Intelligent Management Method for Home Nursing Based on Smart Healthcare

Abstract

The present invention relates to the technical field of home rehabilitation care, and discloses an intelligent management method for in-home care based on intelligent healthcare, including: obtaining relevant medical conditions and physiological data of patients, automatically generating a rehabilitation model, judging the rehabilitation progress of patients. When the rehabilitation progress is far from the estimated data, the system gives a timely warning and makes adjustments. This intelligent management method for in-home care based on intelligent healthcare judges the pain tolerance of patients, makes intelligent rehabilitation recommendations, generates a single-day change curve for the heart rate changes of patients under different rehabilitation programs and drug treatments, judges the rehabilitation progress of patients. When the rehabilitation progress of patients is quite different from the estimated model, it promptly prompts the attending physicians of patients to adjust the rehabilitation programs, facilitating the rehabilitation of patients and the work of nursing staff, improving the safety and effectiveness of patient rehabilitation, promoting the development of personalized medicine, improving the quality of medical services, reducing unnecessary medical costs, and enhancing the quality of life of patients.

Description

Technical Field

[0001] The present invention relates to the technical field of home rehabilitation care, and specifically to an intelligent management method for in-home care based on smart healthcare. Background Art

[0002] The intelligent management method for in-home care based on smart healthcare aims to improve the efficiency and quality of in-home care services through modern technological means, ensure the health and safety of patients. By constructing an integrated mobile application and management platform, it facilitates communication between caregivers and patients, arranges in-home care orders, records the care process, etc. An electronic health record system is established to collect and store data such as patients' basic information, medical history, and medication status for caregivers to refer to when providing services. Through data collection and monitoring, patients' vital sign data is collected in real-time and uploaded to the management platform. Through intelligent scheduling and resource management, the service coverage rate is improved. Based on patients' health data and historical records, personalized care plans are generated intelligently and dynamically adjusted to adapt to changes in patients' health conditions. Through patients' feedback and health monitoring data, the care effect is evaluated, and subsequent care plans are optimized. A remote liaison mechanism between doctors and caregivers is built to provide remote medical support;

[0003] In the existing intelligent management method for in-home care based on smart healthcare, when a patient wishes to recover at home out of their own will or due to tight medical resources, it is impossible to judge the patient's pain tolerance level to intelligently recommend rehabilitation, and it is impossible to generate a single-day change curve based on the patient's heart rate changes under different rehabilitation programs and drug treatments to compare with the historical treatment conditions of recovered patients with the same disease in the hospital to judge the patient's rehabilitation progress. When the patient's rehabilitation progress differs greatly from the estimated model, it is impossible to promptly notify the patient's attending physician to adjust the rehabilitation program for timely manual intervention and adjustment, which easily leaves the patient without timely medical support and care at home, resulting in poor recovery of the injured area. When the patient fails to recover or reach the recovery requirements as planned, it is impossible to detect in time, leading to an extended recovery process for the patient, and its practicality has certain limitations. Summary of the Invention

[0004] The present invention provides an intelligent management method for in-home care based on smart healthcare to help solve the problems mentioned in the background art.

[0005] The present invention provides the following technical solution: An intelligent management method for in-home care based on smart healthcare, including:

[0006] Obtain the patient data of the target patient and define it as the target patient data;

[0007] According to the target patient data, obtain the initial collection data and define it as the target initial data;

[0008] Calibrate the target initial data to form calibrated acquisition data of the target patient;

[0009] Obtain the wound data of the target patient and define it as the target wound data;

[0010] Obtain the rehabilitation data of the target patient and define it as the target rehabilitation data;

[0011] Generate a target rehabilitation model for the target patient according to the target wound data, target patient data, target rehabilitation data, and calibrated acquisition data;

[0012] Obtain the acquisition data of the target patient and define it as the target acquisition data;

[0013] Judge whether the data matches the target rehabilitation model according to the target acquisition data, and give corresponding warnings and make adjustments;

[0014] If the data matches the target rehabilitation model, continue to execute the rehabilitation plan according to the target rehabilitation model;

[0015] If the data does not match the target rehabilitation model, give a warning to the attending physician of the patient and adjust the target rehabilitation model.

[0016] As the intelligent management method for home care based on intelligent medicine described in the present invention, wherein: calibrating the target initial data to form calibrated acquisition data of the target patient specifically includes:

[0017] Obtain the test set of the test device;

[0018] Obtain the duration set of the test device;

[0019] Map each element in the test set to each element in the duration set one by one to form a test duration set;

[0020] Recognize each element in the test duration set as the target test element in turn;

[0021] Adjust the test device to the target test element to conduct a pain test on the target patient;

[0022] Obtain the acquisition data of the target patient and define it as the test acquisition data;

[0023] Correspond each test acquisition data with each element in the test duration set one by one to form a test acquisition model;

[0024] Obtain the target initial data;

[0025] Obtain the element in the test set corresponding to the target initial data and define it as the first initial element;

[0026] Obtain the element in the duration set corresponding to the target initial data, and define it as the second initial element;

[0027] Obtain the test acquisition data corresponding to the first initial element and the second initial element in the test acquisition model, and define it as the calibration acquisition data.

[0028] As the intelligent management method for home care based on intelligent healthcare according to the present invention, wherein: performing a pain test on a target patient specifically includes:

[0029] Obtain the trauma site of the target patient, and define it as the target site;

[0030] Obtain the human body model of the target patient;

[0031] Divide the human body model into a first region and a second region;

[0032] If the target site is located in the first region, obtain any point on the target site, and define it as the target point;

[0033] Taking any point in the first region as the origin, form a space coordinate system;

[0034] Obtain the coordinates of the target point in the space coordinate system, and define it as the target coordinate;

[0035] Taking the target point as the origin, establish an auxiliary coordinate system, and each coordinate axis of the auxiliary coordinate system is parallel to each coordinate axis of the space coordinate system one by one;

[0036] Recognize each coordinate axis of the auxiliary coordinate system as an analysis axis respectively;

[0037] Obtain the overlapping part of the analysis axis and the first region as the analysis part;

[0038] Obtain the quantity of the analysis parts, and define it as the analysis quantity;

[0039] If the analysis quantity > 1, it is determined that there are multiple overlapping parts between the analysis axis and the first region, obtain the length value of each analysis part, and define it as the overlapping length;

[0040] Extract the analysis part corresponding to the overlapping length with the largest value, and define it as the analysis overlapping part;

[0041] Obtain the midpoint of the analysis overlapping part, and define it as the analysis point;

[0042] If the analysis quantity = 1, it is determined that there is one overlapping part between the analysis axis and the first region, obtain the midpoint of the analysis part, and define it as the analysis point;

[0043] If the analysis quantity < 1, it is determined that there is no overlapping part between the analysis axis and the first region, and replace the analysis axis;

[0044] If the target part is located in the second area, obtain any point in the second area and define it as the analysis point;

[0045] The testing device outputs to the analysis point with the target test element.

[0046] As the intelligent management method for home care based on intelligent healthcare in the present invention, wherein: obtaining the target rehabilitation data, specifically:

[0047] If the calibrated acquisition data ≥ the initial acquisition data, it is determined that the patient has a low pain tolerance value;

[0048] If the calibrated acquisition data < the initial acquisition data, it is determined that the patient has a high pain tolerance value;

[0049] According to the target patient data, the target wound data, and the patient's pain tolerance value, push the rehabilitation items and rehabilitation drugs to the attending physician of the patient;

[0050] Obtain the operation data of the attending physician of the patient and define it as the physician operation;

[0051] The operation data includes adjustment operations and confirmation operations;

[0052] If the physician operation is an adjustment operation, obtain the adjusted rehabilitation items and rehabilitation drugs by the physician and integrate them into rehabilitation data;

[0053] If the physician operation is a confirmation operation, integrate the pushed rehabilitation items and rehabilitation drugs into rehabilitation data.

[0054] As the intelligent management method for home care based on intelligent healthcare in the present invention, wherein: generating a target rehabilitation model for the target patient, specifically:

[0055] Obtain the medical database;

[0056] Obtain the target wound data, the target patient data, and the target rehabilitation data;

[0057] Extract all the data corresponding to the target wound data and the target patient data in the medical database and define it as historical medical data;

[0058] Obtain the treatment duration of each historical medical data and define it as the historical duration;

[0059] Obtain the quantity of the historical medical data and define it as the historical quantity;

[0060] Calculate the analysis duration, analysis duration = the sum of all historical durations ÷ historical quantity;

[0061] Obtain the recovery time;

[0062] Calculate the estimated time, estimated time = recovery time + analysis duration;

[0063] Taking the recovery time as the starting time and the estimated time as the ending time, an estimated period is formed;

[0064] Set the historical collection period;

[0065] Obtain the rehabilitation data of each historical medical data in the historical collection period, and define it as historical rehabilitation data;

[0066] The historical rehabilitation data includes historical item data and historical drug data;

[0067] The target rehabilitation data includes target item data and target drug data;

[0068] If the coincidence degree between the historical item data and the target item data is ≥ 80% and the coincidence degree between the historical drug data and the target drug data is ≥ 90%, it is determined that the historical rehabilitation data meets the requirements;

[0069] If the coincidence degree between the historical item data and the target item data is < 80% or the coincidence degree between the historical drug data and the target drug data is < 90%, it is determined that the historical rehabilitation data does not meet the requirements;

[0070] Extract all the historical rehabilitation data determined to meet the requirements of the historical rehabilitation data to form a reference set;

[0071] Calculate the change time, change time = recovery time + 7;

[0072] Taking the change time as the starting time and the estimated time as the ending time, a change period is formed;

[0073] Generate change rehabilitation data for the change period according to the reference set;

[0074] Integrate the target rehabilitation data and the change rehabilitation data to form a rehabilitation period set;

[0075] Execute the model generation strategy.

[0076] As the intelligent management method for home care based on intelligent medical care described in the present invention, wherein: the model generation strategy is specifically:

[0077] Obtain the initial collection data and calibrated collection data of each historical medical data, and define them as historical initial data and historical calibrated data;

[0078] Define the historical initial data = target initial data as the first condition;

[0079] Define the historical calibrated data = the calibrated collection data of the target patient as the second condition;

[0080] Extract the historical medical data that simultaneously meets the first condition and the second condition, and define it as the first reference data;

[0081] If there is first reference data, organize all the first reference data to form a first reference set;

[0082] Extract all the historical medical data corresponding to each rehabilitation data in the rehabilitation cycle set within the first reference set, and define it as the first medical data;

[0083] Obtain the acquisition data change model corresponding to each first medical data for this rehabilitation data, and define it as the reference change model;

[0084] Integrate all the reference change models under this rehabilitation data to form a reference change set;

[0085] Correspond each reference change set with each data in the rehabilitation cycle set one by one to form a target rehabilitation model;

[0086] If there is no first reference data, extract the historical medical data of the calibration acquisition data that meets the first condition, and define it as the second reference data;

[0087] Organize all the second reference data to form a second reference set;

[0088] Obtain the calibration acquisition data corresponding to each element in the second reference set, and define it as the reference calibration data;

[0089] Calculate the calibration difference, calibration difference = calibration acquisition data of the target patient - reference calibration data;

[0090] Correspond each calibration difference with each element in the second reference set one by one to form a reference calibration set;

[0091] Extract all the historical medical data corresponding to each rehabilitation data in the rehabilitation cycle set within the reference calibration set, and define it as the second medical data;

[0092] Obtain the acquisition data change model corresponding to each second medical data for this rehabilitation data, and define it as the reference change model;

[0093] Integrate all the reference change models under this rehabilitation data to form a reference change set;

[0094] Correspond each reference change set with each data in the rehabilitation cycle set one by one to form a target rehabilitation model.

[0095] As the intelligent management method for home care based on intelligent medical care described in the present invention, wherein: according to the target acquisition data, judge whether the data matches the target rehabilitation model, and perform corresponding early warning and adjustment, including generating a single-day data change model for the target patient, specifically:

[0096] Obtain the single-day acquisition cycle;

[0097] Obtain the target rehabilitation data within a single-day collection period and define it as the single-day rehabilitation data;

[0098] The single-day rehabilitation data includes single-day item data and single-day drug data;

[0099] Obtain the item time periods of each single-day item data within the single-day rehabilitation data;

[0100] Obtain the effective time periods of each single-day drug data within the single-day rehabilitation data;

[0101] Obtain the item time periods and effective time periods where there is no overlap between all item time periods and effective time periods, and define them as the first time periods;

[0102] Obtain the item time periods where there is an overlap between all item time periods and effective time periods, and define them as the second time periods;

[0103] Obtain the heart rate change curves within each first time period and define them as the first change curves;

[0104] Obtain the heart rate change curves within each second time period and define them as the second change curves;

[0105] Integrate the first change curves and the second change curves to generate a single-day data change model.

[0106] As the intelligent management method for home care based on intelligent healthcare described in the present invention, wherein: according to the target collection data, judge whether the data matches the target rehabilitation model and perform corresponding warnings and adjustments, and also include judging whether the single-day data change model matches the target rehabilitation model. Specifically:

[0107] Obtain the single-day data change model and the target rehabilitation model;

[0108] Obtain the collection date corresponding to the single-day data change model and define it as the analysis date;

[0109] Obtain the collection date corresponding to the recovery time and define it as the initial date;

[0110] Calculate the number of execution days, where the number of execution days = analysis date - initial date;

[0111] Obtain the target rehabilitation data;

[0112] Extract all the reference change sets corresponding to the number of execution days and the target rehabilitation data within the target rehabilitation model, and define them as the analysis change set;

[0113] Extract all the reference change models with similar data to form a reference comparison set;

[0114] Obtain the reference change model of each target item data within the reference comparison set and define it as the item change model;

[0115] Obtain the curve length of the overlap between the first change curve and the project change model, and define it as the first overlap length;

[0116] Obtain the curve length of the first change curve, and define it as the first curve length;

[0117] Obtain the reference change model of each target drug data within the reference comparison set, and define it as the drug change model;

[0118] Obtain the curve length of the overlap between the second change curve and the drug change model, and define it as the second overlap length;

[0119] Obtain the curve length of the second change curve, and define it as the second curve length;

[0120] If the first overlap length ≥ 80% of the first curve length and the second overlap length ≥ 90% of the second curve length, it is determined that the data coincides with the target rehabilitation model;

[0121] If the first overlap length < 80% of the first curve length or the second overlap length < 90% of the second curve length, it is determined that the data does not coincide with the target rehabilitation model.

[0122] As the intelligent management method for home care based on intelligent healthcare described in the present invention, wherein: extract all reference change models with similar data to form a reference comparison set, specifically:

[0123] Obtain all analysis change sets;

[0124] Extract the analysis change sets corresponding to all historical project data, and define it as the first analysis set;

[0125] Form several first sub-analysis sets from all the first analysis sets according to the historical project data;

[0126] Arbitrarily extract two reference change models from each first sub-analysis set, and define them as the first comparison model and the second comparison model respectively;

[0127] Execute the comparison step until all reference change models within each sub-analysis set have been compared;

[0128] Extract the analysis change sets corresponding to all historical drug data, and define it as the second analysis set;

[0129] Form several second sub-analysis sets from all the second analysis sets according to the historical project data;

[0130] Arbitrarily extract two reference change models from each second sub-analysis set, and define them as the first comparison model and the second comparison model respectively;

[0131] Execute the comparison step until all reference change models in each sub-analysis set have been compared;

[0132] The comparison step is as follows:

[0133] Obtain the overlapping curve length between the first comparison model and the second comparison model, and define it as the first analysis length;

[0134] Obtain the curve length of the first comparison model, and define it as the second analysis length;

[0135] If the first analysis length ≥ 80% of the second analysis length, it is determined that the data of the first comparison model and the second comparison model are similar;

[0136] If the first analysis length < 80% of the second analysis length, it is determined that the data of the first comparison model and the second comparison model are quite different.

[0137] The present invention has the following beneficial effects:

[0138] 1. For the intelligent management method of home care based on intelligent healthcare, when a patient wishes to recover at home out of their own will or when the patient needs to recover at home due to tight medical resources, by performing pain tests on parts of the patient's body close to the injured part, the pain tolerance of the patient is judged, so as to recommend rehabilitation to the patient's attending physician, minimizing the use of analgesics within a reasonable range as much as possible, reducing side effects, and automatically generating a rehabilitation model based on the historical treatment conditions of recovered patients with the same disease in the hospital, improving the safety and effectiveness of the patient's rehabilitation, promoting the development of personalized medicine, improving the quality of medical services, reducing unnecessary medical costs, enhancing the patient's quality of life, enabling the patient to receive medical support and care in a timely manner at home, avoiding poor recovery of the patient's injured area, and being able to detect in a timely manner when the patient fails to recover or rehabilitate according to the plan or does not meet the rehabilitation requirements, preventing the prolongation of the patient's recovery process.

[0139] 2. For the intelligent management method of in-home care based on intelligent healthcare, when the patient wishes to recover at home out of their own will or when the patient needs to recover at home due to tight medical resources, by obtaining the patient's heart rate data in real time, a single-day change curve of the patient's heart rate changes under different rehabilitation programs and drug treatments is generated. This curve is compared and analyzed with various heart rate change curves formed by the historical treatment conditions of recovered patients with the same disease in the hospital to determine the patient's rehabilitation progress. If the patient's rehabilitation progress is consistent with the estimated data, the rehabilitation plan can be continued. If not, adjustments should be made in a timely manner to improve the safety and effectiveness of the patient's rehabilitation, promote the development of personalized medicine, improve the quality of medical services, reduce unnecessary medical costs, enhance the patient's quality of life, enable the patient to receive timely medical support and care at home, prevent the improper recovery of the patient's injured area, and be able to detect in a timely manner when the patient fails to recover or rehabilitate according to the plan and does not meet the rehabilitation requirements, so as to avoid prolonging the patient's recovery process.

[0140] 3. For the intelligent management method of in-home care based on intelligent healthcare, when the patient wishes to recover at home out of their own will or when the patient needs to recover at home due to tight medical resources, when the patient's rehabilitation progress differs significantly from the estimated model, a prompt to adjust the rehabilitation data is sent to the patient's attending physician in a timely manner. The patient's attending physician makes manual adjustments to the target rehabilitation model. After the adjustment, the target rehabilitation model is updated and a new rehabilitation plan is executed. Timely manual intervention and adjustment are carried out to improve the safety and effectiveness of the patient's rehabilitation, promote the development of personalized medicine, improve the quality of medical services, reduce unnecessary medical costs, enhance the patient's quality of life, enable the patient to receive timely medical support and care at home, prevent the improper recovery of the patient's injured area, and be able to detect in a timely manner when the patient fails to recover or rehabilitate according to the plan and does not meet the rehabilitation requirements, so as to avoid prolonging the patient's recovery process. BRIEF DESCRIPTION OF THE DRAWINGS

[0141] Figure 1 is the flowchart of the intelligent management method of in-home care based on the present invention;

[0142] Figure 2 is the schematic diagram for determining the analysis point of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0143] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0144] Embodiment 1, a smart management method for home care based on intelligent healthcare, refer to Figure 1 , including:

[0145] Obtain the patient data of the target patient, designated as the target patient data. The patient data is the age, height, and weight of the patient;

[0146] According to the target patient data, obtain the initial acquisition data, designated as the target initial data. The initial acquisition data is the heart rate value obtained based on the patient's age, height, and weight. When the patient's heart rate exceeds this value, it indicates that the patient may have wound discomfort and further analysis is needed to determine whether it is physiological pain or other problems;

[0147] Calibrate the target initial data to form the calibrated acquisition data of the target patient;

[0148] Obtain the wound data of the target patient, designated as the target wound data. The wound data is the patient's condition data, including the length of the wound sutured after the operation and the severity of the condition;

[0149] Obtain the rehabilitation data of the target patient, designated as the target rehabilitation data. The rehabilitation data is the rehabilitation items arranged by the doctor for the patient in a week after the operation and the amount of medicine used;

[0150] Generate a target rehabilitation model for the target patient based on the target wound data, target patient data, target rehabilitation data, and calibrated acquisition data;

[0151] Obtain the acquisition data of the target patient, designated as the target acquisition data. The acquisition data is the heart rate of the patient;

[0152] According to the target acquisition data, judge whether the data matches the target rehabilitation model and perform corresponding warnings and adjustments;

[0153] If the data matches the target rehabilitation model, continue to execute the rehabilitation plan according to the target rehabilitation model;

[0154] If the data does not match the target rehabilitation model, issue a warning to the attending physician of the patient, adjust the target rehabilitation model. At this time, send a prompt to adjust the rehabilitation data to the attending physician of the patient, and the attending physician of the patient makes an artificial adjustment to the target rehabilitation model. After the adjustment, repeat the above operations and update the target rehabilitation model.

[0155] Through the above method, when the patient wishes to recover at home out of his own will or when the shortage of medical resources leads to the patient needing to recover at home, the tolerance of the patient to pain is judged. When a person has a wound pain, the heart rate will increase relatively. Therefore, the tolerance of the patient to pain is judged through the heart rate data, and intelligent rehabilitation recommendations are made accordingly. A single-day change curve of the heart rate change of the patient under different rehabilitation programs and drug treatments is generated to judge the rehabilitation progress of the patient. When the rehabilitation progress of the patient is quite different from the estimated model, the attending physician of the patient is promptly reminded to adjust the rehabilitation program for timely manual intervention and adjustment, improving the safety and effectiveness of the patient's rehabilitation, promoting the development of personalized medicine, improving the quality of medical services, reducing unnecessary medical costs, enhancing the quality of life of the patient, enabling the patient to receive timely medical support and care at home, avoiding poor recovery of the injured part of the patient, and being able to detect in time when the patient fails to recover or rehabilitate according to the plan or fails to meet the rehabilitation requirements, so as to avoid prolonging the patient's recovery process.

[0156] Example 2. This example is an improvement made on the basis of Example 1. As Figure 2 shown, for the intelligent management method of home care based on intelligent medical care, the target initial data is calibrated to form the calibrated acquisition data of the target patient, specifically:

[0157] Obtain the test set of the test device. The test set is all levels output by the test device for judging the tolerance of the patient to pain;

[0158] Obtain the duration set of the test device. The duration set is all durations output by the test device for judging the tolerance of the patient to pain;

[0159] Map each element in the test set to each element in the duration set one by one to form a test duration set. For example, if the elements in the test set are level 1, level 2, and level 3, and the elements in the duration set are duration 1, duration 2, and duration 3, then the elements in the test duration set are level 1 duration 1, level 1 duration 2, level 1 duration 3, level 2 duration 1, level 2 duration 2, level 2 duration 3, level 3 duration 1, level 1 duration 2, level 3 duration 3;

[0160] Successively recognize each element in the test duration set as the target test element;

[0161] Adjust the test device to the target test element to conduct a pain test on the target patient;

[0162] Obtain the acquisition data of the target patient and define it as the test acquisition data;

[0163] Correspond each test acquisition data to each element in the test duration set one by one to form a test acquisition model;

[0164] Obtain the target initial data;

[0165] Obtain the elements in the test set corresponding to the target initial data, and define them as the first initial elements. The target initial data is the initial acquisition data, that is, the heart rate value obtained according to the patient's age, height, and weight. When the patient's heart rate exceeds this value, it indicates that the patient may have wound discomfort and further analysis is needed to determine whether it is physiological pain or other problems. This data is obtained from the cured patients in the medical database with the same age, height, weight, and disease as the current patient. Each cured patient has different test levels and test durations corresponding to the test when collecting their heart rate values. Extract the test level with the most occurrences as the element in the test set corresponding to the target initial data. For example, there are 8 cured patients in the medical database with the same age, height, weight, and disease as the current patient. The heart rate values obtained by each cured patient are 80, 80, 80, 85, 90, 90, 85, 80 respectively. Then the target initial data is 80. The test levels corresponding to the heart rate value of 80 when the cured patients with a heart rate value of 80 collected the heart rate value 80 during the test are level 2, level 2, level 1, and level 3 respectively. Then the element in the test set corresponding to the target initial data is level 2, that is, the first initial element is level 2;

[0166] Obtain the elements in the duration set corresponding to the target initial data, and define them as the second initial elements. Each cured patient has different test levels and test durations corresponding to the test when collecting their heart rate values. Extract the test duration with the most occurrences as the element in the duration set corresponding to the target initial data. For example, there are 8 cured patients in the medical database with the same age, height, weight, and disease as the current patient. The heart rate values obtained by each cured patient are 80, 80, 80, 85, 90, 90, 85, 80 respectively. Then the target initial data is 80. The test durations corresponding to the heart rate value of 80 when the cured patients with a heart rate value of 80 collected the heart rate value 80 during the test are duration 2, duration 2, duration 1, and duration 3 respectively. Then the element in the duration set corresponding to the target initial data is duration 2, that is, the second initial element is duration 2;

[0167] Obtain the test acquisition data corresponding to the first initial element and the second initial element in the test acquisition model, and define it as the calibration acquisition data. The test acquisition data is the heart rate value collected when the patient undergoes a pain test. Obtain the heart rate value collected by the patient during the pain test at the test level corresponding to the first initial element and at the test duration corresponding to the second initial element. For example, if the first initial element is level 2 and the second initial element is duration 2, the calibration acquisition data is the heart rate value of the patient when the test device outputs to the patient's test site at level 2 for duration 2 during the pain test, so as to judge the patient's pain tolerance compared with that of a fully recovered patient under the same test intensity.

[0168] Among them, the pain test for the target patient is specifically as follows:

[0169] Obtain the trauma site of the target patient and define it as the target site;

[0170] Obtain the human body model of the target patient, and the system automatically generates a human body model according to data such as the height and weight of the target patient;

[0171] Divide the human body model into a first region and a second region. The first region is the limbs, and the second region is other parts except the limbs;

[0172] If the target site is located in the first region, obtain any point on the target site and define it as the target point;

[0173] Take any point in the first region as the origin to form a space coordinate system;

[0174] Obtain the coordinates of the target point in the space coordinate system and define it as the target coordinate;

[0175] Take the target point as the origin to establish an auxiliary coordinate system, and each coordinate axis of the auxiliary coordinate system corresponds to and is parallel to each coordinate axis of the space coordinate system. For example, if the coordinate axes of the space coordinate system are x1y1z1 and the coordinate axes of the auxiliary coordinate system are x2y2z2, then x1 is parallel to x2, y1 is parallel to y2, and z1 is parallel to z2, that is, the auxiliary coordinate system is equivalent to the space coordinate system with the origin of the space coordinate system moved to the target point;

[0176] Recognize each coordinate axis of the auxiliary coordinate system as an analysis axis;

[0177] Obtain the overlapping part of the analysis axis and the first region as the analysis part, that is, obtain the part with pain sensation similar to the injured part to judge the patient's pain tolerance, making the data more accurate;

[0178] Obtain the number of analysis parts and define it as the analysis quantity;

[0179] If the number of analyses > 1, it is determined that there are multiple overlapping parts between the analysis axis and the first region, and the length value of each analysis part is obtained and defined as the overlapping length;

[0180] The analysis part corresponding to the maximum overlapping length is extracted and defined as the analysis overlapping part;

[0181] The midpoint of the analysis overlapping part is obtained and defined as the analysis point;

[0182] If the number of analyses = 1, it is determined that there is one overlapping part between the analysis axis and the first region, and the midpoint of the analysis part is obtained and defined as the analysis point;

[0183] If the number of analyses < 1, it is determined that there is no overlapping part between the analysis axis and the first region, and the analysis axis is replaced;

[0184] If the target part is located in the second region, any point in the second region is obtained and defined as the analysis point;

[0185] The testing device outputs to the analysis point with the target testing element. For example, if the elements in the testing duration set are level 1 duration 1, level 1 duration 2, level 1 duration 3, level 2 duration 1, level 2 duration 2, level 2 duration 3, level 3 duration 1, level 1 duration 2, level 3 duration 3, then each element in the testing duration set is sequentially recognized as the target testing element, that is, the testing device outputs to the analysis point with each testing duration at each testing level, and the output method can be electrical stimulation or pressure simulation.

[0186] This embodiment also provides that the target rehabilitation data is obtained specifically as follows:

[0187] If the calibrated acquisition data ≥ the initial acquisition data, it is determined that the patient has a low pain tolerance value;

[0188] If the calibrated acquisition data < the initial acquisition data, it is determined that the patient has a high pain tolerance value; where the calibrated acquisition data is the heart rate value of the patient during the test when in pain, and the initial acquisition data is the heart rate value obtained by the system based on data such as the patient's age, height, and weight. This heart rate value is extracted and formed from the data of past patients in the medical database. If the heart rate value of the patient during the test is higher than the heart rate value generated by the system, it means that this patient may be more sensitive to pain compared to the data of past patients in the database. Therefore, attention needs to be paid to the use of analgesic drugs. If the heart rate value of the patient during the test is lower than the heart rate value generated by the system, it means that this patient may not be as sensitive to pain compared to the data of past patients in the database. Therefore, the use of analgesic drugs can be relatively reduced;

[0189] Push the rehabilitation program and rehabilitation drugs to the attending physician of the patient according to the target patient data, target wound data, and the patient's pain tolerance value. The rehabilitation program is a one-week rehabilitation training program, and the drug data is the amount of drugs used in one week.

[0190] Obtain the operation data of the patient's attending physician and define it as physician operation.

[0191] The operation data includes adjustment operations and confirmation operations.

[0192] If the physician operation is an adjustment operation, obtain the adjusted rehabilitation program and rehabilitation drugs of the physician and integrate them into rehabilitation data.

[0193] If the physician operation is a confirmation operation, integrate the pushed rehabilitation program and rehabilitation drugs into rehabilitation data.

[0194] Example 3. This example is an improvement based on Example 2. In this example, a target rehabilitation model is generated for the target patient, specifically:

[0195] Obtain the medical database, which is a database storing the historical records of all patients treated in this hospital.

[0196] Obtain the target wound data, target patient data, and target rehabilitation data.

[0197] Extract all the data corresponding to the target wound data and target patient data in the medical database and define it as historical medical data.

[0198] Obtain the treatment duration of each historical medical data and define it as historical duration.

[0199] Obtain the quantity of historical medical data and define it as historical quantity.

[0200] Calculate the analysis duration, where the analysis duration = the sum of all historical durations ÷ historical quantity.

[0201] Obtain the recovery time. The recovery time is the time when the patient wakes up after the anesthetic effect of the postoperative anesthesia fails. Since the amount of anesthetic used by each patient during the operation is known, according to data such as the patient's height and weight, the time when the anesthetic effect of the postoperative anesthesia fails for the patient can be estimated, and the waking-up time of the patient after the anesthetic effect of the postoperative anesthesia fails is the recovery time.

[0202] Calculate the estimated time, where the estimated time = the recovery time + the analysis duration.

[0203] Form an estimated period with the recovery time as the starting time and the estimated time as the ending time.

[0204] Set the historical collection period, which is the first week after the operation of the patients who have recovered after getting sick.

[0205] Obtain the rehabilitation data of each historical medical data in the historical collection period, and define it as historical rehabilitation data;

[0206] The historical rehabilitation data includes historical item data and historical drug data. Among them, the item data is the rehabilitation items arranged by the doctor for the patient in one week after the patient's surgery, and the drug data is the amount of drugs used by the doctor for the patient in one week after the patient's surgery;

[0207] The target rehabilitation data includes target item data and target drug data;

[0208] If the coincidence degree between the historical item data and the target item data is ≥80% and the coincidence degree between the historical drug data and the target drug data is ≥90%, then it is determined that the historical rehabilitation data meets the requirements;

[0209] If the coincidence degree between the historical item data and the target item data is <80% or the coincidence degree between the historical drug data and the target drug data is <90%, then it is determined that the historical rehabilitation data does not meet the requirements;

[0210] Extract all the historical rehabilitation data that is determined to meet the requirements of the historical rehabilitation data to form a reference set;

[0211] Calculate the change time, change time = recovery time + 7;

[0212] Use the change time as the start time and the estimated time as the end time to form a change period;

[0213] Generate change rehabilitation data for the change period according to the reference set;

[0214] Integrate the target rehabilitation data and the change rehabilitation data to form a rehabilitation period set;

[0215] Execute the model generation strategy.

[0216] Among them, the model generation strategy is specifically:

[0217] Obtain the initial acquisition data and calibration acquisition data of each historical medical data, and define it as historical initial data and historical calibration data;

[0218] Regard historical initial data = target initial data as the first condition;

[0219] Regard historical calibration data = calibration acquisition data of the target patient as the second condition;

[0220] Extract the historical medical data that simultaneously meets the first condition and the second condition, and define it as the first reference data;

[0221] If there is first reference data, then organize all the first reference data to form a first reference set;

[0222] Extract all historical medical data corresponding to each rehabilitation data in the first reference set from the rehabilitation cycle set, and define it as the first medical data;

[0223] Obtain the acquisition data change model corresponding to each first medical data for this rehabilitation data, and define it as the reference change model. The acquisition data change model is the heart rate change curve during the rehabilitation training and drug treatment after a patient has had surgery after falling ill. Among them, the heart rate change curve during the drug treatment is the heart rate change curve within the period from the start of the patient's current intake of a drug to the next intake of the same drug. If the period from the start of the current intake of a drug to the next intake of the same drug coincides with the period of rehabilitation training, then the heart rate change curve of the rehabilitation training shall prevail;

[0224] Integrate all reference change models under this rehabilitation data to form a reference change set;

[0225] Correspond each reference change set with each data in the rehabilitation cycle set one by one to form a target rehabilitation model;

[0226] If there is no first reference data, extract the historical medical data of the calibrated acquisition data that meets the first condition, and define it as the second reference data;

[0227] Organize all the second reference data to form a second reference set;

[0228] Obtain the calibrated acquisition data corresponding to each element in the second reference set, and define it as the reference calibration data;

[0229] Calculate the calibration difference, calibration difference = calibrated acquisition data of the target patient - reference calibration data;

[0230] Correspond each calibration difference with each element in the second reference set one by one to form a reference calibration set;

[0231] Extract all historical medical data corresponding to each rehabilitation data in the reference calibration set from the rehabilitation cycle set, and define it as the second medical data;

[0232] Obtain the acquisition data change model corresponding to each second medical data for this rehabilitation data, and define it as the reference change model;

[0233] Integrate all reference change models under this rehabilitation data to form a reference change set;

[0234] Correspond each reference change set with each data in the rehabilitation cycle set one by one to form a target rehabilitation model.

[0235] This embodiment also provides for judging whether the data matches the target rehabilitation model based on the target acquisition data, and performing corresponding warnings and adjustments, including generating a single-day data change model for the target patient, specifically as follows:

[0236] Obtain the single-day acquisition period, where the single-day acquisition period is the current day;

[0237] Obtain the target rehabilitation data within the single-day acquisition period, and define it as the single-day rehabilitation data;

[0238] The single-day rehabilitation data includes single-day item data and single-day drug data;

[0239] Obtain the item time period for each single-day item data within the single-day rehabilitation data, where the item time period is the time period when the patient performs the rehabilitation item;

[0240] Obtain the effective time period for each single-day drug data within the single-day rehabilitation data, where the effective time period is the time period formed from the start of taking a drug this time until the next time taking the same drug;

[0241] Obtain the item time periods and effective time periods where there is no overlap between all item time periods and effective time periods, and define them as the first time periods. For example, if the item time periods are 8:00 - 9:00, 11:00 - 12:00, and 15:00 - 16:00, and the effective time periods are 8:30 - 10:00, 12:30 - 2:00, and 18:30 - 20:00, then the first time periods are 8:00 - 8:29, 9:01 - 10:00, 11:00 - 12:00, 15:00 - 16:00, 12:30 - 2:00, and 18:30 - 20:00;

[0242] Obtain the item time periods where there is an overlap between all item time periods and effective time periods, and define them as the second time periods. For example, if the item time periods are 8:00 - 9:00, 11:00 - 12:00, and 15:00 - 16:00, and the effective time periods are 8:30 - 10:00, 12:30 - 2:00, and 18:30 - 20:00, then the second time period is 8:30 - 9:00;

[0243] Obtain the heart rate change curve within each first time period, and define it as the first change curve;

[0244] Obtain the heart rate change curve within each second time period, and define it as the second change curve;

[0245] Integrate the first change curve and the second change curve to generate a single-day data change model.

[0246] This embodiment also provides for judging whether the data matches the target rehabilitation model based on the target acquisition data, and performing corresponding warnings and adjustments, and further includes judging whether the single-day data change model matches the target rehabilitation model, specifically as follows:

[0247] Obtain the single - day data change model and the target rehabilitation model;

[0248] Obtain the collection date corresponding to the single - day data change model and set it as the analysis date;

[0249] Obtain the collection date corresponding to the recovery time and set it as the initial date;

[0250] Calculate the number of execution days, where the number of execution days = analysis date - initial date;

[0251] Obtain the target rehabilitation data;

[0252] Extract all the reference change sets corresponding to the number of execution days and the target rehabilitation data in the target rehabilitation model and set it as the analysis change set;

[0253] Extract all the reference change models with similar data to form a reference comparison set;

[0254] Obtain the reference change model of each target item data in the reference comparison set and set it as the item change model;

[0255] Obtain the overlapping curve length between the first change curve and the item change model and set it as the first overlapping length, where the curve length is the total length of a section of curve after being straightened;

[0256] Obtain the curve length of the first change curve and set it as the first curve length;

[0257] Obtain the reference change model of each target drug data in the reference comparison set and set it as the drug change model;

[0258] Obtain the overlapping curve length between the second change curve and the drug change model and set it as the second overlapping length, where the curve length is the total length of a section of curve after being straightened;

[0259] Obtain the curve length of the second change curve and set it as the second curve length;

[0260] If the first overlapping length ≥ 80% of the first curve length and the second overlapping length ≥ 90% of the second curve length, then it is determined that the data matches the target rehabilitation model;

[0261] If the first overlapping length < 80% of the first curve length or the second overlapping length < 90% of the second curve length, then it is determined that the data does not match the target rehabilitation model.

[0262] Among them, extracting all the reference change models with similar data to form a reference comparison set is specifically:

[0263] Obtain all the analysis change sets;

[0264] Extract the set of analysis changes corresponding to all historical project data and define it as the first analysis set, that is, extract the heart rate change curves corresponding to all rehabilitation trainings. Among them, when the cycle formed from the start of taking a drug until the next time the drug is taken coincides with the period of the rehabilitation training, the heart rate change curve of the rehabilitation training shall prevail. Therefore, this curve includes the heart rate change curve when the drug-taking cycle coincides with the period of the rehabilitation training;

[0265] Based on the historical project data, form several first sub-analysis sets from all the first analysis sets;

[0266] Arbitrarily extract two reference change models from each first sub-analysis set and define them as the first comparison model and the second comparison model respectively;

[0267] Execute the comparison step until all the reference change models within each sub-analysis set have been compared;

[0268] Extract the set of analysis changes corresponding to all historical drug data and define it as the second analysis set, that is, extract the heart rate change curves during all drug treatments. This curve does not include the heart rate change curve when the drug-taking cycle coincides with the period of the rehabilitation training;

[0269] Based on the historical project data, form several second sub-analysis sets from all the second analysis sets;

[0270] Arbitrarily extract two reference change models from each second sub-analysis set and define them as the first comparison model and the second comparison model respectively;

[0271] Execute the comparison step until all the reference change models within each sub-analysis set have been compared;

[0272] The said comparison step is as follows:

[0273] Obtain the overlapping curve length between the first comparison model and the second comparison model and define it as the first analysis length;

[0274] Obtain the curve length of the first comparison model and define it as the second analysis length;

[0275] If the first analysis length ≥ 80% of the second analysis length, then determine that the data of the first comparison model and the second comparison model are similar;

[0276] If the first analysis length < 80% of the second analysis length, then determine that the data of the first comparison model and the second comparison model are quite different.

[0277] In this embodiment, when the patient wishes to recover at home out of his or her own will or when the shortage of medical resources leads to the patient needing to recover at home, the tolerance of the patient to pain is judged, so as to intelligently recommend rehabilitation. A single-day change curve of the patient's heart rate under different rehabilitation programs and drug treatments is generated to judge the patient's rehabilitation progress. When the patient's rehabilitation progress differs greatly from the estimated model, the patient's attending physician is promptly reminded to adjust the rehabilitation program for timely manual intervention and adjustment, improve the safety and effectiveness of the patient's rehabilitation, promote the development of personalized medicine, improve the quality of medical services, reduce unnecessary medical costs, improve the patient's quality of life, enable the patient to receive timely medical support and care at home, avoid poor recovery of the patient's injured area, and be able to promptly detect when the patient fails to recover or rehabilitate as planned or fails to meet the rehabilitation requirements, so as to avoid prolonging the patient's recovery process.

Claims

1. An intelligent management method for in-home care based on intelligent healthcare, characterized in that: Including: Obtain the patient data of the target patient and define it as the target patient data; According to the target patient data, obtain the initial acquisition data and define it as the target initial data; Calibrate the target initial data to form the calibrated acquisition data of the target patient; Obtain the wound data of the target patient and define it as the target wound data; Obtain the rehabilitation data of the target patient and define it as the target rehabilitation data; Generate a target rehabilitation model for the target patient based on the target wound data, target patient data, target rehabilitation data, and calibrated acquisition data; Obtain the acquisition data of the target patient and define it as the target acquisition data; According to the target acquisition data, determine whether the data matches the target rehabilitation model and perform corresponding warnings and adjustments; If the data matches the target rehabilitation model, continue to execute the rehabilitation plan according to the target rehabilitation model; If the data does not match the target rehabilitation model, warn the attending physician of the patient and adjust the target rehabilitation model; Calibrate the target initial data to form the calibrated acquisition data of the target patient, specifically: Obtain the test set of the test device; Obtain the duration set of the test device; Map each element in the test set to each element in the duration set one by one to form a test duration set; Successively identify each element in the test duration set as the target test element; Adjust the test device to the target test element to perform a pain test on the target patient; Obtain the acquisition data of the target patient and define it as the test acquisition data; Correspond each test acquisition data to each element in the test duration set one by one to form a test acquisition model; Obtain the target initial data; Obtain the element in the test set corresponding to the target initial data and define it as the first initial element; Obtain the element in the duration set corresponding to the target initial data and define it as the second initial element; Obtain the test acquisition data corresponding to the first initial element and the second initial element in the test acquisition model and define it as the calibrated acquisition data.

2. The intelligent management method for home care based on intelligent healthcare according to claim 1, wherein: Perform a pain test on the target patient, specifically: Obtain the trauma site of the target patient and define it as the target site; Obtain the human body model of the target patient; Divide the human body model into a first region and a second region; If the target site is located in the first region, obtain any point on the target site and define it as the target point; Take any point in the first region as the origin to form a spatial coordinate system; Obtain the coordinates of the target point in the spatial coordinate system and define it as the target coordinate; Take the target point as the origin to establish an auxiliary coordinate system, and each coordinate axis of the auxiliary coordinate system is parallel to each coordinate axis of the spatial coordinate system one by one; Successively identify each coordinate axis of the auxiliary coordinate system as the analysis axis; Obtain the overlapping part of the analysis axis and the first region as the analysis part; Obtain the number of analysis parts and define it as the analysis quantity; If the analysis quantity > 1, determine that there are multiple overlapping parts between the analysis axis and the first region, obtain the length value of each analysis part and define it as the overlapping length; Extract the analysis part corresponding to the overlapping length with the largest value and define it as the analysis overlapping part; Obtain the midpoint of the analysis overlapping part and define it as the analysis point; If the analysis quantity = 1, determine that there is one overlapping part between the analysis axis and the first region, obtain the midpoint of the analysis part and define it as the analysis point; If the analysis quantity < 1, it is determined that there is no overlapping part between the analysis axis and the first area, and the analysis axis is replaced; If the target part is located in the second area, any point in the second area is obtained and defined as the analysis point; The testing device outputs the analysis point with the target testing element.

3. The intelligent management method for home care based on intelligent healthcare according to claim 1, wherein: Obtain the target rehabilitation data, specifically: If the calibrated acquisition data ≥ the initial acquisition data, it is determined that the patient has a low pain tolerance value; If the calibrated acquisition data < the initial acquisition data, it is determined that the patient has a high pain tolerance value; According to the target patient data, the target wound data, and the patient's pain tolerance value, push the rehabilitation items and rehabilitation drugs to the attending physician of the patient; Obtain the operation data of the attending physician of the patient and define it as the physician operation; The operation data includes an adjustment operation and a confirmation operation; If the physician operation is an adjustment operation, obtain the rehabilitation items and rehabilitation drugs adjusted by the physician and integrate them into the rehabilitation data; If the physician operation is a confirmation operation, integrate the pushed rehabilitation items and rehabilitation drugs into the rehabilitation data.

4. The intelligent management method for home care based on intelligent healthcare according to claim 1, characterized in that: Generate a target rehabilitation model for the target patient, specifically: Obtain the medical database; Obtain the target wound data, the target patient data, and the target rehabilitation data; Extract all the data corresponding to the target wound data and the target patient data in the medical database and define it as the historical medical data; Obtain the treatment duration of each historical medical data and define it as the historical duration; Obtain the quantity of the historical medical data and define it as the historical quantity; Calculate the analysis duration, and the analysis duration = the sum of all historical durations ÷ the historical quantity; Obtain the recovery time; Calculate the estimated time, and the estimated time = the recovery time + the analysis duration; Using the recovery time as the start time and the estimated time as the end time, form an estimated period; Set the historical acquisition period; Obtain the rehabilitation data of each historical medical data in the historical acquisition period and define it as the historical rehabilitation data; The historical rehabilitation data includes historical item data and historical drug data; The target rehabilitation data includes target item data and target drug data; If the overlap degree between the historical item data and the target item data ≥ 80% and the overlap degree between the historical drug data and the target drug data ≥ 90%, it is determined that the historical rehabilitation data meets the requirements; If the overlap degree between the historical item data and the target item data < 80% or the overlap degree between the historical drug data and the target drug data < 90%, it is determined that the historical rehabilitation data does not meet the requirements; Extract all the historical rehabilitation data that is determined to meet the requirements of the historical rehabilitation data to form a reference set; Calculate the change time, and the change time = the recovery time + 7; Using the change time as the start time and the estimated time as the end time, form a change period; According to the reference set, generate change rehabilitation data for the change period; Integrate the target rehabilitation data and the change rehabilitation data to form a rehabilitation period set; Execute the model generation strategy.

5. The intelligent management method for home care based on intelligent healthcare according to claim 4, characterized in that: The model generation strategy, specifically: Obtain the initial acquisition data and the calibrated acquisition data of each historical medical data and define them as the historical initial data and the historical calibrated data; Regard the historical initial data = the target initial data as the first condition; Regard the historical calibrated data = the calibrated acquisition data of the target patient as the second condition; Extract the historical medical data that simultaneously satisfies the first condition and the second condition and define it as the first reference data; If there is first reference data, organize all the first reference data to form a first reference set; Extract all the historical medical data corresponding to each rehabilitation data in the first reference set from the rehabilitation cycle set, and define it as the first medical data; Obtain the acquisition data change model corresponding to each first medical data for the corresponding rehabilitation data, and define it as the reference change model; Integrate all the reference change models under the corresponding rehabilitation data to form a reference change set; Correspond each reference change set with each data in the rehabilitation cycle set one by one to form a target rehabilitation model; If there is no first reference data, extract the historical medical data of the calibrated acquisition data that meets the first condition, and define it as the second reference data; Organize all the second reference data to form a second reference set; Obtain the calibrated acquisition data corresponding to each element in the second reference set, and define it as the reference calibration data; Calculate the calibration difference, calibration difference = calibrated acquisition data of the target patient - reference calibration data; Correspond each calibration difference with each element in the second reference set one by one to form a reference calibration set; Extract all the historical medical data corresponding to each rehabilitation data in the reference calibration set from the rehabilitation cycle set, and define it as the second medical data; Obtain the acquisition data change model corresponding to each second medical data for the corresponding rehabilitation data, and define it as the reference change model; Integrate all the reference change models under the corresponding rehabilitation data to form a reference change set; Correspond each reference change set with each data in the rehabilitation cycle set one by one to form a target rehabilitation model.

6. The intelligent management method for in-home care based on intelligent healthcare according to claim 1, characterized in that: Based on the target acquisition data, determine whether the data matches the target rehabilitation model, and perform corresponding warnings and adjustments, including generating a single-day data change model for the target patient, specifically: Obtain the single-day acquisition cycle; Obtain the target rehabilitation data within the single-day acquisition cycle, and define it as the single-day rehabilitation data; The single-day rehabilitation data includes single-day item data and single-day drug data; Obtain the item time period of each single-day item data within the single-day rehabilitation data; Obtain the effective time period of each single-day drug data within the single-day rehabilitation data; Obtain all the item time periods and effective time periods where there is no overlap between the item time periods and the effective time periods, and define it as the first time period; Obtain all the item time periods where there is an overlap between the item time periods and the effective time periods, and define it as the second time period; Obtain the heart rate change curve within each first time period, and define it as the first change curve; Obtain the heart rate change curve within each second time period, and define it as the second change curve; Integrate the first change curve and the second change curve to generate a single-day data change model.

7. The intelligent management method for home care based on intelligent healthcare according to claim 6, characterized in that: Based on the target acquisition data, determine whether the data matches the target rehabilitation model, and perform corresponding warnings and adjustments, and also include determining whether the single-day data change model matches the target rehabilitation model, specifically: Obtain the single-day data change model and the target rehabilitation model; Obtain the acquisition date corresponding to the single-day data change model, and define it as the analysis date; Obtain the acquisition date corresponding to the recovery time, and define it as the initial date; Calculate the execution days, execution days = analysis date - initial date; Obtain the target rehabilitation data; Extract all the reference change sets corresponding to the execution days and the target rehabilitation data in the target rehabilitation model, and define it as the analysis change set; Extract all reference change models with similar data to form a reference comparison set; Obtain the reference change model of each target project data within the reference comparison set and define it as the project change model; Obtain the overlapping curve length between the first change curve and the project change model and define it as the first overlapping length; Obtain the curve length of the first change curve and define it as the first curve length; Obtain the reference change model of each target drug data within the reference comparison set and define it as the drug change model; Obtain the overlapping curve length between the second change curve and the drug change model and define it as the second overlapping length; Obtain the curve length of the second change curve and define it as the second curve length; If the first overlapping length ≥ 80% of the first curve length and the second overlapping length ≥ 90% of the second curve length, it is determined that the data matches the target rehabilitation model; If the first overlapping length < 80% of the first curve length or the second overlapping length < 90% of the second curve length, it is determined that the data does not match the target rehabilitation model.

8. The intelligent management method for home care based on intelligent healthcare according to claim 7, characterized in that: Extract all reference change models with similar data to form a reference comparison set, specifically: Obtain all analysis change sets; Extract the analysis change sets corresponding to all historical project data and define them as the first analysis set; Form several first sub-analysis sets from all the first analysis sets according to the historical project data; Arbitrarily extract two reference change models from each first sub-analysis set and define them as the first comparison model and the second comparison model respectively; Execute the comparison step until all reference change models within each sub-analysis set have been compared; Extract the analysis change sets corresponding to all historical drug data and define them as the second analysis set; Form several second sub-analysis sets from all the second analysis sets according to the historical project data; Arbitrarily extract two reference change models from each second sub-analysis set and define them as the first comparison model and the second comparison model respectively; Execute the comparison step until all reference change models within each sub-analysis set have been compared; The said comparison step is: Obtain the overlapping curve length between the first comparison model and the second comparison model and define it as the first analysis length; Obtain the curve length of the first comparison model and define it as the second analysis length; If the first analysis length ≥ 80% of the second analysis length, it is determined that the data of the first comparison model and the second comparison model are similar; If the first analysis length < 80% of the second analysis length, it is determined that the data of the first comparison model and the second comparison model are quite different.

Images