CN111696656B - Doctor evaluation method and device of Internet medical platform - Google Patents

Doctor evaluation method and device of Internet medical platform Download PDF

Info

Publication number
CN111696656B
CN111696656B CN202010536388.2A CN202010536388A CN111696656B CN 111696656 B CN111696656 B CN 111696656B CN 202010536388 A CN202010536388 A CN 202010536388A CN 111696656 B CN111696656 B CN 111696656B
Authority
CN
China
Prior art keywords
doctor
hospital
department
authority
feature
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
Application number
CN202010536388.2A
Other languages
Chinese (zh)
Other versions
CN111696656A (en
Inventor
康战辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN202010536388.2A priority Critical patent/CN111696656B/en
Publication of CN111696656A publication Critical patent/CN111696656A/en
Application granted granted Critical
Publication of CN111696656B publication Critical patent/CN111696656B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • 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

Abstract

The invention provides a doctor evaluation method, a doctor evaluation device, electronic equipment and a computer-readable storage medium of an internet medical platform; the method comprises the following steps: according to the hospital ranking list data, acquiring hospital authority features of a hospital to which doctors residing on the Internet medical platform belong; acquiring doctor title characteristics of the doctor; determining doctor specialty characteristics of the doctor according to the department where the doctor is good; and fusing the hospital authority feature, the doctor title feature and the doctor specialty feature to obtain the doctor authority of the doctor. By the invention, accurate evaluation information can be provided for doctors who reside in the Internet medical platform.

Description

Doctor evaluation method and device of Internet medical platform
Technical Field
The invention relates to the technical field of intelligent medical treatment, in particular to a doctor evaluation method and device of an internet medical platform, electronic equipment and a computer readable storage medium.
Background
The Medical cloud is a Medical cloud platform which is created by using cloud computing on the basis of new technologies such as cloud computing, mobile technology, multimedia, 4G communication, big data, internet of things and the like and combining Medical technology, and Medical resources are shared and the Medical scope is expanded. Due to the combination of the cloud computing technology, the medical cloud improves the efficiency of medical institutions and brings convenience to residents to see medical advice. Like the appointment register, the electronic medical record, the medical insurance and the like of the existing hospital are all products combining cloud computing and the medical field, and the medical cloud also has the advantages of data security, information sharing, dynamic expansion and overall layout.
Taking the application scenario of the internet medical platform as an example, because medical professional contents do not have a unified standard, it is difficult to determine whether a doctor is authoritative according to the quality of the contents written by the doctor, and it is a difficult problem for each internet medical platform to determine whether the doctor is authoritative. Therefore, the related technology has no effective scheme for accurately screening out authoritative good doctors on the third-party internet medical platform and medical contents written by the doctors.
Disclosure of Invention
The embodiment of the invention provides a doctor evaluation method and device of an internet medical platform, electronic equipment and a computer readable storage medium, which can provide accurate evaluation information for doctors who reside in the internet medical platform.
The technical scheme of the embodiment of the invention is realized as follows:
the embodiment of the invention provides a doctor evaluation method of an internet medical platform, which comprises the following steps:
according to the hospital ranking list data, hospital authority features of a hospital to which doctors residing on the Internet medical platform belong are obtained;
acquiring doctor title characteristics of the doctor;
determining doctor specialty characteristics of the doctor according to the department where the doctor is good at;
and fusing the hospital authority feature, the doctor title feature and the doctor specialty feature to obtain the doctor authority of the doctor.
The embodiment of the invention provides a doctor evaluation device of an internet medical platform, which comprises:
the data acquisition module is used for acquiring hospital authority features of a hospital to which doctors residing on the Internet medical platform belong according to the hospital ranking list data;
acquiring doctor job title characteristics of the doctor;
determining doctor specialty characteristics of the doctor according to the department where the doctor is good at;
and the model calculation module is used for fusing the hospital authority feature, the doctor title feature and the doctor professional feature to obtain the doctor authority of the doctor.
In the above scheme, the data acquisition module is further configured to
Searching out hospitals to which the doctors belong from hospital leaderboards of different grades;
determining the value of the hospital authority feature of the hospital to which the doctor belongs according to the grade of the hospital ranking list of the hospital to which the hospital belongs;
wherein the value of the hospital authority feature is positively correlated with the grade of the hospital ranking list where the hospital is located.
In the above scheme, the data acquisition module is further configured to
Acquiring a detail page of the doctor, and extracting the doctor job title of the doctor from the detail page;
determining the value of the doctor job title characteristic of the doctor according to the grade of the doctor job title;
wherein, the value of the hospital job title characteristic is positively correlated with the grade of the hospital job title.
In the above scheme, the data acquisition module is further configured to
Obtaining a department that the physician is skilled in;
determining the information amount corresponding to the doctor according to the statistical frequency of each type of department, and taking the information amount as a department concentration ratio;
wherein the statistical number is a number counted in the physician's detail page and inquiry answer;
and determining the value of the characteristic of the professional degree of the doctor according to the department concentration degree.
In the above scheme, the data acquisition module is further configured to
Obtaining the physician-good department by at least one of:
extracting a department which the doctor excels in from a detail page of the doctor;
matching the inquiry answers issued by the doctors with keywords in a department knowledge graph, and taking departments corresponding to the matched keywords as departments which the doctors are good at;
extracting keywords from the inquiry answers issued by the doctor, calling a neural network model to classify word vectors of the keywords to obtain departments associated with each inquiry answer, and taking the departments as departments which the doctor excels in.
In the above scheme, the data acquisition module is further configured to
Determining a ratio between the number of statistics and the total number of departments of each type as a probability of the departments of the each type;
wherein the total number is a count of the physician's detail pages and interview answers;
taking the probability of each type of department as weight, carrying out weighted summation on the information quantity of each type of department, and taking the weighted summation result as the information quantity corresponding to the doctor;
wherein the information amount of each type of the departments is a logarithm of the statistical number of each type of the departments.
In the foregoing solution, the model calculation module is further configured to
Taking a square value of the professional degree feature of the doctor, and calculating the reciprocal of the square value;
and multiplying the hospital authority feature, the doctor title feature and the reciprocal of the square value of the doctor specialty feature, and taking the multiplication result as the doctor authority of the doctor.
In the foregoing solution, an embodiment of the present invention provides a doctor evaluation apparatus for an internet medical platform, further including:
the response module is used for responding to the inquiry request and acquiring an inquiry answer corresponding to the inquiry request; the doctor authority value of the candidate doctor who gives the inquiry answer is larger than an authority threshold value;
and the display module is used for displaying the candidate doctors and the corresponding inquiry answers in an inquiry page.
In the above solution, an embodiment of the present invention provides a doctor evaluation device for an internet medical platform, further including:
a calling module, configured to store the hospital authority characteristic, the doctor title characteristic, and the doctor specialty characteristic in a state database of a blockchain network;
invoking an intelligent contract in the blockchain network to cause the intelligent contract to perform the following:
inquiring the hospital authority feature, the doctor title feature and the doctor professional feature of the doctor from the state database, and fusing to obtain the doctor authority of the doctor;
and performing consensus processing on the doctor authority of the doctor, and returning the doctor authority of the doctor as a calling result when the consensus is passed.
The embodiment of the invention provides electronic equipment for doctor evaluation of an internet medical platform, which comprises:
a memory for storing executable instructions;
and the processor is used for realizing the doctor evaluation method of the Internet medical platform provided by the embodiment of the invention when the executable instructions stored in the memory are executed.
The embodiment of the invention provides a computer-readable storage medium, which stores executable instructions and is used for realizing the doctor evaluation method of the internet medical platform provided by the embodiment of the invention when being executed by a processor.
The embodiment of the invention has the following beneficial effects:
the authority of the doctor is determined according to three-dimensional characteristics of the hospital authority characteristic, the doctor title characteristic and the doctor professional characteristic, evaluation information is provided for the doctor who resides in the Internet medical platform, and compared with a manual evaluation mode of a self-built doctor team and an examination team, the doctor evaluation accuracy, efficiency and coverage rate are improved.
Drawings
Fig. 1a is a schematic architecture diagram of a doctor evaluation system 100 of an internet medical platform according to an embodiment of the present invention;
FIG. 1b is a schematic diagram of an application of a doctor evaluation method of an Internet medical platform based on a blockchain according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a server 200 of an internet medical platform provided by an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a doctor evaluation method of an Internet medical platform according to an embodiment of the present invention;
FIG. 4 is a flow chart of a doctor evaluation method of an Internet medical platform according to an embodiment of the invention;
FIG. 5 is a flowchart illustrating a doctor evaluation method of an Internet medical platform according to an embodiment of the present invention;
FIG. 6 is a diagram of a leaderboard of three different ratings provided by embodiments of the invention;
FIG. 7 is a schematic diagram of physician detail page information provided by an embodiment of the present invention;
FIG. 8 is a schematic diagram of physician detail page information provided by an embodiment of the present invention;
FIG. 9 is a schematic diagram of a neural network model according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of an interrogation page in an Internet medical platform provided by an embodiment of the invention;
FIG. 11 is a schematic illustration of a portion of the interview responses issued by a physician provided in accordance with an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings, the described embodiments should not be construed as limiting the present invention, and all other embodiments that can be obtained by a person skilled in the art without making creative efforts fall within the protection scope of the present invention.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
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 is for the purpose of describing embodiments of the invention only and is not intended to be limiting of the invention.
Before further detailed description of the embodiments of the present invention, terms and expressions mentioned in the embodiments of the present invention are explained, and the terms and expressions mentioned in the embodiments of the present invention are applied to the following explanations.
1) Cloud Technology (Cloud Technology), a network Technology, an information Technology, an integration Technology, a management platform Technology, an application Technology and the like based on Cloud computing business model application, can form a resource pool, can be used as required, and is flexible and convenient. Cloud computing technology will become an important support. Background services of the technical network system require a large amount of computing and storage resources, such as video websites, picture-like websites and more web portals. With the high development and application of the internet industry, each article may have its own identification mark and needs to be transmitted to a background system for logic processing, data in different levels are processed separately, and various industrial data need strong system background support and can only be realized through cloud computing.
2) Big Data (Big Data) is a Data set which cannot be captured, managed and processed by a conventional software tool within a certain time range, and is a massive, high-growth-rate and diversified information asset which can have stronger decision-making power, insight discovery power and flow optimization capability only by a new processing mode. With the advent of the cloud era, big data has attracted more and more attention, and the big data needs special technology to effectively process a large amount of data within a tolerance elapsed time. The method is suitable for technologies of big data, including a large-scale parallel processing database, data mining, a distributed file system, a distributed database, a cloud computing platform, the Internet and an extensible storage system.
3) Word transformation vectors (Word 2 vec), a group of related models that are used to generate Word vectors. A word can be quickly and effectively expressed into a vector form through an optimized training model according to a given corpus.
4) Text classification convolutional neural network (Text-CNN), which is an algorithm for classifying texts using convolutional neural network.
5) Department intention classifier, collecting information/content title of question and answer, identifying department category of each content title by supervised machine learning method.
6) A Blockchain Network (Blockchain Network) incorporates new blocks into a set of nodes of a Blockchain in a consensus manner.
7) Intelligent Contracts (Smart Contracts), also known as chain codes (chaincodes) or application codes, are programs deployed in nodes of a blockchain network, and the nodes execute the intelligent Contracts called in received transactions to perform operations of updating or querying key-value data of a state database.
8) Consensus (Consensus), a process in a blockchain network, is used to agree on a transaction in a block between the nodes involved, the agreed block to be appended to the end of the blockchain and used to update the state database.
Various internet medical platforms of the related art are in endless, and resident doctors are in good quality. Since there is no uniform standard for professional medical content, it is difficult to determine whether a doctor is authoritative by the quality of the content written by the doctor. In the related art, when the third-party internet medical platform content is introduced, only the content registered as a doctor in the hospital trimethyl is directly selected, and the content is assumed to be an authoritative hospital (the hospital in trimethyl is the highest-level hospital in China), namely the authoritative content.
In the related art, assuming that a hospital in which a doctor who is resident on a third-party internet medical platform belongs is a high-authority hospital, a method representing that the authority of the doctor is higher is not accurate. There are at least three problems:
1) The first-line cities, provinces, prefectures and counties in the world, such as the northern Shangdong, all have three hospitals, and the three hospitals in China are the same, and the doctor authority degree difference of doctors in the three hospitals in different regions is obvious;
2) The experience and medical level of doctors in the same hospital at different job levels are different greatly;
3) Driven by the interest of third-party internet medical platforms, some resident doctors may engage in medical information writing and inquiry activities inconsistent with the directions of their professional departments in order to obtain higher exposure and platform stimulation, and their doctors are not authoritative in the non-professional field.
In view of the foregoing problems in the related art, embodiments of the present invention provide a doctor evaluation method and apparatus for an internet medical platform, an electronic device, and a computer-readable storage medium, which can provide accurate evaluation information for a doctor who is resident on the internet medical platform, and an exemplary application of the doctor evaluation method for the internet medical platform provided by embodiments of the present invention is described below.
In view of the above problems, embodiments of the present invention provide a doctor evaluation method and apparatus for an internet medical platform, an electronic device, and a computer-readable storage medium, which can provide accurate evaluation information for a doctor who resides in the internet medical platform.
An exemplary application of the doctor evaluation method of the internet medical platform provided by the embodiment of the present invention is described below, referring to fig. 1a, fig. 1a is a schematic structural diagram of a doctor evaluation system 100 of the internet medical platform provided by the embodiment of the present invention, and the doctor evaluation system includes a server 200 of the internet medical platform (hereinafter, referred to as server 200), a terminal 400 (exemplarily showing a client 410 running in the terminal), a list system 300, and a hospital information system 500, which are described below.
The user initiates an interrogation request in an interrogation page of client 410 (which may be, for example, a dedicated APP, browser, or applet of an internet medical platform); when receiving the inquiry request of the client 410, the server 200 sends a query request to the list system 300 and the hospital information system 500; the list system 300 and the hospital information system 500 serve as data sources of the server 200, and after receiving a query request of the server 200, query list data, detail pages and content title data of the query answers related to the query request; then, the server 200 determines the doctor authority of the relevant doctor according to the query result, and returns a page displaying the inquiring doctor with the doctor authority greater than the authority threshold and the corresponding inquiring answer, so that the user can select the inquiring doctor for reference during inquiring.
The server 200 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, which is not limited herein.
The embodiment of the invention can be widely applied to the intelligent medical field such as the Internet medical platform, for example, in the Internet medical information platform, the doctor authority degree of the Internet medical platform is predicted, and the doctor evaluation accuracy is improved, so that the Internet medical platform can screen more professional medical resources and medical teams; by predicting the doctor authority of the doctor, the doctor self-examination can be carried out in the hospital, so that the competition consciousness of the doctor is improved, and the progress of doctor groups is stimulated. Besides, the scenes related to doctor authority prediction belong to potential application scenes of the embodiment of the invention.
An exemplary application of embodiments of the present invention to a blockchain-based network is described below.
Referring to fig. 1b, fig. 1b is a schematic application diagram of a doctor evaluation method of a blockchain-based internet medical platform according to an embodiment of the present invention, which includes a blockchain network 600 (illustratively shown to include nodes 610-1 to 610-3), a server 200, a terminal 400, a list system 300, and a hospital information system 500, which are respectively described below.
The server 200, the chart system 300, and the hospital information system 500 may all be joined (mapped) to the blockchain network 600 as nodes (illustratively shown as including node 610-1 to node 610-3) therein, fig. 1b illustratively shows the chart system 300 mapped to node 610-1 of the blockchain network 600, the server 200 mapped to node 610-2 of the blockchain network 600, and the hospital information system 500 mapped to node 610-3 of the blockchain network 600, each node (e.g., node 610-1 to node 610-3) having a consensus function and a billing (i.e., maintaining a status database, such as a KV database) function.
The state database of each node (e.g., the node 610-1 to the node 610-3) records the list data of the list system 300, the detail pages of the hospital information system 500 and the content title data of the inquiry answers, so that the server 200 queries the data recorded in the state database to determine the authority of the doctor to be queried.
A user initiates an inquiry request in an inquiry page of a client 410 (e.g., APP, a browser or an applet), the client 410 (e.g., APP, browser or applet) sends the inquiry request initiated by the user (including an identifier of a doctor to be inquired) to the server 200, the server 200 has been mapped to a node 610-2 of the blockchain network 600, processing logic of an embodiment of the present invention for determining the authority of the doctor is invoked according to the inquiry request, a status database in the node 610-2 is queried, a hospital authority feature, a doctor job authority feature and a doctor specialty feature (to be stored in the status database for reuse) are determined, and the authority of the doctor to be inquired is determined according to the hospital authority feature, the doctor job authority feature and the doctor specialty feature.
The authority degree of the doctor to be queried, which is determined by the node 610-2, is sent to the node 610-1 mapped by the list system 300 and the node 610-3 mapped by the hospital information system 500 to perform consensus (i.e., a process of agreeing with the authority degree of the doctor to be queried), after the consensus is passed, the authority degree of the doctor to be queried is signed with the digital signatures of the list system 300, the hospital information system 500 and the server 200 and is returned to the client 410 (e.g., APP, browser or applet), and after the client 410 verifies that the digital signatures are successful, the authority degree is determined to be reliable and is used as reference information for selecting the doctor to be queried when the user makes a consultation.
In the embodiment of the invention, the block chain network comprises nodes of the list system, the hospital information system and the internet medical platform, and the reliability of data for calculating authority and the credibility of a calculation process can be ensured through a common recognition mechanism among the nodes.
The electronic device for doctor evaluation according to the embodiment of the present invention is described below, and the electronic device may be various terminal devices such as a smart phone, a desktop computer, a notebook computer, and a vehicle-mounted terminal, and may also be the server described above.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a server 200 of an internet medical platform according to an embodiment of the present invention, and the server 200 for doctor evaluation of the internet medical platform shown in fig. 2 includes: at least one processor 210, memory 240, and at least one network interface 220. The various components in server 200 are coupled together by a bus system 230. It is understood that the bus system 230 is used to enable connected communication between these components. The bus system 230 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 230 in fig. 2.
The Processor 210 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like, wherein the general purpose Processor may be a microprocessor or any conventional Processor, or the like.
The memory 240 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard disk drives, optical disk drives, and the like. Memory 240 optionally includes one or more storage devices physically located remote from processor 210.
The memory 240 includes either volatile memory or nonvolatile memory, and may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read Only Memory (ROM), and the volatile Memory may be a Random Access Memory (RAM). The memory 240 described in connection with embodiments of the present invention is intended to comprise any suitable type of memory.
In some embodiments, memory 240 is capable of storing data, examples of which include programs, modules, and data structures, or subsets or supersets thereof, to support various operations, as exemplified below.
An operating system 241, including system programs for handling various basic system services and performing hardware related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and handling hardware-based tasks;
a network communication module 242 for communicating to other computing devices via one or more (wired or wireless) network interfaces 220, exemplary network interfaces 220 including: bluetooth, wireless compatibility authentication (WiFi), and Universal Serial Bus (USB), etc.;
in some embodiments, the doctor evaluation device of the internet medical platform provided by the embodiments of the present invention may be implemented in software, and fig. 2 shows the doctor evaluation device 243 of the internet medical platform stored in the memory 240, which may be software in the form of programs and plug-ins, and includes the following software modules: a data acquisition module 2431 and a model calculation module 2432, which are logical and thus can be arbitrarily combined or further separated depending on the functions implemented. The functions of the respective modules will be explained below.
The following is a description of an example in which the server of the internet medical platform described above implements the doctor evaluation method of the internet medical platform provided in the embodiment of the present invention. Referring to fig. 3, fig. 3 is a flowchart of a doctor evaluation method for an internet medical platform according to an embodiment of the present invention, which can be applied to the server of the internet medical platform described above, and will be described with reference to the steps shown in fig. 3.
In step S101, according to the hospital ranking list data, hospital authority characteristics of a hospital to which a doctor who resides on the internet medical platform belongs are acquired.
In some embodiments, the server obtains, according to the hospital leaderboard data, hospital authority characteristics of a hospital to which a doctor who resides on the internet medical platform belongs, including: the hospitals to which the doctors belong are searched out from hospital ranking lists of different grades; determining the value of the hospital authority feature of the hospital to which the doctor belongs according to the ranking of the ranking list of the hospital to which the doctor belongs; wherein, the value of the authority degree characteristic of the hospital is positively correlated with the grade of the ranking list of the hospital where the hospital is. The positive correlation comprises a linear positive correlation and a non-linear positive correlation, and when the ranking of the leaderboard of the hospital is higher, the value of the authority feature of the hospital is larger.
As an example, referring to fig. 6, fig. 6 is a schematic diagram of ranking lists of three different levels provided by the embodiment of the present invention, where the ranking list of the level a is top100 famous hospitals in China, the ranking list of the level B is 100 strong hospitals in the local city level city, and the ranking list of the level C is 300 strong hospitals in other local city level hospitals. The server assigns different hospital authority level characteristics hospital _ level for the three hospitals with different levels A, B and C, and the values of the hospital authority level characteristics hospital _ level are alpha, beta and gama respectively. Wherein, alpha, beta and gama are arranged in descending order. The server finds out the hospitals to which the doctors belong from the hospital ranking lists with the three different grades A, B and C; and determining the value of the hospital authority feature hospital _ level given by the hospital to which the doctor belongs according to the grade of the hospital ranking list.
In step S102, doctor job title characteristics of the doctor are acquired.
In some embodiments, the server obtains doctor title characteristics for the doctor, including: acquiring a detail page of a doctor, and extracting the doctor job title of the doctor from the detail page; determining the value of the doctor job title characteristic of the doctor according to the grade of the doctor job title; wherein, the value of the hospital job title characteristic is positively correlated with the grade of the hospital job title.
Referring to fig. 7 by way of example, fig. 7 is a schematic diagram of doctor detail page information provided by an embodiment of the present invention, fig. 7 shows a doctor job title 303, and the server obtains the job title of the doctor by obtaining the doctor detail page information and extracting fields for representing the doctor job title in the doctor detail page information. And according to the value corresponding to the doctor job title level, giving the value of a doctor job level characteristic vector _ level.
By way of example, doctors can be generally classified into at least doctors, main doctors, assistant main doctors and main doctors according to their job title from low to high, and the higher the general grade means that the longer the time of the practitioner, the higher the authority.
In the embodiment of the invention, compared with the prior art that only the hospital to which the doctor belongs is taken as the reference information for evaluating the doctor and the job title level of the doctor is also taken into consideration, the reference information is more comprehensive and has higher reliability; the reference information of the doctor is obtained by acquiring the job title grade information of the doctor on the detail page, so that the evaluation process is more efficient and the evaluation result is more accurate.
In step S103, the doctor' S professional characteristics are determined according to the department in which the doctor is skilled.
In some embodiments, referring to fig. 4, fig. 4 is a flowchart illustrating a doctor evaluation method of an internet medical platform according to an embodiment of the present invention, and fig. 4 shows that step S103 in fig. 3 can be implemented by steps S1031 to S1033 shown in fig. 4. In step S1031, a department that the doctor excels in is acquired; in step S1032, determining an information amount of a corresponding doctor according to the statistical number of times of each type of department, and taking the information amount as a department concentration; in step S1033, a value of the characteristic of the professional degree of the doctor is determined according to the concentration degree of the department.
In some embodiments, a department that gains physician excellence comprises: the department that the doctor excels in is extracted from the doctor's detail page. For example, referring to fig. 8, fig. 8 is a schematic diagram of doctor detail page information provided by the embodiment of the present invention, fig. 8 shows a good department 301 and a good department 302, the server extracts fields characterizing doctor good departments from the doctor detail page, and the departments filled with the doctor registration can be obtained as two good departments: department of stomatology, department of internal medicine, and record the number of times that each type of good department is counted in the doctor's detail page as the number of times that each type of good department is counted, and count the doctor's detail page as the total number; determining a ratio between the number of statistics and the total number of types of good departments as a probability of good departments of each type; taking the probability of each type of the expert departments as weight, carrying out weighted summation on the information quantity of each type of the expert departments, and taking the weighted summation result as the information quantity of corresponding doctors; wherein the amount of information for each type of good department is a logarithm of the number of statistics for each type of good department, e.g., a base 2 logarithm; using the obtained information amount of the doctor as a department concentration degree department _ conc _ score; and determining the value of the doctor specialty characteristic vector _ prof _ score according to the department concentration department _ conc _ score.
It should be noted that, when some doctors register the third-party internet medical platform, if the field indicating the expert department does not completely mark the information of the department good for the doctor, or mark the content that the department information and the actual subsequently published medical information do not belong to the same department, the information published by the doctor and/or the content title of the question and answer can be collected, and the department intention of each information and/or content title of the question and answer can be identified by a supervised machine learning method, so as to obtain the department good for the doctor.
Accordingly, in other embodiments, obtaining a department that is good for a physician further comprises: matching all information and/or inquiry answers issued by the doctor in a period of time with keywords in the department knowledge graph, and taking the department corresponding to the matched keywords as the department good at the doctor. The corresponding relation between the keywords and departments is stored in the department knowledge graph in advance, when the server obtains information/inquiry answers issued by the doctor, the obtained medical contents are matched with the keywords in the department knowledge graph through simple and hard rules, according to the keywords obtained through matching, the departments corresponding to each piece of information and/or inquiry answer are found out in the corresponding relation of the department knowledge graph, and the departments to which each piece of information and/or inquiry answer of the doctor belongs are obtained. Recording the counted times of the doctor information and/or the inquiry answers of each type of the expert departments as the counted times of each type of the expert departments, and taking the count of the doctor information and/or the inquiry answers as the total number; determining a ratio between the number of statistics and the total number of each type of expert department as a probability of each type of expert department; taking the probability of each type of the expert departments as weight, carrying out weighted summation on the information quantity of each type of the expert departments, and taking the weighted summation result as the information quantity of corresponding doctors; wherein the amount of information for each type of good department is the logarithm of the number of statistics for each type of good department, e.g., the base 2 logarithm; taking the obtained information amount of the doctor as a department concentration degree department _ conc _ score; and determining the value of the doctor specialty characteristic vector _ prof _ score according to the department concentration department _ conc _ score.
In other examples, a department that gains physician excellence includes: and performing word segmentation processing on the information and/or inquiry answers issued by the doctor to extract keywords, calling a neural network model to perform classification processing on word vectors of the keywords, and obtaining departments associated with each piece of information and/or inquiry answer to serve as departments which the doctor excels in. Recording the counted times of the doctor information and/or the inquiry answers of each type of the expert departments as the counted times of each type of the expert departments, and taking the count of the doctor information and/or the inquiry answers as the total number; determining a ratio between the number of statistics and the total number of types of good departments as a probability of good departments of each type; taking the probability of each type of the adept departments as weight, carrying out weighted summation on the information quantity of each type of the adept departments, and taking the weighted summation result as the information quantity of corresponding doctors; wherein the amount of information for each type of good department is the logarithm of the number of statistics for each type of good department, e.g., the base 2 logarithm; using the obtained information amount of the doctor as a department concentration degree department _ conc _ score; and determining the value of the doctor specialty characteristic vector _ prof _ score according to the department concentration department _ conc _ score.
For example, referring to fig. 9, fig. 9 is a schematic structural diagram of a Neural Network model provided in the embodiment of the present invention, an input layer obtains Word vectors corresponding to N words in each piece of information and/or inquiry answer based on Word2vec, the Word vectors with a dimension of K pass through a convolutional layer, a pooling layer and a full-link layer, and finally, a department classification result of each piece of information and/or inquiry answer is output, the department classification result includes multiple department categories and confidence probabilities corresponding to the multiple department categories, and the department categories with the confidence probabilities exceeding confidence thresholds are used as departments associated with each piece of information and/or inquiry answer, where the Neural Network model may be a Text-CN N model or a deep learning classification model based on a Recurrent Neural Network (RNN), where N and K are positive integers.
As an example, the neural network model provided by the embodiment of the present invention classifies the department intentions based on Word2vec and Text-CNN models, and the neural network model is mainly divided into four layers:
1) An input layer: the layer mainly functions to encode each Word in the input natural language into a Word vector with uniform meaning dimension, for example, based on a vector computing tool Word2vec, the Word vector is constructed by constructing the text in the information and/or inquiry answer issued by the doctor, after the Word vector is constructed, all the Word vectors are spliced to form a two-dimensional matrix of n x K, wherein n represents the Word number of the keywords obtained by segmenting the information and/or inquiry answer issued by the doctor, and K represents the dimension of the vector.
The Word2vec algorithm performs Word segmentation on the information published by the doctor and/or the text of the inquiry answer to obtain a Word n, takes the Word in the context where the Word n is located as input, takes the Word n as output, and sets the position of the Word in the context appearing in the vocabulary to be 1, otherwise sets the position of the Word in the context to be 0, thereby mapping each Word after the Word segmentation of the information published by the doctor and/or the text of the inquiry answer into a numerical vector of a dimension K, such as an ith Word vector W in the information published by the doctor and/or the text of the inquiry answer shown in fig. 9 i ＝(W (i,1) ，W (i,2) ，…，W (i,K) ) Wherein W is (i,K) The word vector of the keyword after word segmentation processing is carried out on the information issued by a doctor and/or the text of the inquiry answer.
In order to perform model training on the information and/or inquiry responses issued by the doctor, vectorization processing needs to be performed on the information and/or inquiry response text issued by the doctor, so that vectorization representation of the information and/or inquiry response text issued by the doctor needs to be performed, that is, the above-mentioned process of converting into a numerical vector. Word2vec can reflect approximate relation of semanteme and co-occurrence frequency relation between words, and can convert words with close semanteme in information and/or inquiry answer text published by a doctor or words with higher co-occurrence frequency in the information and/or inquiry answer text published by the doctor into vectors with closer spatial positions, and the higher the similarity between the vectors is, the closer the semanteme is.
In the embodiment of the invention, a Word vector model with low dimensionality is generated through a Word2Vec model and is used for calculating the similarity between words; word2vec considers context, and can better represent Word similarity; the vector dimensionality obtained through Word2vec is less, so that the calculation cost of classification is lower, and the classification speed is higher; and Word2vec has strong universality and can be used in various Natural Language Processing (NLP) tasks.
2) And (3) rolling layers: this layer is mainly characterized by convolution processing. The input information and/or the inquiry answer text is converted into a two-dimensional matrix with the size of n x K after passing through the input layer, and the subsequent convolution operation is carried out on the two-dimensional matrix with the size of n x K. The size of the convolution kernel is generally set to t × K, t is the length of the convolution kernel, K is the width of the convolution kernel, and this width is set to be the same as the dimension of the word vector, and the convolution operation is performed only along the text sequence, where t may have various choices, such as 2, 3, 4, 5, and so on. In the Text-CNN model, multiple convolution kernels of different types can be used simultaneously, and there can be multiple convolution kernels of each type size.
3) Maximum pooling layer: and taking the maximum value of a plurality of vectors obtained after convolution, and then splicing the vectors into one block to be used as the output value of the layer. If the sizes of the convolution kernels are 2, 3, 4 and 5, and there are 1024 convolution kernels in each size, 4 × 1024 one-dimensional vectors are obtained after convolution and 4 × 1024 values are obtained after maximal pooling. The significance of the maximum pooling layer is to extract the most active features for the convolutional layer.
4) Full connection layer: used to integrate all the features obtained after pooling together to obtain a final structure with a 4096 x 1 feature vector. The last full connection layer is also connected with a classification system, the output value of the full connection layer is transmitted to the classification system, the classification system can adopt logistic regression softmax (softmax re regression) to classify the information and/or inquiry answer issued by the doctor, and the information and/or inquiry answer issued by the doctor is obtained to belong to the department type, so as to be used as the department good at the doctor. In order to improve the learning ability of the neural network model in the actual implementation process, a plurality of fully connected layers can be connected.
It should be noted that, when determining the department which the doctor excels in according to the detail pages or inquiry answers of the doctor, the statistical frequency of the department which the doctor excels in is +1, until all the detail pages and inquiry answers of the doctor are traversed, the statistical frequency of each type of department which the doctor excels in is obtained. Department concentration, specifically the amount of information of the doctor; the amount of information of the doctor is a result of weighted summation of the amount of information of each type of department that the doctor excels in.
For example, the department concentration profile may be as shown in equation (1):
department_conc_score(X)＝-∑ x∈X p(x)log 2 p(x) (1)
wherein x represents the type of department that the physician is skilled in; x represents the total number, i.e., the physician's detail page and/or the count of the inquiry answers; p (x) represents the probability of each type of good department, i.e. the ratio between the number of statistics and the total number of good departments per type.
And determining the value of a doctor specialty characteristic vector _ prof _ score according to the department concentration, wherein the vector _ prof _ score (i) = department _ con _ score (X).
In the embodiment of the invention, the department intentions are classified based on the Word2vec and Text-CNN models, so that the models are simple, the speed is higher, and departments which doctors are good at can be accurately classified.
In step 104, the hospital authority feature, the doctor job title feature and the doctor specialty feature are fused to obtain the doctor authority of the doctor.
In some embodiments, the fusing the hospital authority feature, the doctor job title feature, and the doctor specialty feature to obtain the doctor authority of the doctor comprises: taking a square value of the professional degree characteristics of the doctor, and calculating the reciprocal of the square value; and multiplying the hospital authority characteristic, the doctor title characteristic and the reciprocal of the square value of the doctor specialty characteristic, and taking the multiplication result as the doctor authority of the doctor.
For example, the physician authority may be as shown in equation (2):
Figure BDA0002537203010000171
wherein, square (sector _ prof _ score (i)) refers to the operation of squaring the professional characteristics of the doctor. It is worth explaining that, in order to increase the influence discrimination of the doctor specialty features on the final doctor authority value, the doctor specialty features are squared.
In some embodiments, based on the department information identified from the doctor's details page and the published questions and answers measuring the doctor's department concentration, different departments in the department concentration are weighted according to the feedback information published by the doctor for each department. For example, feedback information such as the number of times of approval and comment of the user on the inquiry response and the like is used as the weight of the doctor information amount according to the information published by each department, and the department concentration formula is updated through the obtained weight of the doctor information amount.
It should be noted that in some embodiments, the doctor's adept department may be predicted only by the department knowledge graph or the neural network model, and in other embodiments, the department knowledge graph or the neural network model may be combined with the department that the doctor is adept at extracting from the doctor detail page, that is, when no department information is extracted from the doctor detail page, the doctor's adept department may be predicted by the department knowledge graph or the neural network model. By the method of department knowledge map or neural network model prediction, even if department information is not extracted from the field of the detail page, the department which the doctor excels in can be accurately determined; and updating the weights of different types of departments adept in the department concentration ratio according to the feedback information, so that the evaluation information is more accurate.
In some embodiments, referring to fig. 5, fig. 5 is a flowchart of a doctor evaluation method of an internet medical platform according to an embodiment of the present invention, and based on fig. 3, after step S104, the following steps may be further performed:
in step S105, in response to the inquiry request, acquiring an inquiry answer corresponding to the inquiry request; wherein, the doctor authority value of the candidate doctor who issues the inquiry answer is larger than the authority threshold value;
in step S106, a plurality of candidate doctors and corresponding inquiry answers are displayed in an inquiry page.
In some embodiments, a terminal user opens an internet medical page to send an inquiry request, a server receives the inquiry request sent by the terminal user, acquires inquiry inquiries related to the inquiry request, acquires doctor authority degrees of doctors issuing the inquiry inquiries, selects doctors with the doctor authority degree values larger than an authority degree threshold value K as candidate doctors, and displays the candidate doctors and the internet medical pages of the inquiry answers corresponding to the candidate doctors when responding to the inquiry request. In the embodiment of the invention, the server can intelligently recommend doctors with high doctor authority and written inquiry answers according to inquiry requests of users, and by the mode, the internet medical platform can be kept to be obviously higher than the average level of other third-party internet medical platforms in the aspect of doctor authority.
According to the doctor evaluation method of the internet medical platform, provided by the embodiment of the invention, the doctor authority is considered from three dimensions of the hospital authority, the doctor title level and the department concentration, accurate evaluation information is provided for a doctor who resides in the internet medical platform, and an authoritative good doctor and issued content on a third-party internet medical platform can be carefully and accurately screened out according to the evaluation information.
In the following, an exemplary application of the embodiments of the present invention in a practical application scenario will be described.
The embodiment of the invention can be applied to an internet medical platform, for example, doctors screen, that is, medical contents of authoritative doctors are displayed for users, as shown in fig. 1a, a terminal 400 is connected with a server 200 (hereinafter, referred to as server 200) of the internet medical platform through a network, a client 410 (for example, a doctor APP) is installed on the terminal 400, the users visit the server 200 of the internet medical platform through the client 410 to perform inquiry, the internet medical platform sends inquiry requests sent by the users to the server 200 through the network, the server 200 executes a doctor evaluation method of the internet medical platform provided by the embodiment of the invention, evaluates doctors writing inquiry answers corresponding to the inquiry requests, predicts the authority degree of the doctors, selects the doctors with the authority degree larger than an authority degree threshold value as candidate doctors, and sends the candidate doctors and the corresponding inquiry answers to the client 410 for presentation.
Referring to fig. 10, fig. 10 is a schematic diagram of an inquiry page in an internet medical platform according to an embodiment of the present invention. Fig. 10 shows hospitals to which doctors who issue inquiry responses on the inquiry page belong, and it can be understood that the inquiry responses displayed on the inquiry page are issued by doctors in the third hospital. In the implementation process of the embodiment of the invention, the following relevant technologies are found: when the hospital where the resident doctor on the third-party internet medical platform belongs is a high-authority hospital, the doctor authority of the doctor is judged to be high, and the produced content authority is good. This method has at least three problems:
1) The first-line cities, provincial meetings, prefectures and counties which are wide in north and the like all have three hospitals, and are domestic three hospitals, and the doctor authority degrees of the internal doctors of the three hospitals in different regions are obviously different;
2) The experience and medical level of doctors in the same hospital at different job levels are different greatly;
3) Driven by the interest of third-party internet medical platforms, part of resident doctors may engage in medical information writing and inquiry activities inconsistent with the professional direction of their own expert departments in order to obtain higher exposure and platform stimulation, and doctors are not authoritative about medical contents published in non-professional fields.
In order to solve the problems, the embodiment of the invention adopts a doctor evaluation method of an internet medical platform, the doctor authority is considered from three dimensions of the hospital authority, the doctor job title level and the department concentration, accurate evaluation information is provided for a doctor who resides in the internet medical platform, and an authoritative good doctor and issued content on a third-party internet medical platform can be carefully and accurately screened out according to the evaluation information.
According to the doctor evaluation method of the internet medical platform, provided by the embodiment of the invention, the doctor authority is comprehensively obtained according to the hospital authority characteristic, the doctor title characteristic and the department concentration characteristic, accurate evaluation information is provided for a doctor who resides in the internet medical platform, and the authority of the doctor who resides in the internet medical platform can be carefully and accurately evaluated according to the evaluation information.
Aiming at the three problems of the related technology, the doctor evaluation method of the Internet medical platform provided by the embodiment of the invention classifies three corresponding characteristics, namely hospital authority characteristics, doctor title characteristics and doctor specialty characteristics.
1) According to the hospital chart accepted in the industry, the hospital chart that entered the compound medical chart and Ailisi hospital chart in the last 5 years is collected in the chart system, for example, referring to fig. 6, the ranking list of the a-level is top100 famous hospital in China, the ranking list of the grade B is 100 strong hospitals in the metro grade city, and the ranking list of the grade C is 300 strong hospitals in other metro grade hospitals. Three hospitals with three different levels of A, B and C are endowed with different hospital authority level characteristics hospital _ level, and the values of the hospital authority level characteristics are alpha, beta and gama. Wherein, alpha, beta and gama are arranged in descending order.
2) Referring to fig. 7, fig. 7 shows the doctor's job title 303, and doctors can be classified into at least a doctor, a primary doctor, a subordinate primary doctor and a primary doctor according to their job titles from low to high, wherein a higher general grade means that the longer the practitioner time, the higher the authority of the doctor. And extracting corresponding fields for representing the job titles of the doctors from the doctor detail page information by grabbing the doctor detail page information. And for the doctor job level feature vector _ level, giving the value of the doctor job level feature vector _ level according to the value corresponding to the doctor job title level.
3) Referring to fig. 8, in fig. 8, the more intensive departments 301 and 302 are shown, the more intensive departments the physician is skilled in, and the more intensive departments the published information/inquiry answer relates to, the more authoritative the physician is in the relevant field. The physician's good department set is determined by two steps of extraction + identification. The 'good' field in the doctor detail page is extracted, and then departments filled with the doctor registration, such as 'stomatology' and 'medical department', are identified to serve as departments good for the doctor.
Considering that some doctors register the third-party internet medical platform, the "good at" field does not completely mark department information, or marks that the department information and actual subsequently published medical information do not belong to the same department. Therefore, after identifying the detail page, it is necessary to collect all the information/content titles of the inquiry answers issued by the doctor, and identify the department intentions of each content title by the supervised machine learning method. For example, when performing department intent classification, the department category may be about 50 departments existing in the field of physicians, and is solved by using 50 classifiers. There are several implementations here: a. performing simple hard rule matching on all information/content titles of the inquiry answers issued by the doctor based on the artificial medical-department knowledge map to identify the department intentions related to all the information/content titles of the inquiry answers issued by the doctor; b. the method comprises the steps of manually labeling hundreds of positive sample data of each department intention in advance, randomly sampling the corresponding negative sample data of other department category positive sample data which do not belong to the department, then training a department intention classifier by using a deep learning model based on Word2vec Word vectors and a Text-CNN model proposed by Kim in 2013, and classifying information/inquiry answers issued by doctors based on the trained department intention classifier.
Referring to fig. 11, fig. 11 is a schematic diagram of partial inquiry answers issued by the doctor according to the embodiment of the present invention, and it can be known from the department classification model that the department skilled in the doctor also issues contents of departments such as "gynecology," "ophthalmology," "dermatology," and "endocrinology," in addition to the extracted "oral cavity" and "internal medicine" above. An information entropy algorithm is introduced to calculate department concentration characteristic of contents published by a doctor, the lower the entropy is, the higher the department concentration is, the more focused the doctor is, and the more authoritative the doctor is in the professional field.
The department concentration characteristic may be as shown in equation (1):
department_conc_score(X)＝-∑ x∈X p(x)log 2 p(x) (1)
wherein x represents the type of department that the physician is skilled in; x represents the total number, i.e., the physician's details page and/or the count of the inquiry answers; p (x) represents the probability of each type of good department, i.e. the ratio between the number of statistics and the total number of good departments per type.
And determining the value of a doctor specialty characteristic vector _ prof _ score according to the department concentration, wherein the vector _ prof _ score (i) = department _ conc _ score (X), and i represents a doctor identifier.
Based on the values calculated in 1), 2), 3), the authority factor _ auth _ score algorithm formula (2) of doctor i can be calculated as follows:
Figure BDA0002537203010000211
wherein, square (vector _ auth _ score (i)) refers to the operation of squaring the professional characteristics of the doctor. It is worth explaining that, in order to increase the influence discrimination of the doctor specialty features on the final doctor authority value, the doctor specialty features are squared.
Continuing with the exemplary structure of the implementation of the doctor evaluation device 243 of the internet medical platform provided by the embodiment of the present invention as a software module, in some embodiments, as shown in fig. 2, the software module stored in the doctor evaluation device 243 of the internet medical platform of the memory 240 may include:
the data acquisition module 2431 is configured to acquire hospital authority features of a hospital to which a doctor belongs according to the hospital ranking list data; acquiring doctor job title characteristics of the doctor; determining doctor specialty characteristics of the doctor according to the department information where the doctor is good at; and the model calculation module 2432 is configured to fuse the hospital authority characteristic, the doctor title characteristic and the doctor specialty characteristic to obtain the doctor authority of the doctor.
In the above scheme, the data collection module 2431 is further configured to find out a hospital to which the doctor belongs from hospital leaderboards of different grades; determining the value of the hospital authority feature of the hospital to which the doctor belongs according to the grade of the hospital ranking list of the hospital to which the hospital belongs; wherein the value of the hospital authority feature is positively correlated with the grade of the hospital ranking list where the hospital is located.
In the above scheme, the data acquisition module 2431 is further configured to obtain a detail page of the doctor, and extract a doctor's job title of the doctor from the detail page; determining the value of the doctor job title characteristic of the doctor according to the grade of the doctor job title; wherein the value of the hospital job title characteristic is positively correlated with the grade of the hospital job title.
In the above solution, the data acquisition module 2431 is further configured to obtain a department where the doctor is good at; determining the information amount corresponding to the doctor according to the statistical frequency of each type of department, and taking the information amount as a department concentration ratio; wherein the number of statistics is the number of times counted in the physician's details page and interview answers; and determining the value of the characteristic of the professional degree of the doctor according to the department concentration degree.
In the above solution, the data collecting module 2431 is further configured to obtain a department good for the doctor by at least one of the following manners: extracting a department which the doctor excels in from a detail page of the doctor; matching the inquiry answers issued by the doctors with keywords in a department knowledge graph, and taking departments corresponding to the matched keywords as departments which the doctors are good at; extracting keywords from the inquiry answers issued by the doctor, calling a neural network model to classify word vectors of the keywords to obtain departments associated with each inquiry answer, and taking the departments as departments which the doctor excels in.
In the foregoing solution, the data collecting module 2431 is further configured to determine a ratio between the statistical number of times of each type of department and the total number of departments, as a probability of each type of department; wherein the total number is a count of the physician's detail pages and interview answers; taking the probability of each type of department as weight, carrying out weighted summation on the information quantity of each type of department, and taking the weighted summation result as the information quantity corresponding to the doctor; wherein the information amount of each type of the departments is a logarithm of the statistical number of each type of the departments.
In the above solution, the model calculation module 2432 is further configured to take a square value of the professional degree feature of the doctor and calculate a reciprocal of the square value; and multiplying the hospital authority feature, the doctor title feature and the reciprocal of the square value of the doctor specialty feature, and taking the multiplication result as the doctor authority of the doctor.
In the above solution, an embodiment of the present invention provides a doctor evaluation device for an internet medical platform, further including: the response module is used for responding to the inquiry request and acquiring an inquiry answer corresponding to the inquiry request; wherein, the doctor authority value of the candidate doctor who gives the inquiry answer is larger than the authority threshold value; and the display module is used for displaying the candidate doctors and the corresponding inquiry answers in an inquiry page.
In the foregoing solution, an embodiment of the present invention provides a doctor evaluation apparatus for an internet medical platform, further including: a calling module, configured to store the hospital authority feature, the doctor title feature, and the doctor specialty feature in a state database of a blockchain network; invoking an intelligent contract in the blockchain network to cause the intelligent contract to perform the following: inquiring the hospital authority feature, the doctor title feature and the doctor professional feature of the doctor from the state database, and fusing to obtain the doctor authority of the doctor; and performing consensus processing on the doctor authority of the doctor, and returning the doctor authority of the doctor as a calling result when the consensus is passed.
Embodiments of the present invention provide a computer-readable storage medium having stored therein executable instructions that, when executed by a processor, cause the processor to perform a doctor evaluation method of an internet medical platform provided by embodiments of the present invention, for example, the method shown in fig. 3, 4 and 5.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.
In some embodiments, the executable instructions may be in the form of a program, software module, script, or code written in any form of programming language, including compiled or interpreted languages, or declarative or procedural languages, and it may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may, but need not, correspond to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
In conclusion, the authority of the doctor is determined according to the feature fusion of three dimensions of the hospital authority level, the doctor title feature and the doctor professional feature, and accurate evaluation information is provided for the doctor who resides in the internet medical platform, so that the detailed and accurate scoring of the authority of the doctor can be realized; moreover, the manual evaluation mode of a self-built doctor team and a review team is not needed, so that the evaluation efficiency and the coverage rate of doctors are improved; a server, a list system and a medical information system of the internet medical platform are added into the blockchain network to become nodes; the list data of the list system, the detailed pages of the medical information system and the content title data of the inquiry question and answer are synchronized into a state database of the block chain network in a consensus mode, and a server of the internet medical platform calls an intelligent contract of the block chain network in a transaction initiating mode so that the intelligent contract inquires the data in the block chain to calculate the authority of a doctor.
The above description is only an example of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present invention are included in the protection scope of the present invention.

Claims (10)

1. A doctor evaluation method of an internet medical platform, the method comprising:
according to the hospital ranking list data, acquiring hospital authority features of a hospital to which doctors residing on the Internet medical platform belong;
acquiring doctor job title characteristics of the doctor;
acquiring departments which are good at the doctor, determining the information amount corresponding to the doctor according to the counting times of each type of department, and taking the information amount as a department concentration ratio; the number of times is counted in the physician's details page and the interview answers; the department that obtains the doctor's excellence includes: obtaining the physician-good department by at least one of:
extracting a department which the doctor excels in from a detail page of the doctor;
matching the inquiry answers issued by the doctors with keywords in a department knowledge graph, and taking departments corresponding to the matched keywords as departments which the doctors are good at;
extracting keywords from the inquiry answers issued by the doctor, calling a neural network model to classify word vectors of the keywords to obtain departments associated with each inquiry answer, and taking the departments as departments which the doctor excels in;
determining doctor specialty characteristics of the doctor according to the department concentration;
and fusing the hospital authority feature, the doctor title feature and the doctor specialty feature to obtain the doctor authority of the doctor.
2. The method according to claim 1, wherein the obtaining the hospital authority characteristics of the hospital to which the doctor who resides on the internet medical platform belongs according to the hospital leaderboard data comprises:
searching out hospitals to which the doctors belong from hospital leaderboards of different grades;
determining the value of the hospital authority feature of the hospital to which the doctor belongs according to the grade of the hospital ranking list of the hospital to which the hospital belongs;
wherein the value of the hospital authority feature is positively correlated with the grade of the hospital ranking list where the hospital is located.
3. The method of claim 1, wherein the obtaining of doctor title characteristics of the doctor comprises:
acquiring a detail page of the doctor, and extracting the doctor job title of the doctor from the detail page;
determining the value of the doctor job title characteristic of the doctor according to the grade of the doctor job title;
wherein the value of the hospital job title characteristic is positively correlated with the grade of the hospital job title.
4. The method of claim 1, wherein said determining an amount of information corresponding to said doctor based on a statistical count of said departments of each type comprises:
determining a ratio between the statistical number of times and the total number of departments of each type as a probability of the departments of the each type;
wherein the total number is a count of the physician's detail pages and interview answers;
taking the probability of each type of department as weight, carrying out weighted summation on the information quantity of each type of department, and taking the weighted summation result as the information quantity corresponding to the doctor;
wherein the information amount of each type of department is a logarithm of the statistical number of times of each type of department.
5. The method of claim 1, wherein the fusing the hospital authority feature, the doctor job title feature, and the doctor expertise feature to obtain the doctor authority of the doctor comprises:
taking a square value of the professional degree characteristic of the doctor, and calculating the reciprocal of the square value;
and multiplying the hospital authority feature, the doctor title feature and the reciprocal of the square value of the doctor specialty feature, and taking the multiplication result as the doctor authority of the doctor.
6. The method according to any one of claims 1 to 5, further comprising:
responding to an inquiry request, and acquiring an inquiry answer corresponding to the inquiry request; wherein, the doctor authority value of the candidate doctor who gives the inquiry answer is larger than the authority threshold value;
displaying a plurality of the candidate physicians and the corresponding inquiry answers in an inquiry page.
7. The method according to any one of claims 1 to 5,
the hospital authority characteristic, the doctor title characteristic and the doctor specialty characteristic are stored in a state database of a blockchain network;
fusing the hospital authority feature, the doctor title feature and the doctor specialty feature to obtain the doctor authority of the doctor, including:
invoking an intelligent contract in the blockchain network to cause the intelligent contract to perform the following:
inquiring the hospital authority feature, the doctor title feature and the doctor professional feature of the doctor from the state database, and fusing to obtain the doctor authority of the doctor;
and performing consensus processing on the doctor authority of the doctor, and returning the doctor authority of the doctor as a calling result when the consensus is passed.
8. A doctor evaluation device of an internet medical platform, comprising:
a data acquisition module to:
according to the hospital ranking list data, acquiring hospital authority features of a hospital to which doctors residing on the Internet medical platform belong;
acquiring doctor title characteristics of the doctor;
acquiring departments which the doctors are good at, determining information quantity corresponding to the doctors according to the counting times of each type of department, and taking the information quantity as department concentration; the statistical number is the number counted in the doctor's detail page and inquiry answer; the department that obtains the doctor's excellence includes: obtaining a department that the physician excels in by at least one of:
extracting a department which the doctor excels in from a detail page of the doctor;
matching the inquiry answers issued by the doctor with keywords in a department knowledge graph, and taking departments corresponding to the matched keywords as departments which are good at the doctor;
extracting keywords from the inquiry answers issued by the doctor, calling a neural network model to classify word vectors of the keywords to obtain departments associated with each inquiry answer, and taking the departments as departments which the doctor excels in;
determining doctor specialty characteristics of the doctor according to the department concentration;
a model calculation module to:
and fusing the hospital authority feature, the doctor title feature and the doctor specialty feature to obtain the doctor authority of the doctor.
9. An electronic device for physician evaluation of an internet medical platform, comprising:
a memory for storing executable instructions;
a processor for implementing the doctor evaluation method of the internet medical platform of any one of claims 1 to 7 when executing the executable instructions stored in the memory.
10. A computer readable storage medium storing executable instructions for implementing the doctor assessment method of the internet medical platform of any one of claims 1 to 7 when executed by a processor.
CN202010536388.2A 2020-06-12 2020-06-12 Doctor evaluation method and device of Internet medical platform Active CN111696656B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010536388.2A CN111696656B (en) 2020-06-12 2020-06-12 Doctor evaluation method and device of Internet medical platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010536388.2A CN111696656B (en) 2020-06-12 2020-06-12 Doctor evaluation method and device of Internet medical platform

Publications (2)

Publication Number Publication Date
CN111696656A CN111696656A (en) 2020-09-22
CN111696656B true CN111696656B (en) 2023-04-07

Family

ID=72480684

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010536388.2A Active CN111696656B (en) 2020-06-12 2020-06-12 Doctor evaluation method and device of Internet medical platform

Country Status (1)

Country Link
CN (1) CN111696656B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112259215A (en) * 2020-10-22 2021-01-22 海南亿保医药科技有限公司 Method, device and equipment for processing inquiry request
CN112508636B (en) * 2020-11-03 2023-01-24 上海财经大学 Skin care product recommendation method
CN116646065B (en) * 2023-05-25 2024-03-19 浙江蕙康科技有限公司 Internet hospital data security management method and device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109377091A (en) * 2018-11-21 2019-02-22 北京春雨天下软件有限公司 Doctor's evaluation method and device based on medical treatment & health platform
CN109920508A (en) * 2018-12-28 2019-06-21 安徽省立医院 prescription auditing method and system
CN110491490A (en) * 2019-07-11 2019-11-22 深圳市翩翩科技有限公司 A kind of doctor's appraisal procedure and device

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130073344A1 (en) * 2011-04-19 2013-03-21 Karen Parent Method and system of function analysis for optimizing productivity and performance of a workforce within a workspace

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109377091A (en) * 2018-11-21 2019-02-22 北京春雨天下软件有限公司 Doctor's evaluation method and device based on medical treatment & health platform
CN109920508A (en) * 2018-12-28 2019-06-21 安徽省立医院 prescription auditing method and system
CN110491490A (en) * 2019-07-11 2019-11-22 深圳市翩翩科技有限公司 A kind of doctor's appraisal procedure and device

Also Published As

Publication number Publication date
CN111696656A (en) 2020-09-22

Similar Documents

Publication Publication Date Title
EP3985578A1 (en) Method and system for automatically training machine learning model
US10402379B2 (en) Predictive search and navigation for functional information systems
US10599623B2 (en) Matching multidimensional projections of functional space
CN111696656B (en) Doctor evaluation method and device of Internet medical platform
US20200379958A1 (en) Dynamic syntactic affinity group formation in a high-dimensional functional information system
CN111708949B (en) Medical resource recommendation method and device, electronic equipment and storage medium
CN110765301B (en) Picture processing method, device, equipment and storage medium
CN114238573B (en) Text countercheck sample-based information pushing method and device
CN111723292A (en) Recommendation method and system based on graph neural network, electronic device and storage medium
CN111429161B (en) Feature extraction method, feature extraction device, storage medium and electronic equipment
CN115659008A (en) Information pushing system and method for big data information feedback, electronic device and medium
Hu et al. A practice mining system for the delivery of sustainable retirement villages
CN114330482A (en) Data processing method and device and computer readable storage medium
CN113705698A (en) Information pushing method and device based on click behavior prediction
CN111403011B (en) Registration department pushing method, device and system, electronic equipment and storage medium
Nguyen et al. Estimating county health indices using graph neural networks
US20150339602A1 (en) System and method for modeling health care costs
CN112084408B (en) List data screening method, device, computer equipment and storage medium
Rama Satish et al. A framework for big data pre-processing and search optimization using HMGA-ACO: a hierarchical optimization approach
TWI419071B (en) Active knowledge management system, method and computer program product for problem solving
CN111460300A (en) Network content pushing method and device and storage medium
CN114610921B (en) Object cluster portrait determination method, device, computer equipment and storage medium
Aiza et al. Features, techniques and evaluation in predicting articles’ citations: a review from years 2010–2023
Kavitha et al. Zero shot image classification system using an optimized generalized adversarial network
CN114298118B (en) Data processing method based on deep learning, related equipment and storage medium

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
GR01 Patent grant
GR01 Patent grant