CN108932974B - Method, device, computer equipment and storage medium for allocating doctors for online inquiry - Google Patents
Method, device, computer equipment and storage medium for allocating doctors for online inquiry Download PDFInfo
- Publication number
- CN108932974B CN108932974B CN201810550865.3A CN201810550865A CN108932974B CN 108932974 B CN108932974 B CN 108932974B CN 201810550865 A CN201810550865 A CN 201810550865A CN 108932974 B CN108932974 B CN 108932974B
- Authority
- CN
- China
- Prior art keywords
- doctor
- user
- dynamic parameters
- queuing
- department
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Pathology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The application relates to a method, a device, computer equipment and a storage medium for allocating doctors for online inquiry. The method comprises the following steps: receiving an inquiry request uploaded by a user terminal, wherein the inquiry request carries a user identifier; distributing corresponding departments for the user identification according to the inquiry request; acquiring a plurality of doctor dynamic parameters in a department; calculating the idle degree of a plurality of doctors according to the dynamic parameters; and determining the doctor assigned to the user identification according to the idle degree. By adopting the method, the waiting time of the consultation user can be shortened.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a computer device, and a storage medium for allocating doctors for online inquiry.
Background
With the improvement of living standard, the attention of all parties to medical treatment is also higher and higher. When some common disease symptoms appear, the disease diagnosis cannot be made by the patient himself, and the hospital is far away, or the hospital is time-consuming and troublesome to queue and register. Therefore, most people will choose to consult the doctor online.
However, the current way of assigning consultants for online consultation is usually to evenly distribute a class of questions to physicians in the same department. However, the ability to receive and process each doctor is not the same, and if the consultants are simply distributed to the doctors equally, the consultants of the individual doctors can be queued up too long, and some doctors can peacock. Conventionally, the selection is given to the department doctors, so that the doctors can decide the number of the patients receiving the treatment, but the problem that a part of the doctors receive a large number of treatments for seeking personal benefits is solved, and the problem that the waiting response time of the users is too long is not actually solved.
Disclosure of Invention
In view of the above, there is a need to provide a method, an apparatus, a computer device and a storage medium for allocating doctors for online inquiry, which can reduce the waiting time of users.
An online interview assignment physician method, the method comprising:
receiving an inquiry request uploaded by a user terminal, wherein the inquiry request carries a user identifier;
distributing corresponding departments to the user identification according to the inquiry request;
acquiring dynamic parameters of a plurality of doctors in the department;
calculating the idle degree of a plurality of doctors according to the dynamic parameters;
and determining doctors allocated to the user identification according to the idle degree.
In one embodiment, the allocating corresponding departments to the user according to the inquiry request includes:
acquiring various user information according to the user identification;
vectorizing the user information to obtain a multi-dimensional vector matrix;
performing prediction operation based on the multi-dimensional vector matrix through a neural network model to obtain a department corresponding to the user identifier;
marking the department as a department assigned to the user identification.
In one embodiment, after determining the doctor assigned to the user identification according to the idle degree, the method further comprises:
acquiring a queuing wheel disc of the doctor, wherein the queuing wheel disc comprises a plurality of queues;
identifying a queuing grade corresponding to the user identification;
storing the user identification into a corresponding queue according to the queuing grade;
and when a pulling request of a doctor terminal is received, pulling the user identification from the queue of the queuing wheel disc according to the pulling request.
In one embodiment, the calculating the idleness of the doctors according to the dynamic parameters comprises:
acquiring a state logic value of a doctor and a weight corresponding to the dynamic parameter;
determining a doctor state according to the doctor state logic value, wherein the doctor state comprises an online state;
if the doctor state is an online state, respectively calculating the product of the dynamic parameters and the weights corresponding to the dynamic parameters to obtain a plurality of weight values;
summing the plurality of weight values to determine the degree of idleness of the doctor.
In one embodiment, after pulling the user identifier from the queue of the queued carousel according to the pull request, the method further comprises:
updating the dynamic parameters of the doctor;
and covering the dynamic parameters before updating with the updated dynamic parameters.
An online interview distribution physician apparatus, the apparatus comprising:
the system comprises a receiving module, a processing module and a processing module, wherein the receiving module is used for receiving an inquiry request uploaded by a user terminal, and the inquiry request carries a user identifier;
the distribution module is used for distributing corresponding departments to the user identification according to the inquiry request;
the acquisition module is used for acquiring dynamic parameters of a plurality of doctors in the department;
the calculating module is used for calculating the idle degrees of a plurality of doctors according to the dynamic parameters;
and the selection module is used for determining doctors distributed to the user identification according to the idle degree.
In one embodiment, the allocation module is further configured to obtain a plurality of user information according to the user identifier; vectorizing the user information to obtain a multi-dimensional vector matrix; performing prediction operation based on the multi-dimensional vector matrix through a neural network model to obtain a department corresponding to the user identifier; marking the department as a department assigned to the user identification.
In one embodiment, the obtaining module is further configured to obtain a queuing wheel of the doctor, where the queuing wheel includes a plurality of queues;
the device further comprises:
the identification module is used for identifying the queuing level corresponding to the user identifier;
the storage module is used for storing the user identification into a corresponding queue according to the queuing grade;
and the pulling module is used for pulling the user identifier from the queue of the queuing wheel disc according to the pulling request when the pulling request of the doctor terminal is received.
A computer device comprising a memory storing a computer program and a processor implementing the online interrogation doctor assignment method as claimed in any one of the preceding claims when the computer program is executed by the processor.
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the online interrogation doctor assignment method as described in any one of the above.
According to the method and device for allocating doctors for on-line inquiry, the computer equipment and the storage medium, the server receives the inquiry request uploaded by the user terminal, the inquiry request carries the user identification, and the corresponding department is allocated to the user identification according to the inquiry request. When the user needs on-line inquiry, the department does not need to be manually selected. And after the department is allocated, the server acquires dynamic parameters of a plurality of doctors in the department, calculates the idle degree of the plurality of doctors according to the dynamic parameters, and determines the doctors allocated to the user identifier according to the idle degree. Doctors are allocated to the users according to the idle degrees of different doctors, so that the consultation waiting time of the users is shortened.
Drawings
FIG. 1 is a diagram of an exemplary implementation of a method for assigning physicians for online interrogation;
FIG. 2 is a schematic flow chart illustrating a method for assigning physicians for online interrogation in one embodiment;
FIG. 3 is a schematic flow chart diagram illustrating the steps of assigning corresponding departments to user identifiers based on an interrogation request in one embodiment;
FIG. 4 is a schematic flow chart illustrating a method for assigning physicians for online interrogation in another embodiment;
FIG. 5 is a block diagram of an apparatus for assigning physicians for online interrogation according to one embodiment;
FIG. 6 is a diagram of the internal structure of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The online inquiry doctor allocation method provided by the application can be applied to the application environment shown in fig. 1. Including a user terminal 102, a doctor terminal 106, and a server 104. Wherein a user terminal 102 communicates with a server 104 over a network. The doctor terminal 106 communicates with the server 104 through a network. The user terminal 102 and the doctor terminal 106 may be, but are not limited to, various personal computers, laptops, smart phones, tablets and portable wearable devices, and the server 104 may be implemented as a stand-alone server or a server cluster composed of a plurality of servers. Specifically, when the user needs to consult a doctor online, the inquiry request may be uploaded to the server 104 through the user terminal 102. The server 104 receives the inquiry request uploaded by the user terminal 102, wherein the inquiry request carries the user identifier. The server 104 assigns a corresponding department to the user identifier according to the inquiry request. After the server 104 allocates departments to the users, the server also obtains a plurality of doctor dynamic parameters in the departments, calculates the idle degrees of a plurality of doctors according to the dynamic parameters, selects the most idle doctor according to the idle degrees, and determines the doctor allocated to the user identifier for the most idle doctor. After the server 104 distributes the doctor, the communication connection between the user terminal 102 and the doctor terminal 106 can be established, and online inquiry is realized.
In one embodiment, as shown in fig. 2, an online consultation assignment doctor method is provided, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:
s202, receiving an inquiry request uploaded by a user terminal, wherein the inquiry request carries a user identifier.
And an application program for online inquiry is installed on the user terminal. The user needs to register before logging into the application. The registration information includes basic information such as user identification and gender. When a user wants to consult a doctor on line, the user does not need to manually select a department, can click an inquiry button in the application program to generate an inquiry request, and sends the inquiry request to the server through the application program.
And S204, distributing corresponding departments for the user identification according to the inquiry request.
And the server collects various user information according to the user identification carried in the inquiry request. By vectorizing the user information, a corresponding multidimensional vector matrix can be obtained. The server calls the deep neural network model, and prediction operation is carried out on the basis of the multidimensional vector matrix through the deep neural network model, so that departments allocated to the user identification are accurately obtained. Therefore, departments can be automatically allocated to the user without manually selecting the departments by the user.
S206, acquiring a plurality of doctor dynamic parameters in the department.
And S208, calculating the idle degrees of a plurality of doctors according to the dynamic parameters.
The dynamic parameters include the number of queues, the number of concurrences, the ability to receive a call, and the time from the last pull. Wherein the queue number represents the number of users in the current doctor queue to queue up for consultation. The concurrence number represents the actual number of the current doctors, namely the number of consulting users currently processed by the doctors at the same time. The number of patients who can receive the treatment is the reference of the ability value of receiving the treatment. The server obtains the dynamic parameters from the database or the doctor terminal, and then substitutes the dynamic parameters into a calculation formula to calculate the vacancy degree of the doctor, and simultaneously can calculate the vacancy degrees of a plurality of doctors.
And S210, determining doctors allocated to the user identification according to the idle degree.
The level of idleness varies from doctor to doctor, with doctors with lower idleness being more busy. The longer the user waits for a response if the user is assigned to a busy doctor. Therefore, when the idle degrees of doctors in departments are different, the doctor who is the most idle in the current department is selected according to the idle degree, and the doctor who is the most idle is determined as the doctor assigned to the user identifier. When the vacancy degrees of a plurality of doctors in the department are the same, the server acquires the doctor information table of the doctors from the database, wherein the doctor information table comprises basic personal data such as the names and the sexes of the doctors, the department to which the doctors belong, the titles of the doctors and the like. And selecting the doctor with the highest job rank from a plurality of doctors with the same idle degree according to the doctor job, and determining the doctor as the doctor assigned to the user identifier. If a plurality of doctors with the same job title level exist at the same time, the server randomly selects one doctor to be determined as the doctor distributed to the user identification.
In the above method for allocating doctors for on-line inquiry, the server receives an inquiry request uploaded by the user terminal, the inquiry request carries the user identifier, and allocates a corresponding department to the user identifier according to the inquiry request. When the user needs on-line inquiry, the department does not need to be manually selected. And after the department is allocated, the server acquires dynamic parameters of a plurality of doctors in the department, calculates the idle degree of the plurality of doctors according to the dynamic parameters, and determines the doctors allocated to the user identifier according to the idle degree. Doctors are allocated to the users according to the idle degrees of different doctors, so that the consultation waiting time of the users is shortened.
In one embodiment, as shown in fig. 3, assigning a corresponding department to a user identifier according to an inquiry request comprises the following steps:
s302, obtaining various user information according to the user identification.
And the server receives an inquiry request uploaded by the user terminal through the application program. The user identification is carried in the inquiry request. The server acquires various user information according to the user identification, including: chief complaint information, basic information, history information, and the like.
The complaint information includes symptom information that is currently uploaded by the user through the application. And when receiving the inquiry request, the server returns a corresponding question to the user terminal. The user can answer these questions through the user terminal. The user, when answering the questions, may describe content related to the current symptom. The user terminal uploads the answer of the user to the server, and the server marks the answer as the chief complaint information.
The server collects corresponding basic information and historical information in parallel while collecting the chief complaint information corresponding to the user identification. The basic information may be information uploaded to the server through the user terminal when the user registers the application program, and includes: age, sex, etc. Users of different ages or sexes may have similar complaint information but need to be distributed to different departments during the inquiry. For example, the complaint information includes "lower abdominal pain", a female user may be assigned to a gynecology department, and a male user may be assigned to a medical department.
The history information includes a history of online inquiry by the user through an application program, a medical record of the current medical institution, and the like. Because the user usually enters the same department as the first diagnosis in the second diagnosis, if the user is in the second diagnosis in the online inquiry, the probability of entering the same department is higher. Therefore, the historical information of the user can help to improve the accuracy of department allocation.
S304, vectorizing the user information to obtain a multi-dimensional vector matrix.
The server preprocesses the collected information of the plurality of users. The pretreatment comprises the following steps: word segmentation, word stop, simple reproduction, etc. And the server selects the features from the preprocessed multiple user information to obtain multiple features. And the server converts each selected feature into a corresponding one-dimensional vector, and converts the one-dimensional vectors corresponding to the plurality of features through a word vector model to obtain a multi-dimensional vector matrix corresponding to the user identifier.
And S306, carrying out prediction operation through the deep neural network model based on the multi-dimensional vector matrix to obtain a department corresponding to the user identification.
S308, marking departments as departments assigned to the user identification.
The chief information, the basic information and the historical information in the user information can also be respectively regarded as the input categories of the deep neural network. The server can obtain the multidimensional vector matrix corresponding to each input category through the word vector model, and then combines the multidimensional vector matrices corresponding to a plurality of input categories to generate the input vector matrix corresponding to the deep neural network model.
The server calls the deep neural network model, the input vector matrix is used as the input of the deep neural network model, the deep neural network model carries out operation, and the probability of the department corresponding to the multidimensional vector matrix is predicted. The server may take the department with the highest probability as the department corresponding to the user identifier, and determine the department as the department assigned to the user identifier. Because the input vector matrix contains the contents of basic information, historical information, chief complaint information and the like, departments required by the online inquiry of the user can be obtained through accurate analysis of the deep neural network model.
The deep neural network model may be a convolutional neural network including a convolutional layer, a fully-connected layer, and an output layer. The convolutional layer, the fully-connected layer, and the output layer include a plurality of neurons. The neuron is also a unit for calculation and storage in the deep neural network model. The number of neurons in the convolutional layer, the fully-connected layer, and the output layer is different. The number of neurons in the convolutional layer may be the same as the number of dimensions for each input category. The number of dimensions of the input category may be the number of dimensions of a multi-dimensional vector matrix corresponding to the input category. For example, if the multidimensional vector matrix is a 256 × 256 matrix, the number of neurons in the convolutional layer may be 256. The corresponding multi-dimensional vector matrices for different input classes may be of the same dimension. The convolutional layers may include a plurality of layers, and the number of neurons in each convolutional layer may be the same. The number of neurons in the fully-connected layer is greater than the number of neurons in the convolutional layer, and for example, the number of neurons in the fully-connected layer is a multiple of the number of neurons in the convolutional layer. The number of neurons in the output layer may be the same as the number of departments.
Wherein, the deep neural network model is trained in advance. Before training, the convolutional layer, the fully-connected layer and the output layer of the deep neural network model are all set with corresponding initialization parameters. The variance of the initialization parameters can be increased layer by layer, so that the initialization parameters in the deep neural network model are dispersed more and more, and the learning speed and the prediction accuracy of the deep neural network model can be improved in the training process. The convolution layers are also provided with corresponding activation functions and pooling layers, wherein different convolution layers can adopt different pooling layers and can also adopt corresponding pooling layers, and different convolution layers can adopt different activation functions. The interrelationship between the features of each dimension can be calculated through a plurality of convolutional layers, data interference irrelevant to the features can be reduced through the pooling layer, overfitting is reduced, and a result close to the features is obtained through training.
In this embodiment, when the user needs online inquiry, the inquiry request can be uploaded through the user terminal without manually selecting a department. And the server collects various user information according to the user identification carried in the inquiry request. By vectorizing the user information, a corresponding multidimensional vector matrix can be obtained. The server calls the deep neural network model, and prediction operation is carried out on the basis of the multidimensional vector matrix through the deep neural network model, so that departments allocated to the user identification are accurately obtained. Therefore, departments can be automatically allocated to the user when the client makes an on-line inquiry, and the accuracy of department allocation is effectively improved.
In one embodiment, as shown in fig. 4, after determining the doctor assigned to the user identification according to the idle degree, the method further comprises the following steps:
s402, acquiring a queuing wheel disc of a doctor, wherein the queuing wheel disc comprises a plurality of queues.
Each doctor is provided with a corresponding queuing wheel which can support independent configuration by the doctor. The doctor can divide the scale number and the queue number according to the actual situation, and can set the queue level in a targeted manner, wherein the higher the level is, the more the scale number occupied by the queue is, which means that the higher the probability that the user waiting for inquiry in the queue is out of queue is, the shorter the waiting response time is.
The queuing wheel disc is a queuing mode in a wheel disc mode, a plurality of scales can be arranged on the wheel disc, and the number of the scales can be set according to actual requirements. The queuing carousel comprises a plurality of queues, and each queue comprises a plurality of scales, namely, one queue comprises at least one scale. Therefore, as long as the queue is set, the number of scales belonging to at least one grid of the queue can be found on the queuing wheel. The number of the queues can be multiple, and the specific number of the queues in the queuing wheel disc can be set according to actual requirements. And the queues are all provided with different grades, the grade is determined by the scale number forming the queue, and the more the scale number forming the queue is, the higher the grade of the queue is. The number of scales can only determine the level of the queue and the number of the user identifications which can be dequeued when the roulette rotates for one circle, but cannot determine the number of the user identifications which can be queued in the queue. That is, the number of queues that can be accommodated by the queue is independent of the number of scales, and the number of scales can only represent the level of the user, because the larger the number of scales occupied by the queue, the higher the dequeuing probability of the queue when the roulette rotates one turn. Therefore, the queuing number which can be accommodated by the queue can be set freely according to the actual situation. Therefore, the dequeue mode using the roulette mode can ensure that the users with high grade can enjoy certain priority, and meanwhile, the waiting time of the users with low grade can be reduced.
S404, identifying the queuing level corresponding to the user identification.
The user identification is carried in the inquiry request. The server acquires various user information according to the user identification, including: chief complaint information, basic information, history information, and the like. Each user can store the queuing level in the basic information when registering, so that the queuing level of the user can be obtained from the basic information.
S406, storing the user identification into the corresponding queue according to the queuing grade.
Different queues have different levels, and the queuing level of the user identifier waiting in each queue is consistent with the queue level. That is, each queuing level can find a queue corresponding to the level in the queuing roulette, and if the queuing level of the user identifier is 2, the entered queue is a queue of level 2 in the queuing roulette. Therefore, the user identification is stored in the queue of the queue grade corresponding to the queuing grade according to the queuing grade of the user.
S408, when a pulling request of the doctor terminal is received, pulling the user identification from the queue of the queuing wheel disc according to the pulling request.
The pull request refers to the information carrying the queued carousel. The queuing wheel disc information comprises account information of doctors corresponding to the queuing wheel disc, each doctor has the queuing wheel disc, and the server can determine the queuing wheel disc corresponding to the doctor according to the account information of the doctor. Specifically, the server receives a pull request containing the information of the queuing roulette from the second terminal, and pulls the user identifier from the queue in the corresponding queuing roulette according to the pull request. Because the user identification has uniqueness, after the user identification is pulled, the corresponding user terminal can be determined according to the user identification, and the server can establish the online communication connection between the user terminal and the doctor terminal.
In this embodiment, the server stores the user-identified queue rating in the queue corresponding to the doctor's queuing wheel. When a doctor asks a user to be consulted online, a pulling request can be uploaded to the server through the doctor terminal, so that the corresponding user identification can be pulled in the wheel-disk type queue, and the users of different grades can be guaranteed to respond at the highest speed.
In one implementation, as shown in FIG. 5, calculating the idleness of a plurality of physicians based on the dynamic parameters includes: acquiring the state logic value of the doctor and the weight corresponding to the dynamic parameter; determining the doctor state according to the doctor state logic value, wherein the doctor state comprises an online state; if the doctor state is an online state, respectively calculating the dynamic parameters and the riding machine of the weights corresponding to the dynamic parameters to obtain a plurality of weighted values; the plurality of weight values are summed to determine the degree of idleness of the doctor.
Before acquiring doctor dynamic parameters and calculating the idle degree, the server needs to judge the doctor state. The doctor status includes not only an online status but also an offline status, and when the doctor is in the offline status, the doctor cannot perform the examination receiving work. Therefore, the server first acquires the state logic value of the department doctor, and if the state logic value acquired by the server is 1, the state logic value indicates that the doctor is currently in an offline state. The doctor in the off-line state is directly excluded from doctors who need to calculate the degree of idleness, and does not perform calculation. If the acquired state logic value is 0, the current doctor is in an online state, and the idleness of the doctor can be calculated.
The dynamic parameters comprise the number of queues, the number of concurrences, the ability to receive a diagnosis and the time interval from the last user pulling, and each dynamic parameter can be set with a corresponding weight. Wherein, the queuing number and the concurrency number represent the number of people who are queued or in consultation in the queue of the current doctor, and the more the queuing number and the consultation number represent the busyness of the doctor. The number of doctors that can receive the doctor at the same time and the length of the rest time till now are respectively represented by the diagnosis receiving capability value and the time interval from the last pulling user, so that the higher the diagnosis receiving capability value and the time interval from the last pulling user are, the more idle the doctors are. Therefore, the queuing number and the concurrence number are busy dynamic parameters, and the visit ability value and the time interval from the last user pulling are idle dynamic parameters.
When the overall idle degree of the doctor is calculated, the idle degree of the doctor is calculated only by using the idle dynamic parameters, and in order to ensure the accuracy of the busy and idle state of the doctor, the influence caused by the busy dynamic parameters is also considered. And finally, the idle degree is calculated by adopting a mode of summing a plurality of weighted values. Therefore, to counteract the effect of the physician's busy dynamics parameters on the actual level of idleness, the weight of the busy dynamics parameters may be represented by a negative number and the weight of the idle dynamics parameters may be represented by a positive number. For example, the queue number may be weighted by-0.4, the concurrency number by-0.2, the receptivity value by 0.1, and the time interval from the last pull user by 0.3.
The idle degree calculation formula is as follows: the queue number weight + the concurrency number + the consultation capacity value weight (consultation capacity value-concurrency number) + the time interval weight from the last user pulling and the time interval from the last user pulling.
The number of the doctors who can receive the doctors at the same time is the receiving capacity value, and the number of the concurrent visits is the number of the doctors who have received the doctors at the same time, so that the difference value between the receiving capacity value and the number of the concurrent visits can represent the actual receiving capacity value of the current doctors. Therefore, the weight of the ability value of the reception call (the ability value of the reception call-the number of concurrent times) is calculated in the formula. The formula can show that the larger the queuing number and the concurrency number, the lower the score of the idle degree, the larger the difference value between the diagnosis receiving capability value and the concurrency number, and the longer the time interval from the last pulling of the user, the higher the score of the idle degree.
When calculating the vacancy degrees of a plurality of doctors, the final value may be negative in partial doctor vacancy degree values and positive in partial doctor vacancy degree values according to different dynamic parameters of doctors. Therefore, in order to keep the format of the final calculation result consistent and easy to view, a basic value may be added before the calculation formula, for example, the basic value is 1000, and the calculation formula is: 10000+ queuing weight + concurrency value + reception ability value weight (reception ability value-concurrency number) + time interval weight from last user pulling and time interval from last user pulling.
The time interval from the last pulling user is in units of minutes, and if the time from the last pulling user is 0.5 hour, the time is converted into 30 minutes. I.e. the time interval weight of the last pulled user at 30 x distance. Assuming that the number of queues is 30, the number of concurrences is 20, the accessibility value is 50, and the time interval from the last pulling user is 30 minutes, the result of the idle degree calculated by the calculation formula is:
10000-0.4*30-0.2*20+0.1*(50-20)+0.3*30=9996
the calculated result score can be used for dividing the idleness of the doctor, for example, when the doctor score is higher than the 9996 score, the idleness of the doctor is larger than the 9996 score. A doctor with a score lower than 9996 is less idle than a doctor with a score of 9996. Also, by dividing the division into sections by the division value, the level of the degree of idleness of each section can be set to be different. For example, the doctor's vacancy degree with a score in the range of [9000,10000] is ranked 1, the doctor's vacancy degree with a score in the range of [8000, 9000 ] is ranked 2, and the specific vacancy degree expression mode can be set according to actual conditions.
In this embodiment, the dynamic parameters and the corresponding different weights of the dynamic parameters are obtained, and the product of the dynamic parameters and the corresponding weights is calculated to obtain multiple weight scores, and the scores of the idle degree are obtained after summation. The calculated idle degree score is consistent with the actual idle state of the doctor by using the actual dynamic parameters which can indicate that the doctor is idle or busy, and the accuracy of calculating the idle degree score is ensured.
In one embodiment, after pulling the user identification from the queue of the queuing carousel in accordance with the pull request, comprises: updating the dynamic parameters of the doctor; and covering the dynamic parameters before updating by using the updated dynamic parameters.
After the user identification is pulled from the physician's queuing wheel, the physician's queue number and concurrency number are changed. The idle degree should be calculated according to the latest dynamic parameters to be closer to the actual situation. Therefore, after the user identifier is pulled, the dynamic parameters of the doctor should be updated, and the updated dynamic parameters are overlaid on the dynamic parameters before the update. And the latest dynamic parameters can be used for calculation at the next calculation.
In the above method for allocating doctors for on-line inquiry, the server receives an inquiry request uploaded by the user terminal, the inquiry request carries a user identifier, and allocates a corresponding department to the user identifier according to the inquiry request. When the user needs on-line inquiry, the department does not need to be manually selected. And after the department is allocated, the server acquires dynamic parameters of a plurality of doctors in the department, calculates the idle degree of the plurality of doctors according to the dynamic parameters, selects the most idle doctor according to the idle degree, and determines the most idle doctor to identify the doctor allocated to the user. And the most leisure doctors are allocated to the users according to the leisure degrees of different doctors, so that the consultation waiting time of the users is shortened.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 5, there is provided an online inquiry assignment physician apparatus 500, comprising: a receiving module 502, an assigning module 504, an obtaining module 506, a calculating module 508, and a selecting module 510, wherein:
the receiving module 502 is configured to receive an inquiry request uploaded by a user terminal, where the inquiry request carries a user identifier.
And the allocating module 504 is configured to allocate a corresponding department to the user identifier according to the inquiry request.
An obtaining module 506 is configured to obtain dynamic parameters of a plurality of doctors in a department.
A calculating module 508 for calculating the idleness of the plurality of doctors according to the dynamic parameters.
A selection module 510 for determining the assigned doctor to the user identification based on the degree of idleness.
In one embodiment, the assignment module 504 is further configured to obtain a plurality of user information according to the user identifier. And vectorizing the user information to obtain a multi-dimensional vector matrix. And performing prediction operation on the basis of the multidimensional vector matrix through a neural network model to obtain a department corresponding to the user identification. The department is marked as the department assigned to the user identification.
In one embodiment, the acquisition module is further configured to acquire a queue wheel of the doctor, the queue wheel including a plurality of queues.
The apparatus 500 further comprises:
and the identification module is used for identifying the queuing level corresponding to the user identifier.
And the storing module is used for storing the user identification into the corresponding queue according to the queuing grade.
And the pulling module is used for pulling the user identifier from the queue of the queuing wheel disc according to the pulling request when the pulling request of the doctor terminal is received.
In one embodiment, the calculation module 508 is further configured to obtain the corresponding weights of the status logic values and the dynamic parameters of the doctor. And determining the doctor state according to the doctor state logic value, wherein the doctor state comprises an online state. And if the doctor state is in an online state, respectively calculating the products of the dynamic parameters and the weights corresponding to the dynamic parameters to obtain a plurality of weight values. The plurality of weight values are summed to determine the degree of idleness of the doctor.
In one embodiment, the apparatus 500 further comprises an update module for updating the physician's dynamic parameters. And covering the dynamic parameters before updating by using the updated dynamic parameters.
For the specific definition of the on-line inquiry allocation doctor device, reference may be made to the above definition of the method for allocating doctors for on-line inquiry, and details are not described herein again. The various modules in the above-described online interrogation distribution physician apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data such as user identification, dynamic parameters and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an online consultation assignment physician method.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory having a computer program stored therein and a processor that when executing the computer program performs the steps of:
receiving an inquiry request uploaded by a user terminal, wherein the inquiry request carries a user identifier;
distributing corresponding departments for the user identification according to the inquiry request;
acquiring a plurality of doctor dynamic parameters in a department;
calculating the idle degree of a plurality of doctors according to the dynamic parameters;
and determining the doctor assigned to the user identification according to the idle degree.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring various user information according to the user identification;
vectorizing the user information to obtain a multi-dimensional vector matrix;
performing prediction operation based on a multi-dimensional vector matrix through a deep neural network model to obtain departments corresponding to the user identification;
the department is marked as the department assigned to the user identification.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring a queuing wheel disc of a doctor, wherein the queuing wheel disc comprises a plurality of queues;
identifying a queuing grade corresponding to the user identification;
storing the user identification into a corresponding queue according to the queuing grade;
and when a pulling request of the doctor terminal is received, pulling the user identifier from the queue of the queuing wheel disc according to the pulling request.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a state logic value of a doctor and a weight corresponding to the dynamic parameter; determining the doctor state according to the doctor state logic value, wherein the doctor state comprises an online state; if the doctor state is an online state, respectively calculating the dynamic parameters and the riding machine of the weights corresponding to the dynamic parameters to obtain a plurality of weighted values; the plurality of weight values are summed to determine the degree of idleness of the doctor.
In one embodiment, the processor, when executing the computer program, further performs the steps of: updating the dynamic parameters of the doctor; and covering the dynamic parameters before updating by using the updated dynamic parameters.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
receiving an inquiry request uploaded by a user terminal, wherein the inquiry request carries a user identifier;
distributing corresponding departments for the user identification according to the inquiry request;
acquiring a plurality of doctor dynamic parameters in a department;
calculating the idle degree of a plurality of doctors according to the dynamic parameters;
and determining the doctor assigned to the user identification according to the idle degree.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring various user information according to the user identification;
vectorizing the user information to obtain a multi-dimensional vector matrix;
performing prediction operation based on a multi-dimensional vector matrix through a deep neural network model to obtain departments corresponding to the user identification;
the department is marked as the department assigned to the user identification.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring a queuing wheel disc of a doctor, wherein the queuing wheel disc comprises a plurality of queues;
identifying a queuing grade corresponding to the user identification;
storing the user identification into a corresponding queue according to the queuing grade;
and when a pulling request of the doctor terminal is received, pulling the user identification from the queue of the queuing wheel disc according to the pulling request.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a state logic value of a doctor and a weight corresponding to the dynamic parameter; determining the doctor state according to the doctor state logic value, wherein the doctor state comprises an online state; if the doctor state is an online state, respectively calculating the dynamic parameters and the riding machine of the weights corresponding to the dynamic parameters to obtain a plurality of weighted values; the plurality of weight values are summed to determine the degree of idleness of the doctor.
In one embodiment, the computer program when executed by the processor further performs the steps of: updating the dynamic parameters of the doctor; and covering the dynamic parameters before updating by using the updated dynamic parameters.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An online consultant assignment method, the method comprising:
receiving an inquiry request uploaded by a user terminal, wherein the inquiry request carries a user identifier;
distributing corresponding departments to the user identification according to the inquiry request;
acquiring dynamic parameters of a plurality of doctors in the department;
acquiring a state logic value of a doctor and a weight corresponding to the dynamic parameter;
determining a doctor state according to the doctor state logic value, wherein the doctor state comprises an online state;
if the doctor state is an online state, respectively calculating the product of the dynamic parameters and the weights corresponding to the dynamic parameters to obtain a plurality of weight values;
summing the plurality of weight values to determine a level of idleness of the doctor;
determining doctors allocated to the user identification according to the idle degree;
the calculation formula of the idle degree is the queuing weight, the queuing number, the concurrency weight, the concurrency value, the visit ability value weight (the visit ability value-concurrency number) + the time interval weight from the last user pulling and the time interval from the last user pulling.
2. The method of claim 1, wherein assigning the corresponding department to the user identifier according to the interrogation request comprises:
acquiring various user information according to the user identification;
vectorizing the user information to obtain a multi-dimensional vector matrix;
performing prediction operation based on the multi-dimensional vector matrix through a neural network model to obtain a department corresponding to the user identification;
marking the department as a department assigned to the user identification.
3. The method of claim 1, wherein after determining the doctor assigned to the user identification based on the idleness level, the method further comprises:
acquiring a queuing wheel disc of the doctor, wherein the queuing wheel disc comprises a plurality of queues;
identifying a queuing level corresponding to the user identifier;
storing the user identification into a corresponding queue according to the queuing grade;
and when a pulling request of a doctor terminal is received, pulling the user identification from the queue of the queuing wheel disc according to the pulling request.
4. The method of claim 3, wherein after pulling the user identification from the queue of the queued carousel in accordance with the pull request, the method further comprises:
updating the dynamic parameters of the doctor;
and covering the dynamic parameters before updating by using the updated dynamic parameters.
5. An online interview assignment physician device, comprising:
the system comprises a receiving module, a sending module and a receiving module, wherein the receiving module is used for receiving an inquiry request uploaded by a user terminal, and the inquiry request carries a user identifier;
the distribution module is used for distributing corresponding departments to the user identification according to the inquiry request;
the acquisition module is used for acquiring dynamic parameters of a plurality of doctors in the department;
the calculation module is used for acquiring the state logic value of the doctor and the weight corresponding to the dynamic parameter; determining a doctor state according to the doctor state logic value, wherein the doctor state comprises an online state; if the doctor state is an online state, respectively calculating the product of the dynamic parameters and the weights corresponding to the dynamic parameters to obtain a plurality of weight values; summing the plurality of weight values to determine a degree of idleness of the doctor; the calculation formula of the idle degree is the weight of a queue number, the weight of a concurrency number, the weight of a reception capability value, the weight of the reception capability value (the reception capability value, the concurrency number), the weight of a time interval from the last user pulling and the time interval from the last user pulling;
and the selection module is used for determining doctors distributed to the user identification according to the idle degree.
6. The apparatus of claim 5, wherein the allocating module is further configured to obtain a plurality of user information according to the user identifier; vectorizing the user information to obtain a multi-dimensional vector matrix; performing prediction operation based on the multi-dimensional vector matrix through a neural network model to obtain a department corresponding to the user identifier; marking the department as a department assigned to the user identification.
7. The apparatus of claim 5, wherein the obtaining module is further configured to obtain a queue wheel of the physician, the queue wheel comprising a plurality of queues;
the device further comprises:
the identification module is used for identifying the queuing level corresponding to the user identifier;
the storage module is used for storing the user identification into a corresponding queue according to the queuing grade;
and the pulling module is used for pulling the user identifier from the queue of the queuing wheel disc according to the pulling request when the pulling request of the doctor terminal is received.
8. The apparatus of claim 7, further comprising an update module for updating the dynamic parameters of the doctor; and covering the dynamic parameters before updating by using the updated dynamic parameters.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program performs the steps of the method according to any of claims 1 to 4.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4.
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 CN108932974A (en) | 2018-12-04 |
CN108932974B true 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) |
Families Citing this family (13)
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 |
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 |
CN111507414B (en) * | 2020-04-20 | 2022-02-08 | 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 |
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 |
CN113764081B (en) * | 2021-03-26 | 2024-07-16 | 北京京东拓先科技有限公司 | Method, device, equipment and computer readable storage medium for determining inquiry number |
CN113241134B (en) * | 2021-04-26 | 2023-07-04 | 哈尔滨工业大学(深圳) | On-line consultation 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 |
CN116646065B (en) * | 2023-05-25 | 2024-03-19 | 浙江蕙康科技有限公司 | Internet hospital data security management method and device |
Citations (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 |
Also Published As
Publication number | Publication date |
---|---|
CN108932974A (en) | 2018-12-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108932974B (en) | Method, device, computer equipment and storage medium for allocating doctors for online inquiry | |
CN112017789B (en) | Triage data processing method, triage data processing device, triage data processing equipment and triage data processing medium | |
US11152119B2 (en) | Care path analysis and management platform | |
US8260636B2 (en) | Method and system for prioritizing communication of a health risk | |
US20210151140A1 (en) | Event Data Modelling | |
CN116453706B (en) | Hemodialysis scheme making method and system based on reinforcement learning | |
CN111667890A (en) | Medication recommendation method, device, equipment and storage medium based on artificial intelligence | |
JP2019063027A (en) | Menstrual type identification system and program | |
CN115132356A (en) | Internet medical triage method and device, electronic equipment and storage medium | |
CN112132624A (en) | Medical claims data prediction system | |
CN111696661A (en) | Patient clustering model construction method, patient clustering method and related equipment | |
CN108847278B (en) | On-line inquiry automatic allocation method, device, computer equipment and storage medium | |
CN114783580A (en) | Medical data quality evaluation method and system | |
CN111354451A (en) | Intelligent recommendation method and system for hospital nursing service personnel | |
WO2021193864A1 (en) | Method and system for determining event class by ai | |
CN113657970A (en) | Artificial intelligence based medicine recommendation method, device, equipment and storage medium | |
JP2006163489A (en) | Disease onset probability calculating device, and program | |
CN113360941A (en) | Medical data processing method and device based on digital twins and computer equipment | |
JP4499503B2 (en) | Onset risk calculation system and program | |
CN113724824B (en) | Chronic patient follow-up method, device, computer equipment and readable storage medium | |
JP7143892B2 (en) | Apparatus for predicting human weight and health care apparatus and method | |
JP2003526137A (en) | Method and apparatus for automatically allocating staffing | |
CN111354449B (en) | Long-term care strategy distribution method, device, computer equipment and storage medium | |
WO2020115730A1 (en) | Integrated system and method for personalized stratification and prediction of neurodegenerative disease | |
CN114334106A (en) | Doctor allocation algorithm based on inquiry data |
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 |