infusion is ρρ 血 , the calculation formula is: ; Relation 4; Process C52: From Relation 4 and Equation 1-3, the blood density of the patient after infusion is proportional to v2; The mathematical expression of equation 1-3 is as follows: ; Process C53: Combining constraint 1, relation 4 and equation 1-3, it can be seen that the square of the patient's blood pressure change rate is proportional to the first power of the v2 change rate; Assume that the rate of change of the patient's blood pressure from before to after infusion is b (ρ 血 ), the rate of change of v2 is b(v2), then b(ρ 血 ) and b(v2) satisfy the following relationship: [b(ρ 血 )] 2 ∝b(v2); Constraint 2; Process C6: Obtain the patient's blood pressure before infusion and record it as ρb; Obtain monitoring video of the patient during infusion, calculate the falling speed of the liquid medicine in the infusion bottle when the patient starts infusion based on the monitoring video, and calculate the infusion speed of the liquid medicine in the infusion tube based on the falling speed of the liquid medicine, recorded as vo; Obtain the patient's blood pressure in real time during the infusion process and adjust the value of vo according to constraint 2.

[0014] Furthermore, the specific process of process C4 is as follows: Process C41: During the infusion process, there is a dynamic balance between the gas pressure in the infusion bottle, the liquid pressure of the liquid drug, and the atmospheric pressure connected to the air inlet pipe, that is: P (gas) + P (drug) = P 大气 ; Equation 1-1 Among them, P (gas) represents the pressure of the gas in the bottle, and P (drug) represents the liquid pressure of the liquid drug in the bottle; Substituting the calculated data of P (drug) into equation 1-1, we get relation 1; Relationship 1: P (gas) + (ρ 液 ×g×h1)=P 大气 ; Where g represents the acceleration due to gravity, g is 9.8m / s 2 ; Process C42: During the infusion process, the gas in the bottle does positive work, the gravity of the liquid medicine does positive work, the atmospheric pressure connected to the air inlet pipe does negative work, and the patient's blood does negative work; according to the law of conservation of energy, the algebraic sum of the work done by the gas in the bottle, the gravity of the liquid medicine, the atmospheric pressure, and the blood is equal to the change in kinetic energy, that is: W (gas) + W (weight) - W (atmosphere) - W (blood) = ΔEk; Equation 1-2 Wherein, W(gas) represents the work done by the gas in the bottle, W(gas) = ​​P(gas) × ΔV; W (weight) represents the work done by the gravity of liquid medicine, W (weight) = (ρ 液 ×ΔV×g)×(h1+h2);where g represents the acceleration due to gravity; W(atmosphere) represents the work done by atmospheric pressure, W(atmosphere) = P 大气 ×ΔV; W(blood) represents the work done by blood, W(blood) = P 血 ×ΔV; ΔEk represents the change in kinetic energy, ΔEk = 1 / 2 × (Δm) × (v2 2 -v1 2 ); where Δm represents the weight reduction of the liquid medicine, Δm = ρ 液 ×ΔV; Process C43: Substitute the calculation formulas of W(gas), W(weight), W(atmosphere) and W(blood) into equation 1-2 to obtain equation 2; equation 2: ; The volume of liquid medicine in the infusion bottle that is reduced is the same as the volume of liquid medicine in the infusion tube that is injected into the patient's body, that is: ; Equation 1-3; where π represents pi; Rearranging equations 1-3 yields equation 3; Relation 3: ; Process C44: Combine equations 1 to 3 to obtain the determinant of v2 as constraint 1; Determinant of v2: .

[0015] Furthermore, the specific process of process C6 is as follows: Process C61: record the adjusted vo as ve; Obtain the patient's blood pressure in real time during the infusion process, recorded as ρd; Take [0,10] as the error range, compare the size of ρd and ρb, and determine the calculation formula of ve; Process C62: If ρd=ρb, it means that the infusion rate is normal and vo is not adjusted, that is, ve=vo; If ρd<ρb, it means that the infusion speed is faster, and the calculation formula for reducing vo,ve is: ; If ρd>ρb, it means that the infusion speed is slow, and the calculation formula for increasing vo,ve is: .

[0016] Compared with the prior art, the present invention has the following beneficial effects: Improve infusion safety: The present invention can accurately monitor the infusion speed. Once it is found that the infusion speed is too fast or too slow, the infusion speed will be adjusted immediately, thereby avoiding physical discomfort or even life-threatening safety of patients caused by improper infusion speed.

[0017] Improve nursing work efficiency: The traditional infusion process requires medical staff to constantly patrol and manually manage, which increases the burden on medical staff. The present invention can automatically complete the monitoring of infusion and immediately issue a warning signal once an abnormal situation is found, thereby reducing the workload of medical staff and improving medical efficiency.

[0018] Realize real-time monitoring and management of infusion: The present invention monitors and manages the patient's infusion process based on monitoring data, allowing medical staff to view the real-time status and historical records of infusion treatment in any department through the network from anywhere in the hospital; this remote monitoring and management function enables medical staff to communicate and collaborate more efficiently, providing patients with better medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 It is a schematic diagram of the system of the present invention; Figure 2 This is a schematic diagram of the present invention before infusion; Figure 3 It is a schematic diagram after infusion of the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] See also Figure 1 The infusion management system based on monitoring data includes: a medical record acquisition module, a patient diagnosis module, an infusion control module, an infusion monitoring module, a database and a server; wherein the medical record acquisition module, the patient diagnosis module, the infusion control module and the infusion monitoring module are connected to the database and the server respectively.

[0022] Among them, the database and server are used for data transmission and data calculation between the medical record acquisition module, the patient diagnosis module, the infusion control module and the infusion monitoring module; Medical record acquisition module: used to obtain all medical record information of the target hospital and extract patient information, disease information and medication information from the medical record information; build a disease recognition model based on the disease information, calculate the standard dose of the drug corresponding to each disease based on the patient information and medication information, and build a disease-drug table; It should be noted that the "target hospital" in the present invention means: a county-level hospital that uses the present invention to manage infusion; the "drug" in the present invention, unless otherwise specified, means "(medical liquid) injection"; Process A: The workflow of the medical record acquisition module is as follows: Process A1: Obtain all medical records in the target hospital; extract the patient information, disease information and medication information corresponding to each medical record; Patient information includes: patient identity information, gender, age, and BMI index; Disease information includes: disease name, lesion picture and symptoms; Medication information includes: medication name and dosage; It should be noted that the "BMI index" in the present invention refers to the "body mass index", which is a standard for "measuring the degree of fatness and health of the human body"; the normal range of the BMI index is between 18.5 and 23.9 kg / m² (or 18.5 and 24.9 kg / m²); "Patient's identity information" refers to information that can uniquely indicate the patient's personal identity, such as: the patient's name, ID number, mobile phone number, etc.

[0023] Process A2: Construct a medical record table based on patient information, disease information, and medication information. The patient identity information is the primary key of the medical record table. The corresponding SQL statement is as follows: Medical Records Form: Create table medical records( Patient identity information String, patient gender String, patient age String, patient BMI index String, onset time DATA, Disease name String, lesion image BLOB, symptoms CLOB, Medication name String, medication dosage Double, primary key (patient identification information) According to the medical record table, (using SQL statement 1) count the total number of all symptoms in the medical record information, recorded as bn; SQL statement 1 is as follows: select count(distinct disease name) as bn from medical records; Process A3: In the medical record table, use SQL statement a to summarize all medical record information corresponding to the first disease to obtain medical record table 1` (that is, the representation range of medical record table 1: medical record information of the first disease); SQL statement a is as follows: select * from medical records where disease name = 'the first disease'; Based on the medical record table 1', the disease information corresponding to the first disease is counted, and according to the patient information and medication information corresponding to the first disease, the standard dosage of the drug for treating the first disease is calculated; Process A31: In the medical record table 1', use SQL statement b to summarize all the lesion images and symptoms corresponding to the first disease as the first disease symptom set; SQL statement b is as follows: select blob_column,clob_column as symptom set of the first disease from medical record table 1`; The name of the medication corresponding to the first symptom is used as the target medication; the name and dosage of all target medications are counted using SQL statement c; SQL statement c is as follows: select medication name as target medication name, medication dosage as target medication dosage from medical record table 1`; Process A32: Take the patients in medical record table 1` as target patients; (using SQL statement d) count the number of all target patients, recorded as fb; SQL statement d is as follows: select count(*) from medical record table 1`; Count the number of target medications, recorded as mm; According to the patient's age, the age-weighted dose of the target medication is calculated to obtain qm(1), qm(2) to qm(mm); Process A321: Refer to Table 1, count the number of patients corresponding to age groups 1 to 4 in medical record table 1`, and record them as fp1, fp2, fp3 and fp4; fp1, fp2, fp3, fp4 and fb satisfy: fp1+fp2+fp3+fp4=fb; Age range Age Group (0，18] 1 [19，40] 2 [41，60) 3 ≥60 4 Table 1 (Age group classification table) Process A322: Let the ternary formula a-1: m （p） (q, i); the ternary formula a-1 represents the dose of the i-th target drug for the p-th age group, the q-th target patient; where the value range of p is 1 to 4, and the value range of i is: 1 to mm; If p=1, the value range of q is: 1~fp1; if p=2, the value range of q is: 1~fp2; if p=3, the value range of q is: 1~fp3; if p=4, the value range of q is: 1~fp4; Using the ternary formula a-1 to represent the dosage of all target drugs for patients in age groups 1 to 4, we get: m （1） (1,1),m （1） (1,2)~m （1） (1, mm)~m （1） (fp1, mm)~m （4） (fp4, mm); Among them, m （1） (1,1) indicates the first age group, the first target patient, and the first target medication dose; m （1） (1,2) indicates the first age group, the first target patient, and the dose of the second target medication; By analogy, m （1） (1, mm) means the first age group, the first target patient, and the dose of the mmth target drug; m （1） (fp1, mm) indicates the dose of the mmth target drug in the first age group, the fp1th target patient; m （4） (fp4, mm) means the 4th age group, the fp4th target patient, and the mmth target drug dose; Process A323: Calculate the age-weighted dose of the first target drug, denoted as qm(1); Calculate m （1） (1,1)~m （1） The average value of (fp1, 1) is denoted as am(1); Calculate m （2） (1,1)~m （2） The average value of (fp2, 1) is denoted as am(2); Calculate m （3） (1,1)~m （3） The average value of (fp3, 1) is denoted as am(3); Calculate m （4） (1,1)~m （4） The average value of (fp4, 1) is denoted as am(4); The calculation formula of qm (1) is as follows: ; Process A324: Repeat the same process of calculating qm(1) to calculate the age-weighted doses of the 2nd to mmth target drugs, and obtain: qm(2), qm(3)~qm(mm); Wherein, qm(2) represents the age-weighted dose of the second target drug; qm(3) represents the age-weighted dose of the third target drug; and so on, qm(mm) represents the age-weighted dose of the mmth target drug; Process A33: The number of male target patients is recorded as fbm, and the number of female target patients is recorded as fbw; fbm, fbw and fp satisfy: fbm+fbw=fp; According to the patient's gender, the sex-weighted dose of the target medication was calculated to obtain rm(1), rm(2) to rm(mm); Process A331: Let binary formula a-2: mm(x, y); ternary formula a-2 represents the dosage of the yth target medication for the xth male target patient; wherein the value range of x is: 1~fbm, and the value range of y is: 1~mm; Let the binary formula a-3: mw(w, z); the ternary formula a-1 represents the dose of the zth target medication for the wth female target patient; where the value range of w is: 1~fbw, and the value range of z is: 1~mm; Process A332: Use binary formula a-2 to represent the target drug dosage for all male patients, and obtain: mm(1,1), mm(1,2)~mm(1,m)~mm(fbm,m); Among them, mm(1,1) represents the dose of the first target medication for the first male target patient; mm(1,2) indicates the dose of the second target medication for the first male target patient; By analogy, mm(1, m) represents the dose of the mth target medication for the first male target patient; mm(fbm,m) represents the dose of the mth target medication for the fbmth male target patient; Process A333: Use binary formula a-3 to represent the target drug dosage for all female patients, and obtain: mw(1,1), mw(1,2)~mw(1,m)~mw(fbm,m); Among them, mw(1,1) represents the first female target patient and the dose of the first target medication; mw(1,2) represents the first female target patient and the dose of the second target medication; By analogy, mw(1, m) represents the dose of the mth target medication for the first female target patient; mw(fbw,m) represents the dose of the mth target medication for the fbwth female target patient; Process A334: Calculate the sex-weighted dose of the first target drug, denoted as rm(1); Calculate the average value of mm(1,1) to mm(fbm,1), recorded as bm(1); Calculate the average value of mw(1,1) to mw(fbw,1), denoted as bm(2); The calculation formula of rm(1) is as follows: ; Process A335: Repeat the same process of calculating rm(1) to calculate the sex-weighted doses of the second to mmth target drugs, and obtain: rm(2), rm(3)~rm(mm); Among them, rm(2) represents the sex-weighted dose of the second target drug; rm(3) represents the sex-weighted dose of the third target drug; and so on, rm(mm) represents the sex-weighted dose of the mmth target drug; Process A34: The number of target patients whose BMI index is not within the normal range (i.e., BMI index is between 18.5 and 23.9 kg / m² (or 18.5 and 24.9 kg / m²)) is recorded as fpa, and the number of target patients whose BMI index is within the normal range is recorded as fpb; the relationship between fpa, fpb and fp satisfies: fpa+fpb=fp; According to the patient's BMI index, the body-weighted dose of the target medication is calculated to obtain pm(1), pm(2)~pm(mm); Process A341: Let binary formula a-4: ma(u, v); binary formula a-4 represents the dose of the vth target medication for the uth target patient whose BMI index is not within the normal range; the value range of u is: 1~fpa, and the value range of v is: 1~mm; Assume binary formula a-5: mb(k, l); binary formula a-5 represents the dose of the lth target medication for the target patient whose BMI index is below the normal range; the value range of k is: 1~fpb, and the value range of l is: 1~mm; Process A342: Use binary formula a-4 to represent the target drug dosage for all patients whose BMI index is not within the normal range, and obtain: ma(1,1), ma(1,2)~ma(1,mm)~ma(fpa,mm); Among them, ma(1,1) represents the dose of the first target medication for the first target patient whose BMI index is not within the normal range; ma(1,2) represents the dose of the second target medication for the first target patient whose BMI index is not within the normal range; By analogy, ma(1, mm) represents the dose of the mmth target medication for the first target patient whose BMI index is not within the normal range; ma (fpa, mm) represents the dose of the mmth target medication for the fpath target patient whose BMI index is not within the normal range; Process A343: using binary formula a-5 to represent the target drug dosage for all patients whose BMI index is within the normal range, to obtain: mb(1,1), mb(1,2)~mb(1,mm)~mb(fpb,mm); Among them, mb(1,1) represents the dose of the first target medication for the first target patient whose BMI index is within the normal range; mb(1,2) represents the dose of the second target medication for the first target patient whose BMI index is within the normal range; By analogy, mb(1, mm) represents the dose of the mmth target medication for the first target patient whose BMI index is within the normal range; MB (fpa, mm) indicates the dose of the mmth target medication for the target patient with the fpbth BMI index in the normal range; Process A344: Calculate the constitution-weighted dose of the first target drug, denoted as pm(1); Calculate the average value of ma(1,1)~ma(fpa,1), recorded as cm(1); Calculate the average value of MB(1,1) to MB(fpb,1), recorded as cm(2); The calculation formula of pm(1) is as follows: ; Process A345: Repeat the same process of calculating pm(1) to calculate the constitution weighted doses of the second to mmth target drugs, and obtain: pm(2), pm(3)~pm(mm); Among them, pm(2) represents the body weighted dose of the second target drug; pm(3) represents the body weighted dose of the third target drug; and so on, pm(mm) represents the body weighted dose of the mmth target drug; Process A35: Summarize the age-weighted doses of the first to mmth target medications: qm(1), qm(2)~qm(mm); Gender-weighted dose: rm(2), rm(3)~rm(mm); Body weighted dose: pm(1), pm(2)~pm(mm); The standard dose of the first target drug is recorded as bzm(1). The calculation formula of bzm(1) is as follows: ; The standard dose of the second target drug is recorded as bzm(2). The calculation formula of bzm(2) is as follows: ; By analogy, the standard dose of the mmth target drug is recorded as bzm (mm). The calculation formula of bzm (mm) is as follows: ; Bzm (1) to bzm (mm) are summarized as the standard dose of drugs for the treatment of the first disease; Process A4: repeat the same process of counting the disease information corresponding to the first disease and calculating the standard dose of the treatment drug for the first disease (i.e., process A31 to process A35), counting the disease information corresponding to the second to bnth diseases, and calculating the standard dose of the treatment drug corresponding to the second to bnth diseases; Construct a disease-drug table in the format of "the i-th disease - the standard dose of the drug for the i-th disease"; Process A5: Summarize the disease information corresponding to the 1st to bnth diseases as sample information; use the sample information as the training object, design the model structure of the CNN model, and build a disease recognition model; Process A51: Design the layer structure of the CNN model; Import library: Import the Keras module and use it to create a sequential model (Sequential); Add layer: Convolutional layer 1: The number of filters is set to 32; the convolution kernel size is set to 3×3; Use ReLU (Rectified Linear Unit) as the activation function; The output shape is set to: 128×128 pixels, 3 color channels (RGB); Max pooling layer 1: The pooling window is set to: 2×2; Process A52: Adding layers: Convolutional layer 2: Set the number of filters to 64; the rest of the settings are the same as convolutional layer 1; Max pooling layer 2: The settings are the same as max pooling layer 1; Convolutional layer 3: Set the number of filters to 128; the rest of the settings are the same as convolutional layer 1; Max pooling layer 3: The settings are the same as max pooling layer 1; Process A53: Adding layers: Flatten layer: Use the Flatten() function to flatten the multi-dimensional feature map output by the maximum pooling layer 3 into a one-dimensional array; Fully connected layer: Use the add() function and the Dense() function to add 128 neurons, and use the ReLU function as the activation function to learn high-level features; Dropout layer: Use regularization techniques to randomly discard 50% of neurons to reduce overfitting; Output layer: The number of neurons output is equal to the number of different categories (i.e. the names of diseases that the patient may suffer from), and the Softmax function is used as the activation function to convert the output into a probability distribution, outputting the name of the disease with the highest probability of the patient suffering from the disease; Process A54: Back up the sample information three times, and use them as training set, test set and validation set respectively; use the cross entropy loss function as the loss function, use the training set and test set to train the model constructed by processes A51 to A53, and use the validation set to test the model until the output value of the loss function is minimized, completing the construction of the disease recognition model and entering the patient diagnosis module.

[0024] Patient diagnosis module: used to obtain the patient's medical examination report, use the medical examination report as the input of the disease recognition model, and determine the patient's disease name; according to the disease name and medical examination report and combined with the disease-drug table, determine the patient's medication name and dosage, and obtain primary prescription information; Process B: The workflow of the patient diagnosis module is as follows: Process B1: Obtain the patient's medical examination report, use the medical examination report as the input of the disease recognition model, and determine the patient's disease name as the disease name; Search the disease-drug table according to the disease name, and use the drug name that has the same disease name as the disease name as the prescription drug; The dosage of the prescribed medication is by default: (in the disease-drug table) the standard dosage of the disease name corresponding to the medication name; Process B2: Obtain the patient's MBI index and calculate the reduction ratio of prescribed medication, recorded as cu; Process B21: The MBI index of the patient is recorded as tz, and the normal range of the MBI index is recorded as [tz1, tz2]; determine whether tz is within the interval [tz1, tz2]; If tz is in the interval [tz1,tz2], then cu=0; If tz is not in the interval [tz1,tz2], compare tz with tz1 and tz2, and enter process B22; Process B22: If tz<tz1, the calculation formula of cu is as follows: ; If tz>tz1, the calculation formula of cu is as follows: ; Process B3: The patient's disease name, prescribed medications and the reduction ratio of prescribed medications are sent to the infusion control module as primary prescription information.

[0025] Infusion control module: used to feed back primary prescription information to the physician, and obtain quasi-prescription information (after modification and confirmation by the physician); perform intravenous injection for the patient according to the quasi-prescription information, obtain the injection video of the drug intravenous injection and the patient's blood pressure in real time, and adjust the injection speed of the drug in real time according to the injection video to ensure uniform injection of the drug; Process C: The workflow of the infusion control module is as follows: Process C1: Feedback the primary prescription information to the physician, and obtain the quasi-prescription information (after modification and confirmation by the physician); Process C2: Please refer to Figure 2 , before infusion; let the width of the infusion bottle be d1; let the width of the infusion tube be d2; Assume that before infusion, the liquid level in the infusion bottle is h1 (i.e. Figure 2 The liquid level in the infusion bottle); let the vertical distance from the mouth of the infusion bottle to the palm be h2; Get the density of the liquid drug in the infusion bottle, denoted as ρ 液 ; Process C3: Please refer to Figure 3 , after infusion; after infusion, the volume of the liquid medicine in the infusion bottle is reduced, recorded as ΔV (i.e. Figure 3 The volume between the original liquid level height and the liquid level height); The speed at which the liquid level in the infusion bottle drops is recorded as v1 (i.e. Figure 3The speed of the liquid level in the infusion tube is recorded as v2; The time it takes for the liquid level in the infusion bottle to drop is recorded as Δt; Process C4: Assume the patient's blood pressure before infusion is P 血 ; Atmospheric pressure is recorded as P 大气 ; Assuming that the patient's blood pressure remains unchanged during the infusion process, derive the constraint condition 1 of the infusion speed v2; Process C41: During the infusion process, there is a dynamic balance between the "gas pressure in the infusion bottle", the "liquid pressure of the liquid drug" and the "atmospheric pressure connected to the air inlet pipe", that is: P (gas) + P (drug) = P 大气 ; Equation 1-1 Among them, P (gas) represents the pressure of the gas in the bottle, and P (drug) represents the liquid pressure of the liquid drug in the bottle; Substituting the calculated data of P (drug) into equation 1-1, we get relation 1; Relationship 1: P (gas) + (ρ 液 ×g×h1)=P 大气 ; Where g represents the acceleration due to gravity, g is 9.8m / s 2 ; Process C42: During the infusion process, the gas in the bottle does positive work, the gravity of the liquid medicine does positive work, the atmospheric pressure connected to the air inlet pipe does negative work, and the patient's blood does negative work; according to the law of conservation of energy, the algebraic sum of the work done by the gas in the bottle, the gravity of the liquid medicine, the atmospheric pressure, and the blood is equal to the change in kinetic energy, that is: W (gas) + W (weight) - W (atmosphere) - W (blood) = ΔEk; Equation 1-2 Wherein, W(gas) represents the work done by the gas in the bottle, W(gas) = ​​P(gas) × ΔV; W (weight) represents the work done by the gravity of liquid medicine, W (weight) = (ρ 液 ×ΔV×g)×(h1+h2);where g represents the acceleration due to gravity; W(atmosphere) represents the work done by atmospheric pressure, W(atmosphere) = P 大气 ×ΔV; W(blood) represents the work done by blood, W(blood) = P 血 ×ΔV; (It should be noted that because the work done by the liquid = the work done by the displacement of the liquid volume = the work done by the pressure difference of the liquid surface; and because it is set here that the patient's blood pressure remains unchanged during the infusion process, so "P 血 ×ΔV” is equivalent to the work done by the blood, please note) ΔEk represents the change in kinetic energy, ΔEk = 1 / 2 × (Δm) × (v2 2-v1 2 ); where Δm represents the weight reduction of the liquid medicine, Δm = ρ 液 ×ΔV; Process C43: Substitute the calculation formulas of W(gas), W(weight), W(atmosphere) and W(blood) into equation 1-2 to obtain equation 2; equation 2: ; The volume of liquid medicine in the infusion bottle that is reduced is the same as the volume of liquid medicine in the infusion tube that is injected into the patient's body, that is: ; Equation 1-3; where π represents pi; Rearranging equations 1-3 yields equation 3; Relation 3: ; Process C44: Combine equations 1 to 3 to obtain the determinant of v2 as constraint 1; Determinant of v2: ; Process C5: Combine constraint 1 to derive constraint 2 of v2; Process C51: According to the definition of liquid pressure (liquid pressure = liquid density × liquid level × gravity acceleration), during the infusion process, the patient's blood pressure is proportional to the density of the patient's blood after the infusion; Assume that the total volume of human blood is V 血 , the density of blood is ρ 血 ; Assume that the blood density of the patient after infusion is ρρ 血 , the calculation formula is: ; Relation 4; Process C52: From Relation 4 and Equation 1-3, the blood density of the patient after infusion is proportional to v2; The mathematical expression of equation 1-3 is as follows: ; Process C53: Combining constraint 1, relation 4 and equation 1-3, it can be seen that the square of the patient's blood pressure change rate is proportional to the first power of the v2 change rate; Assume that the rate of change of the patient's blood pressure from before to after infusion is b (ρ 血 ), the rate of change of v2 is b(v2), then b(ρ 血 ) and b(v2) satisfy the following relationship: [b(ρ 血 )] 2 ∝b(v2); Constraint 2; Process C6: Obtain the patient's blood pressure before infusion and record it as ρb; Obtain the monitoring video of the patient during the infusion process, calculate the falling speed of the liquid medicine in the infusion bottle when the patient starts the infusion based on the monitoring video, and calculate the infusion speed of the liquid medicine in the infusion tube based on the falling speed of the liquid medicine, recorded as vo; (Refer to Relationship 3) Obtain the patient's blood pressure in real time during the infusion process and adjust the value of vo according to constraint 2; Process C61: record the adjusted vo as ve; Obtain the patient's blood pressure in real time during the infusion process, recorded as ρd; Take [0,10] as the error range, compare the size of ρd and ρb, and determine the calculation formula of ve; Process C62: If ρd=ρb, it means that the infusion rate is normal and vo is not adjusted, that is, ve=vo; If ρd<ρb, it means that the infusion speed is faster, and the calculation formula for reducing vo,ve is: ; If ρd>ρb, it means that the infusion speed is slow, and the calculation formula for increasing vo,ve is: .

[0026] It should be noted that, in the infusion control module of the present invention, the "uniform speed injection" in "making the drug injected at a uniform speed" is not "absolute uniform speed injection" but "equivalent uniform speed injection"; that is, the infusion control module adjusts the injection speed of the drip, that is, the speed of v2, so that the patient's blood pressure, drug and injection speed reach a dynamic balance during the infusion process, thereby preventing the patient from experiencing discomfort due to too fast or too slow infusion speed during the infusion process.

[0027] Infusion monitoring module: used to monitor in real time whether the patient has adverse reactions (allergic, shock, fainting, etc.) during the infusion process; if it occurs, notify the doctor immediately; if it does not occur, continue to monitor until the patient's infusion is completed.

[0028] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technical personnel in this field according to actual conditions. For example, if there are weight coefficients and proportional coefficients, their set sizes are to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison. Regarding the size of the weight coefficient and the proportional coefficient, it is sufficient as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0029] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An infusion management system based on monitoring data, characterized in that: The infusion management system comprises: Medical record acquisition module: used to obtain all medical record information of the target hospital and extract patient information, disease information and medication information from the medical record information; build a disease recognition model based on the disease information, calculate the standard dose of the drug corresponding to each disease based on the patient information and medication information, and build a disease-drug table; Patient diagnosis module: used to obtain the patient's medical examination report, use the medical examination report as the input of the disease recognition model, and determine the patient's disease name; according to the disease name and medical examination report and combined with the disease-drug table, determine the patient's medication name and dosage, and obtain primary prescription information; Infusion control module: used to feed back primary prescription information to the physician to obtain quasi-prescription information; perform intravenous injection for the patient according to the quasi-prescription information, obtain the injection video of the drug intravenous injection and the patient's blood pressure in real time, and adjust the injection speed of the drug in real time according to the injection video to ensure uniform injection of the drug; Infusion monitoring module: used to monitor the patient in real time during the infusion process to see if any adverse reactions occur; if so, notify the physician immediately; if not, continue monitoring until the patient's infusion is completed.

2. The infusion management system based on monitoring data according to claim 1, characterized in that: The workflow of the medical record acquisition module is as follows: Process A1: Obtain all medical records in the target hospital; Extract the patient information, disease information and medication information corresponding to each medical record information; Patient information includes: patient identity information, gender, age, and BMI index; Disease information includes: disease name, lesion picture and symptoms; Medication information includes: medication name and dosage; Process A2: Construct a medical record table based on patient information, disease information, and medication information. The patient identity information is the primary key of the medical record table. According to the medical record table, count the total number of all symptoms in the medical record information, recorded as bn; Process A3: Summarize all medical record information corresponding to the first disease in the medical record table to obtain medical record table 1'; Based on the medical record table 1', the disease information corresponding to the first disease is counted, and according to the patient information and medication information corresponding to the first disease, the standard dosage of the drug for treating the first disease is calculated; Process A4: repeat the same process of counting the disease information corresponding to the first disease and calculating the standard dose of the therapeutic drug for the first disease, counting the disease information corresponding to the second to bn diseases, and calculating the standard dose of the therapeutic drug corresponding to the second to bn diseases; Construct a disease-drug table in the format of the i-th disease-the standard dosage of the drug for the i-th disease; Process A5: Summarize the disease information corresponding to the 1st to bnth diseases as sample information; use the sample information as the training object, design the model structure of the CNN model, build a disease recognition model; and enter the patient diagnosis module.

3. The infusion management system based on monitoring data according to claim 2, characterized in that: The specific process of process A3 is as follows: Process A31: In the medical record table 1', all lesion images and symptoms corresponding to the first disease are summarized as the first disease symptom set; The name of the medication corresponding to the first disease is used as the target medication; Count the names and dosages of all target medications; Process A32: The patient in medical record table 1` is used as the target patient; Count the number of all target patients, denoted as fb; Count the number of target medications, recorded as mm; According to the patient's age, the age-weighted dose of the target medication is calculated to obtain qm(1), qm(2) to qm(mm); Process A33: The number of male target patients is recorded as fbm, and the number of female target patients is recorded as fbw; fbm, fbw and fp satisfy: fbm+fbw=fp; According to the patient's gender, the sex-weighted dose of the target medication was calculated to obtain rm(1), rm(2) to rm(mm); Process A34: The number of target patients whose BMI index is not within the normal range is recorded as fpa, and the number of target patients whose BMI index is within the normal range is recorded as fpb; the relationship between fpa, fpb and fp satisfies: fpa+fpb=fp; Repeat the same process of calculating rm(1)~rm(mm), calculate the body-weighted dose of the target medication according to the patient's BMI index, and obtain pm(1), pm(2)~pm(mm); Process A35: Summarize the age-weighted doses of the first to mmth target medications: qm(1), qm(2)~qm(mm); Gender-weighted dose: rm(2), rm(3)~rm(mm); Body weighted dose: pm(1), pm(2)~pm(mm); The standard dose of the first target drug is recorded as bzm(1). The calculation formula of bzm(1) is as follows: ； The standard dose of the second target drug is recorded as bzm(2). The calculation formula of bzm(2) is as follows: ； By analogy, the standard dose of the mmth target drug is recorded as bzm (mm). The calculation formula of bzm (mm) is as follows: ； BZM (1) ~ BZM (mm) are summarized as the standard doses of drugs for the treatment of the first disease.

4. The infusion management system based on monitoring data according to claim 3, characterized in that: The specific process of process A32 is as follows: Process A321: Count the number of patients corresponding to age groups 1 to 4 in medical record table 1`, and record them as fp1, fp2, fp3 and fp4; fp1, fp2, fp3, fp4 and fb satisfy: fp1+fp2+fp3+fp4=fb; Process A322: Let the ternary formula a-1: m （p） (q, i); the ternary formula a-1 represents the dose of the i-th target drug for the p-th age group, the q-th target patient; where the value range of p is 1 to 4, and the value range of i is: 1 to mm; If p=1, the value range of q is: 1~fp1; if p=2, the value range of q is: 1~fp2; if p=3, the value range of q is: 1~fp3; if p=4, the value range of q is: 1~fp4; Using the ternary formula a-1 to represent the dosage of all target drugs for patients in age groups 1 to 4, we get: m （1） (1,1),m （1） (1,2)~m （1） (1, mm)~m （1） (fp1, mm)~m （4） (fp4, mm); Among them, m （1） (1,1) indicates the first age group, the first target patient, and the first target medication dose; m （1） (1,2) indicates the first age group, the first target patient, and the dose of the second target medication; By analogy, m （1） (1, mm) means the first age group, the first target patient, and the dose of the mmth target drug; m （1） (fp1, mm) indicates the dose of the mmth target drug in the first age group, the fp1th target patient; m （4） (fp4, mm) means the 4th age group, the fp4th target patient, and the mmth target drug dose; Process A323: Calculate the age-weighted dose of the first target drug, denoted as qm(1); Calculate m （1） (1,1)~m （1） The average value of (fp1, 1) is denoted as am(1); Calculate m （2） (1,1)~m （2） The average value of (fp2, 1) is denoted as am(2); Calculate m （3） (1,1)~m （3） The average value of (fp3, 1) is denoted as am(3); Calculate m （4） (1,1)~m （4） The average value of (fp4, 1) is denoted as am(4); The calculation formula of qm (1) is as follows: ； Process A324: Repeat the same process of calculating qm(1) to calculate the age-weighted doses of the 2nd to mmth target drugs, and obtain: qm(2), qm(3)~qm(mm); Among them, qm(2) represents the age-weighted dose of the second target drug; qm(3) represents the age-weighted dose of the third target drug; and so on, qm(mm) represents the age-weighted dose of the mmth target drug.

5. The infusion management system based on monitoring data according to claim 3, characterized in that: The specific process of process A33 is as follows: Process A331: Let binary formula a-2: mm(x, y); ternary formula a-2 represents the dosage of the yth target medication for the xth male target patient; wherein the value range of x is: 1~fbm, and the value range of y is: 1~mm; Let the binary formula a-3: mw(w, z); the ternary formula a-1 represents the dose of the zth target medication for the wth female target patient; where the value range of w is: 1~fbw, and the value range of z is: 1~mm; Process A332: Use binary formula a-2 to represent the target drug dosage for all male patients, and obtain: mm(1,1), mm(1,2)~mm(1,m)~mm(fbm,m); Among them, mm(1,1) represents the dose of the first target medication for the first male target patient; mm(1,2) indicates the dose of the second target medication for the first male target patient; By analogy, mm(1, m) represents the dose of the mth target medication for the first male target patient; mm(fbm,m) represents the dose of the mth target medication for the fbmth male target patient; Process A333: Use binary formula a-3 to represent the target drug dosage for all female patients, and obtain: mw(1,1), mw(1,2)~mw(1,m)~mw(fbm,m); Among them, mw(1,1) represents the first female target patient and the dose of the first target medication; mw(1,2) represents the first female target patient and the dose of the second target medication; By analogy, mw(1, m) represents the dose of the mth target medication for the first female target patient; mw(fbw,m) represents the dose of the mth target medication for the fbwth female target patient; Process A334: Calculate the sex-weighted dose of the first target drug, denoted as rm(1); Calculate the average value of mm(1,1) to mm(fbm,1), recorded as bm(1); Calculate the average value of mw(1,1) to mw(fbw,1), recorded as bm(2); The calculation formula of rm(1) is as follows: ； Process A335: Repeat the same process of calculating rm(1) to calculate the sex-weighted doses of the second to mmth target drugs, and obtain: rm(2), rm(3)~rm(mm); Among them, rm(2) represents the sex-weighted dose of the second target drug; rm(3) represents the sex-weighted dose of the third target drug; and so on, rm(mm) represents the sex-weighted dose of the mmth target drug.

6. The infusion management system based on monitoring data according to claim 2, characterized in that: The workflow of the patient diagnosis module is as follows: Process B1: Obtain the patient's medical examination report, use the medical examination report as the input of the disease recognition model, and determine the patient's disease name as the disease name; Search the disease-drug table according to the disease name, and use the drug name that has the same disease name as the disease name as the prescription drug; The dosage of the prescribed medication is by default: the standard dosage of the disease name corresponding to the medication name; Process B2: Obtain the patient's MBI index and calculate the reduction ratio of prescribed medication, recorded as cu; Process B21: The MBI index of the patient is recorded as tz, and the normal range of the MBI index is recorded as [tz1, tz2]; determine whether tz is within the interval [tz1, tz2]; If tz is in the interval [tz1,tz2], then cu=0; If tz is not in the interval [tz1,tz2], compare tz with tz1 and tz2, and enter process B22; Process B22: If tz<tz1, the calculation formula of cu is as follows: ； If tz>tz1, the calculation formula of cu is as follows: ； Process B3: The patient's disease name, prescribed medications and the reduction ratio of prescribed medications are sent to the infusion control module as primary prescription information.

7. The infusion management system based on monitoring data according to claim 6, characterized in that: The workflow of the infusion control module is as follows: Process C1: Feedback primary prescription information to physicians to obtain quasi-prescription information; Process C2: before infusion; assuming that the width of the infusion bottle is d1; the width of the infusion tube is d2; Assume that the height of the liquid level in the infusion bottle before infusion is h1; Assume that the longitudinal distance from the mouth of the infusion bottle to the palm is h2; Get the density of the liquid drug in the infusion bottle, denoted as ρ 液 ; Process C3: After infusion; after infusion, the volume of the liquid medicine in the infusion bottle is reduced, which is recorded as ΔV; The speed at which the liquid level in the infusion bottle drops is recorded as v1; the speed at which the liquid medicine in the infusion tube is infused is recorded as v2; The time it takes for the liquid level in the infusion bottle to drop is recorded as Δt; Process C4: Assume the patient's blood pressure before infusion is P 血 ; Atmospheric pressure is recorded as P 大气 ; Assume that the patient's blood pressure remains unchanged during the infusion process, and derive the constraint 1 of the infusion speed v2; Process C5: Combine constraint 1 to derive constraint 2 of v2; Process C51: During the infusion process, the patient's blood pressure is proportional to the density of the patient's blood after the infusion; Assume that the total volume of human blood is V 血 , the density of blood is ρ 血 ; Assume that the blood density of the patient after infusion is ρρ 血 , the calculation formula is: ; Relation 4; Process C52: From Relation 4 and Equation 1-3, the blood density of the patient after infusion is proportional to v2; The mathematical expression of equation 1-3 is as follows: ； Process C53: Assume that the rate of change of the patient's blood pressure from before to after infusion is b (ρ 血 ), the rate of change of v2 is b(v2), then b(ρ 血 ) and b(v2) satisfy the following relationship: [b(ρ 血 )] 2 ∝b(v2); Constraint 2; Process C6: Obtain the patient's blood pressure before infusion and record it as ρb; Obtain monitoring video of the patient during infusion, calculate the falling speed of the liquid medicine in the infusion bottle when the patient starts infusion based on the monitoring video, and calculate the infusion speed of the liquid medicine in the infusion tube based on the falling speed of the liquid medicine, recorded as vo; Obtain the patient's blood pressure in real time during the infusion process and adjust the value of vo according to constraint 2.

8. The infusion management system based on monitoring data according to claim 7, characterized in that: The specific process of process C4 is as follows: Process C41: During the infusion process, there is a dynamic balance between the gas pressure in the infusion bottle, the liquid pressure of the liquid drug, and the atmospheric pressure connected to the air inlet pipe, that is: P (gas) + P (drug) = P 大气 ; Equation 1-1 Among them, P (gas) represents the pressure of the gas in the bottle, and P (drug) represents the liquid pressure of the liquid drug in the bottle; Substituting the calculated data of P (drug) into equation 1-1, we get relation 1; Relationship 1: P (gas) + (ρ 液 ×g×h1)=P 大气 ; Where g represents the acceleration due to gravity; Process C42: The algebraic sum of the gas in the bottle, the gravity of the liquid drug, the atmospheric pressure, and the work done by the blood is equal to the change in kinetic energy, that is: W (gas) + W (weight) - W (atmosphere) - W (blood) = ΔEk; Equation 1-2 Wherein, W(gas) represents the work done by the gas in the bottle, W(gas) = ​​P(gas) × ΔV; W (weight) represents the work done by the gravity of liquid medicine, W (weight) = (ρ 液 ×ΔV×g)×(h1+h2);where g represents the acceleration due to gravity; W(atmosphere) represents the work done by atmospheric pressure, W(atmosphere) = P 大气 ×ΔV; W(blood) represents the work done by blood, W(blood) = P 血 ×ΔV; ΔEk represents the change in kinetic energy, ΔEk = 1 / 2 × (Δm) × (v2 2 -v1 2 ); where Δm represents the weight reduction of the liquid medicine, Δm = ρ 液 ×ΔV; Process C43: Substitute the calculated formulas of W(gas), W(weight), W(atmosphere) and W(blood) into equation 1-2 to obtain equation 2; ； The volume of liquid medicine in the infusion bottle that is reduced is the same as the volume of liquid medicine in the infusion tube that is injected into the patient's body, that is: ; Equation 1-3; where π represents pi; Rearranging equations 1-3 yields equation 3; ； Process C44: Combine equations 1 to 3 to obtain the determinant of v2 as constraint 1; Determinant of v2: 。 9. The infusion management system based on monitoring data according to claim 6, characterized in that: The specific process of process C6 is as follows: Process C61: record the adjusted vo as ve; Obtain the patient's blood pressure in real time during the infusion process, recorded as ρd; Take [0,10] as the error range, compare the size of ρd and ρb, and determine the calculation formula of ve; Process C62: If ρd=ρb, it means that the infusion rate is normal and vo is not adjusted, that is, ve=vo; If ρd<ρb, it means that the infusion speed is faster, and the calculation formula for reducing vo,ve is: ； If ρd>ρb, it means that the infusion speed is slow, and the calculation formula for increasing vo,ve is: 。

Images