CN112562836A

CN112562836A - Doctor recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN112562836A
Application number: CN202011507196.5A
Authority: CN
Inventors: 舒艳波; 李海同
Original assignee: Shenzhen Saiante Technology Service Co Ltd
Current assignee: Shenzhen Saiante Technology Service Co Ltd
Priority date: 2020-12-18
Filing date: 2020-12-18
Publication date: 2021-03-26

Abstract

The invention relates to the technical field of digital medical treatment, and provides a doctor recommendation method, a doctor recommendation device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a plurality of disease characteristic attributes of a patient, inputting the acquired disease characteristic attributes into a department identification model for identification to obtain a clinic, and determining the disease grade of the patient according to the plurality of disease characteristic attributes; acquiring at least one recommended doctor according to the position coordinates of the starting point of the patient, the clinic for treatment and the disease grade; determining a quality label of the patient according to the basic information of the patient; and determining to obtain a target recommended doctor according to a plurality of disease characteristic attributes, disease grades, quality labels and doctor images of at least one recommended doctor of the patient. The target recommending doctor is determined according to the disease characteristic attributes, the disease grades, the quality labels and the doctor portrait of the patient, the target recommending doctor is prevented from being directly obtained according to the disease characteristic attributes of the patient singly, and the matching degree of the doctor and the patient requirements and the recommending accuracy of the target recommending doctor are improved.

Description

Doctor recommendation method and device, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of digital medical treatment, in particular to a doctor recommendation method, a doctor recommendation device, electronic equipment and a storage medium.

Background

With the increase of medical institutions and the refinement of each department, a patient can hardly make an appointment with a proper hospital, department and doctor according to the disease condition of the patient, most of the existing intelligent doctor recommendation systems are performed for the doctor, and intelligent recommendation is performed for the patient by comprehensively acquiring the attributes of the doctor, such as the sitting hospital, the job and the department. The doctor recommended by the traditional recommendation system is low in matching degree with the requirements of the patient, the recommendation result is not accurate, and even the treatment of the patient can be delayed.

Disclosure of Invention

In view of the above, there is a need for a method, an apparatus, an electronic device and a storage medium for recommending a doctor, which determine a target recommending doctor according to a plurality of disease characteristic attributes, disease levels, quality labels and doctor profiles of a patient, avoid directly obtaining the target recommending doctor according to the disease characteristic attributes of the patient, and improve the matching degree between the doctor and the patient and the recommendation accuracy of the target recommending doctor.

A first aspect of the present invention provides a doctor recommendation method, the method comprising:

acquiring disease information input by a patient, and analyzing the disease information to obtain a plurality of disease characteristic attributes, wherein the disease information comprises the position coordinates of the starting point of the patient and basic information;

inputting the plurality of disease characteristic attributes into a pre-trained department recognition model for recognition to obtain a clinic, and determining the disease grade of the patient according to the plurality of disease characteristic attributes;

acquiring at least one recommended doctor according to the starting point position coordinates of the patient, the clinic and the disease level;

determining a quality label of the patient according to the basic information of the patient;

and determining to obtain a target recommended doctor according to the plurality of disease characteristic attributes of the patient, the disease grade, the quality label and the doctor portrait of the at least one recommended doctor.

Optionally, the obtaining at least one recommended doctor according to the coordinates of the origin point of the patient, the clinic and the disease level includes:

acquiring at least one recommended hospital according to the position coordinates of the starting point of the patient and the disease grade;

and acquiring at least one recommended doctor in the at least one recommended hospital according to the clinic and the disease grade.

Optionally, the method further includes:

acquiring first doctor information and second doctor information of each recommended doctor from a plurality of preset data sources;

extracting a plurality of first key fields in the first doctor information and extracting a plurality of second key fields in the second doctor information;

performing label conversion on the plurality of first key fields to obtain a label set of each recommended doctor, and inputting the plurality of second key fields into a recommendation score model to identify to obtain a recommendation score of each recommended doctor;

and merging the label set of each recommended doctor and the corresponding recommendation score to obtain the doctor portrait of each recommended doctor.

Optionally, the determining the quality label of the patient according to the basic information of the patient includes:

extracting multi-dimensional target features from the basic information of the patient, and classifying the multi-dimensional target features according to a preset classification model to obtain a quality label of the patient.

Optionally, the determining a target recommended doctor according to the plurality of disease characteristic attributes of the patient, the disease grade, the quality label and the doctor profile of the at least one recommended doctor includes:

constructing a decision tree according to a plurality of disease characteristic attributes of the patient, the disease grade, the quality label and the doctor portrait of the at least one recommended doctor, wherein each layer of the decision tree comprises attribute nodes and rule nodes corresponding to the attribute nodes;

positioning to a target attribute node corresponding to the attribute of the patient in the decision tree to obtain a first target rule node corresponding to the target attribute node of a target layer;

if the first target rule node of the target layer is a subtree, continuing positioning according to the attribute node of the next layer of the subtree to obtain a second target rule node corresponding to the attribute node of the next layer until the target rule node is determined to be a leaf node, and determining that the recommended doctor of the target rule node is a target recommended doctor;

and if the first target rule node of the target layer is a leaf node, determining that the recommended doctor of the first target rule node is a target recommended doctor.

Optionally, the constructing a decision tree according to the plurality of disease feature attributes of the patient, the disease grade, the quality label and the doctor profile of the at least one recommended doctor comprises:

determining attribute nodes from a plurality of disease characteristic attributes of the patient, the disease grade, and the quality label;

traversing all the attribute nodes and doctor figures of at least one recommended doctor of all the recommended doctors to obtain at least one recommended doctor of all the recommended doctors corresponding to each attribute node as a rule node;

taking the attribute with the maximum weight as a root node in the attribute nodes;

if the rule node comprises a recommended doctor, determining the rule node as a leaf node;

determining the rule node as a sub-tree if the rule node includes at least two recommended doctors;

and selecting the attribute with the maximum weight except the upper layer as the attribute node of the next layer of the subtree.

Optionally, after obtaining the target recommending doctor, the method further includes:

when an appointment result returned by the patient is received, generating an appointment record based on the appointment result, and monitoring whether the visit time of each stage of the patient exceeds the corresponding appointment visit time in the appointment record;

calculating a time difference between the visit time of each stage of the patient and the corresponding appointment visit time in the appointment record;

judging whether the time difference is larger than a preset time difference threshold value of the corresponding treatment stage;

when the time difference is greater than or equal to a preset time difference threshold of the corresponding treatment stage, obtaining treatment information of the treatment stage corresponding to the time difference, and judging whether abnormal information occurs in the treatment stage based on the treatment information;

and when abnormal information occurs in the visit information, triggering a claim settlement instruction based on the abnormal information.

A second aspect of the present invention provides a doctor recommendation apparatus, the apparatus comprising:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring disease information input by a patient and analyzing the disease information to obtain a plurality of disease characteristic attributes, and the disease information comprises the position coordinates of the starting point of the patient and basic information;

the identification module is used for inputting the plurality of disease characteristic attributes into a pre-trained department identification model for identification to obtain a clinic, and determining the disease grade of the patient according to the plurality of disease characteristic attributes;

the second acquisition module is used for acquiring at least one recommended doctor according to the position coordinates of the starting point of the patient, the clinic and the disease level;

a first determination module for determining a quality label of the patient based on the patient's basic information;

and the second determination module is used for determining and obtaining a target recommended doctor according to the plurality of disease characteristic attributes of the patient, the disease grade, the quality label and the doctor portrait of the at least one recommended doctor.

A third aspect of the invention provides an electronic device comprising a processor and a memory, the processor being adapted to implement the doctor recommendation method when executing a computer program stored in the memory.

A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the doctor recommendation method.

In summary, according to the doctor recommendation method, the doctor recommendation device, the terminal electronic device and the storage medium of the present invention, on one hand, a target recommended doctor is determined and obtained according to a plurality of disease characteristic attributes, disease levels, quality labels of the patient and the doctor profile of the at least one recommended doctor, so that a single target recommended doctor is directly obtained according to a plurality of disease characteristic attributes of the patient, recommendation of the target recommended doctor is avoided from a plurality of dimensions while considering, and matching degree between the doctor and the patient and recommendation accuracy of the target recommended doctor are improved; on the other hand, at least one recommended hospital is obtained according to the coordinates of the starting point of the patient and the disease level, at least one recommended doctor is obtained from the at least one recommended hospital, the accuracy of obtaining the recommended doctor is improved by determining the at least one recommended doctor for multiple times, and finally, whether a claim settlement instruction is triggered is determined by monitoring the treatment time of each treatment stage, so that the phenomenon that the patient is unsatisfied with medical accidents caused by abnormal information in the treatment process is avoided, and the safety and the satisfaction degree of the patient in the treatment process are improved.

Drawings

Fig. 1 is a flowchart of a doctor recommendation method according to an embodiment of the present invention.

Fig. 2 is a structural diagram of a doctor recommendation apparatus according to a second embodiment of the present invention.

Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.

Detailed Description

In order that the above objects, features and advantages of the present invention can be more clearly understood, a detailed description of the present invention will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

Example one

In this embodiment, the doctor recommendation method may be applied to an electronic device, and for an electronic device that needs to make doctor recommendation, the function recommended by the doctor provided by the method of the present invention may be directly integrated on the electronic device, or may be run in the electronic device in the form of a Software Development Kit (SKD).

As shown in FIG. 1, the physician recommendation method specifically includes the following steps, and the order of the steps in the flowchart can be changed and some steps can be omitted according to different requirements.

S11, acquiring disease information input by a patient, and analyzing the disease information to obtain a plurality of disease characteristic attributes, wherein the disease information comprises the position coordinates of the starting point of the patient and basic information.

In this embodiment, the disease information input by the patient is acquired by receiving a doctor recommendation request of the patient, specifically, the doctor recommendation request is sent to the server by the electronic device, and is used to request a doctor recommendation for the disease information input by the patient, specifically, the doctor recommendation request is sent to the server by the electronic device before the patient visits, for example, the doctor recommendation platform in the hospital medical system can be logged in to a medical institution by the electronic device, and the doctor recommendation request is sent to the medical system server in the doctor recommendation platform, where the doctor recommendation request includes the disease information input by the patient.

It is emphasized that the patient-entered disease information may also be stored in a node of a blockchain in order to further ensure privacy and security of the patient-entered disease information.

In this embodiment, the disease information input by the patient is obtained by analyzing the doctor recommendation request, where the disease information includes, but is not limited to, historical disease information of the patient, current disease information, coordinates of an origin point of the patient, and basic information, and the disease information is analyzed to obtain a plurality of disease characteristic attributes.

And S12, inputting the plurality of disease characteristic attributes into a pre-trained department recognition model for recognition to obtain a clinic, and determining the disease grade of the patient according to the plurality of disease characteristic attributes.

In this embodiment, the department identification model is trained in advance, and after the plurality of disease characteristic attributes of the patient are obtained, the plurality of disease characteristic attributes of the patient are input to the pre-trained department identification model for training, so as to identify the treatment department corresponding to the patient.

Specifically, the training process of the department identification model comprises the following steps:

21) acquiring a plurality of departments and historical disease characteristic attributes corresponding to each department as a sample data set;

22) dividing a training set and a testing set from the sample data set;

23) inputting the training set into a preset neural network for training to obtain a department recognition model;

24) inputting the test set into the department identification model for testing, and calculating a test passing rate;

25) if the test passing rate is larger than a preset passing rate threshold value, determining that the department recognition model is finished training; and if the test passing rate is smaller than the preset passing rate threshold value, increasing the number of training sets, and re-training the department recognition model.

In this embodiment, training is performed according to different historical disease characteristic attributes corresponding to different departments to obtain a department recognition model, the multiple disease characteristic attributes of the patient are input into a pre-trained department recognition model to be recognized to obtain a corresponding visiting department, and in a subsequent training process, the disease characteristic attribute of each patient is used as new data to increase the number of the data sets, the department recognition model is retrained based on the new data sets, and the department recognition model is continuously updated, so that the recognition rate is continuously improved.

In this embodiment, the disease level may be set by the medical institution according to advice after the doctor is experienced, or may be obtained by the medical institution through machine learning according to the historical visit information of the patient and the treatment information of the doctor, and different disease levels are set for different diseases, for example, the disease level set for diarrhea is: diarrhea is more than 7 times per day, and severe diarrhea; diarrhea 3 to 7 times a day, generally; diarrhea is less than 3 times a day, and slight diarrhea is caused; the disease grade set for fever was: body temperature above 38.5 degrees, severe; body temperature is less than 38.5 degrees, normal.

Optionally, the determining the disease grade of the patient according to the plurality of disease characteristic attributes comprises:

extracting a plurality of preset target disease characteristic attributes from the plurality of disease characteristic attributes;

and determining the disease grade of the patient according to the preset multiple target disease characteristic attributes.

Illustratively, the plurality of disease characteristic attributes includes a target disease characteristic: diarrhea, 4 times per day, the patient is determined to be normal in disease grade.

In this embodiment, by setting different disease levels according to different diseases, diversity of disease level settings is improved, and by extracting a plurality of target disease characteristic attributes preset in a plurality of disease characteristic attributes to determine the disease level of the patient, efficiency of determining the disease level of the patient is improved.

S13, acquiring at least one recommended doctor according to the position coordinates of the origin point of the patient, the clinic and the disease level.

In this embodiment, the at least one recommended doctor is determined and obtained from a plurality of dimensional data according to the coordinates of the starting point of the patient, the clinic and the disease level, so that the accuracy of recommendation is improved.

Optionally, the obtaining at least one recommended doctor according to the coordinates of the origin point of the patient, the clinic and the disease level comprises:

In the embodiment, at least one recommended hospital is acquired according to the coordinates of the starting point of the patient and the disease grade, if the disease grade of the patient is serious, the hospital three closest to the coordinates of the starting point of the patient is recommended, and doctors of the level higher than that of the principal doctor are recommended in the hospital three according to the treatment department and the disease grade of the patient, so that the patient can be ensured to see the treatment in time, and the accuracy of recommendation of the doctors is improved.

In this embodiment, at least one recommended hospital is obtained according to the coordinates of the starting point of the patient and the disease level, at least one recommended doctor is obtained in the at least one recommended hospital, and the at least one recommended doctor is obtained through multiple determinations, so that the accuracy of obtaining the recommended doctor is improved.

S14, determining the quality label of the patient according to the basic information of the patient.

In this embodiment, the basic information includes the age, sex, credit card consumption habit, grade of a historical doctor, a deposit, and the like of the patient, and the quality label of the patient is determined based on the basic information.

Optionally, the determining the quality label of the patient according to the basic information of the patient comprises:

In this embodiment, the target features refer to the age, sex, credit card consumption habit, grade of a historical doctor, and a diagnosis price of the patient in the basic information, and the target features are classified according to a clustering algorithm to obtain a quality label of the patient, specifically, the quality label may include: high quality, medium quality and low quality.

Illustratively, the physician's history for a patient visit: if the grades of the patients' historical visitors are all experts, determining the quality label of the patient as follows: the quality is high; if the grade of the patient historical doctor is the master doctor within the preset range, determining that the quality label of the patient is as follows: medium quality; if the grades of the patients' historical visitors are all general doctors, determining that the quality label of the patient is as follows: the quality is low. Aiming at the credit card consumption habit of the patient, if the credit card consumption of the patient exceeds the preset high-quality consumption amount every month, determining that the quality label of the patient is as follows: the quality is high; if the credit card consumption amount of the patient in each month is lower than the preset low-quality consumption amount, determining that the quality label of the patient is as follows: and if the credit card consumption amount of each month of the patient is smaller than the preset high-quality consumption amount and larger than the preset low-quality consumption amount, determining that the quality label of the patient is as follows: medium quality.

And S15, determining and obtaining a target recommended doctor according to the plurality of disease characteristic attributes of the patient, the disease grade, the quality label and the doctor portrait of the at least one recommended doctor.

In this embodiment, in the process of determining to obtain a target recommended doctor, an image needs to be created for each recommended doctor according to doctor information of each recommended doctor, and specifically, the method further includes:

and S151, collecting first doctor information and second doctor information of each recommended doctor from a plurality of preset data sources.

S152, a plurality of first key fields in the first doctor information are extracted, and a plurality of second key fields in the second doctor information are extracted.

In this embodiment, the first doctor information refers to basic information of each recommended doctor, and specifically includes: age, gender, areas of good expertise, disease diagnosis information, etc., extracting a plurality of first key fields from the basic information, and performing label conversion on the first key fields according to a preset label conversion strategy, for example: the preset label conversion strategy specifically comprises the following steps: an age transformation strategy is used to transform the actual age into an age label, which is an infant if the patient is less than 3 years old; patients are 4 to 18 years of age, labeled adolescents; the patient is 18-40 years old and labeled youth; patients are 40-55 years old, labeled middle age; patients were over 55 years old and the label was old.

The second doctor information refers to review information of each recommended doctor, a second key field is extracted from the review information, specifically, the second key field comprises scores of multiple visits and recommendation score rules corresponding to the scores of the visits, and the scores of the multiple visits and the recommendation score rules corresponding to the scores of the multiple visits of each recommended doctor are input into a pre-trained recommendation score model to be identified so as to obtain the recommendation score of each recommended doctor.

S153, performing label conversion on the plurality of first key fields to obtain a label set of each recommended doctor, and inputting the plurality of second key fields into a recommendation score model to identify to obtain a recommendation score of each recommended doctor.

In this embodiment, the recommendation score model is trained in advance, a plurality of visit scores of a plurality of recommended doctors and a recommendation score rule corresponding to each visit score are acquired as a sample data set for training, the training process is the same as the training process of the department identification model, and details are not described here. In this embodiment, different recommendation score rules are set according to the multiple visit scores of each recommended doctor, for example: the multiple visit scores of doctor a include: scoring the treatment effect and scoring the treatment attitude, wherein the recommended scoring rule set for the treatment effect is as follows: the treatment effect score is more than or equal to 9.0 points, and the corresponding recommendation score is as follows: 9.5 min; the score of the treatment effect is more than 9.0 and less than or equal to 8.0, and the corresponding recommended score is as follows: 8.5 min; the treatment effect score is more than 8.0 and less than or equal to 7.0 points, and the corresponding recommendation score is as follows: 7.5 min; the treatment effect score is less than 7.0 points, and the corresponding recommendation score is 5 points; the recommendation scoring rules set for the visit attitude are as follows: the diagnosis attitude score is more than or equal to 8.0 points, and the corresponding recommendation score is as follows: 9.0 min; the visit attitude score is more than 8.0 and less than or equal to 6.0 points, and the corresponding recommendation score is as follows: 7.0 min; the diagnosis attitude score is less than 6.0 points, and the corresponding recommendation score is as follows: and 5 minutes.

And S154, merging the label set of each recommended doctor and the corresponding recommendation score to obtain the doctor portrait of each recommended doctor.

In this embodiment, the doctor portrait of each recommended doctor is obtained by merging the tag set and the recommendation score of each recommended doctor, for example: the chief physician-fever-bronchitis-recommended score was 9.2 points.

In the embodiment, the recommended score of each recommended doctor is obtained by inputting the plurality of second key fields into the recommended score model for identification, so that the accuracy of obtaining the recommended score of each recommended doctor is improved, the label set and the recommended score of each recommended doctor are combined to obtain the doctor portrait of each recommended doctor, the doctor portrait of each recommended doctor is obtained from different dimensions, and the integrity of the created doctor portrait is improved.

Optionally, the determining a target recommended doctor according to the plurality of disease characteristic attributes of the patient, the disease grade, the quality label and the doctor profile of the at least one recommended doctor comprises:

In this embodiment, the attribute node is an attribute node corresponding to a plurality of attributes obtained by combining a plurality of disease characteristic attributes, disease levels, and quality labels of the patient.

Further, the constructing a decision tree from the plurality of disease characteristic attributes of the patient, the disease rating, the quality label, and the doctor profile of the at least one referring doctor comprises:

traversing all the attribute nodes and doctor figures of the at least one recommended doctor to obtain at least one recommended doctor corresponding to each attribute node as a rule node;

Illustratively, the plurality of disease characteristic attributes corresponding to the patient are: fever-cough, disease grade: severe, quality label: and high quality, determining the attribute node sequence of the patient as follows according to the weight value: fever node-cough node-severe node-high quality node.

Doctor profiles for all recommended doctors: doctor portrait of doctor A: chief and ren physicians-fever-bronchitis-recommendation score 9.2 points; doctor image of doctor B: expert-fever-cough-pneumonia-recommended score of 9.5 points; doctor portrait of doctor C: chief physician-fever-lung infection-recommendation score 9.2; doctor image of doctor: chief physician-lung infection-recommended score 8.9; doctor portrait of doctor E: expert-fever-cough-pneumonia recommended score of 9.6 points; doctor portrait of doctor F: the chief and ren physician-fever-cough-pneumonia recommended score was 9.6.

Traversing all the attribute nodes and the doctor figures of all the recommended doctors to obtain the rule nodes corresponding to each attribute node of the patient as follows: the rule nodes corresponding to the fever nodes are as follows: doctor A, doctor B, doctor C, doctor E and doctor F; the rule nodes corresponding to the cough nodes are: doctor B, doctor E and doctor F; the rule nodes corresponding to the serious nodes are as follows: doctors B and E; the regular nodes corresponding to the high-quality nodes are as follows: and E, doctors.

Inputting the fever, cough, severity and high quality of the patient into a system as attributes of the patient, according to a decision tree and attributes of the patient: the method comprises the steps of fever, positioning to attribute node fever nodes of a first layer of a decision tree, matching the fever nodes to obtain doctors A, doctors B, doctors C, doctors E and doctors F, determining that the doctors A, the doctors B, the doctors C, the doctors E and the doctors F are subtrees, continuing to position to attribute node cough nodes of a second layer of the decision tree below the doctors A, the doctors B, the doctors C, the doctors E and the doctors F, matching the cough nodes to obtain doctors B, the doctors E and the doctors F, determining that the doctors B, the doctors E and the doctors F are subtrees, continuing to position to attribute node serious nodes of a third layer of the decision tree below the doctors B, the doctors E and the doctors F, matching the serious nodes to the doctors B and the doctors E, determining that the doctors B and the doctors E are subtrees, continuing to position to attribute node high-quality nodes of a fourth layer of the decision tree below the doctors B and the doctors E, matching the high-quality nodes with E doctors, determining that the E doctors are leaf nodes, and determining the E doctors as target recommended doctors.

In the embodiment, a decision tree algorithm is adopted for the disease characteristic attributes, the disease grades, the quality labels of the patient and the doctor portrait of the at least one recommending doctor, the disease characteristic attributes, the disease grades and the quality labels of the patient are matched layer by layer in the decision tree to determine the target recommending doctor, the target recommending doctor is prevented from being directly obtained according to the disease characteristic attributes of the patient singly, the target recommending doctor is considered from multiple dimensions at the same time, and the recommending accuracy of the target recommending doctor is improved.

Further, after obtaining the target recommended doctor, the method further comprises:

acquiring the visit information of the target recommended doctor;

and generating reservation information of the patient according to the plurality of disease characteristic attributes and disease grades of the patient and the visit information of the target recommending doctor.

In this embodiment, when the reservation information is generated, the server sends the reservation information to the patient, and the patient determines whether to visit according to the reservation information, specifically, the reservation information includes examination items, examination notice items, time of visiting and the like for each visiting stage.

Illustratively, when a target recommending doctor is matched, the visit time is determined according to the visit information of the target recommending doctor, and then the examination items possibly needed to be done, such as stomachache, are judged according to a plurality of disease characteristic attributes and disease grades of the patient, and if the patient possibly needs to have gastroscopy on an empty stomach, the number of 8 am is recommended; the foot pain does not need fasting examination, but the walking is inconvenient, and the number of 2 pm is recommended to be hung to avoid the peak period of going to work and getting out of work; recommending to hang the earliest number if the disease grade of the patient is serious; if the patient's disease level is general and a fasting check is not required, then a relative idle period number (e.g., 2 to 3 pm) is recommended; if the patient only reviews the results or takes the medicine, the time period that the doctor is hung to be on duty soon is recommended, the patient only needs to go to the hospital for seeing the results 1 hour in advance, the patient is assisted to schedule time reasonably for seeing a doctor, the seeing-doctor efficiency and the seeing-doctor satisfaction of the patient are improved, and meanwhile the seeing-doctor efficiency of the doctor is improved.

Further, after obtaining the target recommending doctor, the method further comprises:

In this embodiment, when an appointment result returned by the patient is received, it is determined that the patient receives the recommended appointment information, an appointment record is generated according to the appointment result, the appointment record is stored in a to-be-monitored visit queue, when it is monitored that the appointment record is triggered, a time difference between a visit time of the patient in each visit stage and a scheduled visit time of the corresponding visit stage in the appointment record is monitored, and when the time difference of each stage is greater than or equal to a preset time difference threshold of the corresponding visit stage, whether abnormal information occurs in the visit stage is determined, specifically, the visit information in the visit stage is obtained, whether abnormal information exists in the visit information is identified, specifically, the abnormal information may be generated in the visit stage by the target recommending doctor, or the system can be caused by the fault of equipment of a medical structure during the visit of a patient, and after abnormal information occurs, a claim settlement instruction is triggered according to the abnormal information.

In this embodiment, the claim settlement instruction refers to an overtime claim settlement performed when abnormal information occurs, and different claim settlement rules are set according to an overtime condition, and specifically, the claim settlement rules may be set according to historical attendance data, the number of people in the current day of the hospital, and the number of people on duty in the current day of the hospital.

Illustratively, if the patient is 1 hour later than the predetermined time in the in-line examination period of the visit, the reimbursement instruction is triggered to execute the reimbursement, for example, the patient may be paid for an appropriate amount of money for 1 hour or given items such as health management bags (thermometer, mask, alcohol, cotton swab) and the like.

Further, the method further comprises:

and when the time difference is smaller than the preset time difference threshold value, determining the treatment time of the patient as the normal treatment time.

In the embodiment, the treatment time of each treatment stage is recorded in the reservation record, so that the patient is assisted to schedule time in advance, treatment is planned, the treatment efficiency of the patient is improved, the treatment time of each treatment stage is monitored, whether a claim settlement instruction is triggered or not is determined according to the treatment time of each treatment stage, the phenomenon that the patient is dissatisfied with a medical accident due to abnormal information in the treatment process is avoided, and the safety and the satisfaction degree of the patient in the treatment process are improved.

In summary, in the method recommended by the doctor in this embodiment, a plurality of disease characteristic attributes are obtained by acquiring disease information input by a patient and analyzing the disease information, where the disease information includes a starting point position coordinate and basic information of the patient; inputting the plurality of disease characteristic attributes into a pre-trained department recognition model for recognition to obtain a clinic, and determining the disease grade of the patient according to the plurality of disease characteristic attributes; acquiring at least one recommended doctor according to the starting point position coordinates of the patient, the clinic and the disease level; determining a quality label of the patient according to the basic information of the patient; and determining to obtain a target recommended doctor according to the plurality of disease characteristic attributes of the patient, the disease grade, the quality label and the doctor portrait of the at least one recommended doctor.

In this embodiment, on one hand, a target recommending doctor is determined and obtained according to the multiple disease characteristic attributes, the disease grades, the quality labels of the patient and the doctor portrait of the at least one recommending doctor, so that the situation that the target recommending doctor is directly obtained according to the multiple disease characteristic attributes of the patient is avoided, recommendation of the target recommending doctor is considered from multiple dimensions at the same time, and the matching degree between the doctor and the patient and the recommendation accuracy of the target recommending doctor are improved; on the other hand, at least one recommended hospital is obtained according to the coordinates of the starting point of the patient and the disease level, at least one recommended doctor is obtained in the at least one recommended hospital, the at least one recommended doctor is obtained through multiple determinations, and the accuracy of obtaining the recommended doctor is improved; and finally, the department of treatment is obtained by continuously updating the department recognition model, so that the recognition accuracy of the department of treatment is improved.

In addition, the treatment time of each treatment stage is recorded in the reservation record, the patient is assisted to schedule time in advance, treatment is planned, the treatment efficiency of the patient is improved, the treatment time of each treatment stage is monitored, whether a claim settlement instruction is triggered or not is determined according to the treatment time of each treatment stage, the phenomenon that the patient is dissatisfied to generate medical accidents due to abnormal information in the treatment process of the patient is avoided, and the safety and the satisfaction degree of the patient in the treatment process are improved.

Example two

In some embodiments, the physician recommendation apparatus 20 may comprise a plurality of functional modules comprising program code segments. The program code of the various program segments in the physician recommendation apparatus 20 may be stored in the memory of the electronic device and executed by the at least one processor to perform the functions recommended by the physician (described in detail in fig. 1).

In this embodiment, the doctor recommendation device 20 may be divided into a plurality of functional modules according to the functions performed by the doctor recommendation device. The functional module may include: a first obtaining module 201, a recognition module 202, a second obtaining module 203, a first determining module 204, a second determining module 205, an acquisition module 206, an extraction module 207, and a merging module 208. The module referred to herein is a series of computer program segments capable of being executed by at least one processor and capable of performing a fixed function and is stored in memory. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.

The first obtaining module 201 is configured to obtain disease information input by a patient, and analyze the disease information to obtain a plurality of disease characteristic attributes, where the disease information includes a start point position coordinate and basic information of the patient.

The identification module 202 is configured to input the multiple disease characteristic attributes into a pre-trained department identification model for identification to obtain a clinic, and determine a disease grade of the patient according to the multiple disease characteristic attributes.

22) dividing a training set and a testing set from the sample data set;

Optionally, the determining, by the identification module 202, the disease grade of the patient according to the plurality of disease characteristic attributes includes:

A second obtaining module 203, configured to obtain at least one recommended doctor according to the coordinates of the origin point of the patient, the clinic and the disease level.

Optionally, the obtaining at least one recommended doctor by the second obtaining module 203 according to the coordinates of the origin position of the patient, the clinic and the disease level includes:

A first determining module 204, configured to determine a quality label of the patient according to the basic information of the patient.

Optionally, the determining, by the first determining module 204, the quality label of the patient according to the basic information of the patient includes:

A second determining module 205, configured to determine a target recommended doctor according to the plurality of disease characteristic attributes of the patient, the disease grade, the quality label, and the doctor profile of the at least one recommended doctor.

In this embodiment, in the process of determining to obtain the target recommended doctor, an image needs to be created for each recommended doctor according to the doctor information of each recommended doctor:

the collecting module 206 is configured to collect the first doctor information and the second doctor information of each recommended doctor from a plurality of preset data sources.

The extracting module 207 is configured to extract a plurality of first key fields in the first doctor information and a plurality of second key fields in the second doctor information.

The identification module 202 is configured to perform label conversion on the plurality of first key fields to obtain a label set of each recommended doctor, and input the plurality of second key fields to a recommendation score model to perform identification to obtain a recommendation score of each recommended doctor.

And the merging module 208 is configured to merge the tag set of each recommended doctor and the corresponding recommendation score to obtain a doctor image of each recommended doctor.

Optionally, the determining, by the second determining module 205, a target recommended doctor according to the plurality of disease characteristic attributes of the patient, the disease grade, the quality label, and the doctor profile of the at least one recommended doctor includes:

Further, after a target recommended doctor is obtained, the visit information of the target recommended doctor is obtained; and generating reservation information of the patient according to the plurality of disease characteristic attributes and disease grades of the patient and the visit information of the target recommending doctor.

Further, after the target recommended doctor is obtained, when an appointment result returned by the patient is received, an appointment record is generated based on the appointment result, and whether the visit time of each stage of the patient exceeds the corresponding appointment visit time in the appointment record is monitored; calculating a time difference between the visit time of each stage of the patient and the corresponding appointment visit time in the appointment record; judging whether the time difference is larger than a preset time difference threshold value of the corresponding treatment stage; when the time difference is greater than or equal to a preset time difference threshold of the corresponding treatment stage, obtaining treatment information of the treatment stage corresponding to the time difference, and judging whether abnormal information occurs in the treatment stage based on the treatment information; and when abnormal information occurs in the visit information, triggering a claim settlement instruction based on the abnormal information.

Further, when the time difference value is smaller than the preset time difference value threshold value, the time of the patient is determined as the normal time.

In summary, the apparatus recommended by the doctor in this embodiment obtains a plurality of disease characteristic attributes by obtaining disease information input by a patient and analyzing the disease information, where the disease information includes a starting point position coordinate and basic information of the patient; inputting the plurality of disease characteristic attributes into a pre-trained department recognition model for recognition to obtain a clinic, and determining the disease grade of the patient according to the plurality of disease characteristic attributes; acquiring at least one recommended doctor according to the starting point position coordinates of the patient, the clinic and the disease level; determining a quality label of the patient according to the basic information of the patient; and determining to obtain a target recommended doctor according to the plurality of disease characteristic attributes of the patient, the disease grade, the quality label and the doctor portrait of the at least one recommended doctor.

EXAMPLE III

Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. In the preferred embodiment of the present invention, the electronic device 3 comprises a memory 31, at least one processor 32, at least one communication bus 33 and a transceiver 34.

It will be appreciated by those skilled in the art that the configuration of the electronic device shown in fig. 3 does not constitute a limitation of the embodiment of the present invention, and may be a bus-type configuration or a star-type configuration, and the electronic device 3 may include more or less other hardware or software than those shown, or a different arrangement of components.

In some embodiments, the electronic device 3 is an electronic device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and the hardware thereof includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The electronic device 3 may also include a client device, which includes, but is not limited to, any electronic product that can interact with a client through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a digital camera, and the like.

It should be noted that the electronic device 3 is only an example, and other existing or future electronic products, such as those that can be adapted to the present invention, should also be included in the scope of the present invention, and are included herein by reference.

In some embodiments, the memory 31 is used for storing program codes and various data, such as the doctor recommending apparatus 20 installed in the electronic device 3, and realizes high-speed and automatic access to programs or data during the operation of the electronic device 3. The Memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable rewritable Read-Only Memory (Electrically-Erasable Programmable Read-Only Memory (EEPROM)), an optical Read-Only disk (CD-ROM) or other optical disk Memory, a magnetic disk Memory, a tape Memory, or any other medium readable by a computer capable of carrying or storing data.

In some embodiments, the at least one processor 32 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The at least one processor 32 is a Control Unit (Control Unit) of the electronic device 3, connects various components of the electronic device 3 by using various interfaces and lines, and executes various functions and processes data of the electronic device 3 by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31.

In some embodiments, the at least one communication bus 33 is arranged to enable connection communication between the memory 31 and the at least one processor 32 or the like.

Although not shown, the electronic device 3 may further include a power supply (such as a battery) for supplying power to each component, and optionally, the power supply may be logically connected to the at least one processor 32 through a power management device, so as to implement functions of managing charging, discharging, and power consumption through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 3 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, an electronic device, or a network device) or a processor (processor) to execute parts of the methods according to the embodiments of the present invention.

In a further embodiment, in conjunction with fig. 2, the at least one processor 32 may execute operating means of the electronic device 3 and various installed applications (e.g., the doctor recommendation apparatus 20), program code, etc., such as the various modules described above.

The memory 31 has program code stored therein, and the at least one processor 32 can call the program code stored in the memory 31 to perform related functions. For example, the modules illustrated in fig. 2 are program codes stored in the memory 31 and executed by the at least one processor 32, so as to realize the functions of the modules for the purpose of recommendation of doctors.

In one embodiment of the present invention, the memory 31 stores a plurality of instructions that are executed by the at least one processor 32 to implement the functions recommended by the physician.

Specifically, the at least one processor 32 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, and details are not repeated here.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

Further, the computer-readable storage medium may be non-volatile or volatile.

Further, the computer-readable storage medium mainly includes a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.

The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or that the singular does not exclude the plural. A plurality of units or means recited in the present invention may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method of physician recommendation, the method comprising:

2. The doctor recommendation method of claim 1, wherein said obtaining at least one recommended doctor based on the originating point location coordinates of the patient, the visiting department and the disease level comprises:

3. The physician recommendation method of claim 1 further comprising:

4. The physician recommendation method of claim 1 wherein said determining a quality label for said patient based on said patient's basic information comprises:

5. The doctor recommendation method of claim 1, wherein said determining a target referring doctor based on a plurality of disease characteristic attributes of said patient, said disease rating, said quality label and a doctor profile of said at least one referring doctor comprises:

6. The physician recommendation method of claim 5 wherein said constructing a decision tree based on a plurality of disease characteristic attributes of said patient, said disease grade, said quality label and a physician representation of said at least one recommending physician comprises:

7. The physician recommendation method of claim 1, wherein after obtaining the target referring physician, the method further comprises:

8. A physician recommendation apparatus, the apparatus comprising:

9. An electronic device, characterized in that the electronic device comprises a processor and a memory, the processor being configured to implement the physician recommendation method of any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a doctor recommendation method according to any one of claims 1 to 7.