CN112614578B - Doctor intelligent recommendation method and device, electronic equipment and storage medium - Google Patents
Doctor intelligent recommendation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112614578B CN112614578B CN202011600037.XA CN202011600037A CN112614578B CN 112614578 B CN112614578 B CN 112614578B CN 202011600037 A CN202011600037 A CN 202011600037A CN 112614578 B CN112614578 B CN 112614578B
- Authority
- CN
- China
- Prior art keywords
- doctor
- recommended
- patient
- model
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012549 training Methods 0.000 claims description 32
- 230000006870 function Effects 0.000 claims description 28
- 238000012360 testing method Methods 0.000 claims description 24
- 201000010099 disease Diseases 0.000 claims description 23
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 23
- 238000006243 chemical reaction Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000009193 crawling Effects 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Pathology (AREA)
- Educational Administration (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of digital medical treatment, and provides an intelligent doctor recommendation method, an intelligent doctor recommendation device, electronic equipment and a storage medium, wherein the intelligent doctor recommendation method comprises the following steps: extracting a plurality of original data in the historical visit information of the patient, and inputting the original data into a score recognition model to obtain a recommended score of each historical visit doctor; performing regression fit on the plurality of recommendation scores of the plurality of historical doctor visits and the plurality of key fields of the plurality of historical doctor visits; creating a first doctor model of the initial recommended doctor; acquiring a second doctor model of at least one recommended doctor in a doctor index table; a target recommended doctor of the patient is determined by calculating a similarity between the first doctor model and a second doctor model of the at least one recommended doctor. According to the invention, the initial recommended doctor of the patient is created, and is obtained by taking the initial recommended doctor into consideration based on the dimension of the patient, so that the matching degree between the recommended doctor and the doctor required by the patient is improved.
Description
Technical Field
The invention relates to the technical field of digital medical treatment, in particular to an intelligent doctor recommendation method and device, electronic equipment and a storage medium.
Background
With the increase of medical institutions and the refinement of each department, patients are difficult to reserve to satisfactory doctors according to own disease conditions, most of intelligent doctor recommendation systems are currently aimed at doctors, and intelligent recommendation is performed for the patients by comprehensively collecting the attributes of the doctor, such as a sitting hospital, a job title, a department and the like. The degree of matching between doctors recommended by the traditional recommendation system and doctors required by patients is low, so that the recommendation result is inaccurate.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a method, an apparatus, an electronic device, and a storage medium for intelligent recommendation of a doctor, which improve the matching degree between a recommended doctor and a doctor required by a patient by creating an initial recommended doctor of the patient based on the dimension of the patient.
The first aspect of the invention provides an intelligent recommendation method for doctors, which comprises the following steps:
collecting historical treatment information of a patient from a plurality of preset data sources;
extracting a plurality of original data in the historical visit information, and inputting the plurality of original data into a score recognition model to obtain a recommended score of each historical visit doctor, wherein the plurality of original data comprises a plurality of key fields of the plurality of historical visit doctors and the recommended score of each key field;
Performing regression fitting on the plurality of recommended scores of the plurality of historical doctor visits and the plurality of key fields of the plurality of historical doctor visits to obtain the weight of each key field;
creating a first doctor model of an initial recommended doctor of the patient according to a plurality of key fields of the plurality of historical doctor visits and the weight of each key field;
acquiring a second doctor model of at least one recommended doctor in a doctor index table according to the historical doctor information of the patient;
and calculating the similarity between the first doctor model and the second doctor model of the at least one recommended doctor, and determining the target recommended doctor of the patient according to the calculated similarity.
Optionally, performing regression fit on the plurality of recommendation scores of the plurality of historical doctor and the plurality of key fields of the plurality of historical doctor to obtain the weight of each key field includes:
performing regression fitting on the plurality of recommended scores of the plurality of historical doctor visits and the plurality of key fields of the plurality of historical doctor visits to obtain a plurality of preset fitting functions;
and calculating the weight of each key field according to the plurality of preset fitting functions.
Optionally, the creating the first doctor model of the initial recommended doctor of the patient according to the plurality of key fields of the plurality of historical doctor visits and the weight corresponding to each key field includes:
selecting the doctor with the highest recommendation score as a first recommendation doctor of the patient;
performing label conversion on a plurality of key fields of the first recommended doctor to obtain a label set of the first recommended doctor, wherein each label in the label set contains a weight;
and sorting the labels in the label set in descending order according to the weight to obtain a first doctor model of the initial recommended doctor of the patient.
Optionally, the training process of the scoring identification model includes:
acquiring a plurality of key fields of a plurality of historical consultants and recommendation scores corresponding to the key fields as a sample data set;
dividing a training set and a testing set from the sample data set;
inputting the training set into a preset neural network for training to obtain a scoring identification model;
inputting the test set into the score identification model for testing, and calculating the test passing rate;
if the test passing rate is larger than a preset passing rate threshold value, determining that the score identification model training is finished; if the test passing rate is smaller than the preset passing rate threshold value, increasing the number of training sets, and training the scoring identification model again.
Optionally, the obtaining the second doctor model of the at least one recommended doctor in the doctor index table according to the historical doctor information of the patient includes:
extracting a plurality of disease information from the patient's historical visit information;
word segmentation processing is carried out on the plurality of disease information to obtain a plurality of disease characteristic attributes;
performing label conversion on the disease characteristic attributes to obtain a label set of the patient;
and searching at least one recommended doctor matched with the tag set in a doctor index table, and associating a second doctor model of the at least one recommended doctor from the doctor index table.
Optionally, the calculating the similarity between the first doctor model and the second doctor model of each recommended doctor includes:
extracting all first labels in the first doctor model, and calculating a first label total number of all the first labels;
extracting all second labels in the second doctor model of each recommended doctor;
searching all target tags matched with all first tags from all second tags, and calculating the total number of second tags of all target tags;
and taking the quotient of the second label total number and the first label total number as the similarity between the first doctor model and the second doctor model of each recommended doctor.
Optionally, the determining the target recommended doctor of the patient according to the calculated similarity includes:
sorting the calculated similarity between the first doctor model and the second doctor model of each recommended doctor in a descending order;
selecting a plurality of second recommended doctors corresponding to the plurality of similarity in the prior order from the descending order sequencing results;
determining a preference of the patient based on the patient's historical visit information;
determining a target recommended doctor of the patient from the plurality of second recommended doctors according to the preference of the patient.
A second aspect of the present invention provides an intelligent recommendation apparatus for a doctor, the apparatus comprising:
the acquisition module is used for acquiring historical treatment information of a patient from a plurality of preset data sources;
the extraction module is used for extracting a plurality of original data in the historical doctor information, and inputting the plurality of original data into the score recognition model to obtain the recommended score of each historical doctor, wherein the plurality of original data comprises a plurality of key fields of a plurality of historical doctors and the recommended score of each key field;
the regression fitting module is used for carrying out regression fitting on a plurality of recommended scores of the plurality of historical doctor visits and a plurality of key fields of the plurality of historical doctor visits to obtain the weight of each key field;
The creation module is used for creating a first doctor model of the initial recommended doctor of the patient according to a plurality of key fields of the plurality of historical doctor visits and the weight of each key field;
the acquisition module is used for acquiring a second doctor model of at least one recommended doctor in a doctor index table according to the historical doctor information of the patient;
and the calculation module is used for calculating the similarity between the first doctor model and the second doctor model of the at least one recommended doctor, and determining the target recommended doctor of the patient according to the calculated similarity.
A third aspect of the present invention provides an electronic device comprising a processor and a memory, the processor being adapted to implement the method of intelligent recommendation by a doctor 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 method of intelligent recommendation of a doctor.
In summary, according to the doctor intelligent recommendation method, device, electronic equipment and storage medium of the present invention, on one hand, a first doctor model of an initial recommended doctor of the patient is created according to a plurality of key fields of the plurality of historical doctor visits and weights corresponding to each key field, and as the initial recommended doctor is obtained by considering based on the dimension of the patient, the matching degree between the recommended doctor and the doctor required by the patient is improved; on the other hand, the similarity between the first doctor model and the second doctor model of each recommended doctor is calculated, the target recommended doctor of the patient is determined according to the calculated similarity, the target recommended doctor of the patient is obtained by simultaneously considering the dimensions of the patient and the doctor, the matching degree between the recommended doctor and the doctor required by the patient is improved, and the accuracy of the target recommended doctor is further improved; and finally, carrying out regression fitting on a plurality of recommended scores of the plurality of historical doctor visits and the plurality of key fields to obtain the weight corresponding to each key field, wherein the plurality of key fields are set according to the needs of the patient, and the matching degree between the recommended doctor and the doctor of the patient needs can be improved by calculating the weight corresponding to each key field.
Drawings
Fig. 1 is a flowchart of a doctor intelligent recommendation method according to an embodiment of the present invention.
Fig. 2 is a block diagram of acquiring a plurality of recommendation scores and a plurality of key fields for a plurality of historic medical practitioners according to an embodiment of the invention.
Fig. 3 is a block diagram of an intelligent doctor recommendation device according to a second embodiment of the present invention.
Fig. 4 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
The invention will be further described in the following detailed description in conjunction with the above-described figures.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. It should be noted that, without conflict, the embodiments of the present invention and features in the embodiments may be combined with each other.
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 herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Example 1
Fig. 1 is a flowchart of a doctor intelligent recommendation method according to an embodiment of the present invention.
In this embodiment, the doctor intelligent recommendation method may be applied to an electronic device, and for an electronic device that needs to perform doctor intelligent recommendation, the doctor intelligent recommendation function 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 (Software Development Kit, SKD).
As shown in fig. 1, the method for intelligent recommendation of doctors specifically includes the following steps, the order of the steps in the flowchart may be changed according to different needs, and some may be omitted.
S11, collecting historical treatment information of the patient from a plurality of preset data sources.
In this embodiment, a plurality of data sources may be preset, where the data sources may be a plurality of diagnosis platforms associated with the historical diagnosis information of each patient, and the historical diagnosis information of each patient is crawled from each preset data source, or the historical diagnosis information reported by the preset plurality of data sources is received, and specifically, the historical diagnosis information includes: patient historical disease information and doctor information for a historical doctor.
In other embodiments, the historical doctor information may be a text file, a video file, or a voice file, and if the historical doctor information is a video file, voice information may be collected from the video file, and the voice information is converted into a text file by adopting a voice recognition technology; and if the historical visit information is a voice file, converting the voice file into a text file by adopting a voice recognition technology.
S12, extracting a plurality of original data in the historical doctor information, and inputting the plurality of original data into a scoring identification model to obtain a recommendation score of each historical doctor, wherein the plurality of original data comprise a plurality of key fields of the plurality of historical doctors and the recommendation score of each key field.
In this embodiment, the plurality of raw data are extracted from the historical doctor information, and specifically, the plurality of raw data are a plurality of key fields of a plurality of historical doctor in the historical doctor information and a recommendation score of each key field of each historical doctor, where the plurality of key fields may be set in advance according to a requirement of a patient, and may include: the scoring identification model may be pre-trained to obtain a plurality of key fields of the plurality of historic doctors, and then input the plurality of key fields of the plurality of historic doctors into the pre-trained scoring identification model to obtain a recommended score for each historic doctor.
Specifically, the training process of the scoring identification model includes:
21 Acquiring a plurality of key fields of a plurality of historical consultants and recommendation scores corresponding to the key fields 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 scoring identification model;
24 Inputting the test set into the score identification model for testing, and calculating the test passing rate;
25 If the test passing rate is greater than a preset passing rate threshold value, determining that the score recognition model training is finished; if the test passing rate is smaller than the preset passing rate threshold value, increasing the number of training sets, and training the scoring identification model again.
In this embodiment, training is performed according to different recommendation scores corresponding to each key field of different doctors to obtain a score recognition model, the recommendation scores of the plurality of key fields of the plurality of historical doctors and each key field of each historical doctor are input into a pre-trained score recognition model to be recognized to obtain a recommendation score of each historical doctor, and in a subsequent training process, the recommendation scores of the plurality of key fields of each historical doctor and each key field of each historical doctor corresponding to each patient are used as new data to increase the number of data sets, the score recognition model is retrained based on the new data sets, and the score recognition model is continuously updated, so that the recognition rate is continuously improved.
S13, performing regression fitting on the recommendation scores of the historical doctor and the key fields of the historical doctor to obtain the weight of each key field.
In this embodiment, the plurality of key fields of each historical doctor are consistent, and preferably, the weight corresponding to each key field can be calculated by a regression fit algorithm.
Optionally, performing regression fit on the plurality of recommendation scores of the plurality of historical doctor and the plurality of key fields of the plurality of historical doctor to obtain the weight of each key field includes:
performing regression fitting on the plurality of recommended scores of the plurality of historical doctor visits and the plurality of key fields of the plurality of historical doctor visits to obtain a plurality of preset fitting functions;
and calculating the weight corresponding to each key field according to the plurality of preset fitting functions.
Illustratively, a plurality of recommendation scores and the plurality of key fields for a plurality of historic caregivers are obtained, as shown in fig. 2: and carrying out regression fit on each historical doctor according to a preset fit function to obtain a preset fit function, carrying out regression fit on all the historical doctor to obtain a plurality of preset fit functions, and further calculating to obtain the weight corresponding to each key field according to the plurality of preset fit functions.
For example, if the weight of the historic doctor corresponding to the patient is calculated to be the largest, determining that the patient is the doctor's name with the highest importance; and if the weight of the gender of the historical doctor corresponding to the patient is calculated to be the largest, determining that the gender of the doctor is the most serious for the patient.
In this embodiment, since the plurality of key fields are set according to the needs of the patient, the matching degree between the recommended doctor and the doctor required by the patient can be improved by calculating the weight corresponding to each key field.
S14, creating a first doctor model of the initial recommended doctor of the patient according to a plurality of key fields of the plurality of historical doctor visits and the weight of each key field.
In this embodiment, the first doctor model is an initial recommended doctor created according to a plurality of key fields of a history doctor and weights corresponding to each key field in a history doctor of a patient, and specifically, the initial recommended doctor is created based on a dimension of the patient after consideration.
Optionally, the creating the first doctor model of the initial recommended doctor of the patient according to the plurality of key fields of the plurality of historical doctor visits and the weight corresponding to each key field includes:
Selecting the doctor with the highest recommendation score as a first recommendation doctor of the patient;
performing label conversion on a plurality of key fields of the first recommended doctor to obtain a label set of the first recommended doctor, wherein each label in the label set contains a weight;
and sorting the labels in the label set in descending order according to the weight to obtain a first doctor model of the initial recommended doctor of the patient.
In this embodiment, according to the score of the patient on each historical doctor, selecting the doctor with the highest recommendation score as the first doctor recommended for the patient, and performing label conversion on a plurality of key fields corresponding to the first doctor recommended according to a preset label conversion rule to obtain a label set of the first doctor recommended, for example: aiming at the key field ages corresponding to the first recommended doctor B, according to a preset age conversion rule: 26-35, the year-round; 36-45 years; 46-55, up to year, 56-65, middle-aged; 66-75, the elderly. If the age of the first recommended doctor B is 29 years old, determining that the label corresponding to the age of the first recommended doctor is: and (5) the year is strong.
After the tag set of the first recommended doctor is obtained, the tags in the tag set are sorted in descending order according to the weight to obtain a first doctor model of the initial recommended doctor of the patient, and the matching degree between the recommended doctor and the doctor required by the patient is improved because the initial recommended doctor is obtained by considering the dimension of the patient.
S15, acquiring a second doctor model of at least one recommended doctor in a doctor index table according to the historical doctor information of the patient.
In this embodiment, since the doctor index table is associated with the second doctor model of each recommended doctor, and the second doctor model includes a plurality of labels, at least one recommended doctor can be quickly determined according to the historical doctor-seeing information of the patient, and the second doctor model of the recommended doctor is associated, so that the efficiency of determining the recommended doctor is improved.
Optionally, the acquiring the second doctor model of the at least one recommended doctor in the doctor index table according to the historical doctor information of the patient includes:
extracting a plurality of disease information from the patient's historical visit information;
word segmentation processing is carried out on the plurality of disease information to obtain a plurality of disease characteristic attributes;
performing label conversion on the disease characteristic attributes to obtain a label set of the patient;
and searching at least one recommended doctor matched with the tag set in a doctor index table, and associating a second doctor model of the at least one recommended doctor from the doctor index table.
In this embodiment, the doctor index table includes a second doctor model of each recommended doctor, where the second doctor model includes a plurality of labels, and the plurality of labels can determine the adequacy field, age, sex, doctor name, and the like of the history doctor.
In this embodiment, before the doctor model of at least one recommended doctor is obtained from the doctor index table according to the patient's historical doctor information, a doctor index table needs to be created, and specifically, the creating process of the doctor index table includes: the method comprises the steps of crawling doctor information of a plurality of doctor-seeing doctors from a plurality of preset target data sources by adopting a web crawler technology, extracting a plurality of preset doctor characteristic attributes from the doctor information of each doctor-seeing doctor, converting the plurality of preset doctor characteristic attributes into a target tag set according to a preset target tag conversion rule, and taking the target tag set as a second doctor model of each doctor-seeing doctor.
S16, calculating the similarity between the first doctor model and the second doctor model of the at least one recommended doctor, and determining the target recommended doctor of the patient according to the calculated similarity.
In this embodiment, the target recommending physician is determined by similarity between a first physician model of the initial recommending physician of the patient and a second physician model of each recommending physician recommended by the system.
Optionally, the calculating the similarity between the first doctor model and the second doctor model of each recommended doctor includes:
extracting all first labels in the first doctor model, and calculating a first label total number of all the first labels;
extracting all second labels in the second doctor model of each recommended doctor;
searching all target tags matched with all first tags from all second tags, and calculating the total number of second tags of all target tags;
and taking the quotient of the second label total number and the first label total number as the similarity between the first doctor model and the second doctor model of each recommended doctor.
In this embodiment, the first doctor model includes a plurality of first labels, the second doctor model includes a plurality of second labels, each first label is matched with the plurality of second labels, all target labels matched with the first labels are found, and a quotient of a total number of second labels and a total number of first labels of all target labels is calculated as a similarity between the first doctor model and a second doctor model of each recommended doctor.
Optionally, the determining the target recommended doctor of the patient according to the calculated similarity includes:
sorting the calculated similarity between the first doctor model and the second doctor model of each recommended doctor in a descending order;
selecting a plurality of second recommended doctors corresponding to the plurality of similarity in the prior order from the descending order sequencing results;
determining a preference of the patient based on the patient's historical visit information;
determining a target recommended doctor of the patient from the plurality of second recommended doctors according to the preference of the patient.
In this embodiment, a collaborative filtering recommendation algorithm may be adopted to determine a target recommended doctor of the patient from the plurality of second recommended doctors according to the preference of the patient, and in this embodiment, the similarity between the second doctor model recommended by the computing system and the first doctor recommendation model required by the patient is determined according to the similarity, and the target recommended doctor of the patient is obtained by considering both the dimensions of the patient and the doctor, so that the matching degree between the recommended doctor and the doctor required by the patient is improved, and the accuracy of the target recommended doctor is further improved.
In summary, according to the doctor intelligent recommendation method of the embodiment, the historical treatment information of the patient is collected from a plurality of preset data sources; extracting a plurality of original data in the historical visit information, and inputting the plurality of original data into a score recognition model to obtain a recommended score of each historical visit doctor, wherein the plurality of original data comprises a plurality of key fields of the plurality of historical visit doctors and the recommended score of each key field; performing regression fitting on the plurality of recommended scores of the plurality of historical doctor visits and the plurality of key fields of the plurality of historical doctor visits to obtain the weight of each key field; creating a first doctor model of an initial recommended doctor of the patient according to a plurality of key fields of the plurality of historical doctor visits and the weight of each key field; acquiring a second doctor model of at least one recommended doctor in a doctor index table according to the historical doctor information of the patient; and calculating the similarity between the first doctor model and the second doctor model of the at least one recommended doctor, and determining the target recommended doctor of the patient according to the calculated similarity.
In this embodiment, on the one hand, a first doctor model of an initial recommended doctor of the patient is created according to a plurality of key fields of the plurality of historical doctor visits and weights corresponding to each key field, and because the initial recommended doctor is obtained by taking into consideration based on the dimension of the patient, the matching degree between the recommended doctor and the doctor required by the patient is improved; on the other hand, the similarity between the first doctor model and the second doctor model of each recommended doctor is calculated, the target recommended doctor of the patient is determined according to the calculated similarity, the target recommended doctor of the patient is obtained by simultaneously considering the dimensions of the patient and the doctor, the matching degree between the recommended doctor and the doctor required by the patient is improved, and the accuracy of the target recommended doctor is further improved; and finally, carrying out regression fitting on a plurality of recommended scores of the plurality of historical doctor visits and the plurality of key fields to obtain the weight corresponding to each key field, wherein the plurality of key fields are set according to the needs of the patient, and the matching degree between the recommended doctor and the doctor of the patient needs can be improved by calculating the weight corresponding to each key field.
Example two
Fig. 3 is a block diagram of an intelligent doctor recommendation device according to a second embodiment of the present invention.
In some embodiments, the physician intelligent recommendation device 20 may include a plurality of functional modules that are comprised of program code segments. Program code for each program segment in the physician intelligent recommendation apparatus 20 may be stored in a memory of the electronic device and executed by the at least one processor to perform (see fig. 1 for details) the physician intelligent recommendation function.
In this embodiment, the intelligent recommendation apparatus 20 may be divided into a plurality of functional modules according to the functions performed by the intelligent recommendation apparatus. The functional module may include: the system comprises an acquisition module 201, an extraction module 202, a regression fitting module 203, a creation module 204, an acquisition module 205 and a calculation module 206. The module referred to in the present invention refers to a series of computer program segments capable of being executed by at least one processor and of performing a fixed function, stored in a memory. In the present embodiment, the functions of the respective modules will be described in detail in the following embodiments.
The acquisition module 201 is configured to acquire historical diagnosis information of a patient from a plurality of preset data sources.
In this embodiment, a plurality of data sources may be preset, where the data sources may be a plurality of diagnosis platforms associated with the historical diagnosis information of each patient, and the historical diagnosis information of each patient is crawled from each preset data source, or the historical diagnosis information reported by the preset plurality of data sources is received, and specifically, the historical diagnosis information includes: patient historical disease information and doctor information for a historical doctor.
In other embodiments, the historical doctor information may be a text file, a video file, or a voice file, and if the historical doctor information is a video file, voice information may be collected from the video file, and the voice information is converted into a text file by adopting a voice recognition technology; and if the historical visit information is a voice file, converting the voice file into a text file by adopting a voice recognition technology.
The extracting module 202 is configured to extract a plurality of pieces of raw data in the historical doctor information, and input the plurality of pieces of raw data into a score recognition model to obtain a recommendation score of each historical doctor, where the plurality of pieces of raw data include a plurality of key fields of the plurality of historical doctors and the recommendation score of each key field.
In this embodiment, the plurality of raw data are extracted from the historical doctor information, and specifically, the plurality of raw data are a plurality of key fields of a plurality of historical doctor in the historical doctor information and a recommendation score of each key field of each historical doctor, where the plurality of key fields may be set in advance according to a requirement of a patient, and may include: the scoring identification model may be pre-trained to obtain a plurality of key fields of the plurality of historic doctors, and then input the plurality of key fields of the plurality of historic doctors into the pre-trained scoring identification model to obtain a recommended score for each historic doctor.
Specifically, the training process of the scoring identification model includes:
21 Acquiring a plurality of key fields of a plurality of historical consultants and recommendation scores corresponding to the key fields 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 scoring identification model;
24 Inputting the test set into the score identification model for testing, and calculating the test passing rate;
25 If the test passing rate is greater than a preset passing rate threshold value, determining that the score recognition model training is finished; if the test passing rate is smaller than the preset passing rate threshold value, increasing the number of training sets, and training the scoring identification model again.
In this embodiment, training is performed according to different recommendation scores corresponding to each key field of different doctors to obtain a score recognition model, the recommendation scores of the plurality of key fields of the plurality of historical doctors and each key field of each historical doctor are input into a pre-trained score recognition model to be recognized to obtain a recommendation score of each historical doctor, and in a subsequent training process, the recommendation scores of the plurality of key fields of each historical doctor and each key field of each historical doctor corresponding to each patient are used as new data to increase the number of data sets, the score recognition model is retrained based on the new data sets, and the score recognition model is continuously updated, so that the recognition rate is continuously improved.
The regression fitting module 203 is configured to perform regression fitting on the plurality of recommendation scores of the plurality of historical doctor visits and the plurality of key fields of the plurality of historical doctor visits to obtain a weight of each key field.
In this embodiment, the plurality of key fields of each historical doctor are consistent, and preferably, the weight corresponding to each key field can be calculated by a regression fit algorithm.
Optionally, the regression fitting module 203 performs regression fitting on the plurality of recommendation scores of the plurality of historical doctor and the plurality of key fields of the plurality of historical doctor to obtain the weight of each key field includes:
performing regression fitting on the plurality of recommended scores of the plurality of historical doctor visits and the plurality of key fields of the plurality of historical doctor visits to obtain a plurality of preset fitting functions;
and calculating the weight corresponding to each key field according to the plurality of preset fitting functions.
Illustratively, a plurality of recommendation scores and the plurality of key fields for a plurality of historic caregivers are obtained, as shown in fig. 2: and carrying out regression fit on each historical doctor according to a preset fit function to obtain a preset fit function, carrying out regression fit on all the historical doctor to obtain a plurality of preset fit functions, and further calculating to obtain the weight corresponding to each key field according to the plurality of preset fit functions.
For example, if the weight of the historic doctor corresponding to the patient is calculated to be the largest, determining that the patient is the doctor's name with the highest importance; and if the weight of the gender of the historical doctor corresponding to the patient is calculated to be the largest, determining that the gender of the doctor is the most serious for the patient.
In this embodiment, since the plurality of key fields are set according to the needs of the patient, the matching degree between the recommended doctor and the doctor required by the patient can be improved by calculating the weight corresponding to each key field.
A creation module 204 is configured to create a first doctor model of an initial recommended doctor of the patient according to a plurality of key fields of the plurality of historic doctor visits and a weight of each key field.
In this embodiment, the first doctor model is an initial recommended doctor created according to a plurality of key fields of a history doctor and weights corresponding to each key field in a history doctor of a patient, and specifically, the initial recommended doctor is created based on a dimension of the patient after consideration.
Optionally, the creating module 204 creates the first doctor model of the initial recommended doctor of the patient according to the plurality of key fields of the plurality of historical doctor's and the weight corresponding to each key field includes:
Selecting the doctor with the highest recommendation score as a first recommendation doctor of the patient;
performing label conversion on a plurality of key fields of the first recommended doctor to obtain a label set of the first recommended doctor, wherein each label in the label set contains a weight;
and sorting the labels in the label set in descending order according to the weight to obtain a first doctor model of the initial recommended doctor of the patient.
In this embodiment, according to the score of the patient on each historical doctor, selecting the doctor with the highest recommendation score as the first doctor recommended for the patient, and performing label conversion on a plurality of key fields corresponding to the first doctor recommended according to a preset label conversion rule to obtain a label set of the first doctor recommended, for example: aiming at the key field ages corresponding to the first recommended doctor B, according to a preset age conversion rule: 26-35, the year-round; 36-45 years; 46-55, up to year, 56-65, middle-aged; 66-75, the elderly. If the age of the first recommended doctor B is 29 years old, determining that the label corresponding to the age of the first recommended doctor is: and (5) the year is strong.
After the tag set of the first recommended doctor is obtained, the tags in the tag set are sorted in descending order according to the weight to obtain a first doctor model of the initial recommended doctor of the patient, and the matching degree between the recommended doctor and the doctor required by the patient is improved because the initial recommended doctor is obtained by considering the dimension of the patient.
An obtaining module 205, configured to obtain a second doctor model of at least one recommended doctor in a doctor index table according to the patient's historical doctor information.
In this embodiment, since the doctor index table is associated with the second doctor model of each recommended doctor, and the second doctor model includes a plurality of labels, at least one recommended doctor can be quickly determined according to the historical doctor-seeing information of the patient, and the second doctor model of the recommended doctor is associated, so that the efficiency of determining the recommended doctor is improved.
Optionally, the acquiring module 205 acquires a second doctor model of at least one recommended doctor in a doctor index table according to the historical doctor information of the patient includes:
extracting a plurality of disease information from the patient's historical visit information;
word segmentation processing is carried out on the plurality of disease information to obtain a plurality of disease characteristic attributes;
performing label conversion on the disease characteristic attributes to obtain a label set of the patient;
and searching at least one recommended doctor matched with the tag set in a doctor index table, and associating a second doctor model of the at least one recommended doctor from the doctor index table.
In this embodiment, the doctor index table includes a second doctor model of each recommended doctor, where the second doctor model includes a plurality of labels, and the plurality of labels can determine the adequacy field, age, sex, doctor name, and the like of the history doctor.
In this embodiment, before the doctor model of at least one recommended doctor is obtained from the doctor index table according to the patient's historical doctor information, a doctor index table needs to be created, and specifically, the creating process of the doctor index table includes: the method comprises the steps of crawling doctor information of a plurality of doctor-seeing doctors from a plurality of preset target data sources by adopting a web crawler technology, extracting a plurality of preset doctor characteristic attributes from the doctor information of each doctor-seeing doctor, converting the plurality of preset doctor characteristic attributes into a target tag set according to a preset target tag conversion rule, and taking the target tag set as a second doctor model of each doctor-seeing doctor.
A calculation module 206, configured to calculate a similarity between the first doctor model and a second doctor model of the at least one recommended doctor, and determine a target recommended doctor of the patient according to the calculated similarity.
In this embodiment, the target recommending physician is determined by similarity between a first physician model of the initial recommending physician of the patient and a second physician model of each recommending physician recommended by the system.
Optionally, the calculating module 206 calculates the similarity between the first doctor model and the second doctor model of each recommended doctor includes:
extracting all first labels in the first doctor model, and calculating a first label total number of all the first labels;
extracting all second labels in the second doctor model of each recommended doctor;
searching all target tags matched with all first tags from all second tags, and calculating the total number of second tags of all target tags;
and taking the quotient of the second label total number and the first label total number as the similarity between the first doctor model and the second doctor model of each recommended doctor.
In this embodiment, the first doctor model includes a plurality of first labels, the second doctor model includes a plurality of second labels, each first label is matched with the plurality of second labels, all target labels matched with the first labels are found, and a quotient of a total number of second labels and a total number of first labels of all target labels is calculated as a similarity between the first doctor model and a second doctor model of each recommended doctor.
Optionally, the determining, by the computing module 206, the target recommendation doctor for the patient according to the computed similarity includes:
sorting the calculated similarity between the first doctor model and the second doctor model of each recommended doctor in a descending order;
selecting a plurality of second recommended doctors corresponding to the plurality of similarity in the prior order from the descending order sequencing results;
determining a preference of the patient based on the patient's historical visit information;
determining a target recommended doctor of the patient from the plurality of second recommended doctors according to the preference of the patient.
In this embodiment, a collaborative filtering recommendation algorithm may be adopted to determine a target recommended doctor of the patient from the plurality of second recommended doctors according to the preference of the patient, and in this embodiment, the similarity between the second doctor model recommended by the computing system and the first doctor recommendation model required by the patient is determined according to the similarity, and the target recommended doctor of the patient is obtained by considering both the dimensions of the patient and the doctor, so that the matching degree between the recommended doctor and the doctor required by the patient is improved, and the accuracy of the target recommended doctor is further improved.
In summary, according to the doctor intelligent recommendation device of the embodiment, the history treatment information of the patient is collected from a plurality of preset data sources; extracting a plurality of original data in the historical visit information, and inputting the plurality of original data into a score recognition model to obtain a recommended score of each historical visit doctor, wherein the plurality of original data comprises a plurality of key fields of the plurality of historical visit doctors and the recommended score of each key field; performing regression fitting on the plurality of recommended scores of the plurality of historical doctor visits and the plurality of key fields of the plurality of historical doctor visits to obtain the weight of each key field; creating a first doctor model of an initial recommended doctor of the patient according to a plurality of key fields of the plurality of historical doctor visits and the weight of each key field; acquiring a second doctor model of at least one recommended doctor in a doctor index table according to the historical doctor information of the patient; and calculating the similarity between the first doctor model and the second doctor model of the at least one recommended doctor, and determining the target recommended doctor of the patient according to the calculated similarity.
In this embodiment, on the one hand, a first doctor model of an initial recommended doctor of the patient is created according to a plurality of key fields of the plurality of historical doctor visits and weights corresponding to each key field, and because the initial recommended doctor is obtained by taking into consideration based on the dimension of the patient, the matching degree between the recommended doctor and the doctor required by the patient is improved; on the other hand, the similarity between the first doctor model and the second doctor model of each recommended doctor is calculated, the target recommended doctor of the patient is determined according to the calculated similarity, the target recommended doctor of the patient is obtained by simultaneously considering the dimensions of the patient and the doctor, the matching degree between the recommended doctor and the doctor required by the patient is improved, and the accuracy of the target recommended doctor is further improved; and finally, carrying out regression fitting on a plurality of recommended scores of the plurality of historical doctor visits and the plurality of key fields to obtain the weight corresponding to each key field, wherein the plurality of key fields are set according to the needs of the patient, and the matching degree between the recommended doctor and the doctor of the patient needs can be improved by calculating the weight corresponding to each key field.
Example III
Fig. 4 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. In the preferred embodiment of the 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. 4 is not limiting of the embodiments of the present invention, and that either a bus-type configuration or a star-type configuration is possible, and that the electronic device 3 may also include more or less other hardware or software than that 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 a preset or stored instruction, and its hardware 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 further include a client device, where the client device includes, but is not limited to, any electronic product that can interact with a client by way of a keyboard, a mouse, a remote control, a touch pad, or a voice control device, such as a personal computer, a tablet computer, a smart phone, a digital camera, etc.
It should be noted that the electronic device 3 is only used as an example, and other electronic products that may be present in the present invention or may be present in the future are also included in the scope of the present invention by way of reference.
In some embodiments, the memory 31 is used to store program codes and various data, such as the doctor intelligent recommendation device 20 installed in the electronic device 3, and to implement high-speed, automatic access to programs or data during operation of the electronic device 3. The Memory 31 includes Read-Only Memory (ROM), programmable Read-Only Memory (PROM), erasable programmable Read-Only Memory (EPROM), one-time programmable Read-Only Memory (One-time Programmable Read-Only Memory, OTPROM), electrically erasable rewritable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
In some embodiments, the at least one processor 32 may be comprised of an integrated circuit, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The at least one processor 32 is a Control Unit (Control Unit) of the electronic device 3, connects the respective components of the entire electronic device 3 using various interfaces and lines, and executes various functions of the electronic device 3 and processes data 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 connected 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 source (such as a battery) for powering the various components, and optionally, the power source may be logically connected to the at least one processor 32 via a power management device, thereby implementing functions such as managing charging, discharging, and power consumption by the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 3 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The integrated units implemented in the form of software functional modules described above may be stored in a computer readable storage medium. The software functional modules described above are stored in a storage medium and include instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device, etc.) or a processor (processor) to perform portions of the methods described in the various embodiments of the invention.
In a further embodiment, in connection with fig. 3, the at least one processor 32 may execute the operating means of the electronic device 3 as well as various installed applications (e.g. the doctor intelligent recommendation device 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 invoke the program code stored in the memory 31 to perform related functions. For example, each of the modules depicted in fig. 3 is a program code stored in the memory 31 and executed by the at least one processor 32 to perform the functions of the respective modules for the purpose of intelligent recommendation by a physician.
In one embodiment of the invention, the memory 31 stores a plurality of instructions that are executed by the at least one processor 32 to implement the physician intelligent recommendation function.
Specifically, the specific implementation method of the above instruction by the at least one processor 32 may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
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 characteristics 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 will be obvious that the term "comprising" does not exclude other elements or that the singular does not exclude a plurality. The units or means stated in the invention may also be implemented by one unit or means, either by software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (8)
1. An intelligent recommendation method for doctors, which is characterized by comprising the following steps:
collecting historical treatment information of a patient from a plurality of preset data sources;
extracting a plurality of original data in the historical visit information, and inputting the plurality of original data into a score recognition model to obtain a recommended score of each historical visit doctor, wherein the plurality of original data comprises a plurality of key fields of the plurality of historical visit doctors and the recommended score of each key field;
performing regression fitting on the plurality of recommended scores of the plurality of historical doctor visits and the plurality of key fields of the plurality of historical doctor visits to obtain the weight of each key field;
creating a first doctor model of an initial recommended doctor of the patient according to a plurality of key fields of the plurality of historical doctor visits and the weight of each key field, wherein the first doctor model comprises: selecting the doctor with the highest recommendation score as a first recommendation doctor of the patient; performing label conversion on a plurality of key fields of the first recommended doctor to obtain a label set of the first recommended doctor, wherein each label in the label set contains a weight; the labels in the label set are ordered in descending order according to the weight to obtain a first doctor model of an initial recommended doctor of the patient;
Acquiring a second doctor model of at least one recommended doctor in a doctor index table according to the historical doctor information of the patient, wherein the second doctor model comprises the following components: extracting a plurality of disease information from the patient's historical visit information; word segmentation processing is carried out on the plurality of disease information to obtain a plurality of disease characteristic attributes; performing label conversion on the disease characteristic attributes to obtain a label set of the patient; searching at least one recommended doctor matched with the tag set in a doctor index table, and associating a second doctor model of the at least one recommended doctor from the doctor index table;
and calculating the similarity between the first doctor model and the second doctor model of the at least one recommended doctor, and determining the target recommended doctor of the patient according to the calculated similarity.
2. The intelligent doctor recommending method as claimed in claim 1, wherein said regression fitting the plurality of recommendation scores of the plurality of historic doctor and the plurality of key fields of the plurality of historic doctor to obtain the weight of each key field comprises:
performing regression fitting on the plurality of recommended scores of the plurality of historical doctor visits and the plurality of key fields of the plurality of historical doctor visits to obtain a plurality of preset fitting functions;
And calculating the weight of each key field according to the plurality of preset fitting functions.
3. The doctor intelligent recommendation method as claimed in claim 1, wherein the training process of the score recognition model includes:
acquiring a plurality of key fields of a plurality of historical consultants and recommendation scores corresponding to the key fields as a sample data set;
dividing a training set and a testing set from the sample data set;
inputting the training set into a preset neural network for training to obtain a scoring identification model;
inputting the test set into the score identification model for testing, and calculating the test passing rate;
if the test passing rate is larger than a preset passing rate threshold value, determining that the score identification model training is finished; if the test passing rate is smaller than the preset passing rate threshold value, increasing the number of training sets, and training the scoring identification model again.
4. The doctor intelligent recommendation method as claimed in claim 1, wherein said calculating a similarity between the first doctor model and the second doctor model of each recommended doctor includes:
extracting all first labels in the first doctor model, and calculating a first label total number of all the first labels;
Extracting all second labels in the second doctor model of each recommended doctor;
searching all target tags matched with all first tags from all second tags, and calculating the total number of second tags of all target tags;
and taking the quotient of the second label total number and the first label total number as the similarity between the first doctor model and the second doctor model of each recommended doctor.
5. The intelligent recommendation method for a doctor according to claim 4, wherein the determining a target recommended doctor for the patient based on the calculated similarity includes:
sorting the calculated similarity between the first doctor model and the second doctor model of each recommended doctor in a descending order;
selecting a plurality of second recommended doctors corresponding to the plurality of similarity in the prior order from the descending order sequencing results;
determining a preference of the patient based on the patient's historical visit information;
determining a target recommended doctor of the patient from the plurality of second recommended doctors according to the preference of the patient.
6. An intelligent recommendation device for a doctor, the device comprising:
the acquisition module is used for acquiring historical treatment information of a patient from a plurality of preset data sources;
The extraction module is used for extracting a plurality of original data in the historical doctor information, and inputting the plurality of original data into the score recognition model to obtain the recommended score of each historical doctor, wherein the plurality of original data comprises a plurality of key fields of a plurality of historical doctors and the recommended score of each key field;
the regression fitting module is used for carrying out regression fitting on a plurality of recommended scores of the plurality of historical doctor visits and a plurality of key fields of the plurality of historical doctor visits to obtain the weight of each key field;
a creation module for creating a first doctor model of an initial recommended doctor of the patient according to a plurality of key fields of the plurality of historical doctor's and the weight of each key field, comprising: selecting the doctor with the highest recommendation score as a first recommendation doctor of the patient; performing label conversion on a plurality of key fields of the first recommended doctor to obtain a label set of the first recommended doctor, wherein each label in the label set contains a weight; the labels in the label set are ordered in descending order according to the weight to obtain a first doctor model of an initial recommended doctor of the patient;
An acquisition module, configured to acquire a second doctor model of at least one recommended doctor in a doctor index table according to the historical doctor information of the patient, including: extracting a plurality of disease information from the patient's historical visit information; word segmentation processing is carried out on the plurality of disease information to obtain a plurality of disease characteristic attributes; performing label conversion on the disease characteristic attributes to obtain a label set of the patient; searching at least one recommended doctor matched with the tag set in a doctor index table, and associating a second doctor model of the at least one recommended doctor from the doctor index table;
and the calculation module is used for calculating the similarity between the first doctor model and the second doctor model of the at least one recommended doctor, and determining the target recommended doctor of the patient according to the calculated similarity.
7. An electronic device comprising a processor and a memory, wherein the processor is configured to implement the method of intelligent doctor recommendation according to any of claims 1 to 5 when executing a computer program stored in the memory.
8. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements a method of intelligent recommendation of a doctor according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011600037.XA CN112614578B (en) | 2020-12-29 | 2020-12-29 | Doctor intelligent recommendation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011600037.XA CN112614578B (en) | 2020-12-29 | 2020-12-29 | Doctor intelligent recommendation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112614578A CN112614578A (en) | 2021-04-06 |
| CN112614578B true CN112614578B (en) | 2023-06-09 |
Family
ID=75249113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011600037.XA Active CN112614578B (en) | 2020-12-29 | 2020-12-29 | Doctor intelligent recommendation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112614578B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113539460A (en) * | 2021-07-29 | 2021-10-22 | 深圳万海思数字医疗有限公司 | Intelligent diagnosis guiding method and device for remote medical platform |
| CN113722590B (en) * | 2021-08-30 | 2023-09-19 | 深圳平安智慧医健科技有限公司 | Medical information recommendation method, device, equipment and medium based on artificial intelligence |
| CN113744867B (en) * | 2021-08-30 | 2024-03-08 | 平安科技（深圳）有限公司 | Medicine recommendation evidence-based support method, device, equipment and storage medium |
| CN113724848A (en) * | 2021-08-31 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Medical resource recommendation method, device, server and medium based on artificial intelligence |
| CN114496191A (en) * | 2022-02-10 | 2022-05-13 | 北京京东拓先科技有限公司 | Medical information recommendation method, device, equipment and storage medium |
| US11748361B1 (en) | 2022-08-12 | 2023-09-05 | Ryte Corporation | Systems and methods for multi-dimensional ranking of experts |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108305675A (en) * | 2018-01-26 | 2018-07-20 | 合肥工业大学 | Intelligent hospital guide's method and system of diversity enhancing |
| CN109686429A (en) * | 2018-11-15 | 2019-04-26 | 贵阳朗玛信息技术股份有限公司 | Physician visits period recommended method and device |
| CN110993081A (en) * | 2019-12-03 | 2020-04-10 | 济南大学 | Doctor online recommendation method and system |
| CN111785368A (en) * | 2020-06-30 | 2020-10-16 | 平安科技（深圳）有限公司 | Triage method, device, equipment and storage medium based on medical knowledge map |
-
2020
- 2020-12-29 CN CN202011600037.XA patent/CN112614578B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108305675A (en) * | 2018-01-26 | 2018-07-20 | 合肥工业大学 | Intelligent hospital guide's method and system of diversity enhancing |
| CN109686429A (en) * | 2018-11-15 | 2019-04-26 | 贵阳朗玛信息技术股份有限公司 | Physician visits period recommended method and device |
| CN110993081A (en) * | 2019-12-03 | 2020-04-10 | 济南大学 | Doctor online recommendation method and system |
| CN111785368A (en) * | 2020-06-30 | 2020-10-16 | 平安科技（深圳）有限公司 | Triage method, device, equipment and storage medium based on medical knowledge map |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112614578A (en) | 2021-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112614578B (en) | Doctor intelligent recommendation method and device, electronic equipment and storage medium | |
| KR102088980B1 (en) | System and Method for Providing personalized hospital information | |
| US11232856B2 (en) | Methods for automatic cohort selection in epidemiologic studies and clinical trials | |
| CN110363090B (en) | Intelligent heart disease detection method, device and computer readable storage medium | |
| CN112562836A (en) | Doctor recommendation method and device, electronic equipment and storage medium | |
| US20190057773A1 (en) | Method and system for performing triage | |
| CN112149409B (en) | Medical word cloud generation method and device, computer equipment and storage medium | |
| CN111986744B (en) | Patient interface generation method and device for medical institution, electronic equipment and medium | |
| CN113345577B (en) | Diagnosis and treatment auxiliary information generation method, model training method, device, equipment and storage medium | |
| CN110534185A (en) | Labeled data acquisition methods divide and examine method, apparatus, storage medium and equipment | |
| CN112634889B (en) | Electronic case input method, device, terminal and medium based on artificial intelligence | |
| CN113782125B (en) | Clinic scoring method and device based on artificial intelligence, electronic equipment and medium | |
| CN114781805B (en) | Nursing staff nursing skill assessment method, system and device based on big data | |
| CN111223548A (en) | Method and device for pushing guidance resource information, storage medium and computer equipment | |
| CN114334175B (en) | Hospital epidemic situation monitoring method and device, computer equipment and storage medium | |
| AlZu’Bi et al. | transfer learning enabled CAD system for monkey pox classification | |
| CN117612660A (en) | Medical policy pushing system, method thereof and readable storage medium | |
| CN112530602A (en) | Method and device for analyzing side effect of medicine, electronic equipment and computer storage medium | |
| CN113793668B (en) | Symptom standardization method and device based on artificial intelligence, electronic equipment and medium | |
| CN116844703A (en) | Diagnosis guiding method and system based on artificial intelligence | |
| CN116525053A (en) | Patient report generation method, device, electronic equipment and medium | |
| CN115658858A (en) | Dialog recommendation method based on artificial intelligence and related equipment | |
| CN113963413B (en) | Epidemic situation investigation method and device based on artificial intelligence, electronic equipment and medium | |
| CN113590845B (en) | Knowledge graph-based document retrieval method and device, electronic equipment and medium | |
| Gangavarapu et al. | Coherence-based modeling of clinical concepts inferred from heterogeneous clinical notes for ICU patient risk stratification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220927 Address after: Room 2601 (Unit 07), Qianhai Free Trade Building, No. 3048, Xinghai Avenue, Nanshan Street, Qianhai Shenzhen-Hong Kong Cooperation Zone, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Ping An Smart Healthcare Technology Co.,Ltd. Address before: 1-34 / F, Qianhai free trade building, 3048 Xinghai Avenue, Mawan, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong 518000 Applicant before: Ping An International Smart City Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |