Doctor-patient matching method and device, processing equipment and storage medium

Abstract

The embodiment of the invention discloses a doctor-patient matching method and device, processing equipment and a storage medium. The method comprises the steps that disease types and first features of first-class patients are obtained, the first-class patients are patients needing follow-up visit arrangement, and the first features indicate prognosis effects of the first-class patients; acquiring a second feature of a second type of patient, wherein the second type of patient is a patient historically responsible for the to-be-matched follow-up visit doctor; the second type of patients are patients determined based on disease types, and the second feature indicates the prognosis effect of the second type of patients; and according to a matching result determined based on the first feature and the second feature, determining whether the follow-up visit doctor to be matched is an alternative doctor for follow-up visit of the first type of patients. Compared with a mode of randomly selecting the to-be-matched follow-up visit doctors, the determined alternative doctors can better understand the illness states of the first type of patients and can better adapt to the first type of patients, and targeted application of data between different types of patients can be achieved.

Description

Technical Field

[0001] The present invention relates to but is not limited to the field of information processing, and in particular to a doctor-patient matching method, apparatus, processing device and storage medium. Background Art

[0002] Follow-up mainly refers to the communication and exchange between medical staff and patients who are hospitalized or seen in outpatient clinics after they leave the hospital. Usually, the content of follow-up is to understand the changes in the patient's condition, give follow-up treatment suggestions, and understand the patient's opinions and suggestions on medical care and hospital management. Patient follow-up work is not highly targeted in the selection of patients, which leads to weak comparison between patient data and lack of sufficient basis for doctors to study the patient's condition. In addition, patient follow-up work is mainly led by doctors, which means that the doctors who follow up the patients may not be familiar with the patient's condition and cannot propose better treatment plans, which is not conducive to the patient's recovery after diagnosis. Summary of the invention

[0003] In view of this, the embodiments of the present disclosure disclose a doctor-patient matching method, apparatus, processing device and storage medium.

[0004] According to a first aspect of an embodiment of the present disclosure, a doctor-patient matching method is provided, the method comprising:

[0005] Obtaining a disease type and a first feature of a first category of patients, wherein the first category of patients are patients who need to be followed up, and the first feature indicates a prognosis effect of the first category of patients;

[0006] Obtaining a second feature of a second category of patients, where the second category of patients are patients who are historically responsible for the doctor to be matched for follow-up; the second category of patients are patients determined based on the disease type, and the second feature indicates the prognosis effect of the second category of patients;

[0007] According to the matching result determined based on the first feature and the second feature, it is determined whether the to-be-matched follow-up doctor is an alternative doctor for following up the first category of patients.

[0008] In one embodiment, determining whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients according to the matching result determined based on the first feature and the second feature includes:

[0009] For the first type of patients, determining a third feature corresponding to a prognostic effect within a first time period based on the first feature, wherein the third feature indicates a change trend of the first feature;

[0010] For the second type of patients, determining a fourth feature corresponding to the prognostic effect within a second period based on the second feature, wherein the fourth feature indicates a change trend of the second feature;

[0011] determining whether the third feature matches the fourth feature;

[0012] In response to the third feature matching the fourth feature, the fourth feature and the information of the second type of patients are added to a first reference case library, and the doctors corresponding to the patients included in the first reference case library are the candidate doctors.

[0013] In one embodiment, determining whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients according to the matching result determined based on the first feature and the second feature includes:

[0014] For the first type of patients, determining a first amplitude based on the first time period and the first feature;

[0015] For the second type of patients in the first reference case library, determining a second amplitude based on the second time period and the second feature;

[0016] Determine a magnitude relationship between a difference between the first amplitude and the second amplitude and a first predetermined threshold;

[0017] In response to the difference being less than or equal to the first predetermined threshold, the information of the second type of patients is added to a second reference case library, and the doctors corresponding to the patients included in the second reference case library are the candidate doctors.

[0018] In one embodiment, determining whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients according to the matching result determined based on the first feature and the second feature includes:

[0019] For the first type of patients, determining a first quantity of discrete data per unit time based on the first feature;

[0020] For the second type of patients, determining a second quantity of discrete data per unit time based on the second feature;

[0021] determining a difference between the second amount and the first amount and a first ratio of the second amount;

[0022] In response to the first ratio being less than or equal to a second threshold, the information of the second category of patients is added to a third reference case library, and the doctors corresponding to the patients included in the third reference case library are the candidate doctors.

[0023] In one embodiment, the method further comprises:

[0024] Sorting the number of follow-up arrangements of doctors corresponding to the patient information in the reference case library, and determining doctors whose number of follow-up arrangements is less than a third threshold as follow-up doctors for the first category of patients;

[0025] The reference case library is one of a first reference case library, a second reference case library and a third reference case library.

[0026] In one embodiment, the method further comprises:

[0027] Obtaining keywords and the keywords in the medical records of the first category of patients;

[0028] Determine the number of first occurrences of the keyword in the papers of the to-be-matched follow-up physician;

[0029] The determining, according to the matching result determined based on the first feature and the second feature, whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients includes:

[0030] According to the matching result and the first number of times, it is determined whether the to-be-matched follow-up doctor is an alternative doctor for the first category of patients.

[0031] In one embodiment, determining whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients according to the matching result determined based on the first feature and the second feature includes:

[0032] Whether the to-be-matched follow-up doctor is an alternative doctor for the first category of patients is determined according to the matching result and a fatigue parameter of the to-be-matched follow-up doctor, wherein the fatigue parameter indicates the fatigue degree of the to-be-matched follow-up doctor.

[0033] In one embodiment, the method further comprises:

[0034] Determining the fatigue parameter based on a surgical unexpectedness parameter and / or a surgical proficiency parameter;

[0035] The surgical accident degree parameter indicates the occurrence of an accident during the operation of the to-be-matched follow-up doctor; and the surgical proficiency parameter indicates the proficiency of the to-be-matched follow-up doctor in performing the operation.

[0036] In one embodiment, the method further comprises:

[0037] Acquire first information of the to-be-matched follow-up doctor during the operation, wherein the first information includes at least one of the following: surgical anesthesia dosage information, surgical gauze usage information, total blood aspirated information by the aspirator, and extra bleeding ratio information;

[0038] The surgical accident degree parameter corresponding to the to-be-matched follow-up doctor during the operation is determined based on the first information.

[0039] In one embodiment, the method further comprises:

[0040] Obtain the second number of operations performed by the to-be-matched follow-up doctor and the time of the last operation performed;

[0041] Based on the second number and time, the surgical proficiency parameter is determined.

[0042] According to a second aspect of an embodiment of the present disclosure, a doctor-patient matching device is provided, the device comprising:

[0043] an acquisition module, configured to acquire a disease type and a first feature of a first category of patients, wherein the first category of patients are patients who need to be followed up, and the first feature indicates a prognosis effect of the first category of patients;

[0044] The acquisition module is further configured to acquire a second feature of a second type of patient, wherein the second type of patient is a patient who is historically responsible for the doctor to be matched for follow-up; the second type of patient is a patient determined based on the disease type, and the second feature indicates a prognostic effect of the second type of patient;

[0045] The determination module is also configured to determine whether the to-be-matched follow-up doctor is an alternative doctor for following up the first category of patients according to a matching result determined based on the first feature and the second feature.

[0046] According to a third aspect of an embodiment of the present disclosure, a processing device is provided, the processing device comprising:

[0047] A memory for storing executable programs;

[0048] The processor is used to implement any method described in the embodiments of the present disclosure when executing the executable program stored in the memory.

[0049] According to a fourth aspect of the embodiments of the present disclosure, a computer storage medium is provided, wherein the computer storage medium stores an executable program, and when the executable program is executed by a processor, the method described in any one of the embodiments of the present disclosure is implemented.

[0050] In the disclosed embodiment, the disease type and the first feature of the first category of patients are obtained, the first category of patients are patients who need to be followed up, and the first feature indicates the prognosis of the first category of patients. The second feature of the second category of patients is obtained, the second category of patients are patients who are historically responsible for the follow-up doctor to be matched; the second category of patients are patients determined based on the disease type, and the second feature indicates the prognosis of the second category of patients. According to the matching result determined based on the first feature and the second feature, it is determined whether the follow-up doctor to be matched is an alternative doctor for following up the first category of patients. In the disclosed embodiment, since the first feature of the first category of patients and the second feature of the second category of patients are matched, it is determined whether the follow-up doctor to be matched is an alternative doctor for following up the first category of patients according to the matching result, so that the alternative doctor suitable for the first patient can be determined. Compared with the method of randomly selecting the follow-up doctor to be matched, the determined alternative doctor will have a better understanding of the condition of the first category of patients, will be more suitable for the first category of patients, and can achieve targeted application of data between different types of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flow chart of a doctor-patient matching method according to the first embodiment;

[0052] Figure 2 is a flow chart of a doctor-patient matching method according to the second embodiment;

[0053] Figure 3 is a flow chart of a doctor-patient matching method according to the third embodiment;

[0054] Figure 4 is a schematic diagram of a doctor-patient matching device according to a fourth embodiment;

[0055] Figure 5 FIG. 4 is a schematic diagram of a doctor-patient matching device according to the fifth embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present invention. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present invention.

[0057] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0058] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein.

[0059] In the following description, “greater than” and “less than” are involved. It should be noted that in the present disclosure, “greater than” can be used to indicate “greater than” or “equal to”; “less than” can be used to indicate “less than” or “equal to”.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0061] In order to better understand the embodiments of the present disclosure, the application scenarios of the technical solutions of the present disclosure are first described:

[0062] In some application scenarios, the patient follow-up method is to visit the patient by phone or letter. Doctors may not be able to contact the patient during follow-up. Even if they can contact the patient, the patient's condition data recording efficiency is low, data classification and subsequent query are difficult, and it is impossible to establish a database. For patients, doctors are busy and difficult to contact, and going to the hospital may be inconvenient, so they no longer actively follow up, which leads to a weakened connection between doctors and patients. Patients cannot get the doctor's follow-up treatment plan, which is not conducive to the patient's recovery, nor is it conducive to the doctor's understanding and research of the patient's condition.

[0063] In some embodiments, the patient follow-up work is still mainly based on telephone follow-up and paper records. Not only is the operation complicated, but the work content is also numerous. Most doctors are also busy with consultations, surgeries, etc., which makes them not have enough energy to carry out patient follow-up work. In view of this technical shortcoming, the embodiments of the present disclosure propose how to screen out doctors who have enough energy for follow-up.

[0064] In some embodiments, the patient follow-up work is not highly targeted in the selection of patients. This results in weak comparison between the patient data, which makes the doctor lack sufficient basis for the study of the patient's condition. In view of this technical shortcoming, the embodiment of the present disclosure proposes how to select patients who meet the doctor's needs for follow-up.

[0065] In some embodiments, patient follow-up is mainly led by doctors, resulting in the doctors who follow up patients not necessarily being familiar with the patient's condition and unable to propose better treatment plans, which is not conducive to the patient's recovery after diagnosis. The embodiments of the present disclosure address this technical shortcoming and propose how to match patients with more suitable doctors.

[0066] like Figure 1 As shown, a doctor-patient matching method is provided in an embodiment of the present disclosure, and the method includes:

[0067] Step S101, obtaining a disease type and a first feature of a first category of patients, wherein the first category of patients are patients who need to be followed up, and the first feature indicates a prognosis effect of the first category of patients;

[0068] Step S102, obtaining a second feature of a second category of patients, where the second category of patients are patients who are historically responsible for the doctor to be matched for follow-up; the second category of patients are patients determined based on the disease type, and the second feature indicates the prognosis effect of the second category of patients;

[0069] Step S103: Determine whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients according to the matching result determined based on the first feature and the second feature.

[0070] In some embodiments, the disease type and a first feature of a first category of patients are obtained, the first category of patients are patients who need follow-up arrangements, and the first feature indicates the prognosis of the first category of patients; the second feature of a second category of patients is obtained, the second category of patients are patients who are historically responsible for the follow-up doctor to be matched; the second category of patients are patients determined based on the disease type, and the second feature indicates the prognosis of the second category of patients; according to the matching result determined based on the first feature and the second feature, it is determined whether the follow-up doctor to be matched is an alternative doctor for following up the first category of patients; according to the matching result determined based on the first feature and the second feature, it is determined whether the follow-up doctor to be matched is an alternative doctor for following up the first category of patients, including: in response to determining that the first feature and the second feature match, determining the follow-up doctor to be matched as the alternative doctor.

[0071] In the disclosed embodiment, since the first feature of the first category of patients and the second feature of the second category of patients will be matched, it will be determined based on the matching result whether the to-be-matched follow-up doctor is an alternative doctor for following up the first category of patients. Compared with the method of randomly selecting the to-be-matched follow-up doctor, the determined alternative doctor will have a better understanding of the condition of the first category of patients, will be more suitable for the first category of patients, and can achieve targeted application of data between different types of patients.

[0072] In some embodiments, the first medical record information of the first category of patients who need to be followed up and stored in the blockchain node is read. Based on the first medical record information, the disease type and the first feature of the first category of patients are obtained. The first category of patients are patients who need to be followed up, and the first feature indicates the prognosis of the first category of patients. The second medical record information of the second category of patients stored in the blockchain node is read. Based on the second medical record information, the second feature of the second category of patients is obtained. The second category of patients are patients who are historically responsible for the follow-up doctor to be matched; the second category of patients are patients determined based on the disease type, and the second feature indicates the prognosis of the second category of patients. According to the matching result determined based on the first feature and the second feature, it is determined whether the follow-up doctor to be matched is an alternative doctor for following up the first category of patients. In the disclosed embodiment, the feature can be obtained based on the medical record information, so that the first feature can adapt to the condition of the first category of patients, and the second feature can adapt to the condition of the second category of patients.

[0073] In some embodiments, the specific contents of the prognostic effect can be preset, and the prognostic effect can correspond to the patient's blood sugar changes, temperature changes and / or sleep quality, etc., but is not limited thereto.

[0074] In some embodiments, the second type of patients are patients that the matching follow-up doctor is responsible for during a predetermined period of time; the second type of patients are patients determined based on the disease type. The predetermined period of time may be one week, one month, or one year. Exemplarily, the duration of the predetermined period of time is less than one week, so that the shorter the time, the more reference value the corresponding condition of the second type of patients has for the follow-up of the first type of patients.

[0075] In some embodiments, the disease type and the first feature of the first category of patients are obtained, the first category of patients are patients who need to be followed up, and the first feature indicates the prognosis of the first category of patients. The second feature of the second category of patients is obtained, the second category of patients are patients who are historically responsible for the doctor to be matched for follow-up; the second category of patients are patients determined based on the disease type, and the second feature indicates the prognosis of the second category of patients. For the first category of patients, a third feature corresponding to the prognosis in the first period is determined based on the first feature, and the third feature indicates the change trend of the first feature. For the second category of patients, a fourth feature corresponding to the prognosis in the second period is determined based on the second feature, and the fourth feature indicates the change trend of the second feature. Determine whether the third feature and the fourth feature match. In response to the third feature and the fourth feature matching, the fourth feature and the information of the second category of patients are added to the first reference case library, and the doctor corresponding to the patient included in the first reference case library is the candidate doctor. In the embodiment of the present disclosure, it can be determined whether to add the information of the second category of patients to the first reference case library based on the trend corresponding to the first feature and the second feature, so that patients with the same trend can be accurately obtained, so that the candidate doctor can be accurately determined.

[0076] In some embodiments, the doctor for follow-up may be determined from candidate doctors in the first reference case library.

[0077] In some embodiments, the first time period and the second time period may be the same time period or different time periods, which is not limited here. In one embodiment, the first time period and the second time period may be determined based on the time when the prognosis effect data is obtained just after discharge and the time when the prognosis effect data is most recently obtained. Exemplarily, the initial value a1 when the patient is just discharged and the final value a2 at the most recent detection in the prognosis effect characteristic value are read, and the trend A=a2-a1 of the overall characteristic value of the prognosis effect is determined.

[0078] In some embodiments, the disease type and first feature of a first type of patient are obtained, the first type of patient is a patient who needs to be followed up, and the first feature indicates the prognosis of the first type of patient. The second feature of a second type of patient is obtained, the second type of patient is a patient who is historically responsible for the doctor to be matched for follow-up; the second type of patient is a patient determined based on the disease type, and the second feature indicates the prognosis of the second type of patient. For the first type of patient, a first amplitude is determined based on the first time period and the first feature. For the second type of patient in the first reference case library, a second amplitude is determined based on the second time period and the second feature. The magnitude relationship between the difference between the first amplitude and the second amplitude and the first predetermined threshold is determined. In response to the difference being less than or equal to the first predetermined threshold, the information of the second type of patient is added to the second reference case library, and the doctor corresponding to the second type of patient included in the second reference case library is the candidate doctor. In the embodiment of the present disclosure, it can be determined whether to add the information of the second type of patient to the first reference case library based on the amplitude corresponding to the first feature and the second feature. Only when the amplitude difference is small, the information of the second type of patient will be added to the first reference case library. In this way, patients with the same trend change rate can be accurately obtained, so that the candidate doctor can be accurately determined.

[0079] In some embodiments, the doctor for follow-up may be determined from candidate doctors in the second reference case library.

[0080] In some embodiments, the amplitude may be a rate of change of a trend, for example, the first amplitude may be a rate of change of a third characteristic, and the second amplitude may be a rate of change of a fourth characteristic.

[0081] In some embodiments, the first time period and the second time period may be the same time period or different time periods, which is not limited here. In one embodiment, the first time period and the second time period may be determined based on the time when the prognosis effect data is obtained just after discharge and the time when the prognosis effect data is most recently obtained, for example, t. Exemplarily, the initial value a1 when the patient is just discharged and the final value a2 at the most recent detection in the prognosis effect characteristic value are read, and the trend A=a2-a1 of the overall characteristic value of the prognosis effect is determined, and the amplitude B may be (a2-a1) / t.

[0082] In some embodiments, the disease type and the first feature of the first type of patients are obtained, the first type of patients are patients who need to be followed up, and the first feature indicates the prognosis of the first type of patients. The second feature of the second type of patients is obtained, the second type of patients are patients who are historically responsible for the doctor to be matched for follow-up; the second type of patients are patients determined based on the disease type, and the second feature indicates the prognosis of the second type of patients. For the first type of patients, the first number of discrete data per unit time is determined based on the first feature. For the second type of patients, the second number of discrete data per unit time is determined based on the second feature. The difference between the second number and the first number and the first ratio of the second number are determined. In response to the first ratio being less than or equal to the second threshold, the information of the second type of patients is added to the third reference case library, and the doctor corresponding to the second type of patients included in the third reference case library is the candidate doctor. In the disclosed embodiment, since the number of discrete data reflects the stability of the feature, adding the information of the second type of patients with similar stability to the third reference case library can achieve more accurate determination of the candidate doctor from the third reference case library.

[0083] In some embodiments, the doctor for follow-up may be determined from candidate doctors in the third reference case library.

[0084] In some embodiments, the first quantity is C, the second quantity is D, the first ratio is E, Exemplarily, the second threshold may be 10%. When E is less than or equal to 10%, the information of the second category of patients is added to the third reference case library, and the doctors corresponding to the second category of patients contained in the third reference case library are the candidate doctors.

[0085] In order to better understand the embodiments of the present disclosure, the present disclosure is further described below through an exemplary embodiment:

[0086] Example 1:

[0087] The patient who currently needs to be followed up is a diabetic patient. His prognostic effect characteristic value is blood glucose concentration (corresponding to the first characteristic in the present disclosure), with specific values ​​of 200, 180, 190, 140, 90, 100, 80, in mg / dL, and the interval between each two characteristic values ​​is two months. The trend of the overall characteristic value of the prognostic effect is calculated to be A=-120 (corresponding to the third characteristic), the amplitude of the trend of the overall characteristic value of the prognostic effect is B=-5 (corresponding to the first amplitude), and the number of discrete data per unit time in the overall characteristic value of the prognostic effect of the patient who currently needs to be followed up is C=2 (the first number); the blood glucose concentration of a diabetic patient who was once in charge of the doctor who followed up this week is The sugar concentration (corresponding to the second feature) is 200, 180, 160, 140, 170, 100, 80, in mg / dL, and the interval between each two characteristic values ​​is two months. The trend of the overall characteristic value of the prognostic effect is calculated to be A=-120 (corresponding to the fourth feature), and the amplitude of the trend of the overall characteristic value of the prognostic effect is B=-10 (corresponding to the second amplitude). The number of discrete data per unit time in the overall characteristic value of the prognostic effect of the patient who currently needs to be followed up is D=1 (corresponding to the second number), and the absolute value of the ratio of the number of discrete data per unit time is calculated to be E=50% (corresponding to the first ratio). It cannot be added to the reference case library three (corresponding to the third reference case library).

[0088] In some embodiments, the disease type and first feature of the first category of patients are obtained, the first category of patients are patients who need to be followed up, and the first feature indicates the prognosis of the first category of patients. The second feature of the second category of patients is obtained, the second category of patients are patients who are historically responsible for the follow-up doctor to be matched; the second category of patients are patients determined based on the disease type, and the second feature indicates the prognosis of the second category of patients. According to the matching results determined based on the first feature and the second feature, it is determined whether the follow-up doctor to be matched is an alternative doctor for following up the first category of patients. The information of the second category of patients is added to the reference case library, the number of follow-up arrangements of the doctors corresponding to the patient information in the reference case library is sorted, and the doctor whose number of follow-up arrangements is less than the third threshold is determined as the follow-up doctor of the first category of patients; wherein the reference case library is one of the first reference case library, the second reference case library and the third reference case library. In the embodiment of the present disclosure, it is possible to determine that the doctor with a small number of follow-up arrangements is followed up, which can reduce the situation where the doctor has too many schedules and cannot follow up.

[0089] In order to better understand the embodiments of the present disclosure, the present disclosure is further described below through an exemplary embodiment:

[0090] Example 2:

[0091] See also Figure 2In an embodiment of the present disclosure, a doctor-patient matching method is provided, the method comprising:

[0092] Step S201, reading the medical record information of the patient (corresponding to the first type of patient) who needs to be followed up and arranged, which is stored in the blockchain node;

[0093] Step S202, extracting the disease type (corresponding to the disease type) and the prognosis effect characteristic value (corresponding to the first characteristic) of the patient who needs to be followed up, the prognosis effect characteristic value is set in advance by the doctor, and performing similarity matching with the patients that the doctor has been responsible for this week;

[0094] Step S203, reading the prognosis effect characteristic value records (corresponding to the second characteristic) of the patients who were once taken care of by the follow-up doctor this week and whose disease type is the same as that of the patient who needs to be followed up (corresponding to the second type of patients) from the medical records of the patients who were once taken care of by the follow-up doctor this week, and performing an overall analysis on the prognosis effect characteristic value records;

[0095] Step S204, after removing the discrete data in the overall characteristic value of the prognostic effect, read the initial value a1 when the patient is just discharged from the hospital and the final value a2 when the patient is most recently tested in the characteristic value of the prognostic effect, and determine the trend A=a2-a1 (corresponding to the third characteristic) of the overall characteristic value of the prognostic effect, and then preliminarily match the patients who currently need to be followed up with the patients who were previously responsible for the follow-up doctor this week through the trend of the overall characteristic value of the prognostic effect, and add the patients who were previously responsible for the follow-up doctor this week and whose trend of the overall characteristic value of the prognostic effect (corresponding to the fourth characteristic) is the same as the patient who currently needs to be followed up and who are the same as the patient who are previously responsible for the follow-up doctor this week to the reference case library 1 (the first reference case library); the reference case library 1 is used to store the data of the patients who were previously responsible for the follow-up doctor this week and whose trend of the overall characteristic value of the prognostic effect is the same as the patient who currently needs to be followed up;

[0096] Step S205, calculating the amplitude B of the trend of the overall characteristic value of the prognostic effect = (a2-a1) / t (corresponding to the first amplitude) through the interval time t between the initial value a1 and the final value a2 in the characteristic value of the prognostic effect, and comparing the amplitude B of the trend of the overall characteristic value of the prognostic effect of the patient in the reference case library 1 (corresponding to the second amplitude) with the amplitude B of the trend of the overall characteristic value of the prognostic effect of the patient who currently needs to be followed up, if the difference does not exceed the associated threshold, then adding the patient in the reference case library 1 currently being compared to the reference case library 2 (the second reference case library); the reference case library 2 is used to store the data of the patient in the reference case library 1 whose difference in the amplitude B of the trend of the overall characteristic value of the prognostic effect does not exceed the associated threshold compared with the patient who needs to be followed up;

[0097] Step S206, counting the number C (corresponding to the first number) of discrete data per unit time in the overall characteristic value of the prognosis effect of the patient who currently needs to arrange a follow-up visit and the number D (corresponding to the second number) of discrete data per unit time in the overall characteristic value of the prognosis effect of the patient in the reference case library 2, and calculating the absolute value E=|(DC) / D| of the ratio of the number of discrete data per unit time. If E is less than 10%, the patient in the reference case library 2 is added to the reference case library 3 (corresponding to the third reference case library), and the follow-up doctor with the largest number of reference cases in the reference case library 3 is selected to match the patient who currently needs to arrange a follow-up visit; the reference case library 3 is used to store the data of the patients in the reference case library 2 whose absolute value E (corresponding to the first ratio) of the ratio of the number of discrete data per unit time in the overall characteristic value of the prognosis effect is less than 10% compared with the patients who need to arrange a follow-up visit;

[0098] Step S207, if the number of follow-up arrangements for the doctor on the same day exceeds the threshold, then judge in sequence from large to small according to the number of reference cases until the number of follow-up arrangements for the doctor on the same day that matches does not exceed the threshold.

[0099] It should be noted that the patient's prognostic effect characteristic value is a main parameter that can reflect the patient's condition, such as the blood sugar content of diabetic patients and the number of cancer cells in cancer patients. By comparing the initial value a1 of the characteristic value when the patient is just discharged from the hospital and the final value a2 of the most recent test, it can reflect the degree of improvement or deterioration of the patient's condition after discharge. By comparing the degree of dispersion of the characteristic value over a period of time, the degree of fluctuation of the patient's condition can be observed. By matching these data with the patients the doctor has been responsible for, the doctor can have a better understanding of the patient's condition, facilitate the doctor's judgment and diagnosis of the condition, and bring better treatment service effects to the patient.

[0100] In some embodiments, the disease type and first feature of a first category of patients are obtained, the first category of patients are patients who need to be followed up, and the first feature indicates the prognosis of the first category of patients. The second feature of a second category of patients is obtained, the second category of patients are patients who are historically responsible for the doctor to be matched for follow-up; the second category of patients are patients determined based on the disease type, and the second feature indicates the prognosis of the second category of patients. Keywords and the keywords in the medical records of the first category of patients are obtained. The number of first times the keyword appears in the paper of the doctor to be matched for follow-up is determined. Based on the matching result determined based on the first feature and the second feature, and the first number of times, it is determined whether the doctor to be matched for follow-up is an alternative doctor for following up the first category of patients.

[0101] In the above embodiment, after determining the list of patients who need to be followed up on that day, the medical record of a patient who needs to be followed up on that day can be read and the keywords in the medical record can be extracted; the keywords in the medical record can be matched with a certain paper of a hospital doctor to obtain the number of times all the keywords in the medical record appear in the paper of the hospital doctor; thereby matching the patient with a doctor who is more familiar with his or her condition; and also matching the doctor with a patient who is more in line with his or her own research direction.

[0102] In some embodiments, after determining the list of patients who need to be followed up on that day, the medical record of a patient who needs to be followed up on that day is read and the keywords in the medical record are extracted, and the number of keywords is J. The keywords in the medical record are matched with a certain paper of a hospital doctor to obtain the number of times all the keywords in the medical record appear in the paper of the hospital doctor. (corresponding to the first number), where ki is the number of times the i-th keyword appears in this paper of the doctor in this hospital, read the number of all papers of the doctors in the hospital L, and get the number of times all the keywords in this medical record appear in all papers of the doctors in the hospital Mi is the number of times all the keywords in this medical record appear in the i-th paper written by the hospital doctor.

[0103] In some embodiments, the number of keywords J=2, k1=5, k2=10, the number of times all the keywords in the medical records appear in a paper written by a hospital doctor is M=k1+k2=15, the number of all papers written by the hospital doctors is 100, and the number of times all the keywords in the medical records appear in all papers written by the hospital doctors is N=15+18+21+...+16=1821 (corresponding to the first number).

[0104] It should be noted that the follow-up order of all patients who need to be followed up on that day is arranged in descending order according to the number of times N that all keywords in the medical records of all patients who need to be followed up on that day appear in all papers of hospital doctors. Matching the medical records of patients who currently need to be followed up with the research results conducted by hospital doctors can facilitate doctors and hospitals to obtain more detailed condition data of patients that match their own research directions, which is conducive to the progress of medical research of hospital doctors, and can also bring more advanced treatment plans to patients and promote the development of the medical system.

[0105] It should be noted that patients can make an appointment with a designated doctor when making a follow-up appointment. If the patient makes an appointment on his own, there will be no doctor-patient matching, and the patient will be directly matched with the designated doctor for the follow-up on the same day. Patients can choose the same doctor by themselves, making the follow-up more targeted.

[0106] In some embodiments, the disease type and first feature of a first category of patients are obtained, the first category of patients are patients who need to be followed up, and the first feature indicates the prognosis of the first category of patients. The second feature of a second category of patients is obtained, the second category of patients are patients who are historically responsible for the doctor to be matched for follow-up; the second category of patients are patients determined based on the disease type, and the second feature indicates the prognosis of the second category of patients. According to the matching results determined based on the first feature and the second feature, and the fatigue parameter of the doctor to be matched for follow-up, it is determined whether the doctor to be matched for follow-up is an alternative doctor for the first category of patients, and the fatigue parameter indicates the fatigue level of the doctor to be matched for follow-up. In the disclosed embodiment, since the doctor's fatigue level is taken into consideration, doctors with mild fatigue or no fatigue can be selected for follow-up to better serve patients.

[0107] In some embodiments, the disease type and first feature of a first category of patients are obtained, the first category of patients are patients who need to be followed up, and the first feature indicates the prognosis of the first category of patients. The second feature of a second category of patients is obtained, the second category of patients are patients who are historically responsible for the matching follow-up doctor; the second category of patients are patients determined based on the disease type, and the second feature indicates the prognosis of the second category of patients. The fatigue parameter is determined based on a surgical accident degree parameter and / or a surgical proficiency parameter; wherein the surgical accident degree parameter indicates an unexpected situation during the operation of the matching follow-up doctor; the surgical proficiency parameter indicates the proficiency of the matching follow-up doctor in performing the operation. According to the matching result determined based on the first feature and the second feature, and the fatigue parameter of the matching follow-up doctor, it is determined whether the matching follow-up doctor is an alternative doctor for the first category of patients, and the fatigue parameter indicates the fatigue degree of the matching follow-up doctor.

[0108] In some embodiments, first information of the doctor to be matched during the operation is obtained, and the first information includes at least one of the following: information on the amount of anesthesia used in the operation, information on the amount of gauze used in the operation, information on the total amount of blood sucked by the aspirator, and information on the percentage of extra bleeding. Based on the first information, the surgical accident degree parameter corresponding to the doctor to be matched during the operation is determined.

[0109] In some embodiments, the second number of times the to-be-matched follow-up doctor has performed surgery and the time of the last surgery are obtained, and the surgery proficiency parameter is determined based on the second number of times and time.

[0110] In order to better understand the embodiments of the present disclosure, the present disclosure is further described below through an exemplary embodiment:

[0111] Example 3:

[0112] See also Figure 3 In an embodiment of the present disclosure, a doctor-patient matching method is provided, the method comprising:

[0113] Step S301, reading the hospital doctor's work schedule for one week stored in the blockchain node, including ward rounds, consultations, surgeries and meetings;

[0114] Step S302, reading the patient's self-booking information, and sorting the number of times the doctor is booked by the patient from the largest to the smallest;

[0115] Step S303, select the doctor with the most self-booked appointments, read the doctor's work calendar, sort the doctor's work schedule in a week from small to large; select the day with the shortest working hours for the doctor;

[0116] Step S304, read the surgical contents of the doctor's shortest working day, query the total amount of anesthetic drugs y1 (corresponding to the first information) used in the doctor's most recent surgery with the same contents, and obtain the proportion of additional anesthetic drugs used in the doctor's most recent surgery with the same contents y=(y1-y2) / y1, where y2 is the amount of anesthetic drugs used in normal surgery;

[0117] Step S305, read the amount of gauze used e and the total amount of blood sucked by the aspirator f (corresponding to the first information) in the doctor's most recent surgery with the same content, and obtain the total amount of bleeding of the patient in the doctor's most recent surgery with the same content x1=h*e+f, where h is the amount of blood that each piece of gauze can absorb; the degree of bleeding during surgery not only reflects whether there is an accident during the surgery, but also affects the surgical field of view, further affecting the difficulty of the surgery. During the operation, the anesthesiologist monitors the patient's vital signs and uses medication to respond in different situations; generally, the process of an operation is fixed, so there are thresholds for the operation time, the amount of anesthetic drugs, and the amount of bleeding during the doctor's resection, transfer and other operations during the operation. When an unexpected situation occurs during the operation, the amount of anesthetic drugs will also be adjusted due to the surgical situation; and an increase in the amount of bleeding during the operation will not only bring new dangers, but also block the surgical field of view and increase the difficulty of the operation. Therefore, the amount of anesthetic drugs and the total amount of bleeding in an operation can be used to reflect the degree of unexpected situations in the operation;

[0118] Step S306, calculate the percentage of extra bleeding in the doctor's most recent surgery with the same content, x = (x1-x2) / x1 (corresponding to the first information), where x2 is the normal amount of bleeding during surgery; the degree of accident in the doctor's most recent surgery with the same content can be obtained as b = 0.67x + 0.33y (corresponding to the parameter of the degree of accident in surgery);

[0119] Step S307, read the total number of times the doctor has performed the same type of surgery c (corresponding to the second number) and the interval d between the doctor's most recent surgery and this surgery (corresponding to the time of the last surgery), and obtain the doctor's surgical proficiency a = c*(1-0.56d 0.06 ); A doctor's surgical proficiency is determined by the number of similar surgeries he has performed. After a period of not performing the same type of surgery, the doctor will gradually become unfamiliar with the surgical content. The doctor's surgical unfamiliarity can be obtained based on the Ebbinghaus forgetting curve. Combined with the total number of similar surgeries performed by the doctor, the doctor's surgical proficiency (corresponding to the surgical proficiency parameter) can be obtained.

[0120] Step S308, calculate the final accident degree T=b / a (corresponding to fatigue parameter) of the doctor's most recent surgery with the same content;

[0121] Step S309, compare T with the doctor's fatigue threshold. If T is less than the fatigue threshold, arrange the doctor to follow up the patient on the same day. If T is greater than the fatigue threshold, read the surgical content of the working day with the second shortest working hours and calculate T. If T is less than the fatigue threshold, arrange the doctor to follow up the patient on the same day. If T is greater than the fatigue threshold, continue the same operation until the doctor's T is less than the fatigue threshold, and arrange the doctor to follow up the patient on the same day.

[0122] Step S310: If the T of the doctor with the most appointments made by the patient is greater than the fatigue threshold in a week, the doctor will be arranged for follow-up in the next week.

[0123] In some embodiments, the total amount of anesthetic drugs y1=12mg, the amount of anesthetic drugs used in normal surgery y2=10mg, the amount of gauze used e=30, the amount of blood that each piece of gauze can absorb h=40ml, the total amount of blood sucked by the suction device f=300ml, the normal surgical bleeding x2=1200ml, the total number of similar surgeries performed by this doctor c=20, the interval time between the doctor's last surgery with the same content and this surgery d=24H, it is calculated that the proportion of additional anesthetic drugs used in the doctor's last surgery with the same content y=0.2, the total amount of patient bleeding in the doctor's last surgery with the same content x1=1500ml, the proportion of additional patient bleeding in the doctor's last surgery with the same content x=0.25, the degree of accident in the doctor's last surgery with the same content b=0.23, the doctor's surgical proficiency a=6.4, and the final degree of accident in the doctor's last surgery with the same content T=0.03. The doctor's fatigue threshold is 0.05, which does not exceed the fatigue threshold, and the doctor is arranged for follow-up on the same day.

[0124] Step S311, after completing the follow-up arrangement for the doctor with the largest number of self-booked appointments by the patient, the same operation is performed on the doctor with the second highest number of self-booked appointments by the patient until the follow-up arrangement for this week is completed.

[0125] In the disclosed embodiment, when doctors perform the same type of surgery and no accidents occur, the doctors' mental state will be more excited and in a better state of mind. However, if an accident occurs during the surgery, it will consume more of the doctors' energy, making them more tired, resulting in lack of concentration or poor mental outlook during subsequent follow-up work, thereby reducing the quality of follow-up. Therefore, no follow-up arrangements will be made for doctors whose surgeries have a greater degree of accidents, so as to provide patients with better quality of medical services.

[0126] like Figure 4 As shown, the embodiment of the present disclosure provides a doctor-patient matching device, the device comprising:

[0127] An acquisition module 41 is configured to acquire a disease type and a first feature of a first category of patients, wherein the first category of patients are patients who need to be followed up, and the first feature indicates a prognosis effect of the first category of patients;

[0128] The acquisition module 41 is further configured to acquire a second feature of a second type of patient, where the second type of patient is a patient who is historically responsible for the doctor to be matched for follow-up; the second type of patient is a patient determined based on the disease type, and the second feature indicates the prognosis effect of the second type of patient;

[0129] The determination module 42 is configured to determine whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients according to a matching result determined based on the first feature and the second feature.

[0130] In some embodiments, the determination module 42 is further configured to:

[0131] For the first type of patients, determining a third feature corresponding to a prognostic effect within a first time period based on the first feature, wherein the third feature indicates a change trend of the first feature;

[0132] For the second type of patients, determining a fourth feature corresponding to the prognostic effect within a second period based on the second feature, wherein the fourth feature indicates a change trend of the second feature;

[0133] determining whether the third feature matches the fourth feature;

[0134] In response to the third feature matching the fourth feature, the fourth feature and the information of the second type of patients are added to the first reference case library, and the doctors corresponding to the second type of patients included in the first reference case library are the candidate doctors.

[0135] In some embodiments, the determination module 42 is further configured to:

[0136] For the first type of patients, determining a first amplitude based on the first time period and the first feature;

[0137] For the second type of patients in the first reference case library, determining a second amplitude based on the second time period and the second feature;

[0138] Determine a magnitude relationship between a difference between the first amplitude and the second amplitude and a first predetermined threshold;

[0139] In response to the difference being less than or equal to the first predetermined threshold, the information of the second category of patients is added to a second reference case library, and the doctors corresponding to the second category of patients included in the second reference case library are the candidate doctors.

[0140] In some embodiments, the determination module 42 is further configured to:

[0141] For the first type of patients, determining a first quantity of discrete data per unit time based on the first feature;

[0142] For the second type of patients in the second reference case library, determining a second quantity of discrete data per unit time based on the second feature;

[0143] determining a difference between the second amount and the first amount and a first ratio of the second amount;

[0144] In response to the first ratio being less than or equal to a second threshold, the information of the second category of patients is added to a third reference case library, and the doctors corresponding to the second category of patients included in the third reference case library are the candidate doctors.

[0145] In some embodiments, the determination module 42 is further configured to:

[0146] Sorting the number of follow-up arrangements of doctors corresponding to the patient information in the reference case library, and determining doctors whose number of follow-up arrangements is less than a third threshold as follow-up doctors for the first category of patients;

[0147] The reference case library is one of the first reference case library, the second reference case library and the third reference case library.

[0148] In some embodiments, the acquisition module 41 is further configured to: acquire the keywords and the keywords in the medical records of the first category of patients;

[0149] The determination module 42 is also configured to: determine the first number of times the keyword appears in the paper of the follow-up doctor to be matched; and determine whether the follow-up doctor to be matched is an alternative doctor for following up the first category of patients based on the matching result determined based on the first feature and the second feature, including: determining whether the follow-up doctor to be matched is an alternative doctor for the first category of patients based on the matching result and the first number of times.

[0150] In some embodiments, the determination module 42 is further configured to:

[0151] Whether the to-be-matched follow-up doctor is an alternative doctor for the first category of patients is determined according to the matching result and a fatigue parameter of the to-be-matched follow-up doctor, wherein the fatigue parameter indicates the fatigue degree of the to-be-matched follow-up doctor.

[0152] In some embodiments, the determination module 42 is further configured to: determine the fatigue parameter based on a surgical unexpectedness parameter and / or a surgical proficiency parameter;

[0153] The surgical accident degree parameter indicates the occurrence of an accident during the operation of the to-be-matched follow-up doctor; and the surgical proficiency parameter indicates the proficiency of the to-be-matched follow-up doctor in performing the operation.

[0154] In some embodiments, the acquisition module 41 is further configured to:

[0155] Acquire first information of the to-be-matched follow-up doctor during the operation, wherein the first information includes at least one of the following: surgical anesthesia dosage information, surgical gauze usage information, total blood aspirated information by the aspirator, and extra bleeding ratio information;

[0156] The determination module 42 is further configured to determine the surgical accident degree parameter corresponding to the to-be-matched follow-up doctor during the surgical procedure based on the first information.

[0157] In some embodiments, the acquisition module 41 is further configured to:

[0158] Obtain the second number of operations performed by the to-be-matched follow-up doctor and the time of the last operation performed;

[0159] The determination module 42 is further configured to determine the surgical proficiency parameter based on the second number of times and time.

[0160] In order to better understand the embodiments of the present disclosure, the technical solution of the present disclosure is further described below through an exemplary embodiment:

[0161] Example 5:

[0162] In some embodiments, the blockchain-based hospital patient intelligent follow-up management system (corresponding to the doctor-patient matching device of the present disclosure) includes a doctor interaction module 51, an intelligent appointment module 52 and a patient interaction module 53.

[0163] In some embodiments, the blockchain-based hospital patient intelligent follow-up management system is connected to the hospital information system, and the doctor interaction module 51 includes an information reading module 511 and a schedule automatic generation module 512. The information reading module 511 reads the hospital doctor's work schedule within a week stored in the blockchain node and transmits it to the schedule automatic generation module 512. The schedule automatic generation module 512 generates a patient follow-up schedule within a week according to the doctor's work schedule within a week.

[0164] In some embodiments, the intelligent appointment module 52 includes a patient information reading module 521, a doctor-patient matching module 522 and a follow-up order arrangement module 523. The patient information reading module 521 reads the patient's medical record information through blockchain technology and transmits it to the doctor-patient matching module 522. The doctor-patient matching module 522 matches the current patient by comparing the medical records and prognosis of other patients of the doctor, and selects a suitable doctor for the patient. The follow-up order arrangement module 523 sorts the follow-up order of patients who need follow-up.

[0165] In some embodiments, the patient interaction module 53 allows patients to make appointments with designated doctors on their own. This system can effectively reduce doctors' workload, improve follow-up efficiency, and provide patients with better medical services.

[0166] In some embodiments, the information reading module 511 reads the work schedule of hospital doctors within a week stored in the blockchain node, including ward rounds schedule, consultation schedule, surgery schedule and meeting schedule;

[0167] In some embodiments, the automatic scheduling module 512 includes an anesthetic medication ratio calculation module, an extra bleeding ratio calculation module, a surgical accident degree calculation module and a proficiency calculation module. The automatic scheduling module automatically reads the patient's self-booking information, and sorts the number of times the doctor is self-booked by the patient from large to small; and selects the doctor with the most self-booked times, reads the doctor's work calendar through the information reading module, and sorts the length of the doctor's work schedule in a week from small to large; selects the day with the shortest working hours of the doctor; reads the surgical content of the day with the shortest working hours of the doctor through the information reading module, queries the total amount of anesthetic medication y1 used in the doctor's most recent surgery with the same content, and transmits it to the anesthetic medication ratio calculation module to obtain the proportion of additional anesthetic medication used in the doctor's most recent surgery with the same content. Among them, y2 is the amount of anesthesia used in normal surgery; the amount of gauze used e and the total amount of blood sucked by the suction device f in the doctor's most recent surgery with the same content are read through the information reading module, and transmitted to the extra bleeding ratio calculation module to obtain the total amount of bleeding of the patient in the doctor's most recent surgery with the same content x1=h*e+f, where h is the amount of blood that each piece of gauze can absorb; the extra bleeding ratio of the patient in the doctor's most recent surgery with the same content is calculated Among them, x2 is the normal amount of bleeding during surgery; the surgical accident degree calculation module is used to calculate the accident degree of the doctor's most recent surgery with the same content b=0.67x+0.33y; the total number of similar surgeries performed by the doctor c and the interval time d between the doctor's most recent surgery with the same content and this surgery are read through the information reading module, and transmitted to the proficiency calculation module to obtain the doctor's surgical proficiency a=c*(1-0.56d 0.06 ); The final degree of accident of the doctor's most recent surgery with the same content is calculated by the surgical accident degree calculation module. T is compared with the doctor's fatigue threshold. If T is less than the fatigue threshold, the doctor is arranged to follow up the patient on the same day. If T is greater than the fatigue threshold, the surgical content of the working day with the second shortest working hours is read and T is calculated. If T is less than the fatigue threshold, the doctor is arranged to follow up the patient on the same day. If T is greater than the fatigue threshold, the same operation is continued until the doctor's T is less than the fatigue threshold, and the doctor is arranged to follow up the patient on the same day; if the doctor with the most self-appointed appointments by patients has T greater than the fatigue threshold within a week, the doctor will be arranged for follow-up in the next week; after completing the follow-up arrangement for the doctor with the largest number of self-appointed appointments by patients, the same operation is performed on the doctor with the second highest number of self-appointed appointments by patients until the follow-up arrangement for this week is completed.

[0168] In some embodiments, the information reading module 511 reads the medical record information of the patient who needs to be followed up and stored in the blockchain node and transmits it to the doctor-patient matching module 522.

[0169] In some embodiments, the doctor-patient matching module 522 includes a trend judgment module 5221, a trend amplitude calculation module 5222 and a discrete data ratio calculation module 5223. After receiving the medical record information of the patient who needs to be followed up, the doctor-patient matching module 522 extracts the disease type and prognosis effect characteristic value of the patient who needs to be followed up, the prognosis effect characteristic value is set in advance by the doctor, and is matched with the patient who was once in charge of the doctor who was following up this week for similarity; in the medical records of the patients who were once in charge of the doctor who was following up this week and had the same disease type as the patient who needs to be followed up, the prognosis effect characteristic value records of the patients who were once in charge of the doctor who was following up this week are read, and the prognosis effect characteristic value records are analyzed as a whole;

[0170] After removing the discrete data in the overall characteristic value of the prognostic effect, the initial value a1 when the patient is just discharged from the hospital and the final value a2 when the patient is most recently tested in the characteristic value of the prognostic effect are read and transmitted to the trend judgment module to determine the trend A=a2-a1 of the overall characteristic value of the prognostic effect, and then the patients who currently need to be followed up are preliminarily matched with the patients who were once responsible for the follow-up doctor this week through the trend of the overall characteristic value of the prognostic effect, and the patients who were once responsible for the follow-up doctor this week and whose trend of the overall characteristic value of the prognostic effect is the same as the patients who currently need to be followed up are added to the reference case library 1; the reference case library 1 is used to store the data of the patients who were once responsible for the follow-up doctor this week and whose trend of the overall characteristic value of the prognostic effect is the same as the patients who currently need to be followed up;

[0171] The interval time t between the initial value a1 and the final value a2 in the prognostic effect characteristic value is read by the information reading module, and transmitted to the trend amplitude calculation module, and the interval time t between the initial value a1 and the final value a2 in the prognostic effect characteristic value is calculated to calculate the amplitude of the trend of the overall prognostic effect characteristic value. The amplitude of the trend of the overall characteristic value of the prognosis effect of the patient in the reference case library 1 is compared with the amplitude B of the trend of the overall characteristic value of the prognosis effect of the patient who currently needs to be followed up. If the difference does not exceed the associated threshold, the patient in the reference case library 1 currently being compared is added to the reference case library 2; the reference case library 2 is used to store the data of the patient in the reference case library 1 whose difference in the amplitude B of the trend of the overall characteristic value of the prognosis effect does not exceed the associated threshold compared with the patient who needs to be followed up;

[0172] The number C of discrete data per unit time in the overall characteristic value of the prognosis effect of the patient who currently needs to be followed up and the number D of discrete data per unit time in the overall characteristic value of the prognosis effect of the patient in the reference case library 2 are read by the information reading module, and transmitted to the discrete data ratio calculation module to calculate the absolute value of the ratio of the number of discrete data per unit time. If E is less than 10%, the patient in the reference case library 2 is added to the reference case library 3, and the follow-up doctor with the largest number of reference cases in the reference case library 3 is selected to match the patient who currently needs to be followed up; the reference case library 3 is used to store the data of the patients in the reference case library 2 whose absolute value E of the ratio of the number of discrete data per unit time in the overall characteristic value of the prognostic effect is less than 10% compared with the patients who need to be followed up;

[0173] If the number of follow-up arrangements for the doctor on the same day exceeds the threshold, the number of reference cases will be judged in descending order until the number of follow-up arrangements for the doctor on the same day that matches does not exceed the threshold.

[0174] In some embodiments, the follow-up sequence arrangement module 523 includes an information reading module 5231, an information transmission module 5232, a keyword extraction module 5233 and a text matching module 5234. The information reading module 5231 is used to read the medical records of all patients who need to be followed up on the day and transmit them to the keyword extraction module 5233 to extract the keywords in the medical records, and the number of keywords is J; the extracted keywords are transmitted to the text matching module 5234 through the information transmission module 5231; the keywords in the medical records are text matched with a certain paper of a doctor in this hospital to obtain the number of times all the keywords in this medical record appear in this paper of the doctor in the hospital Where ki is the number of times the i-th keyword appears in this paper of the doctor in this hospital. Then read the number of all papers of the doctors in this hospital, L, and get the number of times all the keywords in this medical record appear in all papers of the doctors in the hospital. Mi is the number of times all the keywords in the medical record appear in the i-th paper of the hospital doctor; the number of times N that the medical records of all patients who need to be followed up on that day appear in all the papers of the hospital doctor is transmitted to the follow-up order arrangement module through the information transmission module 5232, and the follow-up order of all the patients who need to be followed up on that day is arranged in descending order according to N.

[0175] In some embodiments, the patient interaction module 53 allows the patient to make an appointment with a designated doctor on his own. If the patient makes an appointment on his own, doctor-patient matching is not performed, and the patient is directly matched with a follow-up visit with the designated doctor who made the appointment on the same day.

[0176] The present disclosure provides a processing device, the processing device comprising:

[0177] A memory for storing executable programs;

[0178] The processor is used to implement any method described in the embodiments of the present disclosure when executing the executable program stored in the memory.

[0179] It can be understood that the memory can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAM bus random access memory (DRRAM, Direct Rambus Random Access Memory).The memories described in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0180] Among them, the method for determining the topological structure disclosed in the present invention can be applied to the processor or implemented by the processor. The processor can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the method for determining the topological structure can be completed by an integrated logic circuit of the hardware in the processor or an instruction in the form of software. The above-mentioned processor can be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor can implement or execute the methods, steps and logic block diagrams disclosed in the present invention. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the information in the memory, and completes the steps of the method for determining the topological structure provided in the embodiment of the present application in combination with its hardware.

[0181] The present invention also provides a computer storage medium, wherein the computer storage medium stores an executable program, and when the executable program is executed by a processor, the method for determining the topological structure as described in any of the embodiments of the present disclosure is implemented. Specifically, it can be a computer-readable storage medium, such as a memory including a computer program, and the computer program can be executed by a processor of a processing device to complete the steps described in the method of the embodiment of the present application. The computer-readable storage medium can be a memory such as ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disk, or CD-ROM.

[0182] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A doctor-patient matching method, characterized in that: The method comprises: Obtaining a disease type and a first feature of a first category of patients, wherein the first category of patients are patients who need to be followed up, and the first feature indicates a prognosis effect of the first category of patients; Obtaining a second feature of a second category of patients, where the second category of patients are patients who are historically responsible for the doctor to be matched for follow-up; the second category of patients are patients determined based on the disease type, and the second feature indicates the prognosis effect of the second category of patients; According to the matching result determined based on the first feature and the second feature, it is determined whether the to-be-matched follow-up doctor is an alternative doctor for following up the first category of patients.

2. The method according to claim 1, characterized in that The determining, according to the matching result determined based on the first feature and the second feature, whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients includes: For the first type of patients, determining a third feature corresponding to a prognostic effect within a first time period based on the first feature, wherein the third feature indicates a change trend of the first feature; For the second type of patients, determining a fourth feature corresponding to the prognostic effect within a second period based on the second feature, wherein the fourth feature indicates a change trend of the second feature; determining whether the third feature matches the fourth feature; In response to the third feature matching the fourth feature, the fourth feature and the information of the second type of patients are added to the first reference case library, and the doctors corresponding to the second type of patients included in the first reference case library are the candidate doctors.

3. The method according to claim 2, characterized in that The determining, according to the matching result determined based on the first feature and the second feature, whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients includes: For the first type of patients, determining a first amplitude based on the first time period and the first feature; For the second type of patients in the first reference case library, determining a second amplitude based on the second time period and the second feature; Determine a magnitude relationship between a difference between the first amplitude and the second amplitude and a first predetermined threshold; In response to the difference being less than or equal to the first predetermined threshold, the information of the second category of patients is added to a second reference case library, and the doctors corresponding to the second category of patients included in the second reference case library are the candidate doctors.

4. The method according to claim 3, characterized in that The determining, according to the matching result determined based on the first feature and the second feature, whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients includes: For the first type of patients, determining a first quantity of discrete data per unit time based on the first feature; For the second type of patients in the second reference case library, determining a second quantity of discrete data per unit time based on the second feature; determining a difference between the second amount and the first amount and a first ratio of the second amount; In response to the first ratio being less than or equal to a second threshold, the information of the second category of patients is added to a third reference case library, and the doctors corresponding to the second category of patients included in the third reference case library are the candidate doctors.

5. The method according to claim 4, characterized in that The method further comprises: Sorting the number of follow-up arrangements of doctors corresponding to the patient information in the reference case library, and determining doctors whose number of follow-up arrangements is less than a third threshold as follow-up doctors for the first category of patients; The reference case library is one of the first reference case library, the second reference case library and the third reference case library.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining keywords and the keywords in the medical records of the first category of patients; Determine the number of first occurrences of the keyword in the papers of the to-be-matched follow-up physician; The determining, according to the matching result determined based on the first feature and the second feature, whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients includes: According to the matching result and the first number of times, it is determined whether the to-be-matched follow-up doctor is an alternative doctor for the first category of patients.

7. The method according to claim 1, characterized in that The determining, according to the matching result determined based on the first feature and the second feature, whether the to-be-matched follow-up doctor is a candidate doctor for following up the first category of patients includes: Whether the to-be-matched follow-up doctor is an alternative doctor for the first category of patients is determined according to the matching result and a fatigue parameter of the to-be-matched follow-up doctor, wherein the fatigue parameter indicates the fatigue degree of the to-be-matched follow-up doctor.

8. The method according to claim 7, characterized in that The method further comprises: Determining the fatigue parameter based on a surgical unexpectedness parameter and / or a surgical proficiency parameter; The surgical accident degree parameter indicates the occurrence of an accident during the operation of the to-be-matched follow-up doctor; and the surgical proficiency parameter indicates the proficiency of the to-be-matched follow-up doctor in performing the operation.

9. The method according to claim 8, characterized in that The method further comprises: Acquire first information of the to-be-matched follow-up doctor during the operation, wherein the first information includes at least one of the following: surgical anesthesia dosage information, surgical gauze usage information, total blood aspirated information by the aspirator, and extra bleeding ratio information; The surgical accident degree parameter corresponding to the to-be-matched follow-up doctor during the operation is determined based on the first information.

10. The method according to claim 8, characterized in that The method further comprises: Obtain the second number of operations performed by the to-be-matched follow-up doctor and the time of the last operation performed; Based on the second number and time, the surgical proficiency parameter is determined.

11. A doctor-patient matching device, characterized in that: The device comprises: an acquisition module, configured to acquire a disease type and a first feature of a first category of patients, wherein the first category of patients are patients who need to be followed up, and the first feature indicates a prognosis effect of the first category of patients; The acquisition module is further configured to acquire a second feature of a second type of patient, wherein the second type of patient is a patient who is historically responsible for the doctor to be matched for follow-up; the second type of patient is a patient determined based on the disease type, and the second feature indicates a prognostic effect of the second type of patient; The determination module is also configured to determine whether the to-be-matched follow-up doctor is an alternative doctor for the first category of patients according to a matching result determined based on the first feature and the second feature.

12. A processing device, characterized in that: The processing equipment comprises: A memory for storing executable programs; A processor, configured to implement the method according to any one of claims 1 to 10 when executing the executable program stored in the memory.

13. A computer storage medium, characterized in that: The computer storage medium stores an executable program, and when the executable program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images