CN115132356A - Internet medical triage method and device, electronic equipment and storage medium - Google Patents
Internet medical triage method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115132356A CN115132356A CN202210860822.1A CN202210860822A CN115132356A CN 115132356 A CN115132356 A CN 115132356A CN 202210860822 A CN202210860822 A CN 202210860822A CN 115132356 A CN115132356 A CN 115132356A
- Authority
- CN
- China
- Prior art keywords
- matched
- doctor
- department
- inquiry information
- doctors
- 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.)
- Pending
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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
The application relates to an internet medical triage method, an internet medical triage device, electronic equipment and a storage medium. The internet medical triage method comprises the following steps: receiving inquiry information sent by a user terminal; processing the inquiry information by using a pre-trained department triage model to obtain a matched department; determining a matching doctor from the doctors belonging to the matching department; and sending the inquiry information to the terminal of the matched doctor. According to the internet medical diagnosis method, the inquiry information is processed by the department diagnosis model trained in advance to obtain the matched departments, the matched doctors are determined from the doctors belonging to the matched departments, and the inquiry information is sent to the terminals of the matched doctors, so that the inquiry information can be efficiently subjected to diagnosis processing, the processing efficiency of the doctors on the inquiry information is improved, the balanced distribution of medical resources is realized, the inquiry requirements of users can be well met, and the diagnosis efficiency of the users is improved.
Description
Technical Field
The present application relates to the field of internet medical technology, and in particular, to an internet medical triage method, apparatus, electronic device, and storage medium.
Background
With the development of internet technology, especially mobile internet technology, internet medical treatment has increasingly entered people's daily lives. The high-speed increase of the number of internet medical users leads to increase of the number of medical treatment, the waiting time of the users is increased, the processing efficiency of the internet medical platform on a large amount of inquiry information is low, the time spent is long, the working efficiency of doctors is affected, the medical treatment efficiency of the users is affected, and the problem of unbalanced medical resource distribution is easy to occur. In the prior art, an efficient internet medical diagnosis dividing technical scheme is lacked, so that efficient diagnosis dividing processing on inquiry information cannot be realized, the processing efficiency of doctors on the inquiry information is low, medical resources cannot be distributed evenly, the inquiry requirements of users cannot be met, and the diagnosis efficiency of the users is low.
Disclosure of Invention
The application provides an internet medical triage method, an internet medical triage device, a computer device and a medium, and aims to solve the technical problems that in the prior art, an efficient internet medical triage technical scheme is lacked, efficient triage processing on inquiry information cannot be achieved, so that processing efficiency of a doctor on the inquiry information is low, medical resources cannot be distributed evenly, inquiry requirements of users cannot be met, and diagnosis efficiency of the users is low.
In a first aspect, an internet medical triage method is provided, including:
receiving inquiry information sent by a user terminal;
processing the inquiry information by using a pre-trained department triage model to obtain a matched department;
determining a matching doctor from the doctors belonging to the matching department;
and sending the inquiry information to the terminal of the matched doctor.
In a second aspect, an internet medical triage device is provided, comprising:
the receiving module is used for receiving the inquiry information sent by the user terminal;
the department triage module is used for processing the inquiry information by utilizing a pre-trained department triage model to obtain a matched department;
a determining module for determining a matching doctor from the doctors belonging to the matching department;
and the sending module is used for sending the inquiry information to the terminal of the matched doctor.
In a third aspect, a computer device is provided, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the internet medical triage method when executing the computer program.
In a fourth aspect, a computer-readable storage medium is provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above-mentioned internet medical triage method.
In the scheme implemented by the internet medical triage method, the internet medical triage device, the internet medical triage computer equipment and the internet medical storage medium, the inquiry information is processed by using a pre-trained department triage model to obtain matched departments, the matched doctors are determined from the doctors belonging to the matched departments, and the inquiry information is sent to the terminals of the matched doctors, so that the inquiry information can be efficiently triaged, the inquiry information processing efficiency of the doctors is improved, the balanced distribution of medical resources is realized, the inquiry requirements of users can be well met, the diagnosis efficiency of the users is improved, and the following technical problems in the prior art are solved: the prior art is lack of an efficient internet medical diagnosis dividing technical scheme, and cannot realize efficient diagnosis dividing processing on inquiry information, so that the processing efficiency of doctors on the inquiry information is low, medical resources cannot be evenly distributed, the inquiry requirements of users cannot be met, and the diagnosis efficiency of the users is low.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic diagram of an application environment of an internet medical triage method according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for Internet medical triage according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a department triage model in an example of the present application;
FIG. 4 is a flowchart illustrating one embodiment of step S40 of FIG. 1;
fig. 5 is a block diagram illustrating an internet medical triage apparatus according to an embodiment of the present disclosure;
FIG. 6 is a flow chart of a method for Internet medical triage in another embodiment of the present application;
FIG. 7 is a schematic diagram of a computer apparatus according to an embodiment of the present application;
FIG. 8 is a schematic diagram of another embodiment of a computer device;
FIG. 9 is a schematic diagram of a computer-readable storage medium in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The internet medical triage method provided by the embodiment of the application can be applied to the application environment shown in fig. 1, wherein the user terminal communicates with the server terminal through the internet. The server terminal can receive the inquiry information sent by the user terminal and send the inquiry information to the matched doctor terminal after triage. The user terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, among others. The server side can be implemented by an independent server or a server cluster formed by a plurality of servers. The present application is described in detail below by way of specific examples.
Referring to fig. 2, fig. 2 is a schematic flow chart of an internet medical triage method according to an embodiment of the present application, including the following steps:
and S10, receiving the inquiry information sent by the user terminal.
The technical scheme of the embodiment of the application can be applied to an internet medical platform which comprises a server side and is used as a communication platform between a user and a doctor to realize online inquiry of the user and online examination of the doctor. Through the internet medical platform, a user can interact with a doctor terminal provided with the same type of application program through a corresponding application program (such as a smart phone APP) installed on a user terminal (such as a smart phone, and the like), and the user terminal and the doctor terminal can also interact with a server side through the application program. The method of the embodiment of the application is executed by the server. The user terminal and the doctor terminal can be devices such as a smart phone, a notebook computer, a desktop computer or a tablet computer.
In an actual application scenario, after a user inputs related information on an application program interface of a terminal of the user, inquiry information may be generated, where the inquiry information may include the related information input by the user, and may also include pre-acquired user feature data, for example, the inquiry information may include data of at least one of the following dimensions: name, sex, age, occupation, symptoms, medical history, and historical exam data.
In the embodiment of the present application, any dimension and data thereof included in the inquiry information may be used as an inquiry identifier of the user. For example, data for certain interrogation information includes: female, age 45, with a history of chest distress, asthma in the last half year, the following multiple questionnaire signatures for that user can be extracted: [ sex-woman ], [ age-45 ], [ symptom-chest distress ], [ medical history-asthma ]. As another example, data for another interrogation message includes: for a male, age 78, sudden dizziness, and history of cerebral infarction, the following multiple identification of the user can be extracted from the history: [ sex-male ], [ age-78 ], [ symptom-dizziness ], [ medical history-cerebral infarction ].
After the inquiry information is generated, the user can send the inquiry information to the server side by clicking the corresponding control of the application program interface. And after receiving the inquiry information, the server side further processes the inquiry information.
And S20, processing the inquiry information by using the pre-trained department triage model to obtain a matched department.
The department triage model is used for judging departments corresponding to the inquiry information (for example, secondary departments such as respiratory medicine and cardiac surgery), can be constructed based on machine learning algorithms such as a convolutional neural network, a naive Bayesian algorithm, a random forest algorithm and a cyclic neural network RNN, can be trained by using a supervised learning method, and can form a training set by using a previous inquiry information text record and a determined matching department in the training process.
And the server side inputs the received inquiry information into a pre-trained department triage model. In an actual application scenario, the department triage model outputs a department triage result, and the department triage result is a matching department corresponding to the inquiry information (the matching department refers to a visiting department matching the inquiry information), for example, if the department triage result is an cardiology department, the matching department is an cardiology department.
In a specific example, as shown in fig. 3, the department triage model adopts a model constructed based on a convolutional neural network model, and comprises an input layer, a convolutional layer, a maximal pooling layer, a full connection layer, a compact layer and an output layer which are connected in sequence.
The department triage model of this embodiment may select a pre-trained Word code as a model input layer, such as Word2Vec or Glove, and may also adopt a character-level convolutional neural network model Char-CNN, where characters are directly input to the department triage model in the form of a One-Hot vector for supervised learning, thereby obtaining a Word vector of a low-dimensional space. The department triage model can also respectively construct a single department by utilizing characters and words of inquiry informationThe hot vector is used as an input layer, and simultaneously, the Word2Vec coding is adopted, and the hot vector is directly used in a Static (Static) mode, namely the Word2Vec coding is not finely adjusted in the training process. After coding transformation, each text in the inquiry information is represented as a sequence with the length of s (t) 1 ，t 2 ，…，t s ) Wherein t is i For the representation of the ith word, s represents the fixed length of the text.
The convolutional layer learns the local semantics and the sequence structure of the inquiry information. The convolutional layer is provided with a plurality of layers of hidden units to obtain implied semantics (the implied semantics can also be called latent semantics) of inquiry information, and convolutional operators with different window sizes are used for learning local semantics and sequence structures existing in the implied semantics and the latent semantics, so that correlation between the disease species and the disease representation is found by using correlation factors.
The department triage model of the embodiment has the input of inquiry information and the output of matching departments, can efficiently extract high-level semantics from noisy and unstructured inquiry information, properly adjusts the sequential structure between continuous words, and can acquire symptom correlation between diseases.
Each filter (also called convolution kernel) is used to learn a specific semantic meaning, and h is used to represent the size of the filter, so each filter can be represented as an h × n weight matrix W and an offset term b. Suppose the input to the filter is matrix D i:i+h-1 Then, the calculation formula for obtaining a new eigenvalue through one convolution operation is c i ＝f(<W，D i:i+h-1 >+ b) of a plurality of different types, wherein,<W，D i:i+h-1 >represents the matrix inner product and f (-) represents the nonlinear activation function.
The maximally pooling layer learns important semantic features of the inquiry information. The maximum pooling layer represents the whole text feature learned by each filter in the previous layer as c 1 ，c 2 ，…c s-h+1 And extracting the maximum characteristic value from the convolution operation as the final output of the convolution operation. The pooling layer can not only extract important features, but also reduce the computational complexity.
And setting a full connection layer after the maximum pooling layer for performing weighted summation on the features extracted by the pooling layer. The fully connected layer is followed by a compact layer, and symptom correlations exist among matching departments, disease categories and body parts at the top of the compact layer, and the study of the correlations by the compact layer can promote more accurate department predictions.
It is assumed that patient symptoms of different departments share a set of association factors, which may represent a common feature between diagnosed diseases, which may also be referred to as latent factors. The predictive model for each department is again a linear combination of these associated factors, with different linear coefficients corresponding to different departments for distinguishing differences between departments. The hidden unit of the compact layer automatically learns and updates the parameters in the continuous training process so as to be used for department prediction, and finally the output layer outputs the prediction probability of the whole model to each department.
For example, there are 10 primary departments in total, 10 neurons are set in the output layer, and k neurons are set in the compact layer, so x ∈ R k The weight matrix is w ∈ R 9xk The bias term is b, the output probability of each department is
p i ＝1/[1+exp(-(w T x+b i ))]Wherein, in the step (A),
calculating the error between the prediction probability and the true value of a department using a Cross Entropy Loss function (Cross Entropy Loss), e.g.
Wherein the content of the first and second substances,
and the real value of the j-th user inquiry information from the ith department is shown, and N represents the current inquiry information quantity. The algorithm obtains the model parameters through a random gradient descent process until convergence.
The training of the department triage model can adopt the historical clinic visit data of the internet medical platform to carry out training and testing, and the trained department triage model meeting the accuracy requirement is obtained.
The training process may include: text data such as patient chief complaint information and medical history information are extracted from historical inquiry information through a regular expression and are processed into a first data set and a second data set. And classifying and labeling the data set according to the department information to which the data belongs, and performing preprocessing such as word segmentation and word stop. Training by adopting a convolutional neural network model, and pre-training the model by taking a classification task of the first data set as an original task; and taking the classification task of the second data set as a target task, using the network structure, parameters and weights of the pre-training model into the classification task of the second data set to obtain a final deep network model, testing the training effect and convergence rate of the network model, and evaluating the model, wherein evaluation indexes can comprise test accuracy, recall rate, precision, F value and the like. And obtaining a model which meets the preset standard through training and evaluation, namely the trained department triage model.
In another specific embodiment, the department triage model may also adopt a combined deep network model based on Bi-LSTM and convolutional neural network or a deep neural network model in other structural forms, which is not described herein again.
Through the operation, the inquiry information distribution can be stopped when the departments are overloaded, so that the problem of unbalanced inquiry information quantity among different departments is solved, the situations that some departments accumulate inquiry information due to too much inquiry information quantity and the other departments can not receive the inquiry information are avoided, the inquiry waiting time can be shortened, the medical resources are fully utilized, and the user experience is improved.
And S40, determining a matched doctor from the doctors belonging to the matched department.
In some embodiments, as shown in fig. 4, step S40 includes:
s401, determining online doctors belonging to the matched departments as candidate doctors;
s402, determining matched doctors from the candidate doctors according to the pre-calculated doctor consultation capacity score.
In some embodiments, step S402 includes: whether the candidate doctors meet preset conditions is sequentially judged according to the descending order of the doctor receiving capacity scores, and the candidate doctors meeting the preset conditions are determined as matched doctors; the preset conditions are that the current number of waiting doctors of the candidate doctors is smaller than a corresponding first preset threshold value, and the number of the people who have received the doctors on the same day of the candidate doctors is smaller than a corresponding second preset threshold value.
In some embodiments, the physician receptivity score is a weighted sum of the number of interrogations being performed, the number of interrogations to be received, and the average physician response time.
For example, after determining candidate doctors of a matching department, the server side may determine whether to assign the inquiry information to the doctor to-be-interviewed list according to the interview capability of each candidate doctor. The doctor processing capacity is characterized by the results of scoring by the doctor processing the inquiry, the inquiry to be received by the doctor and the doctor's recent average response time building model. Among the factors influencing the time length of the received diagnosis of the user, the factors of the number of the currently-in-progress inquiry of the doctor and the average response time length are large, so that a response score calculation formula can be adopted: the doctor's ability to receive a diagnosis score α + number of ongoing diagnoses + number of questions to be received + average doctor's response time γ, α + β + γ ═ 1, for example, α ═ 0.3, β ═ 0.1, and γ ═ 0.6. And the doctor can be assigned only when the doctor receiving capacity score is smaller than a preset threshold value, and the preset threshold value can be set according to the actual application requirement.
If the doctor is idle, the platform distributes the inquiry information of the user to a to-be-interviewed list of the doctor. If the doctor is busy, the user's inquiry information will wait in the queue. For the user priority, the platform can perform the inquiry according to the user chief complaint priority (for example, training is performed through a BERF model by using historical inquiry chief complaints and patient information as a data set, the context and symptoms in the user chief complaints are converted into scores to distinguish the inquiry priority, and then the model results are labeled through professional doctors to improve the accuracy of the model), so that users with serious symptoms can start the inquiry preferentially.
On the basis of a queue system, in order to avoid the problem that a user cannot be processed in a queue for too long time, so that user experience is affected and the user is lost, when the user waiting time exceeds a certain time, a platform obtains departments to be asked by the user through a model according to information such as a user chief complaint, age, gender and the like (the department to be asked by the user is trained by using a BERF model and by using historical information of the chief complaint and a patient as a data set, analysis is performed on the medical department to which the chief complaint describes symptoms, and the user patient department is recommended by the model) and processing capacity weight sequencing, so that other doctors capable of receiving a doctor quickly are recommended to the user to select the departments. The method and the system meet the diagnosis requirements of the user through the measures, reduce the waiting time of the user and improve the user experience.
In some embodiments, the doctor interview ability score is a weighted sum of at least two of a good rate, a response time, a platform length influence rate, a doctor business level, a belonging hospital level parameter, and a non-response rate, wherein the weight of each parameter is a preset value.
Specifically, the goodness parameter of a certain doctor can be calculated by the following method: the method comprises the steps of taking the latest 400 inquiry messages for the doctor to take a consultation, dividing each 100 inquiry messages into one group according to the time sequence from near to far, sequentially setting the weight of each group of inquiry messages to be 0.6, 0.4, 0.2 and 0.1, wherein the good evaluation rate of each group is the ratio of the quantity of the inquiry messages with the scores reaching the good evaluation score threshold value to the quantity of all the evaluated inquiry messages, and the evaluation rate parameter is the weighted sum of the good evaluation rates of each group.
The reply duration parameter for a physician may be calculated based on the average of the reply durations of a plurality (e.g., 200) of most recent inquiry messages received by the physician. The reply duration average is inversely proportional to the reply duration parameter.
The influence rate of the platform parking time of a certain doctor can be a decreasing function of the time of the doctor parking the internet medical platform, and the parameter of the influence rate of the platform parking time is beneficial to improving the weight value of the doctor newly parking the internet medical platform, so that the condition that the inquiry information distributed to the doctor newly parking the internet medical platform is too low due to too low weight value can be avoided. The server side can flexibly set the calculation mode of the influence rate of the platform duration, for example, y is set to be 1-0.002x, where y represents the influence rate of the platform duration, x represents the number of days for entering the internet medical platform, and when x is greater than 500, y is zero.
The doctor business level parameters can be weighted according to the working years, the titles, the jobs, the technical specialties and the like of the doctors, and the belonging hospital level parameters can be weighted according to the levels of the hospitals (such as Hospital, Dimethine Hospital and the like), the number of the staff of the hospitals, the number of the high-grade titles of the hospitals, the ownership properties (such as public hospitals or private hospitals), the hospital establishment years and the like. The unanswered rate parameter is the unanswered rate of the doctor in the historical period, for example, a plurality of recent inquiry messages, for example, 400 inquiry messages, which are received by the doctor are taken, every 100 orders are divided into one group according to the order of the time of the inquiry from near to far, the weight of each group is set to 0.6, 0.4, 0.2 and 0.1 in sequence, the unanswered rate of each group is the ratio of the quantity of the inquiry messages which are unanswered (the unanswered includes two cases of no inquiry in a first preset time period after the inquiry messages are received and no answer in a second preset time period after the inquiry) to the total quantity of the inquiry messages, and the unanswered parameter is the weighted sum of the unanswered rates of each group.
The doctor receiving capacity score is calculated in a mode of weighting and summing the parameters, so that the factors related to the professional level and the service attitude of the doctor are integrated, and the matched doctor is determined from candidate doctors in the matched department according to the doctor receiving capacity score. Specifically, according to the sequence from large to small of the doctor receiving capacity score, the candidate doctors are sequentially used as discrimination objects to execute preset discrimination logic until matching doctors are determined. The above discrimination logic is: and when the current number of waiting people of the discrimination object is less than a third numerical value preset for the discrimination object and the number of people who have received a call on the day of the discrimination object is less than a fourth numerical value preset for the discrimination object, determining the discrimination object as a matching doctor.
Specifically, the doctor consultation capacity scores may be arranged in a descending order, then the current number of waiting doctors and the number of people who have been subjected to consultation of each candidate doctor on the same day are sequentially judged, if the current number of waiting doctors is greater than a corresponding first preset threshold or the number of people who have been subjected to consultation on the same day is greater than a corresponding second preset threshold, it is indicated that the doctor is in heavy burden of consultation, and the judgment of the next doctor is performed until a matching doctor is found. The first preset threshold value is the upper limit value of the number of waiting persons of the doctors at any time, and the second preset threshold value is the upper limit value of the number of receiving persons of the doctors on the same day. In specific application, the first preset threshold and the second preset threshold may be set by the server.
And S50, sending the inquiry information to the terminal of the matched doctor.
After determining the matched doctor, the server side sends inquiry information to the terminal of the matched doctor, such as a smart phone, a desktop computer, a notebook computer or a tablet computer.
Through the operation, the inquiry information distribution to the doctor can be stopped when the doctor consultation burden is overlarge, so that the problem of unbalanced inquiry information quantity among different doctors is solved, the situation that some doctors accumulate the inquiry information due to too much inquiry information quantity and another part of doctors do not have the inquiry information accessibility is avoided, the medical resource distribution is balanced, the inquiry waiting time is favorably shortened, and the user experience is improved.
According to the internet medical triage method, the inquiry information is processed by using the pre-trained department triage model to obtain the matched departments, the matched doctors are determined from the doctors belonging to the matched departments, and the inquiry information is sent to the terminals of the matched doctors, so that the inquiry information can be efficiently triaged, the processing efficiency of the doctors on the inquiry information is improved, the balanced distribution of medical resources is realized, the inquiry requirements of users can be well met, the diagnosis efficiency of the users is improved, and the following technical problems in the prior art are solved: the prior art is lack of an efficient internet medical diagnosis dividing technical scheme, and cannot realize efficient diagnosis dividing processing on inquiry information, so that the processing efficiency of doctors on the inquiry information is low, medical resources cannot be evenly distributed, the inquiry requirements of users cannot be met, and the diagnosis efficiency of the users is low.
In some embodiments, the method further comprises:
s60, receiving the received and diagnosed message and the replied message sent by the matched doctor terminal; wherein the received message is sent after the matching doctor confirms the receiving, and the replied message is sent after the matching doctor replies to the user for the first time.
The matched doctor terminal sends the received doctor message and the replied message to the server terminal, and after the server terminal receives the received doctor message and the replied message, the matched doctor can be determined to have received the doctor.
In some embodiments, after the sending of the inquiry information to the matching physician's terminal, the method further comprises:
s70, if the information of the received diagnosis sent by the matched doctor terminal is not received within the first preset time, determining the inquiry information as the information of the to-be-forwarded diagnosis; and if the answered message sent by the matched doctor terminal is not received within a second preset time period after the received diagnosis receiving message sent by the matched doctor terminal is received within the first preset time period, determining the inquiry information as the information to be forwarded.
The first preset time period may be set according to actual needs, and may be set to 3 minutes, 5 minutes, 10 minutes, and so on. Likewise, the second preset time period may also be set according to actual needs, such as 3 minutes, 5 minutes, 10 minutes, and so on.
And S80, re-determining matched doctors from the matched departments corresponding to the information to be referral according to the pre-calculated doctor consultation capacity score, and sending the information to be referral to the matched doctor terminals.
By re-determining the matched doctors and sending the information to be referral to the re-determined matched doctors, the medical resource allocation can be adjusted, and the user can be ensured to see a doctor in time.
As shown in fig. 5, another embodiment of the present application provides an internet medical triage apparatus, including:
the receiving module is used for receiving the inquiry information sent by the user terminal;
the department triage module is used for processing the inquiry information by utilizing a pre-trained department triage model to obtain a matched department;
a matched doctor determining module for determining a matched doctor from the doctors belonging to the matched department;
and the sending module is used for sending the inquiry information to the terminal of the matched doctor.
In some embodiments, the receiving module is further configured to receive a matched doctor terminal sent received message and a matched reply message; wherein the received message is sent after the matching doctor confirms the receiving, and the replied message is sent after the matching doctor replies to the user for the first time.
The matched doctor terminal sends the received doctor message and the replied message to the server terminal, and after the server terminal receives the received doctor message and the replied message, the matched doctor can be determined to have received the doctor.
In some embodiments, the apparatus further comprises:
the system comprises a to-be-referral information determining module, a to-be-referral information determining module and a to-be-referral information determining module, wherein the to-be-referral information determining module is used for determining inquiry information as to-be-referred information if a received information sent by a matched doctor terminal is not received within a first preset time length; and if the answered message sent by the matched doctor terminal is not received within a second preset time period after the diagnosis receiving message sent by the matched doctor terminal is received within the first preset time period, determining the inquiry information as the information to be forwarded for diagnosis.
And the matched doctor determining module is also used for re-determining matched doctors from the matched departments corresponding to the information to be referral according to the pre-calculated doctor receiving capacity score and sending the information to be referral to the matched doctor terminal.
As shown in fig. 6, another embodiment of the present application provides an internet medical triage method, including:
and S100, receiving inquiry information sent by the user terminal.
And S200, processing the inquiry information by using a pre-trained department triage model to obtain a matched department.
S300, judging whether the matched department meets a first preset condition and a second preset condition at the same time.
The first preset condition is that the current number of waiting visits of the matched department is smaller than a third preset threshold value of the matched department, and the second preset condition is that the number of the visited visits of the matched department on the same day is smaller than a fourth preset threshold value of the matched department.
S400, if the matched department meets the first preset condition and the second preset condition at the same time, determining a matched doctor from the doctors belonging to the matched department, and then sending the inquiry information to the terminal of the matched doctor.
And S500, if the matched department does not meet the first preset condition and the second preset condition at the same time, sending the inquiry information to a preset inquiry information database.
After determining the matching department corresponding to the inquiry information, the server side judges whether the current number of waiting persons of the matching department is greater than a third preset threshold value of the matching department, and judges whether the number of received persons of the matching department on the same day is greater than a fourth preset threshold value of the matching department. The third preset threshold value is the upper limit value of the current waiting number of people in the matched department, and the fourth preset threshold value is the upper limit value of the current receiving number of people in the matched department. Specifically, the third preset threshold and the fourth preset threshold may be preset by the server side.
If the current number of waiting doctors in the matched department is larger than a third preset threshold value or the number of people who have received doctors in the day of the matched department is larger than a fourth preset threshold value, the current burden of receiving doctors in the matched department is heavier, and the inquiry information can be sent to a preset inquiry information database. The inquiry information database is visible for all doctors, and the doctors can send instructions to receive inquiry information in the inquiry information database through the terminal. If the current number of waiting doctors in the matched department is smaller than a third preset threshold and the number of the people who have received a doctor in the day of the matched department is smaller than a fourth preset threshold, the matched department is indicated to have the capability of receiving the doctor, and the matched doctor can be determined from the doctors belonging to the matched department according to the pre-calculated doctor capability value.
After the judgment, the server determines all online doctors belonging to the matching departments as candidate doctors, and then determines the matching doctors from all the candidate doctors, namely the doctors to be treated.
In some embodiments, after the sending of the interrogation information to a preset interrogation information database, the method further comprises: s600, receiving a request instruction from a doctor terminal of the matched department, calling the inquiry information from the inquiry information database and sending the inquiry information to the doctor terminal sending the request instruction.
Specifically, when a doctor in a matched department is in an idle state, the inquiry information database can be checked through the terminal, when the inquiry information in the inquiry information database needs to be received, a request instruction is sent to the server through the terminal, and the server sends the inquiry information in the inquiry information database to the doctor terminal after receiving the request instruction.
The internet medical triage method of the embodiment can realize efficient triage processing of inquiry information, improve the processing efficiency of doctors on the inquiry information, realize balanced distribution of medical resources, well meet the inquiry requirements of users, improve the diagnosis efficiency of users, and solve the following technical problems in the prior art: the prior art is lack of an efficient internet medical diagnosis dividing technical scheme, and cannot realize efficient diagnosis dividing processing on inquiry information, so that the processing efficiency of doctors on the inquiry information is low, medical resources cannot be evenly distributed, the inquiry requirements of users cannot be met, and the diagnosis efficiency of the users is low.
Another embodiment of the present application provides an internet medical triage apparatus, including:
the receiving module is used for receiving the inquiry information sent by the user terminal;
the department triage module is used for processing the inquiry information by utilizing a pre-trained department triage model to obtain a matched department;
the judging module is used for judging whether the matched department meets a first preset condition and a second preset condition at the same time; the first preset condition is that the current number of waiting visits of the matched department is smaller than a third preset threshold value of the matched department, and the second preset condition is that the number of the visited visits of the matched department on the same day is smaller than a fourth preset threshold value of the matched department;
the matched doctor determining module is used for determining a matched doctor from doctors belonging to the matched department if the matched department meets a first preset condition and a second preset condition at the same time, and then sending the inquiry information to a terminal of the matched doctor;
and the sending module is used for sending the inquiry information to a preset inquiry information database if the matched department does not simultaneously meet the first preset condition and the second preset condition.
In some embodiments, the apparatus further includes a forwarding module, configured to receive a request instruction from a doctor terminal of the matched department after the inquiry information is sent to a preset inquiry information database, retrieve the inquiry information from the inquiry information database, and send the inquiry information to the doctor terminal that sends the request instruction.
In one embodiment, a computer device is provided, which may be a server side, and its internal structure diagram may be as shown in fig. 7. 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 includes non-volatile and/or volatile storage media, 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 operating system and the computer program to run on the non-volatile storage medium. The network interface of the computer device is used for communicating with an external user terminal through a network connection. The computer program is executed by a processor to implement the steps of the internet medical triage method of any of the above embodiments.
In one embodiment, a computer device is provided, which may be a user terminal, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, a display screen, and an input device 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 and a computer program. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The network interface of the computer device is used for communicating with an external server through a network connection. The computer program is executed by a processor to realize the steps of the internet medical triage method of any one of the above embodiments.
In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the steps of the internet medical triage method of any of the above embodiments are implemented.
It should be noted that, the functions or steps that can be implemented by the computer-readable storage medium or the computer device can be correspondingly described in the foregoing method embodiments, and the description on the server side and the user terminal side is not repeated here to avoid repetition.
Another embodiment of the present application provides a computer-readable storage medium, which stores a computer program, wherein the computer program is configured to implement the steps of the method according to any of the above embodiments when executed by a processor. As shown in fig. 9, the computer readable storage medium is shown as an optical disc 20, on which a computer program (i.e. a program product) is stored, which when executed by a processor, performs the method provided by any of the foregoing embodiments.
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 can include non-volatile and/or volatile memory. 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 Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (11)
1. An internet medical triage method, comprising:
receiving inquiry information sent by a user terminal;
processing the inquiry information by using a pre-trained department triage model to obtain a matched department;
determining a matching doctor from the doctors belonging to the matching department;
and sending the inquiry information to the terminal of the matched doctor.
2. The method of claim 1, wherein said determining a matching physician from the physicians belonging to the matching departments comprises:
determining online doctors belonging to the matching department as candidate doctors;
and determining a matched doctor from the candidate doctors according to the pre-calculated doctor receiving capacity score.
3. The method of claim 2, wherein said determining a matching physician from said candidate physicians based on a pre-calculated physician visits capability score comprises:
whether the candidate doctors meet preset conditions is sequentially judged according to the descending order of the doctor receiving capacity scores, and the candidate doctors meeting the preset conditions are determined as matching doctors;
the preset conditions are that the current number of waiting doctors of the candidate doctors is smaller than a corresponding first preset threshold value, and the number of the people who have received the doctors on the same day of the candidate doctors is smaller than a corresponding second preset threshold value.
4. The method of claim 3, wherein the physician visit ability score is a weighted sum of the number of visits being made, the number of visits to be made, and the average physician response time; alternatively, the first and second liquid crystal display panels may be,
the doctor receiving capacity score is the weighted sum of at least two of the good rating rate, the answering time, the influence rate of the platform entrance time, the doctor service level, the hospital level parameter and the non-answering rate.
5. The method of any one of claims 1-4, wherein prior to determining a matching physician among the physicians belonging to the matching department, the method further comprises:
judging whether the matching department meets a first preset condition and a second preset condition at the same time; the first preset condition is that the current number of waiting visits of the matched department is smaller than a third preset threshold value of the matched department, and the second preset condition is that the number of the visited visits of the matched department on the same day is smaller than a fourth preset threshold value of the matched department;
if yes, determining a matched doctor from the doctors belonging to the matched department;
otherwise, sending the inquiry information to a preset inquiry information database.
6. The method of claim 5, wherein after sending the interrogation information to a predetermined interrogation information database, the method further comprises:
and receiving a request instruction from a doctor terminal of the matched department, calling the inquiry information from the inquiry information database and sending the inquiry information to the doctor terminal sending the request instruction.
7. The method of any one of claims 1-4, wherein after the sending the interrogation information to the matching physician's terminal, the method further comprises:
receiving a received doctor message and a replied message sent by a matched doctor terminal; wherein the received message is sent after the matching doctor confirms the receiving, and the replied message is sent after the matching doctor replies to the user for the first time.
8. The method of any of claims 1-4, wherein after the sending the interrogation information to the matching physician's terminal, the method further comprises:
if the information of the received diagnosis sent by the matched doctor terminal is not received within a first preset time length, determining the inquiry information as information to be forwarded;
if the answer message sent by the matched doctor terminal is not received within a second preset time period after the consultation receiving message sent by the matched doctor terminal is received within the first preset time period, determining the inquiry information as the information to be forwarded;
and re-determining matched doctors from the matched departments corresponding to the information to be referral according to the pre-calculated doctor consultation ability score, and sending the information to be referred to the matched doctor terminal.
9. An internet medical triage device, comprising:
the receiving module is used for receiving the inquiry information sent by the user terminal;
the department triage module is used for processing the inquiry information by utilizing a pre-trained department triage model to obtain a matched department;
a determining module for determining a matching doctor from the doctors belonging to the matching department;
and the sending module is used for sending the inquiry information to the terminal of the matched doctor.
10. A computer arrangement comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 8 when executing the computer program.
11. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of a method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210860822.1A CN115132356A (en) | 2022-07-21 | 2022-07-21 | Internet medical triage method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210860822.1A CN115132356A (en) | 2022-07-21 | 2022-07-21 | Internet medical triage method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115132356A true CN115132356A (en) | 2022-09-30 |
Family
ID=83383579
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210860822.1A Pending CN115132356A (en) | 2022-07-21 | 2022-07-21 | Internet medical triage method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115132356A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116434949A (en) * | 2023-04-27 | 2023-07-14 | 明理医疗科技(武汉)有限公司 | Intelligent pathology sample distribution method and device, electronic equipment and 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 |
| CN117373626A (en) * | 2023-10-10 | 2024-01-09 | 中国医学科学院肿瘤医院 | Telemedicine system based on cloud calculates |
| JP7483995B1 (en) | 2023-08-01 | 2024-05-15 | 貴光 岩田 | Method, program, and server for supporting provision of services via a communication network |
-
2022
- 2022-07-21 CN CN202210860822.1A patent/CN115132356A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116434949A (en) * | 2023-04-27 | 2023-07-14 | 明理医疗科技(武汉)有限公司 | Intelligent pathology sample distribution method and device, electronic equipment and storage medium |
| CN116434949B (en) * | 2023-04-27 | 2024-05-07 | 明理医疗科技(武汉)有限公司 | Intelligent pathology sample distribution method and device, electronic equipment and 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 |
| 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 |
| JP7483995B1 (en) | 2023-08-01 | 2024-05-15 | 貴光 岩田 | Method, program, and server for supporting provision of services via a communication network |
| CN117373626A (en) * | 2023-10-10 | 2024-01-09 | 中国医学科学院肿瘤医院 | Telemedicine system based on cloud calculates |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11120509B2 (en) | Predictive model segmentation platform | |
| US11664097B2 (en) | Healthcare information technology system for predicting or preventing readmissions | |
| CN115132356A (en) | Internet medical triage method and device, electronic equipment and storage medium | |
| CN108932974B (en) | Method, device, computer equipment and storage medium for allocating doctors for online inquiry | |
| EP3391259A1 (en) | Systems and methods for providing personalized prognostic profiles | |
| US20110202486A1 (en) | Healthcare Information Technology System for Predicting Development of Cardiovascular Conditions | |
| JP6132639B2 (en) | Health information utilization system and program used therefor | |
| US20020123906A1 (en) | Chronic pain patient risk stratification system | |
| CN112036738A (en) | Service order distribution method and device, electronic equipment and storage medium | |
| US20210192365A1 (en) | Computer device, system, readable storage medium and medical data analysis method | |
| US11610679B1 (en) | Prediction and prevention of medical events using machine-learning algorithms | |
| KR102416618B1 (en) | System for providing disease classification code predicting service based on medical expense | |
| CN112908452A (en) | Event data modeling | |
| Kadum et al. | Machine learning-based telemedicine framework to prioritize remote patients with multi-chronic diseases for emergency healthcare services | |
| Shukla et al. | Optimization assisted bidirectional gated recurrent unit for healthcare monitoring system in big-data | |
| RU2752792C1 (en) | System for supporting medical decision-making | |
| CN113643798A (en) | Method and device for matching caregivers for disabled persons and computer equipment | |
| US20020123670A1 (en) | Chronic pain patient diagnostic system | |
| Hijry et al. | Application of machine learning algorithms for patient length of stay prediction in emergency department during Hajj | |
| JP2022007687A (en) | Medical assessment support device, medical assessment support method and medical assessment support program | |
| JP2020201697A (en) | Diagnosis support system | |
| Baba et al. | Predictive approaches for low-cost preventive medicine program in developing countries | |
| CN117012380A (en) | Event estimation method, device, equipment, storage medium and program product | |
| KR20160123151A (en) | System for providing medical information | |
| CN115579153A (en) | Inquiry evaluation method, inquiry evaluation device, electronic device, and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |