Health medical cloud service method based on digital general diagnosis

Abstract

The invention discloses a health medical cloud service method based on digital general diagnosis, and relates to the technical field of medical treatment, and the method comprises the steps: obtaining the payment capability of a target patient; obtaining a disease severity coefficient of the target patient; obtaining the basic condition of the cloud doctor; matching at least one recommended cloud doctor; the adaptation coefficients of the recommended cloud doctors are calculated, and the recommended cloud doctor with the maximum adaptation coefficient is selected as a target recommended cloud doctor; performing medical service on the target patient by using the target recommendation cloud doctor, and obtaining a service result; analyzing at least one service result in the cloud service to obtain a cloud service efficiency coefficient; and when the cloud doctors of the cloud service are insufficient, forming a cloud doctor supplement scheme for the cloud service based on the at least one non-cloud doctor who does not perform the cloud service. By matching the target recommended cloud doctors, the doctors of the cloud service are supplemented, so that the medical service with high matching degree is provided to the greatest extent in the economic ability of the patient.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a health care cloud service method based on digital general practice diagnosis. Background Art

[0002] Due to limited medical resources, not only do people waste a lot of time and energy queuing up to register, pay fees and see a doctor in the hospital; for the elderly, due to their limited mobility, it is often inconvenient for them to go to the hospital alone to queue up for treatment; therefore, with the advancement of science, cloud-based medical diagnosis services have emerged.

[0003] The service efficiency and matching degree of existing medical cloud services need to be improved. There are many patients who may not be properly served by the cloud services they receive due to the ability or charging situation of the doctors serving the cloud services. Summary of the invention

[0004] In order to solve the above technical problems, a health care cloud service method based on digital general practice diagnosis is provided. This technical solution solves the problem that the service efficiency and matching degree of the existing medical cloud services proposed in the above background technology need to be improved, and there are many patients who may not be properly served by the cloud services they receive due to the ability or charging situation of the doctors serving the cloud services.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is: A health care cloud service method based on digital general practice diagnosis, comprising: Acquire at least one cloud doctor who provides cloud services, classify the cloud doctors to obtain at least one cloud doctor type, classify the patients to obtain at least one patient type, and pair the cloud doctor type with the patient type; Acquire at least one patient receiving the cloud service, select one of the at least one patient as a target patient, perform payment analysis on the target patient based on historical data, and obtain the payment capacity of the target patient; Analyze the test results of the target patient to obtain the disease severity coefficient of the target patient; Obtaining basic information about Cloud Doctor, including diagnosis and treatment quality, diagnosis and treatment efficiency, and diagnosis and treatment costs; Based on the basic information of the cloud doctor and the disease severity coefficient and payment ability of the target patient, at least one recommended cloud doctor is matched; Calculate the fitness coefficient of the recommended cloud doctors, and select the recommended cloud doctor with the largest fitness coefficient as the target recommended cloud doctor; Use the target recommended cloud doctor to provide medical services to the target patients and obtain the service results; Analyze at least one service result of the cloud service to obtain a cloud service efficiency coefficient; When the cloud service efficiency coefficient is greater than the first preset value, no processing is performed, otherwise, it is determined that the cloud doctors performing the cloud service are insufficient; When the cloud service has insufficient cloud doctors, a cloud doctor supplement plan is formed for the cloud service based on at least one non-cloud doctor who is not performing the cloud service.

[0006] Preferably, classifying the cloud doctors to obtain at least one cloud doctor type comprises the following steps: Obtaining the medical records of at least one patient diagnosed by the cloud doctor, extracting the disease characteristics of the patient's medical records, and obtaining at least one abnormal indicator of the patient and the value of the abnormal indicator, wherein the abnormal indicator is an indicator whose value exceeds the normal range of the indicator; Taking the average of the abnormal index values ​​of at least one patient diagnosed by Doctor Yun to obtain the abnormal index average; Obtaining any two cloud doctors from at least one cloud doctor as a first cloud doctor and a second cloud doctor; Use the difference formula to calculate the difference between the first cloud doctor and the second cloud doctor; When the difference between the first cloud doctor and the second cloud doctor is less than a second preset value, the first cloud doctor and the second cloud doctor are aggregated into the same cloud doctor type. When the first cloud doctor and the second cloud doctor traverse all cloud doctors, the classification of cloud doctors is completed; The difference formula is as follows: , Among them, A is the difference between the first cloud doctor and the second cloud doctor, i is the subscript, and n is the total number of all abnormal indicators of the first cloud doctor and the second cloud doctor after duplication. is the mean value of the ith abnormal index of the First Cloud Doctor, is the mean of the ith abnormal index of the second cloud doctor. When the ith abnormal index is not the abnormal index of the patient of the first cloud doctor, Take 0, when the i-th abnormal indicator is not the abnormal indicator of the second cloud doctor's patient, Take 0.

[0007] Preferably, classifying the patients to obtain at least one patient type comprises the following steps: Extracting disease characteristics from the patient's medical records to obtain at least one abnormal indicator of the patient; Select two patients from at least one patient as a first patient and a second patient; Obtaining the overlapping abnormality index of the first patient and the second patient as the overlap abnormality index; Using the overlap formula, calculate the overlap between the first patient and the second patient; Classifying the first patient and the second patient whose overlap is greater than a third preset value into the same patient type, and completing the classification of the patients when the first patient and the second patient traverse at least one patient; The overlap formula is as follows: , Among them, B is the overlap between the first patient and the second patient, c is the total number of overlapping abnormal indicators, d is the total number of abnormal indicators of the first patient, and e is the total number of abnormal indicators of the second patient.

[0008] Preferably, the pairing of the cloud doctor type with the patient type comprises the following steps: Aggregate the abnormal indicators of at least one patient diagnosed by at least one cloud doctor in the cloud doctor type to obtain a first abnormal indicator set; Aggregating abnormal indicators of at least one patient in the patient type to obtain a second abnormal indicator set; Using a distinguishability formula, calculating the distinguishability between the first abnormal indicator set and the second abnormal indicator set; The second abnormal indicator set having the smallest difference from the first abnormal indicator set is used as the target second abnormal indicator set; Match the patient type corresponding to the target second abnormal indicator set to the cloud doctor type corresponding to the first abnormal indicator set; The formula for discrimination is as follows: , Among them, C is the distinction between the first abnormal indicator set and the second abnormal indicator set, f is the number of abnormal indicators that overlap in the first abnormal indicator set and the second abnormal indicator set, g is the number of abnormal indicators in the first abnormal indicator set, and h is the number of abnormal indicators in the second abnormal indicator set.

[0009] Preferably, performing payment analysis on the target patient to obtain the payment ability of the target patient comprises the following steps: The potential payment amount of the target patient is obtained as the payment ability of the target patient, wherein the potential payment amount is the superposition value of the target patient's family deposit and family loan limit.

[0010] Preferably, analyzing the test results of the target patient to obtain the disease severity coefficient of the target patient comprises the following steps: Obtain the patient type into which the target patient is classified as the target patient type; Obtaining the proportion of the value of at least one abnormal indicator of the target patient that exceeds the normal range of the abnormal indicator and taking the average to obtain an abnormal severity coefficient; Based on big data, obtain the average non-recovery rate of at least one patient in the target patient type; The abnormal severity coefficient is multiplied by the average non-recovery rate to obtain the disease severity coefficient of the target patient.

[0011] Preferably, matching at least one recommended cloud doctor based on the basic information of the cloud doctor and the disease severity coefficient and payment ability of the target patient comprises the following steps: At least one patient with a disease severity coefficient equal to the disease severity coefficient of the target patient is obtained from the historical data as a characteristic patient, and a cloud doctor whose cure rate for the characteristic patient is greater than a preset ratio is selected as a characteristic cloud doctor; The average cost of patients with at least one characteristic is taken to obtain the average cost; Calculate the business capability coefficient of the cloud doctor, which is equal to the product of the diagnosis and treatment quality and the diagnosis and treatment efficiency; Calculate the business capability coefficient of the characteristic cloud doctor and take the mean value to obtain the business capability mean coefficient; The cloud doctor whose business capability coefficient is greater than the business capability mean coefficient is selected as the target cloud doctor; When the average cost does not exceed the target patient's family savings, all target cloud doctors whose diagnosis and treatment costs do not exceed the average cost will be recommended as cloud doctors; When the average expenditure is greater than the target patient's family savings, the target cloud doctors whose medical expenses are lower than the target patient's ability to pay will be recommended as cloud doctors.

[0012] Preferably, the calculation of the fitness coefficient of the recommended cloud doctor includes the following steps: Under the condition that there is no limit on the amount of money spent on the target patient, obtain the first treatment plan recommended by the cloud doctor for the target patient; Under the condition of the target patient's ability to pay, obtain the second treatment plan recommended by the cloud doctor for the target patient; Extracting at least one first treatment item in the first treatment plan, and extracting at least one second treatment item in the second treatment plan, wherein the first treatment item and the second treatment item are treatment items for the target patient respectively; The number of the second treatment items is divided by the number of the first treatment items to obtain the fitness coefficient for recommending the cloud doctor.

[0013] Preferably, analyzing at least one service result in the cloud service to obtain the cloud service efficiency coefficient comprises the following steps: Based on big data, the cure status in the service results is obtained, and the cure status is either cured or not cured. If the cure status is cured, the cure time is counted; Based on historical data, obtain historical cure time for the target patient's disease; Obtain the total number of cures for at least one service result, and calculate the average cure time for at least one service result; Use the service efficiency formula to calculate the cloud service efficiency coefficient; The service efficiency formula is as follows: , Among them, D is the cloud service efficiency coefficient, k is the total number of cures, l is the number of at least one service result, m is the historical cure time, and n is the average cure time.

[0014] Preferably, the forming of a cloud doctor supplement scheme for cloud services based on at least one non-cloud doctor who does not provide cloud services comprises the following steps: Obtain the service result of non-cured condition as the target service result; Get the disease served by the target service result as the target disease; The non-cloud doctors whose cure rate for the target disease is greater than a preset ratio are selected as target non-cloud doctors; The target non-cloud doctors are numbered from small to large according to their medical expenses, and the target non-cloud doctors with numbers smaller than the preset numbers are aggregated to form a cloud doctor supplement plan.

[0015] Compared with the prior art, the present invention has the following beneficial effects: By matching the target recommended cloud doctors, we can match the target patients with more suitable cloud doctors, so that the target patients' diseases can be treated to the greatest extent. At the same time, we can limit the medical expenses according to the patients' economic ability. At the same time, we can analyze the service situation of the overall cloud service. When the patient's needs cannot be well met, we can supplement the doctors of the cloud service, so as to improve the service efficiency and matching degree of the medical cloud service, so as to provide the most matching medical services within the patient's economic ability and solve the patient's medical problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a health care cloud service method based on digital general practice diagnosis of the present invention; Figure 2 A flow chart for classifying cloud doctors of the present invention to obtain at least one cloud doctor type; Figure 3 A schematic diagram of a process for classifying patients to obtain at least one patient type according to the present invention; Figure 4 A schematic diagram of the process of pairing cloud doctor types with patient types according to the present invention; Figure 5 A schematic diagram of a process of analyzing the test results of a target patient to obtain a disease severity coefficient of the target patient according to the present invention; Figure 6 A flowchart of matching at least one recommended cloud doctor based on the basic information of the cloud doctor and the disease severity coefficient and payment ability of the target patient according to the present invention; Figure 7 A schematic diagram of a flow chart of the present invention for calculating the fitness coefficient of a recommended cloud doctor; Figure 8 A schematic diagram of a process of analyzing at least one service result in a cloud service to obtain a cloud service efficiency coefficient according to the present invention; Fig. 9 The present invention is a flow chart of forming a cloud doctor supplement scheme for cloud services based on at least one non-cloud doctor who does not provide cloud services. DETAILED DESCRIPTION

[0017] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0018] Reference Figure 1 As shown, a health care cloud service method based on digital general practice diagnosis includes: Acquire at least one cloud doctor who provides cloud services, classify the cloud doctors to obtain at least one cloud doctor type, classify the patients to obtain at least one patient type, and pair the cloud doctor type with the patient type; Acquire at least one patient receiving the cloud service, select one of the at least one patient as a target patient, perform payment analysis on the target patient based on historical data, and obtain the payment capacity of the target patient; Analyze the test results of the target patient to obtain the disease severity coefficient of the target patient; Obtaining basic information about Cloud Doctor, including diagnosis and treatment quality, diagnosis and treatment efficiency, and diagnosis and treatment costs; Based on the basic information of the cloud doctor and the disease severity coefficient and payment ability of the target patient, at least one recommended cloud doctor is matched; Calculate the fitness coefficient of the recommended cloud doctors, and select the recommended cloud doctor with the largest fitness coefficient as the target recommended cloud doctor; Use the target recommended cloud doctor to provide medical services to the target patients and obtain the service results; Analyze at least one service result of the cloud service to obtain a cloud service efficiency coefficient; When the cloud service efficiency coefficient is greater than the first preset value, no processing is performed, otherwise, it is determined that the cloud doctors performing the cloud service are insufficient; When the cloud service has insufficient cloud doctors, a cloud doctor supplement plan is formed for the cloud service based on at least one non-cloud doctor who is not performing the cloud service.

[0019] Reference Figure 2 As shown, classifying cloud doctors to obtain at least one cloud doctor type includes the following steps: Obtaining the medical records of at least one patient diagnosed by the cloud doctor, extracting the disease characteristics of the patient's medical records, and obtaining at least one abnormal indicator of the patient and the value of the abnormal indicator, wherein the abnormal indicator is an indicator whose value exceeds the normal range of the indicator; Taking the average of the abnormal index values ​​of at least one patient diagnosed by Doctor Yun to obtain the abnormal index average; Obtaining any two cloud doctors from at least one cloud doctor as a first cloud doctor and a second cloud doctor; Use the difference formula to calculate the difference between the first cloud doctor and the second cloud doctor; When the difference between the first cloud doctor and the second cloud doctor is less than a second preset value, the first cloud doctor and the second cloud doctor are aggregated into the same cloud doctor type. When the first cloud doctor and the second cloud doctor traverse all cloud doctors, the classification of cloud doctors is completed; The difference formula is as follows: , Among them, A is the difference between the first cloud doctor and the second cloud doctor, i is the subscript, and n is the total number of all abnormal indicators of the first cloud doctor and the second cloud doctor after duplication. is the mean value of the ith abnormal index of the First Cloud Doctor, is the mean of the ith abnormal index of the second cloud doctor. When the ith abnormal index is not the abnormal index of the patient of the first cloud doctor, Take 0, when the i-th abnormal indicator is not the abnormal indicator of the second cloud doctor's patient, Take 0.

[0020] The purpose of classifying cloud doctors and patients is to match patients with cloud doctors, so that the cloud doctor type matched to the patient type is the doctor corresponding to the patient's symptoms in the patient type, so that doctors can be selected in the cloud doctor type, and doctors with better healing effects and treatment costs can be selected; The classification criteria are based on the degree of similarity, and patients or doctors with high degrees of similarity are classified into the same category.

[0021] Reference Figure 3 As shown, classifying patients to obtain at least one patient type includes the following steps: Extracting disease characteristics from the patient's medical records to obtain at least one abnormal indicator of the patient; Select two patients from at least one patient as a first patient and a second patient; Obtaining the overlapping abnormality index of the first patient and the second patient as the overlap abnormality index; Using the overlap formula, calculate the overlap between the first patient and the second patient; Classifying the first patient and the second patient whose overlap is greater than a third preset value into the same patient type, and completing the classification of the patients when the first patient and the second patient traverse at least one patient; The overlap formula is as follows: , Among them, B is the overlap between the first patient and the second patient, c is the total number of overlapping abnormal indicators, d is the total number of abnormal indicators of the first patient, and e is the total number of abnormal indicators of the second patient.

[0022] Reference Figure 4 As shown, pairing cloud doctor types with patient types includes the following steps: Aggregate the abnormal indicators of at least one patient diagnosed by at least one cloud doctor in the cloud doctor type to obtain a first abnormal indicator set; Aggregating abnormal indicators of at least one patient in the patient type to obtain a second abnormal indicator set; Using a distinguishability formula, calculating the distinguishability between the first abnormal indicator set and the second abnormal indicator set; The second abnormal indicator set having the smallest difference from the first abnormal indicator set is used as the target second abnormal indicator set; Match the patient type corresponding to the target second abnormal indicator set to the cloud doctor type corresponding to the first abnormal indicator set; The formula for discrimination is as follows: , Among them, C is the distinction between the first abnormal indicator set and the second abnormal indicator set, f is the number of abnormal indicators that overlap in the first abnormal indicator set and the second abnormal indicator set, g is the number of abnormal indicators in the first abnormal indicator set, and h is the number of abnormal indicators in the second abnormal indicator set.

[0023] Performing payment analysis on target patients and obtaining their payment capacity includes the following steps: The potential payment amount of the target patient is obtained as the payment ability of the target patient, wherein the potential payment amount is the superposition value of the target patient's family deposit and family loan limit.

[0024] Reference Figure 5 As shown, analyzing the test results of the target patient to obtain the disease severity coefficient of the target patient includes the following steps: Obtain the patient type into which the target patient is classified as the target patient type; Obtaining the proportion of the value of at least one abnormal indicator of the target patient that exceeds the normal range of the abnormal indicator and taking the average to obtain an abnormal severity coefficient; Based on big data, obtain the average non-recovery rate of at least one patient in the target patient type; The abnormal severity coefficient is multiplied by the average non-recovery rate to obtain the disease severity coefficient of the target patient.

[0025] The target patients' medical conditions are different, so they need to be treated differently during cloud medical treatment. Otherwise, if the same standards are used to match doctors for medical treatment, the target patients' conditions may not be adequately treated because the doctor's treatment level may not match the condition.

[0026] Reference Figure 6 As shown, matching at least one recommended cloud doctor based on the basic situation of the cloud doctor and the disease severity coefficient and payment ability of the target patient includes the following steps: At least one patient with a disease severity coefficient equal to the disease severity coefficient of the target patient is obtained from the historical data as a characteristic patient, and a cloud doctor whose cure rate for the characteristic patient is greater than a preset ratio is selected as a characteristic cloud doctor; The average cost of patients with at least one characteristic is taken to obtain the average cost; Calculate the business capability coefficient of the cloud doctor, which is equal to the product of the diagnosis and treatment quality and the diagnosis and treatment efficiency; Calculate the business capability coefficient of the characteristic cloud doctor and take the mean value to obtain the business capability mean coefficient; The cloud doctor whose business capability coefficient is greater than the business capability mean coefficient is selected as the target cloud doctor; When the average cost does not exceed the target patient's family savings, all target cloud doctors whose diagnosis and treatment costs do not exceed the average cost will be recommended as cloud doctors; When the average expenditure is greater than the target patient's family savings, the target cloud doctors whose medical expenses are lower than the target patient's ability to pay will be recommended as cloud doctors.

[0027] The doctor matched for the patient must ensure that he has a high cure rate for the patient's disease. Otherwise, simply matching the patient will easily affect the service effect. At the same time, when matching the doctor, the speed and quality of the doctor's treatment must also be considered, and the doctor whose treatment speed and quality meet the patient's needs must be matched as much as possible. At the same time, the doctor must be matched for the patient based on the patient's economic conditions so that the patient can receive as comprehensive medical care as possible.

[0028] Reference Figure 7 As shown, calculating the fitness coefficient of the recommended cloud doctor includes the following steps: Under the condition that there is no limit on the amount of money spent on the target patient, obtain the first treatment plan recommended by the cloud doctor for the target patient; Under the condition of the target patient's ability to pay, obtain the second treatment plan recommended by the cloud doctor for the target patient; Extracting at least one first treatment item in the first treatment plan, and extracting at least one second treatment item in the second treatment plan, wherein the first treatment item and the second treatment item are treatment items for the target patient respectively; The number of the second treatment items is divided by the number of the first treatment items to obtain the fitness coefficient for recommending the cloud doctor.

[0029] The adaptation coefficient is mainly carried out when the target patient's ability to pay is limited. Because when the target patient's ability to pay is insufficient, the recommended cloud doctor will appropriately reduce the service items so that the medical expenses can be accepted by the target patient. Therefore, when selecting a doctor, it is necessary to ensure that the target patient can receive more comprehensive medical services as much as possible. Therefore, the recommended cloud doctor with the largest adaptation coefficient is selected as the target recommended cloud doctor.

[0030] Reference Figure 8 As shown, analyzing at least one service result in the cloud service to obtain the cloud service efficiency coefficient includes the following steps: Based on big data, the cure status in the service results is obtained, and the cure status is either cured or not cured. If the cure status is cured, the cure time is counted; Based on historical data, obtain historical cure time for the target patient's disease; Obtain the total number of cures for at least one service result, and calculate the average cure time for at least one service result; Use the service efficiency formula to calculate the cloud service efficiency coefficient; The service efficiency formula is as follows: , Among them, D is the cloud service efficiency coefficient, k is the total number of cures, l is the number of at least one service result, m is the historical cure time, and n is the average cure time.

[0031] Since doctors cannot be fully matched with patients, there will be certain deviations in cloud services, and this situation needs to be monitored, specifically the cure rate and speed of cloud services. When the cloud service efficiency coefficient is small, it means that cloud services are difficult to meet the needs of patients, and the quality of their services needs to be improved. The doctors participating in cloud services play a decisive role in cloud services. Therefore, targeted doctor supplementation is needed to ensure that doctors matched to patients can provide patients with sufficient medical services that their financial conditions can afford, thereby improving the cure rate of patients.

[0032] Reference Fig. 9 As shown, based on at least one non-cloud doctor who does not provide cloud services, forming a cloud doctor supplement plan for cloud services includes the following steps: Obtain the service result of non-cured condition as the target service result; Get the disease served by the target service result as the target disease; The non-cloud doctors whose cure rate for the target disease is greater than a preset ratio are selected as target non-cloud doctors; The target non-cloud doctors are numbered from small to large according to their medical expenses, and the target non-cloud doctors with numbers smaller than the preset numbers are aggregated to form a cloud doctor supplement plan.

[0033] Furthermore, the present solution also proposes a storage medium on which a computer-readable program is stored, and when the computer-readable program is called, the above-mentioned health care cloud service method based on digital general practice diagnosis is executed.

[0034] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0035] To sum up, the advantages of the present invention are: by matching the target recommended cloud doctors, a more suitable cloud doctor can be matched for the target patient, so that the target patient's illness can be treated to the greatest extent. At the same time, the medical expenses can be limited according to the patient's economic ability. At the same time, the service situation of the overall cloud service is analyzed. When the patient's needs cannot be well met, the doctors of the cloud service are supplemented, thereby improving the service efficiency and matching degree of the medical cloud service, so as to provide high-matching medical services to the maximum extent within the patient's economic ability and solve the patient's medical problems.

[0036] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A health care cloud service method based on digital general practice diagnosis, characterized in that: include: Acquire at least one cloud doctor who provides cloud services, classify the cloud doctors to obtain at least one cloud doctor type, classify the patients to obtain at least one patient type, and pair the cloud doctor type with the patient type; Acquire at least one patient receiving the cloud service, select one of the at least one patient as a target patient, perform payment analysis on the target patient based on historical data, and obtain the payment capacity of the target patient; Analyze the test results of the target patient to obtain the disease severity coefficient of the target patient; Obtaining basic information about Cloud Doctor, including diagnosis and treatment quality, diagnosis and treatment efficiency, and diagnosis and treatment costs; Based on the basic information of the cloud doctor and the disease severity coefficient and payment ability of the target patient, at least one recommended cloud doctor is matched; Calculate the fitness coefficient of the recommended cloud doctors, and select the recommended cloud doctor with the largest fitness coefficient as the target recommended cloud doctor; Use the target recommended cloud doctor to provide medical services to the target patients and obtain the service results; Analyze at least one service result of the cloud service to obtain a cloud service efficiency coefficient; When the cloud service efficiency coefficient is greater than the first preset value, no processing is performed, otherwise, it is determined that the cloud doctors performing the cloud service are insufficient; When the cloud service has insufficient cloud doctors, a cloud doctor supplement plan is formed for the cloud service based on at least one non-cloud doctor who is not performing the cloud service.

2. A health care cloud service method based on digital general practice diagnosis according to claim 1, characterized in that: The classifying of cloud doctors to obtain at least one cloud doctor type comprises the following steps: Obtaining the medical records of at least one patient diagnosed by the cloud doctor, extracting the disease characteristics of the patient's medical records, and obtaining at least one abnormal indicator of the patient and the value of the abnormal indicator, wherein the abnormal indicator is an indicator whose value exceeds the normal range of the indicator; Taking the average of the abnormal index values ​​of at least one patient diagnosed by Doctor Yun to obtain the abnormal index average; Obtaining any two cloud doctors from at least one cloud doctor as a first cloud doctor and a second cloud doctor; Use the difference formula to calculate the difference between the first cloud doctor and the second cloud doctor; When the difference between the first cloud doctor and the second cloud doctor is less than a second preset value, the first cloud doctor and the second cloud doctor are aggregated into the same cloud doctor type. When the first cloud doctor and the second cloud doctor traverse all cloud doctors, the classification of cloud doctors is completed; The difference formula is as follows: , Among them, A is the difference between the first cloud doctor and the second cloud doctor, i is the subscript, and n is the total number of all abnormal indicators of the first cloud doctor and the second cloud doctor after duplication. is the mean value of the ith abnormal index of the First Cloud Doctor, is the mean of the ith abnormal index of the second cloud doctor. When the ith abnormal index is not the abnormal index of the patient of the first cloud doctor, Take 0, when the i-th abnormal indicator is not the abnormal indicator of the second cloud doctor's patient, Take 0.

3. A health care cloud service method based on digital general practice diagnosis according to claim 2, characterized in that: The classifying of patients to obtain at least one patient type comprises the following steps: Extracting disease characteristics from the patient's medical records to obtain at least one abnormal indicator of the patient; Select two patients from at least one patient as a first patient and a second patient; Obtaining the overlapping abnormality index of the first patient and the second patient as the overlap abnormality index; Using the overlap formula, calculate the overlap between the first patient and the second patient; Classifying the first patient and the second patient whose overlap is greater than a third preset value into the same patient type, and completing the classification of the patients when the first patient and the second patient traverse at least one patient; The overlap formula is as follows: , Among them, B is the overlap between the first patient and the second patient, c is the total number of overlapping abnormal indicators, d is the total number of abnormal indicators of the first patient, and e is the total number of abnormal indicators of the second patient.

4. A health care cloud service method based on digital general practice diagnosis according to claim 3, characterized in that: The pairing of the cloud doctor type with the patient type comprises the following steps: Aggregate the abnormal indicators of at least one patient diagnosed by at least one cloud doctor in the cloud doctor type to obtain a first abnormal indicator set; Aggregating abnormal indicators of at least one patient in the patient type to obtain a second abnormal indicator set; Using a distinguishability formula, calculating the distinguishability between the first abnormal indicator set and the second abnormal indicator set; The second abnormal indicator set having the smallest difference from the first abnormal indicator set is used as the target second abnormal indicator set; Match the patient type corresponding to the target second abnormal indicator set to the cloud doctor type corresponding to the first abnormal indicator set; The formula for discrimination is as follows: , Among them, C is the distinction between the first abnormal indicator set and the second abnormal indicator set, f is the number of abnormal indicators that overlap in the first abnormal indicator set and the second abnormal indicator set, g is the number of abnormal indicators in the first abnormal indicator set, and h is the number of abnormal indicators in the second abnormal indicator set.

5. A health care cloud service method based on digital general practice diagnosis according to claim 4, characterized in that: The payment analysis of the target patient to obtain the payment ability of the target patient comprises the following steps: The potential payment amount of the target patient is obtained as the payment ability of the target patient, wherein the potential payment amount is the superposition value of the target patient's family deposit and family loan limit.

6. A health care cloud service method based on digital general practice diagnosis according to claim 5, characterized in that: Analyzing the test results of the target patient to obtain the disease severity coefficient of the target patient includes the following steps: Obtain the patient type into which the target patient is classified as the target patient type; Obtaining the proportion of the value of at least one abnormal indicator of the target patient that exceeds the normal range of the abnormal indicator and taking the average to obtain an abnormal severity coefficient; Based on big data, obtain the average non-recovery rate of at least one patient in the target patient type; The abnormal severity coefficient is multiplied by the average non-recovery rate to obtain the disease severity coefficient of the target patient.

7. A health care cloud service method based on digital general practice diagnosis according to claim 6, characterized in that: The matching of at least one recommended cloud doctor based on the basic information of the cloud doctor and the disease severity coefficient and payment ability of the target patient comprises the following steps: At least one patient with a disease severity coefficient equal to the disease severity coefficient of the target patient is obtained from the historical data as a characteristic patient, and a cloud doctor whose cure rate for the characteristic patient is greater than a preset ratio is selected as a characteristic cloud doctor; The average cost of patients with at least one characteristic is taken to obtain the average cost; Calculate the business capability coefficient of the cloud doctor, which is equal to the product of the diagnosis and treatment quality and the diagnosis and treatment efficiency; Calculate the business capability coefficient of the characteristic cloud doctor and take the mean value to obtain the business capability mean coefficient; The cloud doctor whose business capability coefficient is greater than the business capability mean coefficient is selected as the target cloud doctor; When the average cost does not exceed the target patient's family savings, all target cloud doctors whose diagnosis and treatment costs do not exceed the average cost will be recommended as cloud doctors; When the average expenditure is greater than the target patient's family savings, the target cloud doctors whose medical expenses are lower than the target patient's ability to pay will be recommended as cloud doctors.

8. A health care cloud service method based on digital general practice diagnosis according to claim 7, characterized in that: The calculation of the fitness coefficient of the recommended cloud doctor includes the following steps: Under the condition that there is no limit on the amount of money spent on the target patient, obtain the first treatment plan recommended by the cloud doctor for the target patient; Under the condition of the target patient's ability to pay, obtain the second treatment plan recommended by the cloud doctor for the target patient; Extracting at least one first treatment item in the first treatment plan, and extracting at least one second treatment item in the second treatment plan, wherein the first treatment item and the second treatment item are treatment items for the target patient respectively; The number of the second treatment items is divided by the number of the first treatment items to obtain the fitness coefficient for recommending the cloud doctor.

9. A health care cloud service method based on digital general practice diagnosis according to claim 8, characterized in that: Analyzing at least one service result in the cloud service to obtain the cloud service efficiency coefficient comprises the following steps: Based on big data, the cure status in the service results is obtained, and the cure status is either cured or not cured. If the cure status is cured, the cure time is counted; Based on historical data, obtain historical cure time for the target patient's disease; Obtain the total number of cures for at least one service result, and calculate the average cure time for at least one service result; Use the service efficiency formula to calculate the cloud service efficiency coefficient; The service efficiency formula is as follows: , Among them, D is the cloud service efficiency coefficient, k is the total number of cures, l is the number of at least one service result, m is the historical cure time, and n is the average cure time.

10. A health care cloud service method based on digital general practice diagnosis according to claim 9, characterized in that: The forming of a cloud doctor supplement scheme for cloud services based on at least one non-cloud doctor who does not provide cloud services comprises the following steps: Obtain the service result of non-cured condition as the target service result; Get the disease served by the target service result as the target disease; The non-cloud doctors whose cure rate for the target disease is greater than a preset ratio are selected as target non-cloud doctors; The target non-cloud doctors are numbered from small to large according to their medical expenses, and the target non-cloud doctors with numbers smaller than the preset numbers are aggregated to form a cloud doctor supplement plan.

Images