Online consultation and dispatching method, device and system

Abstract

The present invention discloses an online consultation dispatching method, device and system, and relates to the field of computer technology. A specific implementation of the method includes: receiving a consultation order submitted by a patient terminal, the consultation order containing descriptive information related to the consultation; inputting the descriptive information into a pre-trained triage model; when the triage model outputs a triage result, determining the target department corresponding to the consultation order from the triage result; when the triage model does not output a triage result, matching the descriptive information with a plurality of pre-set mapping rules, and determining the target department corresponding to the consultation order from the mapping rules matching the descriptive information; determining the target doctor from the doctors belonging to the target department according to the pre-calculated doctor weight value, and sending an order dispatching notification generated based on the consultation order to the target doctor terminal. This implementation can improve the accuracy of department triage and patient experience in non-directional consultations in Internet hospitals.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an online medical consultation and dispatching method and device. Background Art

[0002] With the rapid development of Internet medical care, online consultation has become an important way for patients to consult. The advantages of online consultation include: reducing the pressure on doctors and patients in tertiary hospitals, avoiding tension in doctor-patient relationships, taking on the role of preliminary screening, and supporting cross-regional patients to seek medical treatment. At present, non-directional consultation (i.e., the patient does not specify a doctor, and the doctor who receives the consultation is automatically assigned by the system) accounts for about 70% of the total online consultation.

[0003] In the existing non-directional consultation technology, machine learning models are mainly used for department triage, and then the attending doctors are randomly assigned in the department. Its defects are: First, department triage is inaccurate. The machine learning model has a strong classification ability for a single type of symptom description, but it is often unable to output classification results when faced with multiple types of symptom descriptions. In this case, the existing technology may randomly select departments, resulting in reduced triage accuracy. Second, the number of orders sent to different doctors is unbalanced, which may easily lead to some doctors being unable to accept orders due to too many orders, and other doctors having no orders to accept. Third, there are cases where some doctors do not accept orders or respond in a timely manner, affecting the patient's medical experience. Summary of the invention

[0004] In view of this, the embodiments of the present invention provide an online consultation dispatching method, device and system, which can improve the accuracy of department triage and patient experience in non-directional consultations in Internet hospitals.

[0005] To achieve the above objective, according to one aspect of the present invention, a method for online medical consultation and dispatching orders is provided.

[0006] The online medical consultation dispatching method of an embodiment of the present invention includes: receiving a medical consultation order submitted by a patient terminal, the medical consultation order containing descriptive information related to the medical consultation; inputting the descriptive information into a pre-trained triage model; when the triage model outputs a triage result, determining the target department corresponding to the medical consultation order from the triage result; when the triage model does not output a triage result, matching the descriptive information with a plurality of pre-set mapping rules, and determining the target department corresponding to the medical consultation order from the mapping rules matching the descriptive information; wherein each mapping rule represents: a mapping relationship between at least one predetermined medical consultation label and a corresponding department; determining a target doctor from doctors belonging to the target department according to a pre-calculated doctor weight value, and sending an order dispatching notification generated based on the medical consultation order to the target doctor terminal.

[0007] Optionally, matching the descriptive information with a plurality of pre-set mapping rules and determining the target department corresponding to the medical consultation order from the mapping rules matching the descriptive information comprises: extracting at least one medical consultation tag from the descriptive information, determining the mapping rule containing the medical consultation tag as the mapping rule matching the descriptive information, and determining the department in the mapping rule as the target department corresponding to the medical consultation order.

[0008] Optionally, determining the target doctor from the doctors belonging to the target department according to the pre-calculated doctor weight value includes: if the target department is determined based on the triage model, the doctors belonging to the target department are determined as candidate doctors, and the target doctor is determined from the candidate doctors according to the pre-calculated doctor weight value; if the target department is determined based on the mapping rule, the doctors in the pre-configured whitelist of general practitioners corresponding to the target department are determined as candidate doctors, and the target doctor is determined from the candidate doctors according to the pre-calculated doctor weight value.

[0009] Optionally, the method further includes: after determining the target department, judging whether the current number of patients waiting in the target department is greater than a first value preset for the target department, and judging whether the number of patients received by the target department on that day is greater than a second value preset for the target department; when any judgment result is "yes", sending the consultation order to a preset order grabbing pool; wherein the consultation orders in the order grabbing pool are dispatched according to the order grabbing instructions issued by the doctor terminal; when both judgment results are "no", determining the target doctor from the doctors belonging to the target department according to the pre-calculated doctor weight value.

[0010] Optionally, determining the target doctor from the candidate doctors based on the pre-calculated doctor weight values ​​includes: executing a preset discrimination logic on the candidate doctors as discrimination objects in order of the doctor weight values ​​from large to small until the target doctor is determined; the discrimination logic is: when the current number of waiting patients of the discrimination object is not greater than a third value preset for the discrimination object, and the number of patients received by the discrimination object on that day is not greater than a fourth value preset for the discrimination object, the discrimination object is determined as the target doctor.

[0011] Optionally, the doctor weight value is determined based on at least one of the following indicator data: a favorable review rate indicator, a reply time indicator, a settlement time indicator, a physical conversion indicator, a doctor's own indicator, an affiliated hospital indicator, and a non-response indicator.

[0012] Optionally, the method further includes: after sending the order dispatch notification to the target doctor terminal, receiving a consultation notification and a reply notification issued by the target doctor terminal; wherein the consultation notification is issued after the target doctor confirms the consultation, and the reply notification is issued after the target doctor replies to the patient for the first time.

[0013] Optionally, the method further includes: after sending the order dispatch notification to the target doctor terminal, if no consultation notification is received from the target doctor terminal within a preset first time period, determining the consultation order as an order to be referred; if after receiving the consultation notification from the target doctor terminal within the first time period, no reply notification is received from the target doctor terminal within a preset second time period, determining the consultation order as an order to be referred; re-determining the target doctor from the target department corresponding to the order to be referred according to a pre-calculated doctor weight value, and sending an order dispatch notification generated based on the order to be referred to the target doctor terminal.

[0014] To achieve the above objective, according to another aspect of the present invention, an online medical consultation and dispatching device is provided.

[0015] An online medical consultation dispatching device according to an embodiment of the present invention may include: a receiving unit for receiving a medical consultation order submitted by a patient terminal, wherein the medical consultation order contains descriptive information related to the medical consultation; a triage unit for inputting the descriptive information into a pre-trained triage model; when the triage model outputs a triage result, determining a target department corresponding to the medical consultation order from the triage result; when the triage model does not output a triage result, matching the descriptive information with a plurality of pre-set mapping rules, and determining the target department corresponding to the medical consultation order from the mapping rules matching the descriptive information; wherein each mapping rule represents: a mapping relationship between at least one predetermined medical consultation label and a corresponding department; and a dispatching unit for determining a target doctor from doctors belonging to the target department according to a pre-calculated doctor weight value, and sending an order dispatching notification generated based on the medical consultation order to the target doctor terminal.

[0016] Optionally, the triage unit may be further used to: extract at least one medical consultation tag from the description information, determine the mapping rule containing the medical consultation tag as a mapping rule that matches the description information, and determine the department in the mapping rule as the target department corresponding to the medical consultation order; if the target department is determined based on the triage model, determine the doctor belonging to the target department as the candidate doctor; if the target department is determined based on the mapping rule, determine the doctor in the pre-configured general practitioner whitelist corresponding to the target department as the candidate doctor; the dispatch unit may be further used to: execute the preset discrimination logic on the candidate doctors as discrimination objects in order of the doctor weight value from large to small until the target doctor is determined; the discrimination logic is: when the current number of waiting patients of the discrimination object is not greater than the third value preset for the discrimination object, and the number of patients received by the discrimination object on that day is not greater than the fourth value preset for the discrimination object, the discrimination object is determined as the target doctor.

[0017] To achieve the above objective, according to another aspect of the present invention, an online medical consultation and dispatching system is provided.

[0018] An online medical consultation dispatching system according to an embodiment of the present invention may include: a server, a patient terminal and a doctor terminal; wherein the server receives a medical consultation order submitted by a patient terminal, wherein the medical consultation order contains descriptive information related to the medical consultation; the server inputs the descriptive information into a pre-trained triage model; when the triage model outputs a triage result, the target department corresponding to the medical consultation order is determined from the triage result; when the triage model does not output a triage result, the descriptive information is matched with a plurality of pre-set mapping rules, and the target department corresponding to the medical consultation order is determined from the mapping rules matching the descriptive information; wherein each mapping rule represents: a mapping relationship between at least one pre-determined medical consultation label and a corresponding department; the server determines a target doctor from doctors belonging to the target department according to a pre-calculated doctor weight value, and sends an order dispatching notification generated based on the medical consultation order to the target doctor terminal.

[0019] To achieve the above objective, according to another aspect of the present invention, an electronic device is provided.

[0020] An electronic device of the present invention includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the online consultation and dispatching method provided by the present invention.

[0021] To achieve the above objective, according to yet another aspect of the present invention, a computer-readable storage medium is provided.

[0022] A computer-readable storage medium of the present invention stores a computer program, which, when executed by a processor, implements the online medical consultation and dispatching method provided by the present invention.

[0023] According to the technical solution of the present invention, the embodiments of the above invention have the following advantages or beneficial effects:

[0024] The technical solution of the present invention is further optimized on the basis of the triage model based on the machine learning algorithm, and a plurality of mapping rules representing the mapping relationship between the consultation label and the department are pre-set. When the triage model does not output the triage result, the description information in the consultation order is matched with the above mapping rules to obtain the target department corresponding to the consultation order, thereby improving the accuracy of department triage. In the process of determining the target doctor after obtaining the target department, the current number of waiting patients and the number of patients received on the day of the department and the doctor can be judged. When the current number of waiting patients or the number of patients received on the day exceeds the threshold, the order distribution is stopped, thereby avoiding uneven order distribution. After the target doctor is determined, whether referral is needed is determined based on whether the target doctor terminal returns a notification of having been received or a notification of having been replied within a preset period of time, thereby ensuring the patient's medical experience. In addition, in an embodiment of the present invention, after obtaining the target department based on the mapping rules, the target doctor is determined according to the pre-configured whitelist of general practitioners of the target department, so as to meet the needs of patients with multiple types of symptoms; in the process of determining the target doctor, the doctor's weight value calculated by multiple data such as the praise rate index, the reply time index, the settlement time index, the physical conversion index, the doctor's own index, the hospital index, the non-response index, etc. is used to make an orderly judgment, which helps to match the patient with a doctor with better medical skills.

[0025] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0027] Figure 1 This is a schematic diagram of the main steps of the online medical consultation and dispatching method in an embodiment of the present invention;

[0028] Figure 2 This is a schematic diagram of specific execution steps of the online medical consultation and dispatching method in an embodiment of the present invention;

[0029] Figure 3 It is a schematic diagram of components of an online medical consultation and dispatching device in an embodiment of the present invention;

[0030] Figure 4 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;

[0031] Figure 5 It is a schematic diagram of the structure of an electronic device used to implement the online medical consultation and dispatching method in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0033] It should be pointed out that the embodiments of the present invention and the technical features therein may be combined with each other without conflict.

[0034] Figure 1 It is a schematic diagram of the main steps of the online medical consultation and dispatching method according to an embodiment of the present invention.

[0035] like Figure 1 As shown, the online consultation and dispatching method of the embodiment of the present invention can be specifically performed according to the following steps:

[0036] Step S101: receiving a consultation order submitted by a patient terminal, wherein the consultation order contains descriptive information related to the consultation.

[0037] The technical solution of the embodiment of the present invention can be applied in the Internet medical platform. The Internet medical platform can use the server as a bridge between patients and doctors to realize patient consultation and doctor consultation. Patients can interact with the doctor terminal installed with the same software through the corresponding software installed on the patient terminal (such as mobile software APP), and the patient terminal and the doctor terminal can also interact with the server through the above software. The online consultation and dispatching method of the embodiment of the present invention is executed on the server.

[0038] In actual applications, a consultation order can be generated after the patient enters relevant information on the software page of his terminal. The consultation order can carry descriptive information related to the consultation, which may include the above information entered by the patient and may also include pre-known patient characteristic data. Exemplarily, the descriptive information can be data of one or more of the following dimensions: name, gender, age, occupation, symptoms, medical history, and historical examination data.

[0039] In the embodiment of the present invention, any dimension and its data contained in the description information can be used as a patient's medical consultation label. For example, if the description information of a medical consultation order is: male, 37 years old, continuous headache in the past month, history of hypertension, then the following multiple medical consultation labels of the patient can be extracted from it: (sex: male), (age: 37), (symptoms: headache), (medical history: hypertension).

[0040] After generating the consultation order, the patient can click the corresponding button on the software page to submit the consultation order to the server. After the server receives the consultation order, it can implement the order dispatch by executing the following steps.

[0041] Step S102: input the description information into a pre-trained triage model; when the triage model outputs the triage result, determine the target department corresponding to the consultation order from the triage result; when the triage model does not output the triage result, match the description information with multiple pre-set mapping rules, and determine the target department corresponding to the consultation order from the mapping rules that match the description information.

[0042] In this step, the server first obtains the description information from the consultation order and inputs the description information into the pre-trained triage model. The above triage model is used to determine the department corresponding to the description information (generally secondary departments such as respiratory medicine and cardiac surgery). It can be constructed based on machine learning algorithms such as naive Bayes, random forest, and recurrent neural network RNN. It can be trained using supervised learning methods. During the training process, the consultation text records of the historical period and the corresponding departments that have been determined can be used to form a training set.

[0043] In specific applications, the above triage model has a strong classification ability when facing a single type of symptom description in the description information, but it is often unable to judge and output the classification result when facing multiple types of symptom descriptions. In this case, the existing technology will randomly select the department, resulting in a decrease in the accuracy of its department triage. Specifically, in an embodiment of the present invention, if the triage model outputs a triage result, it means that the description information in the consultation order may contain a single symptom description. Since the accuracy of the triage model is higher in this case, the target department corresponding to the consultation order can be directly determined from the triage result (the target department refers to the consultation department that is suitable for the consultation order). For example, if the triage result is the identification of a department, the corresponding target department can be determined based on the identification.

[0044] In actual scenarios, the server can also pre-set rules to supplement the target department output by the triage model. For example, a rule is: age over 60 - geriatric department. If the target department corresponding to a consultation order output by the triage model is gastroenterology, if the description information in the consultation order meets the above rules, the geriatric department can be used as the target department at the same time.

[0045] If the triage model does not output the triage result, the description information can be matched with multiple pre-set mapping rules, and the target department corresponding to the consultation order can be determined from the mapping rules that match the description information. Among them, the above mapping rules can be pre-configured based on medical knowledge or diagnostic experience, and can characterize the mapping relationship between one or more consultation labels and the applicable department. For example, mapping rule A is: symptoms are headache and chest tightness-cardiology department, mapping rule B is: symptoms are cough, thick fingertips and back pain-respiratory medicine department. It can be understood that the mapping rules can also be related to dimensions such as age and gender, or only to a single type of symptoms. For example, the following mapping rules can also be set: age less than or equal to 60 years old-Department of Integrated Traditional Chinese and Western Medicine, long-term redness of the palms-Gastroenterology Department.

[0046] The mapping rule that matches the description information refers to the mapping rule that contains the medical inquiry tag and the description information. Generally, after the server obtains the description information, it can first extract the medical inquiry tag from the description information, and through sequential matching with the mapping rules, determine the mapping rule that contains the medical inquiry tag in the description information (the above inclusion can include all the medical inquiry tags in the description information, or can include some of the medical inquiry tags in the description information) as the mapping rule that matches the description information, and finally determine the department in the mapping rule as the target department corresponding to the medical inquiry order. For example, if the medical inquiry tag extracted from the description information is (symptoms: cough and thick fingertips), then the aforementioned mapping rule B containing the medical inquiry tag can be determined as the mapping rule that matches the description information, and the "Department of Respiratory Medicine" in B can be determined as the target department corresponding to the medical inquiry order.

[0047] By setting the above mapping rules, it is possible to use medical knowledge and historical experience to accurately determine the target department corresponding to multiple types of symptoms when the triage model is unable to output the triage results, thereby overcoming the inherent defect of the existing technology of randomly selecting departments when the triage model is unable to make a judgment, and improving the accuracy of department triage.

[0048] Step S103: Determine a target doctor from the doctors belonging to the target department according to the pre-calculated doctor weight value, and send an order dispatch notification generated based on the consultation order to the target doctor terminal.

[0049] After determining the target department corresponding to the consultation order, the server can first determine whether the current number of patients waiting in the target department is greater than the first value preset for the target department, and determine whether the number of patients received by the target department on that day is greater than the second value preset for the target department (the above two judgments can be performed in any order or simultaneously). Among them, the first value is the threshold value of the number of concurrent patients waiting in the target department (that is, the threshold value of the number of patients waiting at any time), and the second value is the threshold value of the number of patients received by the target department on that day. In specific applications, the first value and the second value can be set by the server, can be set by the doctor in the department, and can also be set jointly by the server and the doctor. For example, the server sets a value range, and the doctor sets a certain value within the range.

[0050] If a judgment result is "yes" (that is, the current number of waiting patients in the target department is greater than the first value or the number of patients received by the target department on the day is greater than the second value), it means that the current reception load of the target department is high, and the consultation order can be sent to the preset order grabbing pool. The order grabbing pool is visible to all doctors, and doctors can grab orders by issuing grabbing instructions. If both judgment results are "no" (that is, the current number of waiting patients in the target department is not greater than the first value and the number of patients received by the target department on the day is not greater than the second value), it means that the target department still has the ability to receive patients. At this time, the target doctor can be determined from the doctors belonging to the target department according to the pre-calculated doctor weight value.

[0051] Through the above judgment, it is possible to stop dispatching orders when the department load is too high, thereby solving the problem of unbalanced order volumes between different departments, avoiding the situation where some departments have order backlogs due to too many orders while other departments have no orders to accept. It also helps to shorten the waiting time for medical treatment and improve the patient experience.

[0052] After the above judgments, the server can first determine the candidate doctors (i.e., doctors who are qualified or eligible to see patients) from the doctors belonging to the target department, and then determine the target doctor (i.e., the doctor to be seen) from the candidate doctors. As a preferred solution, if the target department is determined based on the triage model, all online doctors belonging to the target department are determined as candidate doctors; if the target department is determined based on the mapping rules, the doctors in the pre-configured whitelist of general practitioners corresponding to the target department are determined as candidate doctors. Among them, the above whitelist of general practitioners is established in advance for each department, and the whitelist of general practitioners of a department includes the identification of the general practitioners in the department (such as name), and the above general practitioners refer to doctors who can diagnose multiple types of symptoms.

[0053] The purpose of configuring a whitelist of general practitioners is that, since the aforementioned triage model cannot handle consultation orders with multiple types of symptoms, consultation orders that have used mapping rules often have multiple types of symptoms, so general practitioners in the above whitelist are required to make diagnoses to further improve the patient's medical experience.

[0054] In an embodiment of the present invention, after determining the candidate doctors of the target department, the server can determine a target doctor from the candidate doctors to receive the consultation order according to the pre-calculated doctor weight value. Preferably, the doctor weight value can be calculated according to at least one of the following indicator data: praise rate indicator, reply time indicator, settlement time indicator, physical conversion indicator, doctor's own indicator, affiliated hospital indicator, non-response indicator. For example, the doctor weight value can be the weighted sum of the following multiple indicators (the weighted sum can be calculated based on the indicator weight determined in advance for each indicator data).

[0055] Specifically, in one embodiment, the praise rate index of a doctor can be calculated in the following way: take the most recent 100 consultation orders received by the doctor, divide every 20 orders into a group in order from recent to far, and set the group weights to 1, 0.5, 0.25, 0.125, and 0.0625 respectively. The praise rate of each group is the quotient of the number of orders with a rating higher than three stars (the highest is five stars) and the number of orders with reviews, and the evaluation rate index is the weighted sum of the praise rates of each group.

[0056] The response time index of a doctor can be calculated based on the average response time of the most recent 100 consultation orders received by the doctor. In practical applications, the average response time can be added to a preset first constant and then the logarithm is taken, and the logarithm is added to a preset second value and then the inverse is taken. It can be understood that the larger the average response time, the smaller the response time index.

[0057] The residence time index of a doctor can be a decreasing function of the length of time the doctor has been on the Internet medical platform. This index helps to increase the weight of new doctors to avoid the situation where new doctors cannot see patients because their weight is too low. The server can flexibly set the calculation method of the residence time index, for example, it can be set to y = 1-0.001x, where y represents the residence time index, x is the number of days on the Internet medical platform, and when x is greater than 1000, y is zero.

[0058] The physical conversion index of a doctor can be calculated by combining the physical conversion rate index and the physical conversion unit price index (for example, the weighted sum of the two). The physical conversion rate index can be calculated by the following steps: take the most recent 100 consultation orders received by the doctor, divide each 20 orders into a group in order from recent to far, and set the group weights to 1, 0.5, 0.25, 0.125, and 0.0625 respectively. The physical conversion rate of each group is the quotient of the number of orders that generate conversions (conversions are related to payments initiated by patients) and the total number of orders. The physical conversion rate index is the weighted sum of the physical conversion rates of each group. The converted physical unit price index can be calculated by the following steps: take the most recent 100 consultation orders received by the doctor, divide each 20 orders into a group in order from recent to distant, and set the group weights to 1, 0.5, 0.25, 0.125, and 0.0625 respectively. The converted physical unit price of each group is the quotient of the total sales and the total number of orders. The physical conversion rate index is the weighted sum of the converted physical unit prices of each group. Before calculating the physical conversion index, the converted physical unit price index can be normalized to a value between zero and one in advance.

[0059] The doctor's own index can be calculated based on the doctor's professional title, position, technical expertise, etc. The hospital index can be calculated based on the level of the hospital to which the doctor belongs (for example, whether it is a tertiary hospital, etc.), the region (for example, whether it is in a municipality, a provincial capital, etc.), and the ownership nature (for example, whether it is a public hospital, etc.). The non-response index can be calculated based on the doctor's non-response rate in the historical period. Specifically, the doctor's most recent 100 consultation orders are taken, and each 20 orders are divided into a group in order from recent to distant, and the group weights are set to 1, 0.5, 0.25, 0.125, and 0.0625 respectively. The non-response rate of each group is the quotient of the number of orders that have not responded (non-response includes not receiving the consultation within the first period after receiving the consultation order and not responding within the second period after receiving the consultation) and the total number of orders. The non-response index is the weighted sum of the non-response rates of each group.

[0060] Through the above settings, the doctor weight value can be calculated by comprehensively considering the main factors related to the doctor's technical level and professional attitude, and the target doctor can be determined from the candidate doctors of the target department using the doctor weight value. Specifically, the candidate doctors are sequentially used as the discrimination object to execute the preset discrimination logic in the order of the doctor weight value from large to small until the target doctor is determined. The above discrimination logic is: when the current number of waiting patients of the discrimination object is not greater than the third value preset for the discrimination object, and the number of patients received by the discrimination object on the same day is not greater than the fourth value preset for the discrimination object (the above two discriminations can be performed in any order or simultaneously), the discrimination object is determined as the target doctor. That is to say, firstly, each candidate doctor is arranged in descending order according to the doctor weight value, and the current number of waiting patients and the number of patients received on the same day are judged in turn. If the judgment fails, that is, the current number of waiting patients is greater than the corresponding third value, or the number of patients received on the same day is greater than the corresponding fourth value, indicating that the doctor's medical load is heavy, then the next doctor's judgment is executed. If the judgment passes, it means that the doctor has the ability to receive patients, and the doctor is determined as the target doctor. It can be understood that the third value above is the threshold value of the number of concurrent waiting patients of the doctor (i.e., the threshold value of the number of waiting patients at any time), and the fourth value is the threshold value of the number of patients the doctor receives on the same day. In specific applications, the third value and the fourth value can be set by the server, by the doctor, or by the server and the doctor together. For example, the server sets a value range, and the doctor sets a certain value within the range.

[0061] Through the above method, it is possible to stop dispatching orders when the doctor's load is too high, thereby solving the problem of uneven order volume among different doctors, avoiding the situation where some doctors have order backlogs due to too many orders while other doctors have no orders to take, and also helping to shorten the waiting time for medical treatment and improve the patient experience.

[0062] After determining the target doctor, the server may send an order dispatch notification generated based on the consultation order to the target doctor terminal. The above-mentioned order dispatch notification may be in the form of a consultation form, which may include descriptive information related to the consultation. After the target doctor terminal receives the order dispatch notification, the target doctor may operate on his terminal to confirm the consultation and reply after confirming the consultation. In a specific application, after the target doctor confirms the consultation, the target doctor terminal may send a consultation notification to the server, and after the target doctor replies to the patient for the first time, the target doctor terminal may send a reply notification to the server.

[0063] In the prior art, there are cases where doctors do not confirm the consultation or do not reply for a long time, which can easily affect the patient's medical experience. Therefore, it is necessary to distinguish the doctor's consultation and reply response and refer the consultation order when the doctor does not confirm the consultation or does not reply for a long time. In an embodiment of the present invention, after the server sends an order dispatch notification to the target doctor terminal, if the server does not receive a consultation notification issued by the target doctor terminal within the preset first time period, the consultation order is determined as an order to be referred; if after receiving the consultation notification issued by the target doctor terminal within the first time period, the server does not receive a reply notification issued by the target doctor terminal within the preset second time period, the consultation order is also determined as an order to be referred. Thereafter, the server re-determines the target doctor from the target department corresponding to the order to be referred according to the doctor's weight value, and sends an order dispatch notification generated based on the order to be referred to the current target doctor terminal. That is to say, the server re-executes the previously determined steps of judging the reception capacity of the target department (i.e., judging the first and second values ​​mentioned above) and the reception capacity of the target doctor (i.e., judging the third and fourth values ​​mentioned above) for the referral order to determine the target doctor, thereby completing the referral of the consultation order, thereby ensuring that the patient can see the doctor in a shorter time.

[0064] In actual applications, in order to increase doctors' willingness to accept special consultation orders (such as night consultation orders), the server can also set corresponding price increase rules and reflect them in the payment module. For example, the price increase rules can be: increase the fee for night consultation orders by a preset proportion or increase the preset amount.

[0065] Figure 2 Schematic diagram of specific execution steps of the online consultation and dispatching method in an embodiment of the present invention. Figure 2 As shown, after the patient terminal submits the consultation order, the server receives it and inputs the description information in the consultation order into the pre-trained triage model. When the triage model outputs the triage result normally, the target department can be determined from the triage result. At this time, the server can make a judgment based on the dispatch method previously selected by the patient. In specific applications, dispatch methods include full-time dispatch, part-time dispatch and mixed dispatch. Full-time dispatch refers to dispatch for full-time doctors (i.e. doctors who work on the Internet medical platform for all working hours), part-time dispatch refers to dispatch for part-time doctors (i.e. doctors who work on the Internet medical platform for part of their working time), and mixed dispatch refers to dispatch for full-time doctors and part-time doctors.

[0066] If the patient has previously selected full-time dispatch, the system will directly proceed to the target department's concurrency and upper limit judgment (concurrency judgment is to judge whether the current number of patients waiting in the target department is greater than the corresponding first value, and upper limit judgment is to judge whether the number of patients received by the target department on that day is greater than the corresponding second value). If the patient has previously selected part-time dispatch or mixed dispatch, it is necessary to first determine whether the target department currently has an online doctor. If so, the target department's concurrency and upper limit judgment will be executed. If not, the consultation order will be sent to the order grabbing pool.

[0067] If the triage model cannot output the triage result normally, the consultation label in the description information will be matched with the mapping rule, so as to determine the target department through the matching mapping rule. After that, the doctors in the general practitioner whitelist of the target department will be used as candidate doctors to perform the above-mentioned "whether there is an online doctor" judgment. If so, the concurrency and upper limit judgment of the target department will be performed. If not, the consultation order will be sent to the order grabbing pool.

[0068] Thereafter, if the concurrency and upper limit judgment of the target department fails (including concurrency judgment failure and / or upper limit judgment failure), the consultation order will be sent to the order grabbing pool. If the concurrency and upper limit judgment of the target department passes (i.e., the concurrency judgment passes and the upper limit judgment fails), the candidate doctors are sorted in descending order according to the doctor's weight value and the doctor's concurrency and upper limit judgment is performed in sequence (the concurrency judgment is to judge whether the current number of waiting patients of the doctor is greater than the corresponding third value, and the upper limit judgment is to judge whether the number of patients the doctor has received on the day is greater than the corresponding fourth value). If the concurrency and upper limit judgment fails (including concurrency judgment failure and / or upper limit judgment failure), the judgment of the next doctor is executed; if the concurrency and upper limit judgment passes (including concurrency judgment passes and upper limit judgment fails), the current doctor is determined as the target doctor.

[0069] After determining the target doctor, the server can send an order dispatch notification to the target doctor terminal. If no consultation notification is received from the target doctor terminal within the first period of time, or if no reply notification is received within the second period of time after receiving the consultation notification from the target doctor terminal, the consultation order will be determined as a pending referral order. Thereafter, the target department concurrency and upper limit judgment process and the target doctor determination process will be re-executed for the pending referral order.

[0070] In the technical solution of the embodiment of the present invention, the triage model based on the machine learning algorithm is further optimized, and multiple mapping rules representing the mapping relationship between the consultation label and the department are pre-set. When the triage model does not output the triage result, the description information in the consultation order is matched with the above mapping rules to obtain the target department corresponding to the consultation order, thereby improving the accuracy of department triage. In the process of determining the target doctor after obtaining the target department, the current number of waiting patients and the number of patients received on the day of the department and the doctor can be judged. When the current number of waiting patients or the number of patients received on the day exceeds the threshold, the order distribution is stopped, thereby avoiding uneven order distribution. After the target doctor is determined, whether referral is required is determined based on whether the target doctor terminal returns a consultation notification or a reply notification within a preset time, thereby ensuring the patient's medical experience. In addition, in an embodiment of the present invention, after obtaining the target department based on the mapping rules, the target doctor is determined according to the pre-configured whitelist of general practitioners of the target department, so as to meet the needs of patients with multiple types of symptoms; in the process of determining the target doctor, the doctor's weight value calculated by multiple data such as the praise rate index, the reply time index, the settlement time index, the physical conversion index, the doctor's own index, the hospital index, the non-response index, etc. is used to make an orderly judgment, which helps to match the patient with a doctor with better medical skills.

[0071] It should be noted that, for the convenience of description, the aforementioned method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the present invention is not limited by the described action sequence, and some steps can actually be performed in other sequences or simultaneously. In addition, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily necessary to implement the present invention.

[0072] In order to better implement the above-mentioned solution of the embodiment of the present invention, relevant devices for implementing the above-mentioned solution are also provided below.

[0073] See also Figure 3 As shown, the online medical consultation and dispatching device 300 provided in the embodiment of the present invention may include: a receiving unit 301, a triage unit 302 and a dispatching unit 303.

[0074] Among them, the receiving unit 301 can be used to receive a consultation order submitted by a patient terminal, and the consultation order contains descriptive information related to the consultation; the triage unit 302 can be used to input the descriptive information into a pre-trained triage model; when the triage model outputs a triage result, the target department corresponding to the consultation order is determined from the triage result; when the triage model does not output a triage result, the descriptive information is matched with a plurality of pre-set mapping rules, and the target department corresponding to the consultation order is determined from the mapping rules matching the descriptive information; wherein each mapping rule represents: a mapping relationship between at least one predetermined consultation label and a corresponding department; the dispatching unit 303 can be used to determine a target doctor from doctors belonging to the target department according to a pre-calculated doctor weight value, and send an order dispatching notification generated based on the consultation order to the target doctor terminal.

[0075] In an embodiment of the present invention, the triage unit 302 can be further used to: extract at least one consultation tag from the description information, determine the mapping rule containing the consultation tag as a mapping rule that matches the description information, and determine the department in the mapping rule as the target department corresponding to the consultation order; if the target department is determined based on the triage model, determine the doctor belonging to the target department as a candidate doctor; if the target department is determined based on the mapping rule, determine the doctor in the pre-configured general practitioner whitelist corresponding to the target department as a candidate doctor.

[0076] As a preferred solution, the dispatch unit 303 can be further used to: execute the preset judgment logic according to the doctor weight value from large to small, taking the candidate doctors as judgment objects in turn, until the target doctor is determined; the judgment logic is: when the current number of waiting patients of the judgment object is not greater than the third value preset for the judgment object, and the number of patients received by the judgment object on the day is not greater than the fourth value preset for the judgment object, the judgment object is determined as the target doctor.

[0077] Exemplarily, the doctor weight value is determined based on at least one of the following indicator data: a favorable review rate indicator, a reply time indicator, a settlement time indicator, a physical conversion indicator, a doctor's own indicator, an affiliated hospital indicator, and a non-response indicator.

[0078] Preferably, the device 300 may further include a reception capacity judgment unit, which is used to: after determining the target department, judge whether the current number of waiting patients in the target department is greater than a first value preset for the target department, and judge whether the number of patients received by the target department on that day is greater than a second value preset for the target department; when any judgment result is "yes", send the consultation order to a preset order grabbing pool; wherein the consultation orders in the order grabbing pool are distributed according to the order grabbing instructions issued by the doctor terminal; when both judgment results are "no", determine the target doctor from the doctors belonging to the target department according to the pre-calculated doctor weight value.

[0079] In one embodiment, the device 300 may further include a referral judgment unit, which is used to: after sending the order dispatch notification to the target doctor terminal, receive a consultation notification and a reply notification issued by the target doctor terminal; wherein the consultation notification is issued after the target doctor confirms the consultation, and the reply notification is issued after the target doctor replies to the patient for the first time.

[0080] In addition, in an embodiment of the present invention, the referral judgment unit may be further used for: after sending the order dispatch notification to the target doctor terminal, if no consultation notification is received from the target doctor terminal within a preset first time period, determining the consultation order as an order to be referred; if after receiving the consultation notification from the target doctor terminal within the first time period, no reply notification is received from the target doctor terminal within a preset second time period, determining the consultation order as an order to be referred; re-determining the target doctor from the target department corresponding to the order to be referred according to the pre-calculated doctor weight value, and sending an order dispatch notification generated based on the order to be referred to the target doctor terminal.

[0081] According to the technical solution of the embodiment of the present invention, the triage model based on the machine learning algorithm is further optimized, and multiple mapping rules representing the mapping relationship between the consultation label and the department are pre-set. When the triage model does not output the triage result, the description information in the consultation order is matched with the above mapping rules to obtain the target department corresponding to the consultation order, thereby improving the accuracy of department triage. In the process of determining the target doctor after obtaining the target department, the current number of waiting patients and the number of patients received on the day of the department and the doctor can be judged. When the current number of waiting patients or the number of patients received on the day exceeds the threshold, the order distribution is stopped, thereby avoiding uneven order distribution. After the target doctor is determined, whether referral is required is determined based on whether the target doctor terminal returns a notification of having been received or a notification of having been replied within a preset period of time, thereby ensuring the patient's medical experience. In addition, in an embodiment of the present invention, after obtaining the target department based on the mapping rules, the target doctor is determined according to the pre-configured whitelist of general practitioners of the target department, so as to meet the needs of patients with multiple types of symptoms; in the process of determining the target doctor, the doctor's weight value calculated by multiple data such as the praise rate index, the reply time index, the settlement time index, the physical conversion index, the doctor's own index, the hospital index, the non-response index, etc. is used to make an orderly judgment, which helps to match the patient with a doctor with better medical skills.

[0082] In an embodiment of the present invention, an online medical consultation and dispatching system is further provided. The online medical consultation and dispatching system of the embodiment of the present invention may include: a service end, a patient terminal and a doctor terminal.

[0083] Among them, the service end receives a consultation order submitted by a patient terminal, and the consultation order contains descriptive information related to the consultation; the service end inputs the descriptive information into a pre-trained triage model; when the triage model outputs a triage result, the target department corresponding to the consultation order is determined from the triage result; when the triage model does not output a triage result, the descriptive information is matched with a plurality of pre-set mapping rules, and the target department corresponding to the consultation order is determined from the mapping rules matching the descriptive information; wherein each mapping rule represents: a mapping relationship between at least one predetermined consultation label and a corresponding department; the service end determines a target doctor from doctors belonging to the target department according to a pre-calculated doctor weight value, and sends an order dispatch notification generated based on the consultation order to the target doctor terminal.

[0084] As a preferred solution, the server extracts at least one medical consultation tag from the description information, determines the mapping rule containing the medical consultation tag as a mapping rule matching the description information, and determines the department in the mapping rule as the target department corresponding to the medical consultation order.

[0085] Preferably, if the target department is determined based on the triage model, the server will determine the doctors belonging to the target department as candidate doctors, and determine the target doctor from the candidate doctors based on the pre-calculated doctor weight value; if the target department is determined based on the mapping rule, the server will determine the doctors in the pre-configured whitelist of general practitioners corresponding to the target department as candidate doctors, and determine the target doctor from the candidate doctors based on the pre-calculated doctor weight value.

[0086] In a specific application, after determining the target department, the server determines whether the current number of patients waiting in the target department is greater than a first value preset for the target department, and determines whether the number of patients received by the target department on that day is greater than a second value preset for the target department; when any judgment result is "yes", the consultation order is sent to a preset order grabbing pool; wherein the consultation orders in the order grabbing pool are distributed according to the order grabbing instructions issued by the doctor terminal; when both judgment results are "no", the target doctor is determined from the doctors belonging to the target department according to the pre-calculated doctor weight value.

[0087] In actual applications, the server executes the preset judgment logic according to the doctor weight value from large to small, and takes the candidate doctors as the judgment objects in sequence until the target doctor is determined; the judgment logic is: when the current number of waiting patients of the judgment object is not greater than the third value preset for the judgment object, and the number of patients received by the judgment object on the day is not greater than the fourth value preset for the judgment object, the judgment object is determined as the target doctor.

[0088] Exemplarily, the doctor weight value is determined based on at least one of the following indicator data: a favorable review rate indicator, a reply time indicator, a settlement time indicator, a physical conversion indicator, a doctor's own indicator, an affiliated hospital indicator, and a non-response indicator.

[0089] In some embodiments, after sending the order dispatch notification to the target doctor terminal, the server receives a consultation notification and a reply notification issued by the target doctor terminal; wherein, the consultation notification is issued after the target doctor confirms the consultation, and the reply notification is issued after the target doctor replies to the patient for the first time.

[0090] In addition, in an embodiment of the present invention, after the server sends the order dispatch notification to the target doctor terminal, if the server does not receive a consultation notification issued by the target doctor terminal within a preset first time period, the consultation order is determined as an order to be referred; if after receiving the consultation notification issued by the target doctor terminal within the first time period, if the server does not receive a reply notification issued by the target doctor terminal within a preset second time period, the consultation order is determined as an order to be referred; the server re-determines the target doctor from the target department corresponding to the order to be referred based on the pre-calculated doctor weight value, and sends an order dispatch notification generated based on the order to be referred to the target doctor terminal.

[0091] Figure 4 An exemplary system architecture 400 is shown to which an online medical consultation dispatching method or an online medical consultation dispatching device according to an embodiment of the present invention can be applied.

[0092] like Figure 4 As shown, the system architecture 400 may include terminal devices 401, 402, 403, a network 404 and a server 405 (this architecture is only an example, and the components included in the specific architecture may be adjusted according to the specific application). The network 404 is used to provide a medium for a communication link between the terminal devices 401, 402, 403 and the server 405. The network 404 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0093] Users (including doctors and patients) can use terminal devices 401, 402, 403 to interact with server 405 through network 404 to receive or send messages, etc. Various communication client applications, such as Internet medical applications (only as an example), can be installed on terminal devices 401, 402, 403.

[0094] The terminal devices 401 , 402 , and 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0095] The server 405 may be a server that provides various services, such as a backend server (only an example) that provides support for Internet medical applications operated by users using the terminal devices 401, 402, and 403. The backend server may process the consultation order received and submitted by the patient terminal, and send the processing result (such as an order dispatch notification - only an example) to the doctor terminal.

[0096] It should be noted that the online medical consultation and dispatching method provided in the embodiment of the present invention is generally executed by the server 405 , and accordingly, the online medical consultation and dispatching device is generally arranged in the server 405 .

[0097] It should be understood that Figure 4 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0098] The present invention also provides an electronic device. The electronic device of an embodiment of the present invention includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the online consultation and dispatching method provided by the present invention.

[0099] Reference below Figure 5 , which shows a schematic diagram of the structure of a computer system 500 of an electronic device suitable for implementing an embodiment of the present invention. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0100] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the computer system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0101] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage section 508 as needed.

[0102] In particular, according to the embodiments disclosed in the present invention, the process described in the main step diagram above can be implemented as a computer software program. For example, the embodiments of the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the main step diagram. In the above embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit 501, the above functions defined in the system of the present invention are executed.

[0103] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0104] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0105] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be arranged in a processor, for example, may be described as: a processor includes a receiving unit, a triage unit, and a dispatching unit. The names of these units do not constitute limitations on the units themselves in certain circumstances, for example, the receiving unit may also be described as "a unit that provides a consultation order and the description information therein to the triage unit".

[0106] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the device, the steps executed by the device include: receiving a consultation order submitted by a patient terminal, wherein the consultation order contains description information related to the consultation; inputting the description information into a pre-trained triage model; when the triage model outputs a triage result, determining the target department corresponding to the consultation order from the triage result; when the triage model does not output a triage result, matching the description information with a plurality of pre-set mapping rules, and determining the target department corresponding to the consultation order from the mapping rules matching the description information; wherein each mapping rule represents: a mapping relationship between at least one predetermined consultation label and a corresponding department; determining a target doctor from doctors belonging to the target department according to a pre-calculated doctor weight value, and sending an order dispatch notification generated based on the consultation order to the target doctor terminal.

[0107] In the technical solution of the embodiment of the present invention, the triage model based on the machine learning algorithm is further optimized, and multiple mapping rules representing the mapping relationship between the consultation label and the department are pre-set. When the triage model does not output the triage result, the description information in the consultation order is matched with the above mapping rules to obtain the target department corresponding to the consultation order, thereby improving the accuracy of department triage. In the process of determining the target doctor after obtaining the target department, the current number of waiting patients and the number of patients received on the day of the department and the doctor can be judged. When the current number of waiting patients or the number of patients received on the day exceeds the threshold, the order distribution is stopped, thereby avoiding uneven order distribution. After the target doctor is determined, whether referral is required is determined based on whether the target doctor terminal returns a consultation notification or a reply notification within a preset time, thereby ensuring the patient's medical experience. In addition, in an embodiment of the present invention, after obtaining the target department based on the mapping rules, the target doctor is determined according to the pre-configured whitelist of general practitioners of the target department, so as to meet the needs of patients with multiple types of symptoms; in the process of determining the target doctor, the doctor's weight value calculated by multiple data such as the praise rate index, the reply time index, the settlement time index, the physical conversion index, the doctor's own index, the hospital index, the non-response index, etc. is used to make an orderly judgment, which helps to match the patient with a doctor with better medical skills.

[0108] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An online consultation and dispatching method, characterized in that: include: Receiving a consultation order submitted by a patient terminal, wherein the consultation order contains description information related to the consultation; Inputting the description information into a pre-trained triage model; When the triage model outputs a triage result, determining a target department corresponding to the consultation order from the triage result; When the triage model does not output a triage result, the description information is matched with a plurality of pre-set mapping rules, and the target department corresponding to the consultation order is determined from the mapping rules matching the description information; wherein each mapping rule represents: a mapping relationship between at least one pre-determined consultation label and a corresponding department; Determine a target doctor from doctors belonging to the target department according to a pre-calculated doctor weight value, and send an order dispatch notification generated based on the consultation order to the target doctor terminal; After determining the target department, when it is judged that the current number of patients waiting for treatment in the target department is greater than a first value preset for the target department, or when it is judged that the number of patients received by the target department on that day is greater than a second value preset for the target department, the consultation order is sent to a preset order grabbing pool; wherein the consultation orders in the order grabbing pool are dispatched according to the order grabbing instructions issued by the doctor terminal; when it is judged that the current number of patients waiting for treatment in the target department is not greater than the first value, and when it is judged that the number of patients received by the target department on that day is not greater than the second value, the target doctor is determined from the doctors belonging to the target department according to the pre-calculated doctor weight value.

2. The method according to claim 1, characterized in that: The step of matching the description information with a plurality of preset mapping rules, and determining a target department corresponding to the consultation order from the mapping rules matching the description information, includes: At least one medical consultation tag is extracted from the description information, a mapping rule including the medical consultation tag is determined as a mapping rule matching the description information, and a department in the mapping rule is determined as a target department corresponding to the medical consultation order.

3. The method according to claim 1, characterized in that The step of determining a target doctor from doctors belonging to the target department according to a pre-calculated doctor weight value includes: If the target department is determined based on the triage model, a doctor belonging to the target department is determined as a candidate doctor, and a target doctor is determined from the candidate doctors according to a pre-calculated doctor weight value; If the target department is determined based on the mapping rule, the doctors in the pre-configured whitelist of general practitioners corresponding to the target department are determined as candidate doctors, and the target doctor is determined from the candidate doctors according to the pre-calculated doctor weight values.

4. The method according to claim 3, characterized in that The step of determining a target doctor from the candidate doctors according to the pre-calculated doctor weight value comprises: According to the doctor weight value from large to small, the candidate doctors are taken as the judgment objects and the preset judgment logic is executed until the target doctor is determined; The judgment logic is: when the current number of patients waiting for diagnosis is not greater than a third value preset for the patient, and the number of patients received by the patient on the day is not greater than a fourth value preset for the patient, the patient is determined as the target doctor.

5. The method according to claim 4, characterized in that The doctor weight value is determined based on at least one of the following indicator data: a favorable review rate indicator, a reply time indicator, a settlement time indicator, a physical conversion indicator, a doctor's own indicator, an affiliated hospital indicator, and a non-response indicator.

6. The method according to claim 1, characterized in that The method further comprises: After sending the order dispatch notification to the target doctor terminal, a consultation notification and a reply notification are received from the target doctor terminal; wherein, the consultation notification is issued after the target doctor confirms the consultation, and the reply notification is issued after the target doctor replies to the patient for the first time.

7. The method according to claim 6, characterized in that The method further comprises: After sending the order dispatch notification to the target doctor terminal, if no consultation notification is received from the target doctor terminal within a preset first time period, the consultation order is determined as a pending referral order; if after receiving the consultation notification from the target doctor terminal within the first time period, no reply notification is received from the target doctor terminal within a preset second time period, the consultation order is determined as a pending referral order; A target doctor is re-determined from the target departments corresponding to the order to be referred according to the pre-calculated doctor weight value, and an order dispatch notification generated based on the order to be referred is sent to the target doctor terminal.

8. An online consultation and dispatching device, characterized in that: include: A receiving unit, configured to receive a consultation order submitted by a patient terminal, wherein the consultation order contains description information related to the consultation; A triage unit, used for inputting the description information into a pre-trained triage model; When the triage model outputs a triage result, determining a target department corresponding to the consultation order from the triage result; When the triage model does not output a triage result, the description information is matched with a plurality of pre-set mapping rules, and the target department corresponding to the consultation order is determined from the mapping rules matching the description information; wherein each mapping rule represents: a mapping relationship between at least one pre-determined consultation label and a corresponding department; a dispatching unit, configured to determine a target doctor from doctors belonging to the target department according to a pre-calculated doctor weight value, and send an order dispatching notification generated based on the consultation order to the target doctor terminal; The consultation capacity judgment unit is used to: after determining the target department, if it is judged that the current number of patients waiting for treatment in the target department is greater than a first value preset for the target department, or if it is judged that the number of patients received by the target department on that day is greater than a second value preset for the target department, send the consultation order to a preset order grabbing pool; wherein the consultation orders in the order grabbing pool are dispatched according to the order grabbing instruction issued by the doctor terminal; if it is judged that the current number of patients waiting for treatment in the target department is not greater than the first value, and if it is judged that the number of patients received by the target department on that day is not greater than the second value, determine the target doctor from the doctors belonging to the target department according to the pre-calculated doctor weight value.

9. The device according to claim 8, characterized in that The triage unit is further used to: extract at least one medical consultation tag from the description information, determine a mapping rule containing the medical consultation tag as a mapping rule matching the description information, and determine the department in the mapping rule as the target department corresponding to the medical consultation order; If the target department is determined based on the triage model, a doctor belonging to the target department is determined as a candidate doctor; If the target department is determined based on the mapping rule, a doctor in a pre-configured whitelist of general practitioners corresponding to the target department is determined as a candidate doctor; The dispatching unit is further used to: execute a preset discrimination logic on the candidate doctors as discrimination objects in order of the doctor weight values ​​from large to small until a target doctor is determined; the discrimination logic is: when the current number of waiting patients of the discrimination object is not greater than a third value preset for the discrimination object, and the number of patients received by the discrimination object on that day is not greater than a fourth value preset for the discrimination object, the discrimination object is determined as the target doctor.

10. An online medical consultation and dispatching system, characterized in that: include: Server, patient terminal and doctor terminal; among them, The service end receives the consultation order submitted by the patient terminal, wherein the consultation order contains description information related to the consultation; The server inputs the description information into a pre-trained triage model; when the triage model outputs a triage result, the target department corresponding to the consultation order is determined from the triage result; when the triage model does not output a triage result, the description information is matched with a plurality of pre-set mapping rules, and the target department corresponding to the consultation order is determined from the mapping rules matching the description information; wherein each mapping rule represents: a mapping relationship between at least one pre-determined consultation label and a corresponding department; The server determines a target doctor from doctors belonging to the target department according to a pre-calculated doctor weight value, and sends an order dispatch notification generated based on the consultation order to the target doctor terminal; After determining the target department, the server sends the consultation order to a preset order grabbing pool if it determines that the current number of patients waiting for the target department is greater than a first value preset for the target department, or if it determines that the number of patients received by the target department on that day is greater than a second value preset for the target department; wherein the consultation orders in the order grabbing pool are dispatched according to the order grabbing instructions issued by the doctor terminal; and the server determines the target doctor from the doctors belonging to the target department according to a pre-calculated doctor weight value if it determines that the current number of patients waiting for the target department is not greater than the first value, and if it determines that the number of patients received by the target department on that day is not greater than the second value.

11. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images