CN108932974A - Method, apparatus, computer equipment and the storage medium of online interrogation distribution doctor - Google Patents
Method, apparatus, computer equipment and the storage medium of online interrogation distribution doctor Download PDFInfo
- Publication number
- CN108932974A CN108932974A CN201810550865.3A CN201810550865A CN108932974A CN 108932974 A CN108932974 A CN 108932974A CN 201810550865 A CN201810550865 A CN 201810550865A CN 108932974 A CN108932974 A CN 108932974A
- Authority
- CN
- China
- Prior art keywords
- doctor
- user identifier
- user
- dynamic parameter
- interrogation
- 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.)
- Granted
Links
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
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Abstract
This application involves a kind of online interrogation distribution doctor's method, apparatus, computer equipment and storage mediums.The method includes:The interrogation request of user terminal uploads is received, carries user identifier in interrogation request;It is that user identifier distributes corresponding department according to interrogation request;Multiple doctor's dynamic parameters in acquisition section room;The idle degrees of multiple doctors are calculated according to dynamic parameter;The doctor distributed to user identifier is determined according to idle degrees.The waiting time of counsel user can be shortened using this method.
Description
Technical field
This application involves field of computer technology, method, apparatus, meter more particularly to a kind of online interrogation distribution doctor
Calculate machine equipment and storage medium.
Background technique
With the improvement of living standards, each side is also higher and higher to the attention rate of medical treatment.When some ordinary disease symptoms
Itself can not but make medical diagnosis on disease when appearance, farther out or hospital stands in the queue to register time-consuming and trouble due to hospital's distance.Cause
This, most people understand referring physician in selection line.
However, the mode of online interrogation distribution referring physician is usually that a kind of problem is shared out equally to same department at present
Doctor.But each doctor see and treat patients ability and processing speed is not quite similar, if counsel user only to be given to doctor
It is raw, it will lead to individual physician counsel user and be lined up too long, you can catch sparrows on the doorstep by other doctors.Tradition is often by right to choose to section
Room doctor allows doctor oneself to determine number of seeing and treating patients, but thus will lead to part doctor again and carry out Wei individual interest is sought
Largely see and treat patients, there is no from actually solving the problems, such as user's wait-for-response overlong time.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of online interrogation that can shorten period of reservation of number
Distribute doctor's method, apparatus, computer equipment and storage medium.
A kind of online interrogation distribution doctor's method, the method includes:
The interrogation request of user terminal uploads is received, carries user identifier in the interrogation request;
It is that the user identifier distributes corresponding department according to interrogation request;
Obtain the dynamic parameter of multiple doctors in the section room;
The idle degrees of multiple doctors are calculated according to the dynamic parameter;
The doctor distributed to user identifier is determined according to the idle degrees.
It is described in one of the embodiments, to include for the corresponding department of user's distribution according to interrogation request:
A variety of user informations are obtained according to the user identifier;
Vectorization processing is carried out to the user information, obtains multi-C vector matrix;
The multi-C vector matrix is based on by neural network model and carries out prediction operation, is obtained and the user identifier pair
The department answered;
The department is labeled as to the department distributed to the user identifier.
In one of the embodiments, after determining the doctor distributed to user identifier according to the idle degrees, institute
The method of stating further includes:
The queuing wheel disc of the doctor is obtained, the queuing wheel disc includes multiple queues;
Identify the corresponding estimated levels of user identifier;
The user identifier is stored in respective queue according to the estimated levels;
When receiving when pulling request of doctor terminal, request to pull use from the queue for being lined up wheel disc according to described pull
Family mark.
The idle degrees for calculating multiple doctors according to the dynamic parameter include in one of the embodiments,:
Obtain the state logic value and the corresponding weight of the dynamic parameter of doctor;
Doctor's state is determined according to doctor's state logic value, and doctor's state includes presence;
If doctor's state is presence, dynamic parameter power corresponding with the dynamic parameter is calculated separately
The product of weight, obtains multiple weighted values;
The multiple weighted value is subjected to the idle degrees that summation determines the doctor.
In one of the embodiments, pulled according to request from be lined up wheel disc queue in pull user identifier it
Afterwards, the method also includes:
Update the dynamic parameter of the doctor;
Dynamic parameter before the updated dynamic parameter covering is updated.
A kind of online interrogation distribution doctor's device, described device include:
Receiving module, the interrogation for receiving user terminal uploads are requested, and carry user identifier in the interrogation request;
Distribution module, for being that the user identifier distributes corresponding department according to interrogation request;
Module is obtained, for obtaining the dynamic parameter of multiple doctors in the section room;
Computing module, for calculating the idle degrees of multiple doctors according to the dynamic parameter;
Selecting module, for determining the doctor distributed to user identifier according to the idle degrees.
The distribution module is also used to obtain a variety of user's letters according to the user identifier in one of the embodiments,
Breath;Vectorization processing is carried out to the user information, obtains multi-C vector matrix;The multidimensional is based on by neural network model
Vector matrix carries out prediction operation, obtains department corresponding with the user identifier;The department is labeled as to the user
Identify the department of distribution.
The queuing wheel disc for obtaining module and being also used to obtain the doctor in one of the embodiments, the queuing
Wheel disc includes multiple queues;
Described device further includes:
Identification module, for identification corresponding estimated levels of user identifier;
It is stored in module, for the user identifier to be stored in respective queue according to the estimated levels;
Module is pulled, for pulling request from queuing wheel disc according to described when receiving when pulling request of doctor terminal
Queue in pull user identifier.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes online interrogation distribution doctor's method described in above-mentioned any one when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Online interrogation distribution doctor's method described in above-mentioned any one is realized when row.
Above-mentioned online interrogation distribution doctor's method, apparatus, computer equipment and storage medium, server receive user terminal
Your interrogation request is uploaded, user identifier is carried in interrogation request, and is that user identifier distribution is corresponding according to interrogation request
Department.It realizes when user needs online interrogation, without manually selecting department.Also, server obtains after distributing department
The dynamic parameter of multiple doctors in section room, the idle degrees of multiple doctors are calculated according to dynamic parameter, are determined according to idle degrees
The doctor distributed to user identifier.It is that user distributes doctor according to the idle degrees of different doctors, so as to shorten user's consulting
The time of waiting.
Detailed description of the invention
Fig. 1 is the applied environment figure that online interrogation distributes doctor's method in one embodiment;
Fig. 2 is the flow diagram that online interrogation distributes doctor's method in one embodiment;
Fig. 3 be in one embodiment according to interrogation request be user identifier distribute corresponding department's step process illustrate
Figure;
Fig. 4 is the flow diagram that online interrogation distributes doctor's method in another embodiment;
Fig. 5 is the structural block diagram that online interrogation distributes doctor's device in one embodiment;
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Online interrogation provided by the present application distributes doctor's method, can be applied in application environment as shown in Figure 1.Including
User terminal 102, doctor terminal 106 and server 104.Wherein, user terminal 102 is carried out by network and server 104
Communication.Doctor terminal 106 is communicated by network with server 104.User terminal 102 and doctor terminal 106 can with but
It is not limited to various personal computers, laptop, smart phone, tablet computer and portable wearable device, server
104 can be realized with the server cluster of the either multiple server compositions of independent server.Specifically, when user needs
When on-line consulting doctor, interrogation request can be uploaded to server 104 by user terminal 102.It is whole that server 104 receives user
The interrogation that end 102 uploads is requested, and carries user identifier in interrogation request.Server 104 is user identifier according to interrogation request
Distribute corresponding department.Server 104 is also multiple doctor's dynamic parameters in acquisition section room after user distributes department, and according to
Dynamic parameter calculates the idle degrees of multiple doctors, selects most not busy doctor according to idle degrees, by most not busy doctor determine to
The doctor of user identifier distribution.After server 104 distributes doctor, it can establish between user terminal 102 and doctor terminal 106
Communication connection, realizes online interrogation.
In one embodiment, it as shown in Fig. 2, providing a kind of online interrogation distribution doctor's method, applies in this way
It is illustrated, includes the following steps for server 104 in Fig. 1:
S202 receives the interrogation request of user terminal uploads, carries user identifier in interrogation request.
The application program of online interrogation is mounted on user terminal.Before logging in the application program, user needs to carry out
Registration.The essential informations such as user identifier, gender are contained in registration information.When user wishes on-line consulting doctor, it is not necessarily to hand
Dynamic selection department, can click the interrogation button in application program, generate interrogation request, be sent by application program to server
Interrogation request.
S204 is that user identifier distributes corresponding department according to interrogation request.
Server according to interrogation request in the user identifier that carries collect a variety of user informations.By to a variety of user informations
Carry out vectorization processing, available corresponding multi-C vector matrix.Server calls deep-neural-network model, passes through deep layer
Neural network model is based on multi-C vector matrix and carries out prediction operation, thus accurately obtains the department distributed to user identifier.From
And realize and manually select department without user, can department be distributed for user automatically.
S206, multiple doctor's dynamic parameters in acquisition section room.
S208 calculates the idle degrees of multiple doctors according to dynamic parameter.
Dynamic parameter includes being lined up number, number of concurrent, seeing and treating patients ability value and the time apart from last time holding.Wherein,
Being lined up number indicates to carry out waiting in line the number of users of consulting in current physician queue.Number of concurrent indicates that current physician is practical and connects
Examine number, i.e. the current counsel user quantity of processing simultaneously of doctor.Ability value of seeing and treating patients indicates the ability of seeing and treating patients of doctor, can with doctor
It is subject to the number seen and treated patients.Server, then will be upper by from above-mentioned dynamic parameter is obtained in database or on doctor terminal
It states dynamic parameter substitution calculation formula and calculates the idle degrees of doctor, while the idle degrees of multiple doctors can be calculated.
S210 determines the doctor distributed to user identifier according to idle degrees.
The idle degrees of each doctor are different, and the lower doctor of idle degrees is busier.If user given busy
Doctor, then the time of user's wait-for-response is also longer.So when the idle degrees of doctor in section room are all different, root
Doctor most not busy in current section room is selected according to idle degrees, and most not busy doctor is determined as to the doctor distributed to user identifier.When
Have in section room the idle degrees of several doctors it is identical when, server then from database obtain doctor information about doctor table, doctor
Information table includes the information such as the basic personal information such as physician names, gender, affiliated department and doctor academic title.According to doctor academic title
The highest-ranking doctor of academic title is selected to be determined as the doctor distributed to user identifier from the identical doctor of several idle degrees.If
The doctor for having several academic title's ranks equal simultaneously then carries out one doctor of random selection from server and is determined as to user identifier point
The doctor matched.
In above-mentioned online interrogation distribution doctor's method, server receives the interrogation request of user terminal uploads, interrogation request
In carry user identifier, and be that user identifier distributes corresponding department according to interrogation request.It realizes when user needs online
When interrogation, without manually selecting department.Also, after distributing department in server acquisition section room multiple doctors dynamic parameter,
The idle degrees that multiple doctors are calculated according to dynamic parameter determine the doctor distributed to user identifier according to idle degrees.According to
The idle degrees of different doctors are that user distributes doctor, and the time waited is seeked advice from so as to shorten user.
In one embodiment, as shown in figure 3, it includes following for distributing corresponding department according to interrogation request for user identifier
Step:
S302 obtains a variety of user informations according to user identifier.
Server receives user terminal and is requested by the interrogation that application program uploads.User's mark is carried in interrogation request
Know.Server obtains a variety of user informations according to user identifier, including:Main suit's information, essential information, historical information etc..
Main suit's information includes the symptom information that user is currently uploaded by application program.Server receives interrogation request
When, corresponding problem is returned to user terminal.User can answer these problems by user terminal.In answer, these are asked user
When topic, content relevant to current symptomatic can be described.The answer of user is uploaded to server by user terminal, server by its
Mark the information that is chief complaint.
Server while collecting user identifier corresponding main suit's information, can also collect parallel corresponding essential information and
Historical information.When essential information can be user's registration application program, pass through the information of user terminal uploads to server, packet
It includes:Age, gender etc..The user of all ages and classes or different sexes, it is possible to which there are similarities for main suit's information, but in interrogation
When need to distribute to different departments.For example, including " hypogastralgia " in main suit's information, female user may be assigned to woman
Section, male user may be assigned to internal medicine.
Historical information includes the diagnosis and treatment that user carries out the historical record, present diagnosis and treatment mechanism of online interrogation by application program
Record etc..Identical department when would generally enter with first visit when due to user's further consultation, if this online interrogation of user is further consultation,
It then will be higher into the probability of same department.Therefore the historical information of user, which can aid in, improves the accurate of department's distribution
Property.
S304 carries out vectorization processing to user information, obtains multi-C vector matrix.
Server pre-processes a variety of user informations being collected into.Pretreatment includes:It segments, remove stop words, numerous turn
Letter etc..Server carries out feature selecting in a variety of user informations after the pre-treatment, obtains multiple features.Server will select
Each Feature Conversion out is corresponding one-dimensional vector, is turned by term vector model to the corresponding one-dimensional vector of multiple features
It changes, obtains multi-C vector matrix corresponding with user identifier.
S306 is based on multi-C vector matrix by deep-neural-network model and carries out prediction operation, obtains and user identifier
Corresponding department.
Department is labeled as the department distributed to user identifier by S308.
Main suit's information, essential information and historical information can also be respectively seen as the defeated of deep-neural-network in user information
Enter classification.Server can first obtain the corresponding multi-C vector matrix of each input classification by term vector model, then will be multiple
The corresponding multi-C vector matrix of input classification merges, and generates the corresponding input vector matrix of deep-neural-network model.
Server calls deep-neural-network model, using input vector matrix as the input of deep-neural-network model,
Deep-neural-network model carries out operation, predicts the probability of the corresponding department of multi-C vector matrix.Server can be by probability
Highest department is determined as the department to user identifier distribution as the corresponding department of user identifier, and by the department.Due to defeated
The contents such as essential information, historical information and main suit's information are contained in incoming vector matrix, therefore can pass through deep layer nerve net
Network model is accurately analyzed obtain the online interrogation of user needed for department.
Deep-neural-network model can be convolutional neural networks, including convolutional layer, full articulamentum and output layer.Convolution
It include multiple neurons in layer, full articulamentum and output layer.It is calculated in neuron i.e. deep-neural-network model
With the unit of storage.The neuronal quantity of convolutional layer, full articulamentum and output layer is different.The neuronal quantity of convolutional layer
It can be identical as each input number of dimensions of classification.The number of dimensions of input classification can be the corresponding multidimensional of input classification to
The number of dimensions of moment matrix.For example, multi-C vector matrix is that 256*256 ties up matrix, then the neuronal quantity of convolutional layer can be
256.The corresponding multi-C vector matrix of different input classifications can be identical dimensional.Convolutional layer may include it is multiple, often
The neuronal quantity of a convolutional layer can be identical.The neuronal quantity of full articulamentum is greater than the neuronal quantity of convolutional layer, for example,
The neuronal quantity of full articulamentum is the multiple etc. of the neuronal quantity of convolutional layer.The neuronal quantity of output layer can be with department
Quantity it is identical.
Wherein, deep-neural-network model is trained in advance.Before training, the volume of deep-neural-network model
Lamination, full articulamentum and output layer are all provided with corresponding initiation parameter.Wherein, the variance of initiation parameter can be by
Layer increases, it is possible thereby to disperse the initiation parameter in deep-neural-network model increasingly, facilitates in training process
The middle pace of learning for improving deep-neural-network model and the accuracy of prediction.Convolutional layer is also provided with corresponding activation primitive
With pond layer, wherein different convolutional layers can be using different pond layers or using corresponding pond layer, different volumes
Lamination can use different activation primitives.The mutual pass between the feature of each dimension can be calculated by multiple convolutional layers
System can be reduced by pond layer and be interfered with the incoherent data of feature, reduce over-fitting, and training obtains more similar with feature
As a result.
It in the present embodiment,, can be by user terminal without manually selecting department when user needs online interrogation
Arraign examines request.Server according to interrogation request in the user identifier that carries collect a variety of user informations.By to a variety of users
Information carries out vectorization processing, available corresponding multi-C vector matrix.Server calls deep-neural-network model, passes through
Deep-neural-network model is based on multi-C vector matrix and carries out prediction operation, thus accurately obtains the section distributed to user identifier
Room.So that department can be distributed automatically in the online interrogation of client for user and effectively improve the accurate of department's distribution by realizing
Property.
In one embodiment, as shown in figure 4, after determining the doctor distributed to user identifier according to idle degrees also
Include the following steps:
S402 obtains the queuing wheel disc of doctor, and being lined up includes multiple queues in wheel disc.
Each doctor is equipped with a corresponding queuing wheel disc, can support by the independent configuration of doctor.That is doctor can be with
Scale quantity and number of queues are divided according to the actual situation, it can be with specific aim self-setting queue level, higher grade i.e. generation
The scale quantity that the table queue occupies is more, it is meant that and wait the probability for going out team to counsel user of interrogation bigger in the queue,
The wait-for-response time is shorter.
It is lined up wheel disc and refers to a kind of in such a way that wheel form is lined up, multiple scales, number of division can be set in wheel disc
Amount can be set according to actual needs.Being lined up wheel disc includes multiple queues, and queue is made of multiple scales, i.e. a queue
Including at least one scale.Therefore, as long as being provided with queue, it can be found on being lined up wheel disc and belong to a queue at least lattice
Number of division.The quantity of queue can equally have multiple, be lined up in wheel disc that specific number of queues equally can be according to actual needs
It is set.Also, queue is designed with different grades, and the height of grade is determined by the scale quantity for forming the queue, composition
The scale quantity of queue is more, and the grade of queue is also higher.Scale quantity can only determine height and the queue of queue level
The user identifier quantity that team can be gone out in wheel disc one circle of rotation, cannot determine the user identifier quantity that can be lined up in queue.
That is, the queuing quantity that queue can accommodate is unrelated with scale quantity, scale quantity can only represent the height of user gradation,
Because scale quantity shared by queue is more, team's probability out that the queue is enclosed in wheel disc rotation one is higher.Therefore, queue can accommodate
Queuing quantity can arbitrarily set according to the actual situation.So the team's mode that goes out using Wheel-type is to guarantee that grade is high
User can also reduce the waiting time of inferior grade user while can enjoying certain priority.
S404, the corresponding estimated levels of identification user identifier.
User identifier is carried in interrogation request.Server obtains a variety of user informations according to user identifier, including:Main suit
Information, essential information, historical information etc..Estimated levels can be stored in essential information by each user in registration, therefore
The estimated levels of user can be got from essential information.
User identifier is stored in respective queue by S406 according to estimated levels.
Different queues has different grades, the estimated levels and queue level of the user identifier waited in each queue
It is to maintain consistent.That is, each estimated levels can find the corresponding queue of grade in being lined up wheel disc, if user
The estimated levels of mark are 2, then the queue entered is to be lined up the queue that wheel disc middle grade is 2.Therefore, according to queuing of user etc.
User identifier is deposited into the queue of queue level corresponding with estimated levels by grade.
S408 requests to pull from the queue for being lined up wheel disc when receiving when pulling request of doctor terminal according to pulling
User identifier.
It pulls request middle finger and carries queuing wheel disc information.Wherein, it includes opposite with the queuing wheel disc for being lined up wheel disc information
The account information of Ying doctor, each doctor have the queuing wheel disc of oneself, i.e. server can be true according to the account information of doctor
Determine queuing wheel disc corresponding to doctor.Specifically, server is received from second terminal and is asked comprising being lined up pulling for wheel disc information
It asks, pulls user identifier from the queue in corresponding queuing wheel disc according to request is pulled.Because user identifier has uniqueness,
So can determine that corresponding user terminal, server can establish use according to user identifier after pulling user identifier
Family terminal is connected with the online communication of doctor terminal.
In the present embodiment, the queuing wheel disc that server is deposited into doctor according to the estimated levels of user identifier is corresponding
Queue in.When doctor, which treats counsel user, carries out online interrogation, it can be uploaded by doctor terminal and pull request to service
Device, to pull corresponding user identifier in the queuing of Wheel-type, thus realize ensure it is different grades of with per family can be with
Most fast speed is responded.
In one embodiment, as shown in figure 5, including according to the idle degrees that dynamic parameter calculates multiple doctors:, obtain doctor
The raw corresponding weight of state logic value and dynamic parameter;Doctor's state, doctor's state packet are determined according to doctor's state logic value
Include presence;If doctor's state is presence, seizing the opportunity for dynamic parameter weight corresponding with dynamic parameter is calculated separately,
Obtain multiple weighted values;Multiple weighted values sum the idle degrees of determining doctor.
Server needs to judge doctor's state before obtaining doctor's dynamic parameter computation-free degree.Doctor's state is not
Only further include off-line state including presence, work of seeing and treating patients can not be carried out when doctor is off-line state.Therefore,
Server obtains the state logic value of department doctor first, if the state logic value that server is got is 1, then it represents that doctor
It is currently off-line state.The doctor of off-line state directly excludes from the doctor for needing computation-free degree, without calculating.If
The state logic value got is 0, then it represents that current physician is presence, can calculate the idle degrees of the doctor.
Dynamic parameter include be lined up number, number of concurrent, seeing and treating patients ability value and pulls the time interval of user apart from the last time,
Corresponding weight can be arranged in each dynamic parameter.Wherein, due to be lined up that number and number of concurrent indicate be current physician team
The queued or number seeked advice from column, and it is lined up number and consulting number more multilist shows that doctor is busier.And ability value of seeing and treating patients
With distance is last pulls quantity that the doctor that user time interval respectively indicates can see and treat patients simultaneously and stopped so far
The length of time is ceased, therefore the ability value and the pull user time interval apart from the last time the high of seeing and treating patients, indicates that doctor is more idle.
Therefore, being lined up number and number of concurrent is busy dynamic parameter, and seeing and treating patients ability value and apart from the time interval that the last time pulls user is
Idle dynamic parameter.
The idle degrees of calculating doctor are not only only removed with free time dynamic parameter when calculating the idle degrees of doctor's entirety,
In order to guarantee with the accuracy of practical doctor's busy-idle condition, it is also contemplated that busy dynamic parameter brought by influence.Also, due to
It is finally the computation-free degree by the way of the summation of multiple weighted values.So in order to offset the busy dynamic parameter pair of doctor
The weight of the influence of practical idle degrees, busy dynamic parameter can use negative number representation, and the weight of idle dynamic parameter can be used
Positive number indicates.For example, it is that -0.2, ability value of seeing and treating patients is corresponding that the corresponding weight of queuing number, which is the corresponding weight of -0.4, number of concurrent,
Weight is 0.1 and is 0.3 apart from the corresponding weight of time interval that the last time pulls user.
Idle degrees calculation formula is:Be lined up number weight * be lined up number+number of concurrent weight * number of concurrent+see and treat patients ability value power
The last time interval weight * distance for pulling user of weight * (ability value-number of concurrent of seeing and treating patients)+distance is last to pull user's
Time interval.
Wherein, ability value of seeing and treating patients is the number that can see and treat patients simultaneously of doctor, and number of concurrent is expressed as doctor and currently while connecing
The number examined, so the difference seen and treated patients between ability value and number of concurrent could indicate the actual ability value of seeing and treating patients of current physician.Institute
To see and treat patients ability value weight * (ability value-number of concurrent of seeing and treating patients) in calculation formula.By formula it can be shown that being lined up number and simultaneously
Send out that number is bigger, and the score value of idle degrees is lower, the difference of see and treat patients ability value and number of concurrent is bigger, and pulls use apart from the last time
The time interval at family is more long, then the score value of idle degrees is higher.
When calculating the idle degrees of multiple doctors, final numerical value may occur according to the difference of doctor's dynamic parameter
Part doctor's idle degrees numerical value is negative, part doctor's idle degrees numerical value and positive number.So for final calculation result lattice
Formula is consistent to increase by one basic value before calculation formula convenient for checking, such as basic value is 1000, then calculation formula
For:10000+ is lined up number weight * queuing number+number of concurrent weight * number of concurrent+ability value weight of seeing and treating patients *, and (ability value-of seeing and treating patients is concurrent
Number) the last last time interval for pulling user of time interval weight * distance for pulling user of+distance.
The last time interval for pulling user of distance is such as distance last time for pulling user as unit of minute
It is 0.5 hour, then is scaled 30 minutes.The last time interval weight for pulling user of as 30* distance.It is assumed that being lined up number
For 30, number of concurrent 20, ability value of seeing and treating patients be 50 and to pull the time interval of user be 30 minutes apart from the last time, then by counting
Calculating the idle degrees result that formula calculates is:
(10000-0.4*30-0.2*20+0.1* 50-20)+0.3*30=9996
Wherein it is possible to the idle degrees of doctor directly be divided with the score value of calculated result, for example, when there is doctor's score value ratio
9996 score values are high, then the idle degrees of the doctor are greater than the doctor of 9996 score values.The idle degrees of the doctor lower than 9996 score values
Less than the doctor of 9996 score values.Likewise, the idle degrees grade in each section can be arranged not by score value demarcation interval
Equally.For example, score value [9000,10000] section doctor's idle degrees grade be 1 grade, score value [8000,9000) section
Doctor's free time grade be 2 grades, specific idle degrees expression way can be set according to actual conditions.
In the present embodiment, by obtaining the corresponding different weight of dynamic parameter and dynamic parameter, and pass through calculating
The product of dynamic parameter and respective weights obtains multiple weight score values, and the score value of idle degrees is obtained after being summed.Using can
To show the idle or busy practical dynamic parameter of doctor, so that the score value of the idle degrees calculated is with actually doctor's
Idle condition is consistent, and ensure that the accuracy of computation-free degree score value.
In one embodiment, pulling request after pulling user identifier in the queue for being lined up wheel disc in basis includes:
Update the dynamic parameter of doctor;Dynamic parameter before being updated using the covering of updated dynamic parameter.
After user identifier is pulled away from the queuing wheel disc of doctor, the queuing number and number of concurrent of doctor is all to be become
Change.And should be carried out calculating according to newest dynamic parameter could more closing to reality situation for idle degrees.Therefore, useful
After family mark is pulled, it should be updated to the dynamic parameter of the doctor, and more by the covering of updated dynamic parameter
Dynamic parameter before new.Guarantee that being able to use newest dynamic parameter when calculate next time is calculated.
In above-mentioned online interrogation distribution doctor's method, server receives your interrogation request of user terminal uploads, and interrogation is asked
User identifier is carried in asking, and is that user identifier distributes corresponding department according to interrogation request.It realizes when user needs
When line interrogation, without manually selecting department.Also, the dynamic of multiple doctors is joined in server acquisition section room after distributing department
Number, the idle degrees of multiple doctors are calculated according to dynamic parameter, and most not busy doctor is selected according to idle degrees, will be described most not busy
Doctor determines the doctor distributed to user identifier.It is the most not busy doctor of user's distribution according to the idle degrees of different doctors, thus
It shortens user and seeks advice from the time waited.
It should be understood that although each step in the flow chart of Fig. 2-4 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-4
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in fig. 6, providing a kind of online interrogation distribution doctor's device 600, including:It receives
Module 602, obtains module 606, computing module 608 and selecting module 610 at distribution module 604, wherein:
Receiving module 602, the interrogation for receiving user terminal uploads are requested, and carry user identifier in interrogation request.
Distribution module 604, for being that user identifier distributes corresponding department according to interrogation request.
Module 606 is obtained, for obtaining the dynamic parameter of multiple doctors in section room.
Computing module 608, for calculating the idle degrees of multiple doctors according to dynamic parameter.
Selecting module 610, for determining the doctor distributed to user identifier according to idle degrees.
In one embodiment, the distribution module 604 is also used to obtain a variety of user informations according to user identifier.To with
Family information carries out vectorization processing, obtains multi-C vector matrix.Multi-C vector matrix is based on by neural network model to carry out in advance
Operation is surveyed, department corresponding with user identifier is obtained.Department is labeled as to the department distributed to user identifier.
In one embodiment, the queuing wheel disc that module is also used to obtain doctor is obtained, being lined up wheel disc includes multiple queues.
Device 600 further includes:
Identification module, for identification corresponding estimated levels of user identifier.
It is stored in module, for user identifier to be stored in respective queue according to estimated levels.
Module is pulled, for when receiving when pulling request of doctor terminal, according to pulling request from the team for being lined up wheel disc
User identifier is pulled in column.
In one embodiment, computing module 608 be also used to obtain doctor state logic value and dynamic parameter it is corresponding
Weight.Determine that doctor's state, doctor's state include presence according to doctor's state logic value.If doctor's state is in threadiness
State then calculates separately the product of dynamic parameter weight corresponding with dynamic parameter, obtains multiple weighted values.By multiple weighted values into
Row, which is summed, determines the idle degrees of doctor.
In one embodiment, device 600 further includes update module, for updating the dynamic parameter of doctor.Utilize update
The dynamic parameter before dynamic parameter covering update afterwards.
Specific restriction about online interrogation distribution doctor's device may refer to distribute doctor above for online interrogation
The restriction of method, details are not described herein.Modules in above-mentioned online interrogation distribution doctor's device can be fully or partially through
Software, hardware and combinations thereof are realized.Above-mentioned each module can be embedded in the form of hardware or independently of the place in computer equipment
It manages in device, can also be stored in a software form in the memory in computer equipment, in order to which processor calls execution or more
The corresponding operation of modules.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing the data such as user identifier, dynamic parameter.The network interface of the computer equipment be used for it is outer
The terminal in portion passes through network connection communication.To realize a kind of online interrogation distribution doctor when the computer program is executed by processor
Method.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor realize following steps when executing computer program:
The interrogation request of user terminal uploads is received, carries user identifier in interrogation request;
It is that user identifier distributes corresponding department according to interrogation request;
Multiple doctor's dynamic parameters in acquisition section room;
The idle degrees of multiple doctors are calculated according to dynamic parameter;
The doctor distributed to user identifier is determined according to idle degrees.
In one embodiment, following steps are also realized when processor executes computer program:
A variety of user informations are obtained according to user identifier;
Vectorization processing is carried out to user information, obtains multi-C vector matrix;
Multi-C vector matrix is based on by deep-neural-network model and carries out prediction operation, is obtained corresponding with user identifier
Department;
Department is labeled as to the department distributed to user identifier.
In one embodiment, following steps are also realized when processor executes computer program:
The queuing wheel disc of doctor is obtained, being lined up includes multiple queues in wheel disc;
Identify the corresponding estimated levels of user identifier;
User identifier is stored in respective queue according to estimated levels;
When receiving when pulling request of doctor terminal, user's mark is pulled from the queue for being lined up wheel disc according to request is pulled
Know.
In one embodiment, following steps are also realized when processor executes computer program:The state for obtaining doctor is patrolled
Collect value weight corresponding with dynamic parameter;Determine that doctor's state, doctor's state include presence according to doctor's state logic value;
If doctor's state is presence, seizing the opportunity for dynamic parameter weight corresponding with dynamic parameter is calculated separately, multiple power are obtained
Weight values;Multiple weighted values sum the idle degrees of determining doctor.
In one embodiment, following steps are also realized when processor executes computer program:Update the dynamic ginseng of doctor
Number;Dynamic parameter before being updated using the covering of updated dynamic parameter.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes following steps when being executed by processor:
The interrogation request of user terminal uploads is received, carries user identifier in interrogation request;
It is that user identifier distributes corresponding department according to interrogation request;
Multiple doctor's dynamic parameters in acquisition section room;
The idle degrees of multiple doctors are calculated according to dynamic parameter;
The doctor distributed to user identifier is determined according to idle degrees.
In one embodiment, following steps are also realized when computer program is executed by processor:
A variety of user informations are obtained according to user identifier;
Vectorization processing is carried out to user information, obtains multi-C vector matrix;
Multi-C vector matrix is based on by deep-neural-network model and carries out prediction operation, is obtained corresponding with user identifier
Department;
Department is labeled as to the department distributed to user identifier.
In one embodiment, following steps are also realized when computer program is executed by processor:
The queuing wheel disc of doctor is obtained, being lined up includes multiple queues in wheel disc;
Identify the corresponding estimated levels of user identifier;
User identifier is stored in respective queue according to estimated levels;
When receiving when pulling request of doctor terminal, user's mark is pulled from the queue for being lined up wheel disc according to request is pulled
Know.
In one embodiment, following steps are also realized when computer program is executed by processor:Obtain the state of doctor
Logical value and the corresponding weight of dynamic parameter;Determine that doctor's state, doctor's state are included in threadiness according to doctor's state logic value
State;If doctor's state is presence, seizing the opportunity for dynamic parameter weight corresponding with dynamic parameter is calculated separately, is obtained multiple
Weighted value;Multiple weighted values sum the idle degrees of determining doctor.
In one embodiment, following steps are also realized when computer program is executed by processor:Update the dynamic of doctor
Parameter;Dynamic parameter before being updated using the covering of updated dynamic parameter.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of online interrogation doctor distribution method, the method includes:
The interrogation request of user terminal uploads is received, carries user identifier in the interrogation request;
It is that the user identifier distributes corresponding department according to interrogation request;
Obtain the dynamic parameter of multiple doctors in the section room;
The idle degrees of multiple doctors are calculated according to the dynamic parameter;
The doctor distributed to user identifier is determined according to the idle degrees.
2. the method according to claim 1, wherein described divide according to interrogation request for the user identifier
Include with corresponding department:
A variety of user informations are obtained according to the user identifier;
Vectorization processing is carried out to the user information, obtains multi-C vector matrix;
The multi-C vector matrix is based on by neural network model and carries out prediction operation, is obtained corresponding with the user identifier
Department;
The department is labeled as to the department distributed to the user identifier.
3. the method according to claim 1, wherein being distributed being determined according to the idle degrees to user identifier
Doctor after, the method also includes:
The queuing wheel disc of the doctor is obtained, the queuing wheel disc includes multiple queues;
Identify the corresponding estimated levels of user identifier;
The user identifier is stored in respective queue according to the estimated levels;
When receiving when pulling request of doctor terminal, request to pull user's mark from the queue for being lined up wheel disc according to described pull
Know.
4. the method according to claim 1, wherein the sky for calculating multiple doctors according to the dynamic parameter
Not busy degree includes:
Obtain the state logic value and the corresponding weight of the dynamic parameter of doctor;
Doctor's state is determined according to doctor's state logic value, and doctor's state includes presence;
If doctor's state is presence, dynamic parameter weight corresponding with the dynamic parameter is calculated separately
Product obtains multiple weighted values;
The multiple weighted value is subjected to the idle degrees that summation determines the doctor.
5. according to the method described in claim 3, it is characterized in that, pulling request according to from the queue for being lined up wheel disc
After pulling user identifier, the method also includes:
Update the dynamic parameter of the doctor;
Dynamic parameter before being updated using the updated dynamic parameter covering.
6. a kind of online interrogation distributes doctor's device, which is characterized in that described device includes:
Receiving module, the interrogation for receiving user terminal uploads are requested, and carry user identifier in the interrogation request;
Distribution module, for being that the user identifier distributes corresponding department according to interrogation request;
Module is obtained, for obtaining the dynamic parameter of multiple doctors in the section room;
Computing module, for calculating the idle degrees of multiple doctors according to the dynamic parameter;
Selecting module, for determining the doctor distributed to user identifier according to the idle degrees.
7. device according to claim 6, which is characterized in that the distribution module is also used to be obtained according to the user identifier
Take a variety of user informations;Vectorization processing is carried out to the user information, obtains multi-C vector matrix;Pass through neural network model
Prediction operation is carried out based on the multi-C vector matrix, obtains department corresponding with the user identifier;The department is marked
For the department distributed to the user identifier.
8. device according to claim 6, which is characterized in that the queuing for obtaining module and being also used to obtain the doctor
Wheel disc, the queuing wheel disc includes multiple queues;
Described device further includes:
Identification module, for identification corresponding estimated levels of user identifier;
It is stored in module, for the user identifier to be stored in respective queue according to the estimated levels;
Module is pulled, for pulling request from the team for being lined up wheel disc according to described when receiving when pulling request of doctor terminal
User identifier is pulled in column.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 5 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 5 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810550865.3A CN108932974B (en) | 2018-05-31 | 2018-05-31 | Method, device, computer equipment and storage medium for allocating doctors for online inquiry |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810550865.3A CN108932974B (en) | 2018-05-31 | 2018-05-31 | Method, device, computer equipment and storage medium for allocating doctors for online inquiry |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108932974A true CN108932974A (en) | 2018-12-04 |
CN108932974B CN108932974B (en) | 2023-04-18 |
Family
ID=64449655
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810550865.3A Active CN108932974B (en) | 2018-05-31 | 2018-05-31 | Method, device, computer equipment and storage medium for allocating doctors for online inquiry |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108932974B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109903856A (en) * | 2018-12-29 | 2019-06-18 | 苏州问一问健康管理咨询有限公司 | A kind of consultation on-line method and system |
CN110428539A (en) * | 2019-09-11 | 2019-11-08 | 北京大学深圳医院 | It is medical to be lined up wrist strap based reminding method, device, wrist wearing devices and storage medium |
CN110706798A (en) * | 2019-09-16 | 2020-01-17 | 武汉安诠加信息技术有限公司 | Method, device, equipment and medium for allocating inquiry orders suitable for beauty parlor |
CN111403052A (en) * | 2020-02-28 | 2020-07-10 | 广东人联网电子商务有限公司 | Video inquiry method and system |
CN111507414A (en) * | 2020-04-20 | 2020-08-07 | 安徽中科首脑智能医疗研究院有限公司 | Deep learning skin disease picture comparison and classification method, storage medium and robot |
CN112035674A (en) * | 2020-08-28 | 2020-12-04 | 康键信息技术(深圳)有限公司 | Diagnosis guide data acquisition method and device, computer equipment and storage medium |
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 |
CN112542236A (en) * | 2020-12-18 | 2021-03-23 | 微医云(杭州)控股有限公司 | Online task distribution method and device, electronic equipment and storage medium |
CN112802586A (en) * | 2021-01-27 | 2021-05-14 | 挂号网(杭州)科技有限公司 | Task distribution method and device, electronic equipment and storage medium |
CN113241170A (en) * | 2021-05-13 | 2021-08-10 | 阿里健康科技(杭州)有限公司 | Online inquiry method, server and terminal equipment |
CN113241134A (en) * | 2021-04-26 | 2021-08-10 | 哈尔滨工业大学(深圳) | Online consulting doctor distribution method and system and storage medium |
CN113764081A (en) * | 2021-03-26 | 2021-12-07 | 北京京东拓先科技有限公司 | Method, device and equipment for determining inquiry number and computer readable storage medium |
CN116646065A (en) * | 2023-05-25 | 2023-08-25 | 浙江蕙康科技有限公司 | Internet hospital data security management method and device |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107273706A (en) * | 2017-07-25 | 2017-10-20 | 海南聚能科技创新研究院有限公司 | Intelligent medical system based on Internet of things |
CN107705842A (en) * | 2017-10-13 | 2018-02-16 | 合肥工业大学 | Intelligent system for distribution of out-patient department and its method of work |
-
2018
- 2018-05-31 CN CN201810550865.3A patent/CN108932974B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107273706A (en) * | 2017-07-25 | 2017-10-20 | 海南聚能科技创新研究院有限公司 | Intelligent medical system based on Internet of things |
CN107705842A (en) * | 2017-10-13 | 2018-02-16 | 合肥工业大学 | Intelligent system for distribution of out-patient department and its method of work |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109903856B (en) * | 2018-12-29 | 2021-01-29 | 苏州问一问健康管理咨询有限公司 | Online consultation method and system |
CN109903856A (en) * | 2018-12-29 | 2019-06-18 | 苏州问一问健康管理咨询有限公司 | A kind of consultation on-line method and system |
CN110428539A (en) * | 2019-09-11 | 2019-11-08 | 北京大学深圳医院 | It is medical to be lined up wrist strap based reminding method, device, wrist wearing devices and storage medium |
CN110706798A (en) * | 2019-09-16 | 2020-01-17 | 武汉安诠加信息技术有限公司 | Method, device, equipment and medium for allocating inquiry orders suitable for beauty parlor |
CN111403052A (en) * | 2020-02-28 | 2020-07-10 | 广东人联网电子商务有限公司 | Video inquiry method and system |
CN111507414A (en) * | 2020-04-20 | 2020-08-07 | 安徽中科首脑智能医疗研究院有限公司 | Deep learning skin disease picture comparison and classification method, storage medium and robot |
CN112035674B (en) * | 2020-08-28 | 2023-05-23 | 康键信息技术(深圳)有限公司 | Diagnosis guiding data acquisition method, device, computer equipment and storage medium |
CN112035674A (en) * | 2020-08-28 | 2020-12-04 | 康键信息技术(深圳)有限公司 | Diagnosis guide data acquisition method and device, computer equipment and storage medium |
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 |
CN112542236A (en) * | 2020-12-18 | 2021-03-23 | 微医云(杭州)控股有限公司 | Online task distribution method and device, electronic equipment and storage medium |
CN112802586A (en) * | 2021-01-27 | 2021-05-14 | 挂号网(杭州)科技有限公司 | Task distribution method and device, electronic equipment and storage medium |
CN113764081A (en) * | 2021-03-26 | 2021-12-07 | 北京京东拓先科技有限公司 | Method, device and equipment for determining inquiry number and computer readable storage medium |
CN113241134A (en) * | 2021-04-26 | 2021-08-10 | 哈尔滨工业大学(深圳) | Online consulting doctor distribution method and system and storage medium |
CN113241170A (en) * | 2021-05-13 | 2021-08-10 | 阿里健康科技(杭州)有限公司 | Online inquiry method, server and terminal equipment |
CN116646065A (en) * | 2023-05-25 | 2023-08-25 | 浙江蕙康科技有限公司 | Internet hospital data security management method and device |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN108932974B (en) | 2023-04-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108932974A (en) | Method, apparatus, computer equipment and the storage medium of online interrogation distribution doctor | |
Ambekar et al. | Disease risk prediction by using convolutional neural network | |
WO2020220545A1 (en) | Long short-term memory model-based disease prediction method and apparatus, and computer device | |
US20180158552A1 (en) | Interpretable deep learning framework for mining and predictive modeling of health care data | |
CN109979587A (en) | Patient healthcare's interactive device and its implementation method | |
KR20200063364A (en) | Method and system for visualizing classification result of deep neural network for prediction of disease prognosis through time series medical data | |
Liu et al. | A collaborative privacy-preserving deep learning system in distributed mobile environment | |
CN108877929A (en) | It is neural network based to intend examining recommendation process method, apparatus and computer equipment | |
WO2021151327A1 (en) | Triage data processing method and apparatus, and device and medium | |
Krikunov et al. | Complex data-driven predictive modeling in personalized clinical decision support for Acute Coronary Syndrome episodes | |
WO2021179630A1 (en) | Complications risk prediction system, method, apparatus, and device, and medium | |
CN114298234B (en) | Brain medical image classification method and device, computer equipment and storage medium | |
CN108461110A (en) | Medical information processing method, device and equipment | |
CN111666494A (en) | Clustering decision model generation method, clustering processing method, device, equipment and medium | |
CN111696661A (en) | Patient clustering model construction method, patient clustering method and related equipment | |
US20220199254A1 (en) | Universal health machine for the automatic assessment of patients | |
CN108847278B (en) | On-line inquiry automatic allocation method, device, computer equipment and storage medium | |
US20200111576A1 (en) | Producing a multidimensional space data structure to perform survival analysis | |
CN107145723A (en) | Hospital process management system based on artificial neural network | |
CN109377388A (en) | Medical insurance is insured method, apparatus, computer equipment and storage medium | |
CN112908452A (en) | Event data modeling | |
CN108182633A (en) | Loan data processing method, device, computer equipment and storage medium | |
Mudaliar et al. | Disease prediction and drug recommendation android application using data mining (virtual doctor) | |
CN112233747A (en) | Twin network data analysis method and system based on personal digital | |
US20220343160A1 (en) | Time series data processing device configured to process time series data with irregularity |
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 |