CN114416967A

CN114416967A - Method, device and equipment for intelligently recommending doctors and storage medium

Info

Publication number: CN114416967A
Application number: CN202210091349.5A
Authority: CN
Inventors: 欧阳强
Original assignee: Ping An International Smart City Technology Co Ltd
Current assignee: Shenzhen Ping An Smart Healthcare Technology Co ltd
Priority date: 2022-01-26
Filing date: 2022-01-26
Publication date: 2022-04-29

Abstract

The invention relates to artificial intelligence, and provides a method, a device, equipment and a storage medium for intelligently recommending doctors. The method includes the steps of collecting medical record data of historical patients, wherein the medical record data comprises information of diagnosticians of the historical patients, classifying the historical patients according to the medical record data to obtain historical patient categories, generating diagnosis and treatment capability information of the diagnosticians according to diagnosis quantity of the diagnosticians in a plurality of historical patient categories, obtaining dimension information of the diagnosticians in a plurality of preset dimensions, generating a recommendation index of the diagnosticians in each historical patient category according to the dimension information and the diagnosis and treatment capability information, identifying a target user category where a target user is located according to a signing request, recommending the diagnosticians to the target user according to the recommendation index and the target user category, and improving recommendation accuracy of the signing doctors. Furthermore, the invention also relates to a block chain technology, and the recommendation index can be stored in the block chain.

Description

Method, device and equipment for intelligently recommending doctors and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a method, a device, equipment and a storage medium for intelligently recommending doctors.

Background

With the development of artificial intelligence, ways to recommend doctors to users also come along. Through recommending doctors to the user intelligence, the method can assist the user to find suitable doctors for signing quickly. However, in these doctor intelligent recommendation methods, the contracting doctor suitable for the user still cannot be accurately determined.

Therefore, how to accurately recommend a proper contracted doctor to a user becomes a problem which needs to be solved urgently.

Disclosure of Invention

In view of the above, there is a need to provide a method, an apparatus, a device and a storage medium for intelligently recommending doctors, which can accurately recommend suitable contracting doctors to users.

In one aspect, the present invention provides a method for intelligently recommending doctors, including:

acquiring medical record data of a historical patient, wherein the medical record data comprises information of a diagnostician of the historical patient;

classifying the historical patients according to the medical record data to obtain the historical patient categories of the historical patients;

counting the diagnosis quantity of the diagnostician in a plurality of historical patient categories according to the historical patients, and generating diagnosis and treatment capability information of the diagnostician in each historical patient category according to the diagnosis quantity;

acquiring dimension information of the diagnostician on a plurality of preset dimensions;

generating a recommendation index of the diagnostician on each historical patient category according to the dimension information and the diagnosis and treatment capability information;

when a signing request is received, identifying the type of a target user where the target user is located according to the signing request;

and recommending the diagnostician to the target user according to the recommendation index and the target user category.

According to a preferred embodiment of the present invention, the acquiring medical record data of the historical patient comprises:

receiving authorization feedback information sent by the historical patient;

extracting a patient identification code and a secret key from the authorization feedback information;

acquiring ciphertext information from a preset medical system based on the patient identification code;

and decrypting the ciphertext information according to the secret key to obtain the medical record data.

According to a preferred embodiment of the present invention, the classifying the historical patients according to the medical record data to obtain the historical patient categories of the historical patients includes:

acquiring a pre-trained crowd classification model, wherein the crowd classification model comprises a basic classification network, a disease entity extraction network and a semantic analysis network, the basic classification network is generated according to a first field, the disease entity extraction network is generated according to a second field, and the semantic analysis network is generated according to a third field;

extracting first information from the medical record data according to the first field;

acquiring a basic mapping table from the basic classification network, and acquiring a category corresponding to the first information as a first category based on the basic mapping table;

extracting second information from the medical record data according to the second field, and extracting disease information from the second information based on the disease entity extraction network;

acquiring a disease category mapping table from the crowd classification model;

calculating the disease similarity of the disease information and each preset disease in the disease category mapping table, and determining the category corresponding to the preset disease with the largest disease similarity as a second category;

extracting third information from the medical record data according to the third field, and processing the third information based on the semantic analysis network to obtain a target symptom;

detecting whether the target symptom is present in the second category;

determining the first category and the second category as the historic patient category if the target symptom is present in the second category.

According to a preferred embodiment of the present invention, if said target symptom is not present in said second category, said method further comprises:

acquiring a category corresponding to the target symptom from the disease category mapping table as a third category;

acquiring the training users of the third category from a preset user library;

counting the number of users including the target symptom in the training users, and counting the total training amount of the training users;

calculating the ratio of the number of the users in the training total amount to obtain the symptom probability of the target symptom;

acquiring a first prediction weight of the disease entity extraction network and a second prediction weight of the semantic analysis network from the crowd classification model;

calculating the product of the disease similarity of the second category and the first prediction weight to obtain a first score of the second category, and calculating the product of the symptom probability and the second prediction weight to obtain a second score of the third category;

selecting a category corresponding to the score larger than a preset threshold value from the first score and the second score as a screening category;

determining the screening category and the first category as the historical patient category.

According to a preferred embodiment of the present invention, the counting the number of diagnoses of the diagnostician in a plurality of historical patient categories according to the historical patients, and generating the diagnosis and treatment capability information of the diagnostician in each historical patient category according to the number of diagnoses includes:

counting the number of the diagnosticians dealing with each of the historical patient categories as the diagnosis number based on the historical patients;

counting the total number of patients of the historical patients in each historical patient category;

and calculating the ratio of the total amount of the patients to the diagnosis number to obtain the diagnosis and treatment capacity information.

According to a preferred embodiment of the present invention, the dimension information includes a work saturation level and a plurality of feedback information of the diagnostician, and the generating a recommendation index of the diagnostician in each of the historical patient categories according to the dimension information and the clinical ability information includes:

determining the diagnosticians with the working saturation greater than or equal to the configuration saturation as non-idle diagnosticians, and determining the diagnosticians with the working saturation less than the configuration saturation as idle diagnosticians;

determining a recommendation index of the non-idle doctor on the each historical patient category as an initial value;

acquiring a first index weight corresponding to the diagnosis and treatment capability information, and acquiring second index weights corresponding to the preset dimensions, wherein the first index weight is larger than the second index weights;

generating the recommendation index according to the dimension information, the diagnosis and treatment capability information, the first index weight and the second index weight, including:

n>1；

wherein y is the recommendation index, a₁Is the first index weight, a₂…a_tIs a plurality of the second index weights, x₁Refers to the diagnosis and treatment ability information, x₂…x_tRefers to the plurality of feedback information, and n refers to the operating saturation.

According to a preferred embodiment of the present invention, when the target user category includes a plurality of categories, the recommending the diagnostician to the target user according to the recommendation index and the target user category includes:

acquiring user information of the target user;

processing the user information based on a pre-trained severity prediction model to obtain the category severity of the target user in each target user category;

carrying out normalization processing on the category severity to obtain a recommended weight of each target user category;

generating a recommendation total score of the diagnostician according to the recommendation weight and the recommendation index;

selecting a target doctor from the diagnosticians according to the recommendation total score;

recommending the target doctor to the target user.

In another aspect, the present invention further provides an apparatus for intelligently recommending doctors, including:

the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring medical record data of a historical patient, and the medical record data comprises information of a diagnostician of the historical patient;

the classification unit is used for classifying the historical patients according to the medical record data to obtain the historical patient categories of the historical patients;

the generation unit is used for counting the diagnosis number of the diagnostician in a plurality of historical patient categories according to the historical patients and generating diagnosis and treatment capacity information of the diagnostician in each historical patient category according to the diagnosis number;

the acquisition unit is used for acquiring dimension information of the diagnostician on a plurality of preset dimensions;

the generating unit is further used for generating a recommendation index of the diagnostician on each historical patient category according to the dimension information and the diagnosis and treatment capability information;

the identification unit is used for identifying the type of a target user where the target user is located according to a signing request when the signing request is received;

and the recommending unit is used for recommending the diagnostician to the target user according to the recommendation index and the target user category.

In another aspect, the present invention further provides an electronic device, including:

a memory storing computer readable instructions; and

a processor executing computer readable instructions stored in the memory to implement the intelligent doctor recommending method.

In another aspect, the present invention further provides a computer-readable storage medium, in which computer-readable instructions are stored, and the computer-readable instructions are executed by a processor in an electronic device to implement the method for intelligently recommending doctors.

According to the technical scheme, the historical patient categories of the historical patients can be accurately determined through the medical record data, diagnosis and treatment capacity information of the diagnosticians on each historical patient category can be accurately quantized according to the diagnosis quantity, and the recommendation indexes of the diagnosticians on each historical patient category can be accurately generated by combining the dimension information and the diagnosis and treatment capacity information, so that the recommendation accuracy of the contracting doctors is improved.

Drawings

FIG. 1 is a flow chart of a preferred embodiment of the method for intelligently recommending doctors of the present invention.

FIG. 2 is a functional block diagram of a preferred embodiment of the intelligent recommender apparatus of the present invention.

FIG. 3 is a schematic structural diagram of an electronic device according to a preferred embodiment of the method for intelligently recommending doctors in accordance with 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 described in detail with reference to the accompanying drawings and specific embodiments.

FIG. 1 is a flow chart of a preferred embodiment of the method for intelligently recommending doctors according to the present invention. The order of the steps in the flow chart may be changed and some steps may be omitted according to different needs.

The method for intelligently recommending doctors can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

The method for intelligently recommending doctors is applied to one or more electronic devices, which are devices capable of automatically performing numerical calculation and/or information processing according to computer readable instructions set in advance or stored in advance, and the hardware thereof includes but is not limited to a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.

The electronic device may be any electronic product capable of performing human-computer interaction with a user, for example, a Personal computer, a tablet computer, a smart phone, a Personal Digital Assistant (PDA), a game machine, an interactive Internet Protocol Television (IPTV), a smart wearable device, and the like.

The electronic device may include a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network electronic device, an electronic device group consisting of a plurality of network electronic devices, or a Cloud Computing (Cloud Computing) based Cloud consisting of a large number of hosts or network electronic devices.

The network in which the electronic device is located includes, but is not limited to: the internet, a wide area Network, a metropolitan area Network, a local area Network, a Virtual Private Network (VPN), and the like.

And S10, acquiring medical record data of the historical patient, wherein the medical record data comprises information of a diagnostician of the historical patient.

In at least one embodiment of the present invention, the historic patient refers to a patient who has completed a visit. The diagnostician refers to a doctor who diagnoses the historic patient.

In at least one embodiment of the invention, the electronic device acquiring medical record data of a historic patient comprises:

receiving authorization feedback information sent by the historical patient;

Wherein the authorization feedback information refers to a result generated by the historical patient trigger.

The patient identifier is used to indicate the historic patient, and the key may be information set by the historic patient.

The preset medical system stores relevant information of a plurality of patients with clinic records.

The ciphertext information is generated by encrypting the medical record which is stored in the preset medical system by the user and corresponds to the patient identification code.

The collection validity of the medical record data can be ensured through the authorization feedback information, and the medical record data can be accurately obtained through the patient identification code and the secret key.

And S11, classifying the historical patients according to the medical record data to obtain the historical patient categories of the historical patients.

In at least one embodiment of the invention, the historic patient categories include categories of healthy people, chronic diseases, elderly people, infants, pregnant women, severe mental disorders, tuberculosis, disabled people, and the like.

In at least one embodiment of the present invention, the electronic device classifies the historical patient according to the medical record data, and obtaining the historical patient category of the historical patient includes:

acquiring a disease category mapping table from the crowd classification model;

detecting whether the target symptom is present in the second category;

Wherein, the first field refers to the basic fields of age, gender and the like.

The base mapping table stores mapping relationships between a plurality of field information and categories, for example, the base mapping table may include a child category: age 0 to 12 years, young and strong: age 13-60, elderly: age greater than 60, etc.

The second field refers to a field of a medical history, family history, or the like, which directly corresponds to a disease entity.

The disease category mapping table stores mapping relations between a plurality of categories and preset diseases. For example, the disease category mapping table may include, tuberculosis categories: primary pulmonary tuberculosis, blood type disseminated pulmonary tuberculosis, secondary pulmonary tuberculosis, tuberculous pleurisy, etc.

The third field refers to a field related to sign entities such as symptoms.

The first category corresponding to the first information can be accurately determined through the basic mapping table, the problem that the second category cannot be accurately determined due to the fact that any disease contains a plurality of scientific names can be avoided by calculating the similarity of the diseases, and further the key information in the third information can be accurately extracted through the semantic analysis network, so that the determination efficiency of the historical patient category is improved.

In at least one embodiment of the present invention, if the target symptom is not present in the second category, the method further comprises:

acquiring the training users of the third category from a preset user library;

Wherein, the disease category mapping table further comprises mapping relations between a plurality of categories and disease symptoms.

The preset user library comprises relevant illness data of the training users.

The symptom probability refers to the probability that the trained users of the third category suffer from the target symptom.

The first prediction weight and the second prediction weight are generated according to the learning rate adjustment of the crowd classification model.

The preset threshold may be set according to requirements, for example, the preset threshold may be 0.8. It is understood that, when both the first score and the second score are greater than the preset threshold, both the second category and the third category are the screening categories.

The symptom probability that the third category has the target symptom can be rapidly determined by carrying out symptom analysis on the training users of the third category, the first score and the second score can be accurately determined according to the first prediction weight and the second prediction weight in the crowd classification model, and the situation that the historical patient category to which the historical patient having multiple disease categories simultaneously belongs can not be comprehensively and accurately determined by comparing the first score and the second score with the preset threshold value can be avoided.

And S12, counting the diagnosis number of the diagnostician in a plurality of historical patient categories according to the historical patients, and generating diagnosis and treatment capacity information of the diagnostician in each historical patient category according to the diagnosis number.

In at least one embodiment of the present invention, the clinical capability information is used to characterize the diagnosis of the diagnostician on each of the historical patient categories.

In at least one embodiment of the present invention, the electronic device counts the number of diagnoses of the diagnostician in a plurality of historical patient categories according to the historical patients, and generates the diagnosis and treatment capability information of the diagnostician in each historical patient category according to the number of diagnoses includes:

Through the implementation mode, the diagnosis and treatment capability information of the diagnostician on each historical patient category can be rapidly quantized.

And S13, acquiring dimension information of the diagnostician on a plurality of preset dimensions.

In at least one embodiment of the invention, the preset dimensions comprise work saturation conditions, signed service feedback evaluation, physician adept treatment crowd self-evaluation, crowd classification willingness management conditions and the like.

In at least one embodiment of the present invention, the electronic device obtains information corresponding to the plurality of preset dimensions from an information knowledge base based on the doctor identification code as the dimension information.

And S14, generating a recommendation index of the diagnostician on each historical patient category according to the dimension information and the diagnosis and treatment capability information.

In at least one embodiment of the present invention, the recommendation index refers to a quantification of the match of the diagnostician to each of the historical patient categories.

It is emphasized that the recommendation index may also be stored in a node of a blockchain in order to further ensure privacy and security of the recommendation index.

In at least one embodiment of the present invention, the dimension information includes a work saturation level of the diagnostician and a plurality of feedback information, and the generating, by the electronic device, the recommendation index of the diagnostician in each of the historical patient categories according to the dimension information and the clinical capability information includes:

n>1；

Wherein the work saturation is a measure of the work assignment of the diagnostician.

The plurality of feedback information may include: the historical patient's feedback evaluation of contracted service to the diagnostician, the diagnostician's ability to personally specialize in the treatment population, the diagnostician's willingness to the category in which the service population is located, and the like.

The configuration saturation can be set according to actual conditions.

The initial value is typically set to 0. It will be appreciated that no recommendations are made to the user for the non-idle doctor.

The non-idle doctor and the idle doctor can be quickly divided through the configuration saturation, so that the recommendation index of the non-idle doctor can be quickly determined, and the reasonable recommendation index can be accurately determined through setting of the first index weight and the second index weights.

And S15, when receiving the signing request, identifying the target user type of the target user according to the signing request.

In at least one embodiment of the present invention, the subscription request may be triggered and generated by a user having a subscription requirement. The subscription request carries user information related to the target user.

In at least one embodiment of the present invention, the identifying, by the electronic device, the target user category in which the target user is located according to the subscription request includes:

acquiring user information of the target user according to the signing request;

and classifying the target users according to the user information to obtain the target user category.

Specifically, the manner in which the electronic device classifies the target user according to the user information is similar to the manner in which the electronic device classifies the historical patient according to the medical record data, which is not described in detail herein.

And S16, recommending the diagnostician to the target user according to the recommendation index and the target user category.

In at least one embodiment of the present invention, when the target user category includes a plurality of categories, the recommending, by the electronic device, the diagnostician to the target user according to the recommendation index and the target user category includes:

acquiring user information of the target user;

recommending the target doctor to the target user.

Wherein the user information may be information related to the health of the target user.

The severity prediction model is used to predict the patient severity of the user in each of the target user categories. The severity prediction model can be generated based on deep learning training, and the specific training mode of the severity prediction model is not limited by the invention.

The target doctor is the diagnostician with the highest total score of the recommendation. It will be appreciated that the overall recommendation score for the same diagnostician may vary from user to user.

For example, the plurality of target user categories include: the "severe mental disorder" label, the "tuberculosis" label, the "maternal" label, the diagnostician and recommendation index of which include, doctor a: 0.85, doctor B: 0.65, doctor C: 0.50, doctor D: 0.20, the diagnostician and recommendation index of the "tuberculosis" label includes: and a doctor B: 0.75, doctor C: 0.35, doctor A: 0.15, doctor D: 0.10, diagnostician and recommendation index for the "maternal" label includes: and a doctor D: 0.65, doctor C: 0.55, doctor A: 0.45, doctor B: 0.25, the user information is processed and normalized by the severity prediction model, the recommended weight of the severe mental disorder label is 0.4, the recommended weight of the tuberculosis label is 0.35, the recommended weight of the pregnant and lying-in woman label is 0.25, and the recommendation of the doctor A is calculated as follows:

0.85 × 0.4+0.15 × 0.35+0.45 × 0.25 ═ 0.505, and the total recommended score for doctor B was:

0.65 × 0.4+0.75 × 0.35+0.25 × 0.25 ═ 0.585, the recommended overall score for doctor C:

0.50 × 0.4+0.35 × 0.35+0.55 × 0.25 ═ 0.46, the total recommendation from doctor D was: 0.20 × 0.4+0.10 × 0.35+0.65 × 0.25 ═ 0.2775, then the target physician is physician B.

The category severity of the target user in each target user category can be accurately predicted through the severity prediction model, so that the recommendation total score of the user to be recommended for the target user can be accurately determined, and the recommendation accuracy of the target doctor is improved.

In at least one embodiment of the invention, the method further comprises:

acquiring recommendation response information based on the signing request, and receiving recommendation feedback of the target user to the recommendation response information;

identifying emotional information of the recommendation feedback;

counting the feedback quantity of recommended feedback corresponding to the negative feedback category of the emotion information;

and when the feedback quantity is greater than a preset quantity, adjusting the first index weight and the plurality of second index weights.

The recommendation response information refers to a response generated by the electronic device based on the subscription request, and it can be understood that the recommendation response information includes: and recommending the relevant information of the target doctor to the target user.

The emotional information may include emotions such as happy feeling, angry feeling, and the like.

The negative feedback categories include negative emotions such as anger, difficulty and the like.

The preset number can be set according to the requirement on the recommendation effect.

By identifying the emotion information, the feedback quantity can be accurately determined, and the first index weight and the plurality of second index weights are dynamically adjusted according to the feedback quantity, so that the recommendation effect is improved.

FIG. 2 is a functional block diagram of the preferred embodiment of the device for intelligently recommending doctors according to the present invention. The device 11 for intelligently recommending doctors comprises an acquisition unit 110, a classification unit 111, a generation unit 112, an acquisition unit 113, an identification unit 114, a recommendation unit 115, an adjustment unit 116, a statistic unit 117, a calculation unit 118, a selection unit 119 and a determination unit 120. The module/unit referred to herein is a series of computer readable instruction segments that can be accessed by the processor 13 and perform a fixed function and that are stored in the memory 12. In the present embodiment, the functions of the modules/units will be described in detail in the following embodiments.

The acquisition unit 110 acquires medical record data of a historic patient, wherein the medical record data comprises information of a diagnostician of the historic patient.

In at least one embodiment of the present invention, the acquiring unit 110 for acquiring medical record data of historical patients comprises:

receiving authorization feedback information sent by the historical patient;

The classification unit 111 classifies the historical patients according to the medical record data to obtain the historical patient categories of the historical patients.

In at least one embodiment of the present invention, the classifying unit 111 classifies the historical patient according to the medical record data, and obtaining the historical patient category of the historical patient includes:

acquiring a disease category mapping table from the crowd classification model;

detecting whether the target symptom is present in the second category;

The third field refers to a field related to sign entities such as symptoms.

In at least one embodiment of the present invention, if the target symptom does not exist in the second category, the obtaining unit 113 obtains a category corresponding to the target symptom from the disease category mapping table as a third category;

the obtaining unit 113 obtains the training users of the third category from a preset user library;

the counting unit 117 counts the number of users including the target symptom among the training users, and counts the total training amount of the training users;

the calculating unit 118 calculates a ratio of the number of users in the training total to obtain a symptom probability of the target symptom;

the obtaining unit 113 obtains a first prediction weight of the disease entity extraction network and a second prediction weight of the semantic analysis network from the crowd classification model;

the calculating unit 118 calculates a product of the disease similarity of the second category and the first prediction weight to obtain a first score of the second category, and calculates a product of the symptom probability and the second prediction weight to obtain a second score of the third category;

the selecting unit 119 selects a category corresponding to a score greater than a preset threshold from the first score and the second score as a screening category;

the determination unit 120 determines the screening category and the first category as the historical patient category.

The preset user library comprises relevant illness data of the training users.

The generation unit 112 counts the number of diagnoses of the diagnostician in a plurality of the historical patient categories based on the historical patients, and generates the diagnosis and treatment ability information of the diagnostician in each of the historical patient categories based on the number of diagnoses.

In at least one embodiment of the present invention, the generating unit 112 counts the diagnosis number of the diagnostician in a plurality of the historical patient categories according to the historical patients, and generates the diagnosis and treatment capability information of the diagnostician in each of the historical patient categories according to the diagnosis number includes:

The acquisition unit 113 acquires dimension information of the diagnostician in a plurality of preset dimensions.

In at least one embodiment of the present invention, the obtaining unit 113 obtains information corresponding to the plurality of preset dimensions from an information knowledge base based on the doctor identification code as the dimension information.

The generating unit 112 generates a recommendation index of the diagnostician for each of the historical patient categories according to the dimension information and the clinical ability information.

In at least one embodiment of the present invention, the dimension information includes a work saturation level of the diagnostician and a plurality of feedback information, and the generating unit 112 generates the recommendation index of the diagnostician in each of the historical patient categories according to the dimension information and the clinical capability information includes:

n>1；

The configuration saturation can be set according to actual conditions.

When receiving a subscription request, the identifying unit 114 identifies a target user category in which a target user is located according to the subscription request.

In at least one embodiment of the present invention, the identifying unit 114, according to the subscription request, identifies a target user category in which a target user is located, including:

acquiring user information of the target user according to the signing request;

and carrying out crowd classification on the target user according to the user information to obtain the target user category.

Specifically, the manner in which the identification unit 114 classifies the target user according to the user information is similar to the manner in which the classification unit 111 classifies the historical patient according to the medical record data, which is not described in detail herein.

The recommending unit 115 recommends the diagnosing doctor to the target user according to the recommendation index and the target user category.

In at least one embodiment of the present invention, when the target user category includes a plurality of categories, the recommending unit 115 recommends the diagnostician to the target user according to the recommendation index and the target user category includes:

acquiring user information of the target user;

recommending the target doctor to the target user.

0.50 × 0.4+0.35 × 0.35+0.55 × 0.25 ═ 0.46, the total recommendation from doctor D was:

0.20 × 0.4+0.10 × 0.35+0.65 × 0.25 ═ 0.2775, then the target physician is physician B.

In at least one embodiment of the present invention, the obtaining unit 113 obtains recommendation response information based on the subscription request, and receives recommendation feedback of the target user to the recommendation response information;

the recognition unit 114 recognizes emotion information of the recommendation feedback;

the counting unit 117 counts the feedback quantity of the recommended feedback corresponding to the negative feedback category of the emotion information;

when the feedback number is greater than the preset number, the adjusting unit 116 adjusts the first index weight and the plurality of second index weights.

In one embodiment of the present invention, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and computer readable instructions, such as a method program for an intelligent recommender, stored in the memory 12 and executable on the processor 13.

It will be appreciated by a person skilled in the art that the schematic diagram is only an example of the electronic device 1 and does not constitute a limitation of the electronic device 1, and that it may comprise more or less components than shown, or some components may be combined, or different components, e.g. the electronic device 1 may further comprise an input output device, a network access device, a bus, etc.

The Processor 13 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The processor 13 is an operation core and a control center of the electronic device 1, and is connected to each part of the whole electronic device 1 by various interfaces and lines, and executes an operating system of the electronic device 1 and various installed application programs, program codes, and the like.

Illustratively, the computer readable instructions may be partitioned into one or more modules/units that are stored in the memory 12 and executed by the processor 13 to implement the present invention. The one or more modules/units may be a series of computer readable instruction segments capable of performing specific functions, which are used for describing the execution process of the computer readable instructions in the electronic device 1. For example, the computer readable instructions may be divided into an acquisition unit 110, a classification unit 111, a generation unit 112, an acquisition unit 113, a recognition unit 114, a recommendation unit 115, an adjustment unit 116, a statistics unit 117, a calculation unit 118, a selection unit 119, and a determination unit 120.

The memory 12 may be used for storing the computer readable instructions and/or modules, and the processor 13 implements various functions of the electronic device 1 by executing or executing the computer readable instructions and/or modules stored in the memory 12 and invoking data stored in the memory 12. The memory 12 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like. The memory 12 may include non-volatile and volatile memories, such as: a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other storage device.

The memory 12 may be an external memory and/or an internal memory of the electronic device 1. Further, the memory 12 may be a memory having a physical form, such as a memory stick, a TF Card (Trans-flash Card), or the like.

The integrated modules/units of the electronic device 1 may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, all or part of the flow of the method according to the above embodiments may be implemented by hardware that is configured to be instructed by computer readable instructions, which may be stored in a computer readable storage medium, and when the computer readable instructions are executed by a processor, the steps of the method embodiments may be implemented.

Wherein the computer readable instructions comprise computer readable instruction code which may be in source code form, object code form, an executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying said computer readable instruction code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM).

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

With reference to fig. 1, the memory 12 of the electronic device 1 stores computer-readable instructions to implement a method for intelligently recommending doctors, and the processor 13 can execute the computer-readable instructions to implement:

Specifically, the processor 13 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer readable instructions, which is not described herein again.

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

The computer readable storage medium has computer readable instructions stored thereon, wherein the computer readable instructions when executed by the processor 13 are configured to implement the steps of:

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

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

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 signs in the claims shall not be construed as limiting the claim concerned.

Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. The plurality of units or devices may also be implemented by one unit or device through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

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

Claims

1. A method for intelligently recommending doctors is characterized in that the method for intelligently recommending doctors comprises the following steps:

2. The method of claim 1, wherein the collecting historical patient medical record data comprises:

receiving authorization feedback information sent by the historical patient;

3. The method of claim 1, wherein the classifying the historical patient according to the medical record data to obtain the historical patient category of the historical patient comprises:

acquiring a disease category mapping table from the crowd classification model;

detecting whether the target symptom is present in the second category;

4. The method of intelligently recommending physicians according to claim 3, wherein if said target symptom is not present in said second category, said method further comprises:

acquiring the training users of the third category from a preset user library;

5. The method of claim 1, wherein the counting the number of diagnoses of the diagnostician in a plurality of historical patient categories according to the historical patients and generating the diagnosis and treatment capability information of the diagnostician in each historical patient category according to the number of diagnoses comprises:

6. The method of claim 1, wherein the dimension information comprises a work saturation degree of the diagnostician and a plurality of feedback information, and the generating the recommendation index of the diagnostician for each of the historical patient categories according to the dimension information and the clinical capability information comprises:

n>1；

7. The method of claim 1, wherein when the target user category comprises a plurality of categories, the recommending the diagnostician to the target user according to the recommendation index and the target user category comprises:

acquiring user information of the target user;

recommending the target doctor to the target user.

8. An intelligent doctor recommending device, characterized in that the intelligent doctor recommending device comprises:

9. An electronic device, characterized in that the electronic device comprises:

a memory storing computer readable instructions; and

a processor executing computer readable instructions stored in the memory to implement the intelligent recommender method of any of claims 1 to 7.

10. A computer-readable storage medium characterized by: the computer readable storage medium has stored therein computer readable instructions for execution by a processor in an electronic device to implement the intelligent doctor recommending method of any of claims 1-7.