Diagnosis and treatment service task allocation method and device

The target feature data was screened through the correlation analysis method and input it into the extreme gradient enhancement model, and the critical value of the number of tasks of each doctor was calculated, which solved the problem of low accuracy in predicting the number of doctors in the existing technology and improved the retention rate of doctors.

CN118942649APending Publication Date: 2024-11-12BEIJING JINGDONG TUOXIAN TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310524306.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-10
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Existing Internet medical platforms are difficult to accurately predict the critical value of each doctor's task number, resulting in low accuracy in predicting doctor usage rates and unable to effectively improve doctor's retention rate.

Method used

The correlation analysis method is used to filter out the target feature data with specificity, and input these feature data and their weights into the pre-trained extreme gradient enhancement model to calculate the critical value of the number of tasks for each doctor when focusing on different features. Make task assignments.

Benefits of technology

It improves the accuracy of task number prediction and effectively improves doctors' retention rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942649A_ABST
    Figure CN118942649A_ABST
Patent Text Reader

Abstract

The invention discloses a diagnosis and treatment service task allocation method and device, and relates to the technical field of internet medical treatment. The specific implementation mode comprises the steps that multiple pieces of feature data corresponding to one or more doctors are obtained; carrying out dimension reduction processing on the plurality of feature data corresponding to the one or more doctors by utilizing a correlation analysis method to obtain a plurality of target feature data; determining a weight corresponding to each piece of target feature data; inputting each target feature data and the corresponding weight into a pre-trained extreme gradient lifting model, and determining a task number critical value corresponding to each doctor according to the output of the extreme gradient lifting model; and according to the task number critical value, allocating diagnosis and treatment service tasks for doctors. According to the embodiment, the target feature data with specificity is screened out for each doctor, calculation is carried out through the extreme gradient lifting model, and the specificity and accuracy of data prediction are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of Internet medical technology, and in particular to a method and device for allocating diagnosis and treatment service tasks. Background Art

[0002] In the field of Internet medical care, in order to improve the utilization rate of doctors on the platform, the diagnosis and treatment service platform needs to predict the critical value of the number of doctors' tasks, that is, when the doctor's utilization rate is the highest, the doctor can be assigned tasks according to the critical value of the number of tasks in the subsequent dispatch process to improve the doctor's retention rate and user experience. The existing critical value calculation method is usually based on the retention data of all doctors and the number of consultations, and a simple correlation analysis is performed to evaluate the daily critical number of orders corresponding to the overall doctors. It is impossible to accurately predict the individual differences of each doctor and has low accuracy. Summary of the invention

[0003] In view of this, the embodiment of the present invention provides a method and device for allocating diagnosis and treatment service tasks. Through the correlation analysis method, specific target feature data can be screened for each doctor, thereby improving the specificity and accuracy of data prediction. Further, by inputting the target features corresponding to each doctor and the corresponding weights into the pre-trained extreme gradient boosting model, the critical value of the number of tasks corresponding to each doctor when focusing on different features can be obtained, thereby improving the accuracy of the prediction. Furthermore, by assigning tasks to doctors according to the critical value of the number of tasks, the retention rate of doctors can be effectively improved.

[0004] To achieve the above objective, according to one aspect of an embodiment of the present invention, a method for allocating diagnosis and treatment service tasks is provided.

[0005] A method for assigning medical service tasks in an embodiment of the present invention includes: obtaining multiple feature data corresponding to one or more doctors; using a correlation analysis method to perform dimensionality reduction processing on the multiple feature data corresponding to the one or more doctors to obtain multiple target feature data; determining the weights corresponding to each of the target feature data; inputting each of the target feature data and the corresponding weight into a pre-trained extreme gradient boosting model, and determining a critical value of the number of tasks corresponding to each of the doctors based on the output of the extreme gradient boosting model; and assigning the medical service tasks to the doctors based on the critical value of the number of tasks.

[0006] Optionally, the correlation analysis method is used to perform dimensionality reduction processing on multiple feature data corresponding to the one or more doctors to obtain multiple target feature data, including: using the correlation analysis method to calculate the correlation coefficients corresponding to each of the feature data; based on the sorting results of the correlation coefficients, determining the target feature data related to the critical value of the task quantity corresponding to the doctor.

[0007] Optionally, the obtaining of multiple characteristic data corresponding to one or more doctors includes: when the characteristic data of any target doctor is not obtained, determining the average characteristic value corresponding to the other doctors based on the characteristic data of the other doctors that have been obtained, and using the average characteristic value as the characteristic data of the target doctor.

[0008] Optionally, the determining the weights respectively corresponding to the respective target feature data comprises: using a deviation normalization algorithm to determine the weights respectively corresponding to the respective target feature data.

[0009] Optionally, allocating the diagnosis and treatment service tasks to the doctor according to the critical value of the task quantity includes: determining the number of tasks to be allocated according to the critical value of the task quantity corresponding to the doctor and the number of tasks already received by the doctor; and dispatching orders to the user according to the number of tasks to be allocated.

[0010] Optionally, the characteristic data include: average daily login times, average daily online time, average daily order volume, average daily revenue click times and monthly income.

[0011] Optionally, each of the target feature data and the corresponding weights are input into a pre-trained extreme gradient boosting model, and the critical value of the number of tasks corresponding to each of the doctors is determined according to the output of the extreme gradient boosting model, including: determining the model trees corresponding to each of the target feature data; determining the predicted values ​​corresponding to each leaf node in each of the model trees when the function value of the preset function is minimized; and adding each of the predicted values ​​according to the weights to obtain the critical value of the number of tasks corresponding to each of the doctors.

[0012] Optionally, determining the predicted values ​​corresponding to each leaf node in the model tree when the function value of the preset function is minimum includes: calculating the partial derivative of the preset function, and when the partial derivative value is 0, determining the predicted values ​​corresponding to each leaf node in the model tree.

[0013] To achieve the above objective, according to another aspect of an embodiment of the present invention, a device for allocating diagnosis and treatment service tasks is provided.

[0014] A device for allocating medical service tasks in an embodiment of the present invention includes: an acquisition module, which is used to acquire multiple feature data corresponding to one or more doctors; a processing module, which is used to use a correlation analysis method to perform dimensionality reduction processing on the multiple feature data corresponding to the one or more doctors, and obtain multiple target feature data; a determination module, which is used to determine the weights corresponding to each of the target feature data; a calculation module, which is used to input each of the target feature data and the corresponding weight into a pre-trained extreme gradient boosting model, and determine the critical value of the number of tasks corresponding to each of the doctors according to the output of the extreme gradient boosting model; wherein the extreme gradient boosting model is trained based on the true positive rate evaluation index; an allocation module, which is used to allocate the medical service tasks to the doctors according to the critical value of the number of tasks.

[0015] To achieve the above objective, according to another aspect of an embodiment of the present invention, there is provided an electronic device for allocating diagnosis and treatment service tasks.

[0016] An electronic device for allocating diagnosis and treatment service tasks according to an embodiment of the present invention comprises: 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 a method for allocating diagnosis and treatment service tasks according to an embodiment of the present invention.

[0017] To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided.

[0018] A computer-readable storage medium according to an embodiment of the present invention stores a computer program, which, when executed by a processor, implements a method for allocating diagnosis and treatment service tasks according to an embodiment of the present invention.

[0019] One embodiment of the above invention has the following advantages or beneficial effects: through the correlation analysis method, specific target feature data can be screened for each doctor, thereby improving the specificity and accuracy of data prediction. Further, by inputting the target features corresponding to each doctor and the corresponding weights into the pre-trained extreme gradient boosting model, the critical value of the number of tasks corresponding to each doctor when focusing on different features can be obtained, thereby improving the accuracy of prediction. Furthermore, by assigning tasks to doctors according to the critical value of the number of tasks, the retention rate of doctors can be effectively improved.

[0020] 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

[0021] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0022] Figure 1 is a flowchart of a method for allocating diagnosis and treatment service tasks according to an embodiment of the present invention;

[0023] Figure 2 is a schematic diagram of a process of reducing the dimension of feature data according to an embodiment of the present invention;

[0024] Figure 3 is a schematic diagram of a process for determining a critical value of the number of tasks according to an embodiment of the present invention;

[0025] Figure 4 is a flowchart of a specific allocation task according to an embodiment of the present invention;

[0026] Figure 5 is a schematic diagram of main modules of a device for allocating diagnosis and treatment service tasks according to an embodiment of the present invention;

[0027] Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0028] Figure 7 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0029] 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.

[0030] 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.

[0031] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of user personal information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security and national security.

[0032] (For example, after collecting multiple characteristic data of doctors, we will de-identify the characteristic data through technical means. In order to count the usage of our products / services, we will aggregate, analyze and use the technically processed user data, and share the processed statistical information with third parties. We will use secure encryption technology processing and other methods to ensure that the recipient of the information cannot re-identify a specific individual.)

[0033] Figure 1 It is a schematic diagram of the main steps of the method for allocating diagnosis and treatment service tasks according to an embodiment of the present invention.

[0034] like Figure 1 As shown, the method for allocating diagnosis and treatment service tasks in the embodiment of the present invention mainly includes the following steps:

[0035] Step S101: Acquire multiple characteristic data corresponding to one or more doctors respectively;

[0036] Step S102: using a correlation analysis method, respectively performing dimensionality reduction processing on a plurality of feature data corresponding to one or more doctors to obtain a plurality of target feature data;

[0037] Step S103: Determine the weights corresponding to each target feature data;

[0038] Step S104: input each target feature data and the corresponding weight into the pre-trained extreme gradient boosting model, and determine the critical value of the number of tasks corresponding to each doctor according to the output of the extreme gradient boosting model;

[0039] Step S105: Allocate diagnosis and treatment service tasks to doctors according to the critical value of the task quantity.

[0040] Among them, the application scenario can be an Internet medical service platform (such as an APP). The doctor is a doctor who can provide consultation services. Usually, there are multiple doctors registered on the medical service platform, who can distinguish departments, indications, etc., and provide online consultation services for different patients.

[0041] The extreme gradient boosting model in step S104 is trained based on the true positive rate evaluation index, where the true positive rate evaluation index refers to the ratio of the number of correct predictions in machine learning to the total number of predictions. For the binary classification problem, according to different predicted values ​​and actual values, there are usually four situations, as shown in Table 1 below:

[0042] Table 1 Binary classification results

[0043] The predicted value is 1 The predicted value is 0 The actual value is 1 TP FN The actual value is 0 FP TN

[0044] Among them, TP represents the number of correct matches, FN represents the number of matches that were not found correctly, FP represents the number of false matches, and TN represents the number of non-matches that were correctly rejected. On this basis, the true positive rate TRP = TP / (TP+FN), which is the proportion of positive instances in all instances.

[0045] Since the purpose of this application is to improve the retention rate of doctors, that is, to provide doctors with a better user experience from the perspective of doctors, the feature data in step S101 are multiple data related to the doctor's retention rate, such as the doctor's orders and income. In an optional embodiment, it includes: the average number of daily logins, the average daily online time, the average daily order volume, the average daily income clicks and the monthly income. Among them, the average daily login number refers to the number of times the doctor logs into the medical service platform every day, the average daily online time refers to the active time of the doctor on the medical service platform every day, the average daily order volume refers to the number of tasks that the doctor receives every day, and the average daily income clicks refers to the number of times the doctor clicks to browse the income operation every day. In the present invention, there are two main aspects that affect the doctor's retention rate. On the one hand, it is whether the doctor is satisfied with the assigned task volume, and on the other hand, it is whether the doctor is satisfied with the remuneration (income) obtained under the assigned task volume. In the case where other factors affect the doctor's retention rate, the influencing factors can also be added to the feature data.

[0046] For step S102, in an optional embodiment, the process of reducing the dimension of the feature data is as follows: Figure 2 As shown, specifically including:

[0047] Step S201: using the correlation analysis method, calculating the correlation coefficients corresponding to each feature data;

[0048] Step S202: According to the sorting result of the correlation coefficient, the target feature data related to the critical value of the number of tasks corresponding to the doctor is determined.

[0049] Among them, the correlation algorithm can be the Pearson method, which has high calculation efficiency and high accuracy. The obtained correlation coefficient is in the range of -1 to 1. The larger the value, the stronger the correlation. By sorting the correlation coefficients according to size, the target feature data that is more relevant to each doctor can be obtained. For each doctor, the target feature data obtained may be different. Therefore, the above steps can effectively improve the accuracy of subsequent calculations for each doctor.

[0050] In an optional embodiment, when some doctors first accept orders on the diagnosis and treatment service platform, some feature data may be missing and accurate predictions cannot be made. Therefore, it is necessary to make a rough prediction based on the feature data of other doctors with existing historical data. Specifically, if the feature data of any target doctor is not obtained, the average feature value corresponding to other doctors is determined based on the feature data of other doctors that have been obtained, and the average feature value is used as the feature data of the target doctor. By taking the mean as the missing data for prediction, the accuracy of the prediction can be further improved.

[0051] For step S103, in an optional embodiment, a deviation normalization algorithm may be used to determine the weights corresponding to the respective target feature data. For each target feature data X, its weight x is calculated by dividing the first difference between a certain feature data and the minimum value in the data set by the second difference between the maximum value in the data set and the minimum value in the data set, as shown in the following formula:

[0052]

[0053] Where Xmin represents the minimum value in the data set, and Xmax represents the maximum value in the data set.

[0054] The weights obtained by the deviation normalization algorithm can show the importance of the target feature data, that is, according to the size of the weight, it can be intuitively determined which target feature data is more important for the doctor, which is something that the neural network model cannot determine.

[0055] In an optional embodiment, the process of determining the critical value of the number of tasks in step S104 may be as follows: Figure 3 As shown, further comprising:

[0056] Step S301: determining the model trees corresponding to each target feature data;

[0057] Step S302: determining the prediction values ​​corresponding to the leaf nodes in each model tree when the function value of the preset function is the minimum;

[0058] Step S303: summing up the predicted values ​​according to the weights to obtain the critical value of the number of tasks corresponding to each doctor.

[0059] In order to implement step S301, it is necessary to construct a model tree in advance according to the target feature data, that is, each target feature value corresponds to a model tree, and the association relationship between the model trees is the same as in the prior art and will not be repeated here.

[0060] There are multiple leaf nodes on the model tree, and each leaf node can be understood as a classification situation. For example, the average daily login times are divided into 1, 2, 3, and 4 times. Then there are 4 branches on the model tree corresponding to the average daily login times. Under each login number, there are multiple situations for the average daily online time, the average daily order volume, the average daily income clicks, and the monthly income, that is, there are multiple sub-branches under each branch. By calculating the predicted value for each situation and finally weighting it, the prediction result of the critical value of the overall number of tasks for doctors can be obtained.

[0061] Regarding how to determine the minimum function value of the preset function in step S302, in a further optional embodiment, it includes: taking a partial derivative of the preset function, and determining the prediction values ​​corresponding to each leaf node in the model tree when the partial derivative value is 0. By taking the partial derivative operation, the extreme value can be found to achieve the minimum of the preset function.

[0062] In actual application, by inputting a large amount of historical data into the extreme gradient model to be trained, the index value corresponding to the true positive rate evaluation index can be obtained, and whether the index value meets the preset threshold can be judged to determine whether the accuracy of the extreme gradient model meets the requirements, that is, whether the training is completed. If the index value does not meet the preset threshold, the index value is continuously improved by optimizing the coefficients in the preset function until the preset threshold is met.

[0063] After the critical value of the number of tasks is obtained, the specific process of allocating tasks in step S105 can be as follows: Figure 4 As shown, including:

[0064] Step S401: determining the number of tasks to be assigned according to the critical value of the number of tasks corresponding to the doctor and the number of tasks already received by the doctor;

[0065] Step S402: Assigning orders to users according to the number of tasks to be assigned.

[0066] Among them, when the number of tasks received is less than the critical value of the number of tasks, the number of tasks to be assigned = the critical value of the number of tasks - the number of tasks received, that is, the user is assigned tasks based on the difference between the critical value of the number of tasks and the number of tasks received. When the number of tasks received is greater than or equal to the critical value of the number of tasks, no more tasks may be assigned to the user or fewer tasks may be assigned.

[0067] According to the method for allocating diagnosis and treatment service tasks in an embodiment of the present invention, through correlation analysis, specific target feature data can be screened out for each doctor, thereby improving the specificity and accuracy of data prediction. Further, by inputting the target features corresponding to each doctor and the corresponding weights into the pre-trained extreme gradient boosting model, the critical value of the number of tasks corresponding to each doctor when focusing on different features can be obtained, thereby improving the accuracy of the prediction. Furthermore, by assigning tasks to doctors based on the critical value of the number of tasks, the retention rate of doctors can be effectively improved.

[0068] Figure 5 4 is a schematic diagram of main modules of a device for allocating diagnosis and treatment service tasks according to an embodiment of the present invention.

[0069] like Figure 5 As shown, the device 500 for allocating diagnosis and treatment service tasks according to the embodiment of the present invention includes:

[0070] An acquisition module 501 is used to acquire a plurality of characteristic data corresponding to one or more doctors respectively;

[0071] The processing module 502 is used to perform dimensionality reduction processing on the multiple feature data corresponding to the one or more doctors respectively by using a correlation analysis method to obtain multiple target feature data;

[0072] A determination module 503 is used to determine the weights corresponding to each of the target feature data;

[0073] A calculation module 504 is used to input each of the target feature data and the corresponding weight into a pre-trained extreme gradient boosting model, and determine the critical value of the number of tasks corresponding to each of the doctors according to the output of the extreme gradient boosting model; wherein the extreme gradient boosting model is trained based on the true positive rate evaluation index;

[0074] The allocation module 505 is used to allocate the diagnosis and treatment service tasks to the doctors according to the task quantity critical value.

[0075] In an optional embodiment of the present invention, the processing module 502 is also used to calculate the correlation coefficients corresponding to each of the feature data using a correlation analysis method; and determine the target feature data related to the critical value of the number of tasks corresponding to the doctor based on the sorting results of the correlation coefficients.

[0076] In an optional embodiment of the present invention, the acquisition module 501 is also used to, when the characteristic data of any target doctor is not obtained, determine the average characteristic value corresponding to the other doctors based on the characteristic data of the other doctors that have been obtained, and use the average characteristic value as the characteristic data of the target doctor.

[0077] In an optional embodiment of the present invention, the determination module 503 is further configured to determine the weights corresponding to the respective target feature data using a deviation normalization algorithm.

[0078] In an optional embodiment of the present invention, the allocation module 505 is also used to determine the number of tasks to be allocated based on the critical value of the number of tasks corresponding to the doctor and the number of tasks already received by the doctor; and dispatch orders to the user based on the number of tasks to be allocated.

[0079] In an optional embodiment of the present invention, the characteristic data includes: average daily login times, average daily online time, average daily order volume, average daily income click times and monthly income.

[0080] In an optional embodiment of the present invention, the calculation module 504 is also used to determine the model trees corresponding to each of the target feature data; determine the predicted values ​​corresponding to each leaf node in each of the model trees when the function value of the preset function is the smallest; and add each of the predicted values ​​according to the weight to obtain the critical value of the number of tasks corresponding to each of the doctors.

[0081] In an optional embodiment of the present invention, the calculation module 504 is further used to calculate the partial derivative of the preset function, and when the partial derivative value is 0, determine the prediction value corresponding to each leaf node in the model tree.

[0082] According to the device for allocating diagnosis and treatment service tasks of the embodiment of the present invention, through the correlation analysis method, it is possible to screen out specific target feature data for each doctor, thereby improving the specificity and accuracy of data prediction. Further, by inputting the target features corresponding to each doctor and the corresponding weights into the pre-trained extreme gradient boosting model, the critical value of the number of tasks corresponding to each doctor when focusing on different features can be obtained, thereby improving the accuracy of the prediction. Furthermore, by assigning tasks to doctors according to the critical value of the number of tasks, the retention rate of doctors can be effectively improved.

[0083] Figure 6 An exemplary system architecture 600 is shown to which the method for allocating diagnosis and treatment service tasks or the apparatus for allocating diagnosis and treatment service tasks according to the embodiments of the present invention can be applied.

[0084] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0085] The user can use the terminal devices 601, 602, 603 to interact with the server 605 through the network 604 to receive or send data, etc. Various communication client applications can be installed on the terminal devices 601, 602, 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0086] The terminal devices 601 , 602 , and 603 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, etc.

[0087] The server 605 may be a server that provides various services, such as a background management server that provides support for the feature data sent by the user using the terminal devices 601, 602, and 603. The background management server may analyze the received feature data and feed back the processing results (such as task allocation results) to the terminal device.

[0088] It should be noted that the method for allocating diagnosis and treatment service tasks provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the device for allocating diagnosis and treatment service tasks is generally set in the server 605 .

[0089] It should be understood that Figure 6 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.

[0090] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of a terminal device suitable for implementing an embodiment of the present invention. Figure 7 The terminal 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.

[0091] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) first interface 705 is also connected to the bus 704.

[0092] The following components are connected to the I / O first interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network first interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O first interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0093] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present invention are executed.

[0094] 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.

[0095] 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.

[0096] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, they may be described as: a processor includes an acquisition module, a processing module, a determination module, a calculation module, and an allocation module. The names of these modules do not, in some cases, constitute limitations on the modules themselves. For example, the acquisition module may also be described as a "module for acquiring multiple feature data corresponding to one or more doctors".

[0097] 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 it 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 a device, the device includes: obtaining multiple feature data corresponding to one or more doctors; using the correlation analysis method, respectively performing dimensionality reduction processing on the multiple feature data corresponding to the one or more doctors to obtain multiple target feature data; determining the weights corresponding to each of the target feature data; inputting each of the target feature data and the corresponding weights into the pre-trained extreme gradient boosting model, and determining the critical value of the number of tasks corresponding to each of the doctors according to the output of the extreme gradient boosting model; wherein the extreme gradient boosting model is trained based on the true positive rate evaluation index; and according to the critical value of the number of tasks, assigning the diagnosis and treatment service tasks to the doctors.

[0098] According to the technical solution of the embodiment of the present invention, through the correlation analysis method, specific target feature data can be screened for each doctor, thereby improving the specificity and accuracy of data prediction. Further, by inputting the target features corresponding to each doctor and the corresponding weights into the pre-trained extreme gradient boosting model, the critical value of the number of tasks corresponding to each doctor when focusing on different features can be obtained, thereby improving the accuracy of the prediction. Furthermore, by assigning tasks to doctors according to the critical value of the number of tasks, the retention rate of doctors can be effectively improved.

[0099] 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. A method for allocating diagnosis and treatment service tasks, characterized in that: include: Acquire multiple characteristic data corresponding to one or more doctors respectively; Using a correlation analysis method, dimensionality reduction processing is performed on the multiple feature data corresponding to the one or more doctors to obtain multiple target feature data; Determine the weights corresponding to each of the target feature data; Input each of the target feature data and the corresponding weight into a pre-trained extreme gradient boosting model, and determine a critical value of the number of tasks corresponding to each of the doctors according to the output of the extreme gradient boosting model; The diagnosis and treatment service tasks are allocated to doctors according to the task quantity critical value.

2. The method according to claim 1, characterized in that: The correlation analysis method is used to perform dimensionality reduction processing on the multiple feature data corresponding to the one or more doctors to obtain multiple target feature data, including: Calculate the correlation coefficients corresponding to each of the characteristic data by using the correlation analysis method; According to the sorting result of the correlation coefficient, the target feature data related to the critical value of the number of tasks corresponding to the doctor is determined.

3. The method according to claim 1, characterized in that The obtaining of multiple characteristic data corresponding to one or more doctors respectively includes: In the case that the characteristic data of any target doctor is not obtained, the average characteristic value corresponding to the other doctors is determined based on the characteristic data of the other doctors that have been obtained, and the average characteristic value is used as the characteristic data of the target doctor.

4. The method according to claim 1, characterized in that: The determining of the weights corresponding to the respective target feature data includes: The deviation normalization algorithm is used to determine the weights corresponding to each of the target feature data.

5. The method according to claim 1, characterized in that: The step of allocating the diagnosis and treatment service tasks to the doctors according to the task quantity threshold value includes: Determine the number of tasks to be assigned according to the critical value of the number of tasks corresponding to the doctor and the number of tasks already accepted by the doctor; Dispatching tasks for the doctor according to the number of tasks to be assigned; and / or, The characteristic data include: average daily login times, average daily online time, average daily orders, average daily revenue clicks and monthly revenue.

6. The method according to claim 1, characterized in that The target feature data and the corresponding weights are input into a pre-trained extreme gradient boosting model, and the critical value of the number of tasks corresponding to each doctor is determined according to the output of the extreme gradient boosting model, including: Determine a model tree corresponding to each of the target feature data; Determine the prediction values ​​corresponding to the leaf nodes in each of the model trees when the function value of the preset function is the minimum; The predicted values ​​are summed up according to the weights to obtain the critical value of the number of tasks corresponding to each doctor.

7. The method according to claim 6, characterized in that The determining, when the function value of the preset function is the minimum, the prediction values ​​corresponding to the leaf nodes in the model trees respectively include: The partial derivative of the preset function is calculated, and when the partial derivative value is 0, the prediction values ​​corresponding to each leaf node in the model tree are determined.

8. A device for allocating diagnosis and treatment service tasks, characterized in that: include: An acquisition module, used for acquiring a plurality of characteristic data corresponding to one or more doctors respectively; A processing module, used to perform dimensionality reduction processing on the multiple feature data corresponding to the one or more doctors respectively by using a correlation analysis method to obtain multiple target feature data; A determination module, used to determine the weights corresponding to each of the target feature data; A calculation module, used for inputting each of the target feature data and the corresponding weight into a pre-trained extreme gradient boosting model, and determining a critical value of the number of tasks corresponding to each of the doctors according to an output of the extreme gradient boosting model; The allocation module is used to allocate the diagnosis and treatment service tasks to doctors according to the critical value of the task quantity.

9. The device according to claim 8, characterized in that The processing module is also used to calculate the correlation coefficients corresponding to each of the feature data using a correlation analysis method; and determine the target feature data related to the critical value of the number of tasks corresponding to the doctor based on the sorting results of the correlation coefficients.

10. The device according to claim 8, characterized in that The acquisition module is also used to, when the characteristic data of any target doctor is not obtained, determine the average characteristic value corresponding to other doctors based on the characteristic data of other doctors that have been obtained, and use the average characteristic value as the characteristic data of the target doctor.

11. The device according to claim 8, characterized in that The determination module is also used to determine the weights corresponding to each of the target feature data using a deviation normalization algorithm.

12. The device according to claim 8, characterized in that The allocation module is also used to determine the number of tasks to be allocated according to the critical value of the number of tasks corresponding to the doctor and the number of tasks already received by the doctor; and assign tasks to the doctor according to the number of tasks to be allocated; and / or, The characteristic data include: average daily login times, average daily online time, average daily orders, average daily revenue clicks and monthly revenue.

13. The device according to claim 8, characterized in that The calculation module is also used to determine the model trees corresponding to each of the target feature data; determine the prediction values ​​corresponding to each leaf node in each of the model trees when the function value of the preset function is the minimum; The predicted values ​​are summed up according to the weights to obtain the critical value of the number of tasks corresponding to each doctor.

14. The device according to claim 13, characterized in that The calculation module is also used to calculate the partial derivative of the preset function, and when the partial derivative value is 0, determine the prediction value corresponding to each leaf node in the model tree.

15. An electronic device for allocating diagnosis and treatment service tasks, 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.

16. A computer readable 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.