Traffic distribution method and device, computer device and storage medium

Abstract

The application belongs to the field of artificial intelligence and the field of digital medicine, and relates to a traffic distribution method and device, computer equipment and a storage medium, which comprises the following steps: if an inquiry request is received, the account information of a user is acquired, and the historical information of the user is inquired based on the account information; the chief complaint information of the user is collected, and the reception information of each doctor is acquired; the historical information, the chief complaint information and the reception information are subjected to factor generation processing to obtain initial key factors; target key factors related to inquiry traffic distribution are screened out from the initial key factors; target weights corresponding to the target key factors are generated; a multi-traffic factor distribution model is constructed based on the target key factors and the target weights, and the traffic distribution priority value of each doctor is calculated based on the multi-traffic factor distribution model; the target doctor with the highest traffic distribution priority value is screened out from all doctors, and the user is distributed to the target doctor. The application effectively improves the processing accuracy of inquiry traffic distribution.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence development technology and digital healthcare, and in particular to traffic allocation methods, devices, computer equipment and storage media. Background Technology

[0002] With the rapid development of the internet, the healthcare sector has also ushered in a wave of digital transformation. Among these transformations, online medical consultation platforms, serving as a crucial bridge connecting patients and doctors, have seen continuous growth in user numbers and increasingly diversified and personalized service demands. These changes are reflected not only in patients' urgent need for immediate and efficient medical consultation services but also in their high standards for service experience, privacy protection, and professionalism.

[0003] Currently, the traffic allocation mechanism commonly used by online medical consultation platforms is mainly based on the doctor's preset maximum and minimum number of patients, combined with the doctor's busy / idle status coefficient (such as historical patient volume, response time, etc.), to dynamically adjust the number of concurrent patients for each doctor. This traffic allocation method cannot accurately identify the user's actual medical needs for this consultation, resulting in low accuracy of traffic allocation, which in turn affects the user's consultation experience. Summary of the Invention

[0004] The purpose of this application is to provide a traffic allocation method, apparatus, computer device, and storage medium to solve the technical problem that the existing traffic allocation methods used by medical consultation platforms cannot accurately identify the user's actual medical needs during the consultation, resulting in low accuracy of traffic allocation and thus affecting the user's consultation experience.

[0005] To address the aforementioned technical problems, this application provides a traffic allocation method, employing the following technical solution:

[0006] Determine whether a user's consultation request has been received;

[0007] If so, obtain the user's account information and query the user's historical information based on the account information;

[0008] Collect the user's chief complaint information and obtain the consultation information of each doctor;

[0009] Based on a preset factor generation strategy, the historical information, the chief complaint information, and the patient reception information are processed to generate corresponding initial key factors.

[0010] Based on a preset effectiveness screening strategy, target key factors related to consultation traffic allocation are screened from the initial key factors; wherein, the number of target key factors includes multiple factors;

[0011] generate a target weight corresponding to the target key factor;

[0012] construct a corresponding multi-traffic factor allocation model based on the target key factor and the target weight, and calculate a traffic allocation priority value of each of the doctors based on the multi-traffic factor allocation model;

[0013] select a target doctor with the highest traffic allocation priority value from all the doctors, and allocate the user to the target doctor.

[0014] Further, the step of screening the target key factor related to the consultation traffic allocation from the initial key factors based on the preset effectiveness screening strategy specifically includes:

[0015] preprocessing the initial key factors to obtain corresponding first factors;

[0016] performing correlation analysis on the first factors to obtain a correlation coefficient value between the first factors and the consultation quality;

[0017] performing importance evaluation on the first factors based on a preset machine learning model to obtain an importance score of the first factors;

[0018] screening a second factor meeting a preset screening condition from all the first factors based on the correlation coefficient value and the importance score;

[0019] generating a target key factor related to the consultation traffic allocation based on the second factor.

[0020] Further, the step of generating the target key factor related to the consultation traffic allocation based on the second factor specifically includes:

[0021] screening a third factor meeting a preset correlation threshold and a preset importance threshold from the second factors;

[0022] performing redundancy factor removal processing on the third factors to obtain corresponding fourth factors;

[0023] obtaining business significance information of all filtered specified factors;

[0024] extracting important factors from the specified factors based on the business significance information;

[0025] performing supplementary processing on the fourth factors based on the important factors to obtain corresponding fifth factors;

[0026] taking the fifth factors as the target key factors.

[0027] Furthermore, the step of generating the target weights corresponding to the target key factors specifically includes:

[0028] Obtain the preset weight allocation algorithm;

[0029] The target key factors are weighted based on a weight allocation algorithm to obtain the initial weights corresponding to the target key factors.

[0030] Receive input weight feedback information;

[0031] The initial weights of the target key factors are fine-tuned based on the weight feedback information to obtain the fine-tuned initial weights.

[0032] The fine-tuned initial weights are used as the target weights of the target key factors.

[0033] Furthermore, the step of constructing a corresponding multi-flow factor allocation model based on the target key factors and the target weights specifically includes:

[0034] Based on the target key factors and the target weights, a calculation formula for calculating traffic allocation priority is constructed;

[0035] The corresponding target calculation logic is generated based on the calculation formula;

[0036] The multi-flow factor allocation model is obtained by performing model construction processing based on the target calculation logic.

[0037] Furthermore, after the step of selecting the target doctor with the highest traffic allocation priority value from all the doctors and assigning the user to the target doctor, the method further includes:

[0038] After the user completes the consultation, the user's evaluation data on the consultation is collected;

[0039] Obtain feedback from the target doctor regarding the traffic allocation corresponding to the user;

[0040] Data analysis is performed on the evaluation data and the feedback opinions to obtain the corresponding data analysis results;

[0041] The multi-flow factor allocation model is optimized based on the data analysis results.

[0042] Furthermore, after the step of selecting the target doctor with the highest traffic allocation priority value from all the doctors and assigning the user to the target doctor, the method further includes:

[0043] Obtain the patient reception status of the target doctor and the patient consultation status of the user;

[0044] Update the patient reception status of the target doctor;

[0045] The user's consultation status is updated.

[0046] To address the aforementioned technical problems, this application also provides a flow distribution device, which employs the following technical solution:

[0047] The judgment module is used to determine whether a consultation request submitted by the user has been received;

[0048] The query module is used to obtain the user's account information if the condition is met, and to query the user's historical information based on the account information.

[0049] The first processing module is used to collect the user's chief complaint information and obtain the consultation information of each doctor;

[0050] The first generation module is used to perform factor generation processing on the historical information, the chief complaint information and the patient reception information based on a preset factor generation strategy to obtain the corresponding initial key factors.

[0051] The filtering module is used to filter out target key factors related to the allocation of consultation traffic from the initial key factors based on a preset effectiveness filtering strategy; wherein, the number of target key factors includes multiple factors;

[0052] The second generation module is used to generate target weights corresponding to the target key factors;

[0053] The second processing module is used to construct a corresponding multi-flow factor allocation model based on the target key factors and the target weights, and to calculate the flow allocation priority value of each of the doctors based on the multi-flow factor allocation model.

[0054] The allocation module is used to filter out the target doctor with the highest traffic allocation priority value from all the doctors and allocate the user to the target doctor.

[0055] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution:

[0056] Determine whether a user's consultation request has been received;

[0057] If so, obtain the user's account information and query the user's historical information based on the account information;

[0058] Collect the user's chief complaint information and obtain the consultation information of each doctor;

[0059] Based on a preset factor generation strategy, the historical information, the chief complaint information, and the patient reception information are processed to generate corresponding initial key factors.

[0060] Based on a preset effectiveness screening strategy, target key factors related to consultation traffic allocation are screened from the initial key factors; wherein, the number of target key factors includes multiple factors;

[0061] Generate target weights corresponding to the target key factors;

[0062] Based on the target key factors and the target weights, a corresponding multi-flow factor allocation model is constructed, and the flow allocation priority value of each doctor is calculated based on the multi-flow factor allocation model.

[0063] Select the target doctor with the highest traffic allocation priority value from all the doctors, and assign the user to the target doctor.

[0064] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below:

[0065] Determine whether a user's consultation request has been received;

[0066] If so, obtain the user's account information and query the user's historical information based on the account information;

[0067] Collect the user's chief complaint information and obtain the consultation information of each doctor;

[0068] Based on a preset factor generation strategy, the historical information, the chief complaint information, and the patient reception information are processed to generate corresponding initial key factors.

[0069] Based on a preset effectiveness screening strategy, target key factors related to consultation traffic allocation are screened from the initial key factors; wherein, the number of target key factors includes multiple factors;

[0070] Generate target weights corresponding to the target key factors;

[0071] Based on the target key factors and the target weights, a corresponding multi-flow factor allocation model is constructed, and the flow allocation priority value of each doctor is calculated based on the multi-flow factor allocation model.

[0072] Select the target doctor with the highest traffic allocation priority value from all the doctors, and assign the user to the target doctor.

[0073] Compared with the prior art, the embodiments of this application have the following main advantages:

[0074] This application first determines whether a user's consultation request has been received; if so, it obtains the user's account information and queries the user's historical information based on the account information; then it collects the user's chief complaint information and obtains the consultation information of each doctor; subsequently, it performs factor generation processing on the historical information, chief complaint information, and consultation information based on a preset factor generation strategy to obtain corresponding initial key factors; and filters target key factors related to consultation traffic allocation from the initial key factors based on a preset validity screening strategy; wherein, the number of target key factors includes multiple; subsequently, it generates target weights corresponding to the target key factors; further, it constructs a corresponding multi-traffic factor allocation model based on the target key factors and the target weights, and calculates the value of each doctor based on the multi-traffic factor allocation model. Traffic allocation priority value; finally, from all the doctors, the target doctor with the highest traffic allocation priority value is selected, and the user is assigned to the target doctor. In this way, by using a factor generation strategy and an effectiveness screening strategy, this application can accurately determine several target key factors that conform to the medical scenario and are related to the allocation of consultation traffic. Based on the target weights corresponding to the target key factors, a corresponding multi-traffic factor allocation model is constructed. Then, based on the use of the multi-traffic factor allocation model, the traffic allocation priority value of each doctor is calculated, and the target doctor with the highest traffic allocation priority value is selected from all the doctors. Finally, the user is assigned to the target doctor, so as to automatically and accurately complete the consultation traffic allocation processing for users, effectively improve the accuracy of consultation traffic allocation processing, and thus help improve the user's consultation experience. Attached Figure Description

[0075] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0076] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0077] Figure 2 A flowchart of an embodiment of the traffic allocation method according to this application;

[0078] Figure 3 This is a schematic diagram of the structure of one embodiment of the flow distribution device according to this application;

[0079] Figure 4 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0080] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0081] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0082] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0083] like Figure 1 As shown, system architecture 100 may include terminal device 101, network 102, and server 103. Terminal device 101 may be a laptop 1011, tablet 1012, or mobile phone 1013. Network 102 is used as a medium to provide a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0084] Users can use terminal device 101 to interact with server 103 via network 102 to receive or send messages, etc. Various communication client applications can be installed on terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0085] Terminal device 101 can be various electronic devices with a display screen and support web browsing. In addition to laptops 1011, tablets 1012, or mobile phones 1013, terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer, and a desktop computer, etc.

[0086] Server 103 can be a server that provides various services, such as a backend server that provides support for the pages displayed on terminal device 101.

[0087] It should be noted that the traffic allocation method provided in this application embodiment is generally executed by a server / terminal device, and correspondingly, the traffic allocation device is generally set in the server / terminal device.

[0088] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0089] Continue to refer to Figure 2 A flowchart illustrating an embodiment of the traffic allocation method according to this application is shown. The order of steps in the flowchart can be changed, and some steps can be omitted, depending on different needs. The traffic allocation method provided by this application embodiment can be applied to any scenario requiring traffic allocation, and thus can be applied to products in these scenarios, such as online consultation traffic allocation in the digital healthcare field. The traffic allocation method includes the following steps:

[0090] Step S201: Determine whether a consultation request submitted by the user has been received.

[0091] In this embodiment, the traffic allocation method operates on electronic devices (e.g., Figure 1The server / terminal device shown can receive consultation requests via wired or wireless connections. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-wideband) connections, and other currently known or future-developed wireless connection methods. The implementing entity of this application is specifically a traffic allocation system, or simply the system. This application can be applied to consultation traffic allocation scenarios in the field of digital healthcare, specifically for allocating appropriate doctors to users for corresponding consultation processing. The aforementioned consultation request can be a consultation request submitted by the user through the traffic allocation system.

[0092] Step S202: If yes, obtain the user's account information and query the user's historical information based on the account information.

[0093] In this embodiment, during the user's login process to the traffic allocation system, the user's account information can be obtained. This account information refers to the identity information used by the user when registering their identity in the traffic allocation system, such as name or mobile phone number. Then, this account information can be retrieved from a preset user database to obtain the user's historical information. This historical information may include at least user profile information, user historical access information, user transaction information, consultation interval information, and information on the doctor with whom the user recently had a transaction. Specifically, user profile information may include gender, age, and medical history. Historical access information may include modules visited and search keywords. User transaction information may include: number of transactions, transaction amount, name of purchased medicine category, and name of purchased physical goods category. Consultation interval information includes the number of minutes between the current consultation and the last consultation. Information on the doctor with whom the user recently had a transaction includes the doctor's information.

[0094] Step S203: Collect the user's chief complaint information and obtain the consultation information of each doctor.

[0095] In this embodiment, when a user submits a consultation request, the user's chief complaint information is collected through the front-end interface. The chief complaint information refers to the description of the symptoms or problem the user is currently inquiring about. The aforementioned consultation information refers to the real-time consultation status of each doctor, which may include at least: the number of patients a doctor is currently seeing, the maximum number of patients a doctor is configured to see, and the number of patients a doctor is currently queuing for. The consultation information of each doctor can be obtained by querying the doctor status table or by real-time calculation.

[0096] Step S204: Based on a preset factor generation strategy, perform factor generation processing on the historical information, the chief complaint information, and the patient reception information to obtain the corresponding initial key factors.

[0097] In this embodiment, the similarity of the chief complaint can be obtained by calculating the text similarity coefficient between the user's current chief complaint and historical chief complaint information using the aforementioned chief complaint information. Specifically, keywords in the current chief complaint information can be obtained, and natural language similarity analysis can be performed on historical consultation requests. The correlation between the current chief complaint information and historical chief complaint information can be determined based on the similarity level.

[0098] Subsequently, by integrating the user profile information, user historical access information, user transaction information, consultation interval information, recent transaction doctor information, the similarity of the chief complaint, and the number of doctors seeing patients in real time, the maximum number of doctors configured to see patients, and the number of doctors queuing in real time contained in the consultation information obtained by calculation or query, the corresponding initial key factors are obtained.

[0099] Step S205: Based on a preset validity screening strategy, target key factors related to consultation traffic allocation are screened from the initial key factors; wherein, the number of target key factors includes multiple factors.

[0100] In this embodiment, the specific implementation process of filtering out target key factors related to consultation traffic allocation from the initial key factors based on the preset effectiveness screening strategy will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0101] Step S206: Generate target weights corresponding to the target key factors.

[0102] In this embodiment, the specific implementation process of generating the target weights corresponding to the target key factors will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0103] Step S207: Construct a corresponding multi-flow factor allocation model based on the target key factor and the target weight, and calculate the flow allocation priority value of each doctor based on the multi-flow factor allocation model.

[0104] In this embodiment, the specific implementation process of constructing the corresponding multi-flow factor allocation model based on the target key factors and the target weights will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0105] Step S208: Select the target doctor with the highest traffic allocation priority value from all the doctors, and assign the user to the target doctor.

[0106] In this embodiment, by comparing the traffic allocation priority values ​​of all doctors, the target doctor with the highest traffic allocation priority value can be selected from all the doctors, and the user can be assigned to the target doctor, so as to automatically complete the traffic allocation process for the user's consultation.

[0107] This application first determines whether a user's consultation request has been received; if so, it obtains the user's account information and queries the user's historical information based on the account information; then it collects the user's chief complaint information and obtains the consultation information of each doctor; subsequently, it performs factor generation processing on the historical information, chief complaint information, and consultation information based on a preset factor generation strategy to obtain corresponding initial key factors; and filters target key factors related to consultation traffic allocation from the initial key factors based on a preset validity screening strategy; wherein, the number of target key factors includes multiple; subsequently, it generates target weights corresponding to the target key factors; further, it constructs a corresponding multi-traffic factor allocation model based on the target key factors and the target weights, and calculates the value of each doctor based on the multi-traffic factor allocation model. Traffic allocation priority value; finally, from all the doctors, the target doctor with the highest traffic allocation priority value is selected, and the user is assigned to the target doctor. In this way, by using a factor generation strategy and an effectiveness screening strategy, this application can accurately determine several target key factors that conform to the medical scenario and are related to the allocation of consultation traffic. Based on the target weights corresponding to the target key factors, a corresponding multi-traffic factor allocation model is constructed. Then, based on the use of the multi-traffic factor allocation model, the traffic allocation priority value of each doctor is calculated, and the target doctor with the highest traffic allocation priority value is selected from all the doctors. Finally, the user is assigned to the target doctor, so as to automatically and accurately complete the consultation traffic allocation processing for users, effectively improve the accuracy of consultation traffic allocation processing, and thus help improve the user's consultation experience.

[0108] In some alternative implementations, step S205 includes the following steps:

[0109] The initial key factors are preprocessed to obtain the corresponding first factor.

[0110] In this embodiment, the preprocessing mentioned above refers to identifying outliers or missing values ​​in the initial key factors by performing descriptive statistical analysis on the initial key factors, and then performing appropriate processing, such as filling, deleting, or marking.

[0111] Correlation analysis was performed on the first factor to obtain the correlation coefficient between the first factor and the quality of consultation.

[0112] In this embodiment, the correlation between each first factor can be evaluated by using methods such as Pearson correlation coefficient and Spearman rank correlation coefficient, and the correlation between each first factor and consultation quality (e.g., user satisfaction, doctor evaluation) can be further analyzed to obtain the corresponding absolute value of the correlation coefficient, which is used as the above-mentioned correlation coefficient value.

[0113] The importance of the first factor is evaluated based on a pre-defined machine learning model, and an importance score for the first factor is obtained.

[0114] In this embodiment, the aforementioned machine learning model is a pre-built model with consultation quality as the target variable and each first factor as a feature variable. Specifically, it can employ a linear regression model, a logistic regression model, or a random forest model. The model's performance can be evaluated using methods such as cross-validation to determine which factors contribute most to the model's predictions, and then the feature importance of each first factor can be calculated to obtain the aforementioned importance score.

[0115] Based on the correlation coefficient value and the importance score, a second factor that meets the preset screening criteria is selected from all the first factors.

[0116] In this embodiment, the aforementioned preset screening conditions refer to conditions where the correlation coefficient value is greater than a preset correlation threshold, or the importance score is greater than a preset importance threshold. By screening the first factor based on the preset screening conditions, a second factor with a high degree of correlation related to the allocation of consultation traffic can be initially screened out. The values ​​of the aforementioned correlation threshold and importance threshold are not specifically limited and can be set according to actual business needs and model performance requirements.

[0117] Based on the second factor, target key factors related to the allocation of consultation traffic are generated.

[0118] In this embodiment, the specific implementation process of generating target key factors related to consultation traffic allocation based on the second factor will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0119] This application preprocesses the initial key factors to obtain corresponding first factors; then performs correlation analysis on the first factors to obtain the correlation coefficient value between the first factors and consultation quality; and evaluates the importance of the first factors based on a preset machine learning model to obtain an importance score for the first factors; subsequently, based on the correlation coefficient value and the importance score, it selects second factors that meet preset screening conditions from all the first factors; and finally, it generates target key factors related to consultation traffic allocation based on the second factors. This application, by preprocessing the initial key factors to obtain the first factors, and then combining the correlation coefficient value and importance score obtained from the correlation analysis and importance evaluation of the first factors to screen the first factors, can intelligently and accurately select target key factors related to consultation traffic allocation from the first factors, ensuring the data accuracy of the obtained target key factors.

[0120] In some optional implementations of this embodiment, generating the target key factor related to consultation traffic allocation based on the second factor includes the following steps:

[0121] A third factor is selected from the second factor that meets both the preset relevance threshold and the preset importance threshold.

[0122] In this embodiment, the values ​​of the above-mentioned relevance threshold and importance threshold are not specifically limited, and can be set according to actual business needs and model performance requirements.

[0123] Redundancy removal is performed on the third factor to obtain the corresponding fourth factor.

[0124] In this embodiment, the redundant factor removal process includes checking whether there is a high degree of correlation (such as multicollinearity) among the factors. If redundant factors exist, one or more of them are excluded to reduce the complexity of the model.

[0125] Retrieve business significance information for all filtered specified factors.

[0126] In this embodiment, in addition to correlation statistics and feature importance analysis, the business significance of each factor can be further considered. For example, even if a factor has weak statistical correlation, it should still be retained if it represents important business logic (such as the user's historical disease type). Here, the specified factors refer to the factors that have been filtered out, that is, the factors other than the fourth factor mentioned above among the initial key factors.

[0127] Important factors are extracted from the specified factors based on business significance information.

[0128] In this embodiment, the aforementioned important factors refer to those factors that represent important business logic among the specified factors.

[0129] The fourth factor is supplemented based on the aforementioned important factors to obtain the corresponding fifth factor.

[0130] In this embodiment, the fifth factor can be obtained by integrating the fourth factor and the important factor.

[0131] The fifth factor is taken as the target key factor.

[0132] This application selects a third factor from the second factor that meets a preset relevance threshold and a preset importance threshold; then performs redundant factor removal on the third factor to obtain a corresponding fourth factor; subsequently, it obtains the business significance information of all filtered specified factors; and extracts important factors from the specified factors based on the business significance information; then, it performs supplementary processing on the fourth factor based on the important factors to obtain a corresponding fifth factor; finally, it uses the fifth factor as the target key factor. After selecting a second factor that meets preset screening conditions from all the first factors based on the relevance coefficient value and the importance score, this application intelligently selects a third factor from the second factor that meets a preset relevance threshold and a preset importance threshold, performs redundant factor removal on the third factor to obtain a fourth factor, and further extracts important factors from the specified factors based on the business significance information of the filtered specified factors. Subsequently, it performs supplementary processing on the fourth factor based on the important factors to obtain the final target key factor. This effectively improves the accuracy of target key factor selection, ensures the diversity and reliability of the obtained target key factors, and is beneficial to ensuring the model performance of the subsequent multi-traffic factor allocation model built based on the target key factors and target weights.

[0133] In some alternative implementations, step S206 includes the following steps:

[0134] Obtain the preset weight allocation algorithm.

[0135] In this embodiment, the weight allocation algorithm described above can specifically adopt algorithms such as AHP (Analog-Hybrid Hierarchy Process) or expert scoring.

[0136] The target key factors are weighted using a weight allocation algorithm to obtain the initial weights corresponding to the target key factors.

[0137] In this embodiment, the target key factor can be weighted according to the steps of constructing a hierarchical structure, performing pairwise comparisons, and calculating comprehensive weights, based on the selected weight allocation algorithm, thereby obtaining the initial weights corresponding to the target key factor.

[0138] Receive input weight feedback information.

[0139] In this embodiment, experts in the medical field can be further invited to participate in the weight allocation process of the aforementioned key target factors, and their experience and suggestions can be received to obtain the aforementioned weight feedback information.

[0140] The initial weights of the target key factors are fine-tuned based on the weight feedback information to obtain the fine-tuned initial weights.

[0141] In this embodiment, the initial weights of the target key factors can be fine-tuned based on the experience and suggestions mentioned in the above weight feedback information, thereby obtaining the fine-tuned initial weights.

[0142] The fine-tuned initial weights are used as the target weights of the target key factors.

[0143] This application obtains a preset weight allocation algorithm; calculates the weights of the target key factors based on the weight allocation algorithm to obtain initial weights corresponding to the target key factors; then receives input weight feedback information; subsequently, it fine-tunes the initial weights of the target key factors based on the weight feedback information to obtain fine-tuned initial weights; and finally, it uses the fine-tuned initial weights as the target weights of the target key factors. This application, by using a weight allocation algorithm to calculate the weights of the target key factors to obtain initial weights corresponding to the target key factors, and then intelligently fine-tuning the initial weights of the target key factors based on the input weight feedback information to obtain the final target weights of the target key factors, effectively ensures the accuracy of the obtained target weights, which is beneficial to ensuring the model performance of the subsequent multi-flow factor allocation model built based on the target key factors and target weights.

[0144] In some optional implementations, step S207, which involves constructing a corresponding multi-flow factor allocation model based on the target key factor and the target weight, includes the following steps:

[0145] A calculation formula for calculating traffic allocation priority is constructed based on the target key factors and the target weights.

[0146] In this embodiment, the calculation formula for the traffic allocation priority can specifically adopt weighted summation, product, or other complex mathematical expressions. Preferably, the calculation formula for the traffic allocation priority includes: Traffic allocation priority = weight value of the most recent consultation * (1 / number of minutes since the last consultation with the same doctor) + transaction weight value * number of transactions + weight of similar complaints * correlation coefficient with the last complaint + weight value of the number of patients received * (real-time number of patients received / maximum number of patients received) - weight value of the number of people in the queue * the number of people currently in the queue for this doctor.

[0147] The corresponding target calculation logic is generated based on the calculation formula.

[0148] In this embodiment, based on the above calculation formula, the corresponding model calculation logic, i.e., the aforementioned target calculation logic, is implemented using programming languages ​​such as Python. The implementation process of the target calculation logic includes defining functions or classes to encapsulate the calculation process.

[0149] The multi-flow factor allocation model is obtained by performing model construction processing based on the target calculation logic.

[0150] In this embodiment, the target calculation logic is used as the calculation logic for the multi-flow factor allocation model to construct the model, thereby obtaining the corresponding multi-flow factor allocation model. Furthermore, after the multi-flow factor allocation model is constructed, it can be used to calculate the flow allocation priority of relevant doctors using the calculation formula corresponding to the target calculation logic.

[0151] Furthermore, after completing the construction of the multi-factor traffic allocation model, unit tests can be written for each part of the model to ensure that each function or method works as expected. In the absence of actual data, simulated data can be used to test the various functions of the model. Test cases can be run to check for any failures or anomalies and fix any problems found. Subsequently, the tested multi-factor traffic allocation model will be integrated into the consultation process of the medical service platform to ensure that the multi-factor traffic allocation model can correctly assign doctors to users and that the allocation results meet expectations.

[0152] This application constructs a calculation formula for calculating traffic allocation priority based on the target key factors and the target weights; then generates corresponding target calculation logic based on the calculation formula; subsequently, it performs model building processing based on the target calculation logic to obtain the multi-traffic factor allocation model. This application achieves rapid and accurate construction of the required multi-traffic factor allocation model by constructing a calculation formula for calculating traffic allocation priority based on the target key factors and the target weights, generating corresponding target calculation logic based on the calculation formula, and then performing model building processing based on the use of the target calculation logic. This improves the construction efficiency of the multi-traffic factor allocation model and ensures the model performance of the obtained multi-traffic factor allocation model.

[0153] In some optional implementations of this embodiment, after step S208, the electronic device may further perform the following steps:

[0154] After the user completes the consultation, the user's evaluation data on the consultation is collected.

[0155] In this embodiment, after the user completes the consultation, the system's front-end interface can collect the user's rating of the consultation, i.e. the aforementioned evaluation data, and save the evaluation data to the database for subsequent analysis.

[0156] Obtain feedback from the target doctor regarding the traffic allocation corresponding to the user.

[0157] In this embodiment, feedback from doctors regarding traffic allocation corresponding to user consultations can be collected through the doctor's interface or the system, and the feedback can be saved to the database.

[0158] The evaluation data and feedback opinions are analyzed to obtain the corresponding data analysis results.

[0159] In this embodiment, statistical methods or machine learning models can be used to analyze user evaluation data and feedback from target doctors to assess the actual performance of each target key factor and identify ineffective or redundant factors among the target key factors.

[0160] The multi-flow factor allocation model is optimized based on the data analysis results.

[0161] In this embodiment, the model optimization process includes: adjusting the weights of each target key factor based on the data analysis results; removing invalid factors; and recalculating the weights of the remaining factors. Additionally, the calculation formula used to calculate traffic allocation priority in the traffic allocation model can also be adjusted.

[0162] Furthermore, the optimization process described above can be automated, forming a regularly executed task or a real-time monitoring system. New data is continuously collected, and user and physician feedback is analyzed to continuously optimize the multi-factor traffic allocation model. The multi-factor traffic allocation model is also periodically evaluated and adjusted to adapt to changes in the healthcare environment and user needs.

[0163] This application collects user evaluation data after a user completes a consultation; then obtains feedback from the target doctor regarding the traffic allocation corresponding to the user; subsequently, it performs data analysis on the evaluation data and feedback to obtain corresponding data analysis results; and finally, it optimizes the multi-traffic factor allocation model based on the data analysis results. This application intelligently collects user evaluation data and obtains feedback from the target doctor regarding the traffic allocation corresponding to the user after a user completes a consultation, then performs data analysis on the evaluation data and feedback, and optimizes the multi-traffic factor allocation model based on the obtained data analysis results. This allows for real-time dynamic optimization of factors and weights in the multi-traffic factor allocation model based on user and doctor feedback, eliminating ineffective and redundant factors, continuously maintaining the practicality and effectiveness of the multi-traffic factor allocation model, and thus adapting to changes in medical scenarios and user needs.

[0164] In some optional implementations of this embodiment, after step S208, the electronic device may further perform the following steps:

[0165] Obtain the patient reception status of the target doctor and the patient consultation status of the user.

[0166] In this embodiment, the consultation status of the target doctor can be obtained by querying the consultation status information of the target doctor, and the consultation status of the user can be obtained by querying the consultation status information of the user. The original status corresponding to the consultation status of the target doctor is "not consulted," and the consultation status of the user is "pending consultation."

[0167] The patient reception status of the target doctor is updated.

[0168] In this embodiment, the corresponding update process can be completed by updating the target doctor's consultation status from not seeing patients to seeing patients.

[0169] The user's consultation status is updated.

[0170] In this embodiment, the corresponding update process can be completed by updating the user's consultation status from pending consultation to consultation in progress.

[0171] This application obtains the consultation status of the target doctor and the consultation status of the user; then updates the consultation status of the target doctor and the consultation status of the user. After assigning the user to the target doctor, this application automatically and intelligently updates the consultation status of the target doctor and the consultation status of the user, thereby effectively ensuring the accuracy of the consultation status of the target doctor and the consultation status of the user.

[0172] In some alternative implementations, the user information obtained is subject to user consent and complies with relevant laws and policies.

[0173] Furthermore, the traffic allocation method proposed in this application can reduce users' waiting time and consultation rounds, minimizing additional queuing time and the cost of explaining to doctors, thus enabling users to receive more efficient and comfortable medical services. It strengthens the bond between users and doctors, enhancing mutual stickiness. It also simplifies doctors' operating procedures, reduces communication costs between doctors and patients, saves doctors' operating time, and improves their user experience. Additionally, it increases new users' positive first impression of the medical platform, increases the frequency of follow-up visits and purchases, gradually improves conversion rates and average order value, effectively enhancing user experience and increasing satisfaction and dependence on the platform. Moreover, it reduces the likelihood of traffic allocation errors in scenarios with saturated medical traffic, and lowers the probability of uneven workload distribution among doctors.

[0174] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0175] It should be emphasized that, in order to further ensure the privacy and security of the above traffic allocation priority values, these traffic allocation priority values ​​can also be stored in a node of a blockchain.

[0176] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0177] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0178] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0179] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0180] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0181] Further reference Figure 3 As a response to the above Figure 2 To implement the method shown, this application provides an embodiment of a traffic allocation device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0182] like Figure 3As shown, the traffic allocation device 300 described in this embodiment includes: a judgment module 301, a query module 302, a first processing module 303, a first generation module 304, a filtering module 305, a second generation module 306, a second processing module 307, and an allocation module 308. Wherein:

[0183] The judgment module 301 is used to determine whether a consultation request submitted by the user has been received;

[0184] The query module 302 is used to, if yes, obtain the user's account information and query the user's historical information based on the account information;

[0185] The first processing module 303 is used to collect the user's chief complaint information and obtain the consultation information of each doctor.

[0186] The first generation module 304 is used to perform factor generation processing on the historical information, the chief complaint information and the patient reception information based on a preset factor generation strategy to obtain the corresponding initial key factors.

[0187] The filtering module 305 is used to filter out target key factors related to consultation traffic allocation from the initial key factors based on a preset effectiveness filtering strategy; wherein, the number of target key factors includes multiple factors.

[0188] The second generation module 306 is used to generate target weights corresponding to the target key factors;

[0189] The second processing module 307 is used to construct a corresponding multi-flow factor allocation model based on the target key factor and the target weight, and to calculate the flow allocation priority value of each of the doctors based on the multi-flow factor allocation model.

[0190] The allocation module 308 is used to filter out the target doctor with the highest traffic allocation priority value from all the doctors and allocate the user to the target doctor.

[0191] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the traffic allocation method in the aforementioned embodiments, and will not be repeated here.

[0192] In some optional implementations of this embodiment, the filtering module 305 includes:

[0193] The preprocessing submodule is used to preprocess the initial key factors to obtain the corresponding first factor;

[0194] The analysis submodule is used to perform correlation analysis on the first factor to obtain the correlation coefficient value between the first factor and the quality of consultation.

[0195] The evaluation submodule is used to evaluate the importance of the first factor based on a preset machine learning model and obtain the importance score of the first factor.

[0196] A filtering submodule is used to filter out second factors that meet preset filtering conditions from all the first factors based on the correlation coefficient value and the importance score;

[0197] The first generation submodule is used to generate target key factors related to the allocation of consultation traffic based on the second factor.

[0198] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the traffic allocation method in the aforementioned embodiments, and will not be repeated here.

[0199] In some optional implementations of this embodiment, the first generation submodule includes:

[0200] A filtering unit is used to filter out a third factor from the second factor that meets a preset relevance threshold and a preset importance threshold.

[0201] The processing unit is used to perform redundant factor removal processing on the third factor to obtain the corresponding fourth factor;

[0202] The acquisition unit is used to acquire the business meaning information of all filtered specified factors;

[0203] An extraction unit is used to extract important factors from the specified factors based on business significance information;

[0204] The supplementary unit is used to supplement the fourth factor based on the important factors to obtain the corresponding fifth factor;

[0205] A determining unit is used to identify the fifth factor as the target key factor.

[0206] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the traffic allocation method in the aforementioned embodiments, and will not be repeated here.

[0207] In some optional implementations of this embodiment, the second generation module 306 includes:

[0208] The `get` submodule is used to obtain the preset weight allocation algorithm;

[0209] The calculation submodule is used to perform weight calculation processing on the target key factor based on the weight allocation algorithm to obtain the initial weight corresponding to the target key factor;

[0210] The receiving submodule is used to receive the input weight feedback information;

[0211] The fine-tuning submodule is used to fine-tune the initial weights of the target key factors based on the weight feedback information to obtain the fine-tuned initial weights.

[0212] A determination submodule is used to use the fine-tuned initial weights as the target weights of the target key factors.

[0213] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the traffic allocation method in the aforementioned embodiments, and will not be repeated here.

[0214] In some optional implementations of this embodiment, the second processing module 307 includes:

[0215] The first construction submodule is used to construct a calculation formula for calculating traffic allocation priority based on the target key factors and the target weights;

[0216] The second generation submodule is used to generate the corresponding target calculation logic based on the calculation formula;

[0217] The second construction submodule is used to perform model construction processing based on the target calculation logic to obtain the multi-flow factor allocation model.

[0218] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the traffic allocation method in the aforementioned embodiments, and will not be repeated here.

[0219] In some optional implementations of this embodiment, the traffic distribution device further includes:

[0220] The data collection module is used to collect the user's evaluation data on the consultation after the user completes the consultation.

[0221] The first acquisition module is used to acquire the feedback from the target doctor regarding the traffic allocation corresponding to the user;

[0222] The analysis module is used to perform data analysis on the evaluation data and the feedback opinions to obtain the corresponding data analysis results;

[0223] The optimization module is used to optimize the multi-flow factor allocation model based on the data analysis results.

[0224] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the traffic allocation method in the aforementioned embodiments, and will not be repeated here.

[0225] In some optional implementations of this embodiment, the traffic distribution device further includes:

[0226] The second acquisition module is used to acquire the patient reception status of the target doctor and the patient consultation status of the user.

[0227] The first update module is used to update the patient reception status of the target doctor.

[0228] The second update module is used to update the user's consultation status.

[0229] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the traffic allocation method in the aforementioned embodiments, and will not be repeated here.

[0230] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed] for details. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0231] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0232] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0233] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 4. Of course, the memory 41 may also include both the internal storage unit and its external storage device of the computer device 4. In this embodiment, the memory 41 is typically used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for traffic allocation methods. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0234] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or to process data, such as executing computer-readable instructions for the traffic allocation method.

[0235] The network interface 43 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 4 and other electronic devices.

[0236] Compared with the prior art, the embodiments of this application have the following main advantages:

[0237] In this embodiment, by using a factor generation strategy and an effectiveness screening strategy, several target key factors that conform to the medical scenario and are related to the allocation of consultation traffic can be accurately determined. A corresponding multi-traffic factor allocation model is constructed based on the target weights corresponding to the target key factors. Then, based on the use of the multi-traffic factor allocation model, the traffic allocation priority value of each doctor is calculated, and the target doctor with the highest traffic allocation priority value is selected from all doctors. Finally, the user is assigned to the target doctor to achieve automatic and accurate completion of the consultation traffic allocation process for the user, effectively improving the accuracy of consultation traffic allocation and thus improving the user's consultation experience.

[0238] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the traffic allocation method described above.

[0239] Compared with the prior art, the embodiments of this application have the following main advantages:

[0240] In this embodiment, by using a factor generation strategy and an effectiveness screening strategy, several target key factors that conform to the medical scenario and are related to the allocation of consultation traffic can be accurately determined. A corresponding multi-traffic factor allocation model is constructed based on the target weights corresponding to the target key factors. Then, based on the use of the multi-traffic factor allocation model, the traffic allocation priority value of each doctor is calculated, and the target doctor with the highest traffic allocation priority value is selected from all doctors. Finally, the user is assigned to the target doctor to achieve automatic and accurate completion of the consultation traffic allocation process for the user, effectively improving the accuracy of consultation traffic allocation and thus improving the user's consultation experience.

[0241] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0242] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A flow allocation method, characterized in that, Includes the following steps: Determine whether a user's consultation request has been received; If so, obtain the user's account information and query the user's historical information based on the account information; Collect the user's chief complaint information and obtain the consultation information of each doctor; Based on a preset factor generation strategy, the historical information, the chief complaint information, and the patient reception information are processed to generate corresponding initial key factors. Specifically, the similarity coefficient between the user's current chief complaint and historical chief complaint is calculated using the aforementioned chief complaint information. Then, the historical information, chief complaint similarity, and consultation information are integrated to obtain the corresponding initial key factors. Based on a preset effectiveness screening strategy, target key factors related to consultation traffic allocation are screened from the initial key factors; wherein, the number of target key factors includes multiple factors; Generate target weights corresponding to the target key factors; Based on the target key factors and the target weights, a corresponding multi-flow factor allocation model is constructed, and the flow allocation priority value of each doctor is calculated based on the multi-flow factor allocation model. Select the target doctor with the highest traffic allocation priority value from all the doctors, and assign the user to the target doctor; The step of selecting target key factors related to consultation traffic allocation from the initial key factors based on a preset effectiveness screening strategy specifically includes: The initial key factors are preprocessed to obtain the corresponding first factor; A correlation analysis was performed on the first factor to obtain the correlation coefficient between the first factor and the quality of consultation. The importance of the first factor is evaluated based on a pre-defined machine learning model to obtain an importance score for the first factor. Based on the correlation coefficient value and the importance score, a second factor that meets the preset screening criteria is selected from all the first factors; Based on the second factor, target key factors related to the allocation of consultation traffic are generated; The step of generating target key factors related to consultation traffic allocation based on the second factor specifically includes: Select a third factor from the second factor that meets both the preset relevance threshold and the preset importance threshold; Redundancy removal is performed on the third factor to obtain the corresponding fourth factor; Retrieve business significance information for all filtered specified factors; Important factors are extracted from the specified factors based on business significance information; important factors refer to factors among the specified factors that represent important business logic. Based on the aforementioned important factors, the fourth factor is supplemented to obtain the corresponding fifth factor; The fifth factor is taken as the target key factor.

2. The flow allocation method according to claim 1, characterized in that, The step of generating the target weights corresponding to the target key factors specifically includes: Obtain the preset weight allocation algorithm; The target key factors are weighted based on a weight allocation algorithm to obtain the initial weights corresponding to the target key factors. Receive input weight feedback information; The initial weights of the target key factors are fine-tuned based on the weight feedback information to obtain the fine-tuned initial weights. The fine-tuned initial weights are used as the target weights of the target key factors.

3. The flow allocation method according to claim 1, characterized in that, The step of constructing a corresponding multi-flow factor allocation model based on the target key factors and the target weights specifically includes: Based on the target key factors and the target weights, a calculation formula for calculating traffic allocation priority is constructed; The corresponding target calculation logic is generated based on the calculation formula; The multi-flow factor allocation model is obtained by performing model construction processing based on the target calculation logic.

4. The flow allocation method according to claim 1, characterized in that, After the step of selecting the target doctor with the highest traffic allocation priority value from all the doctors and assigning the user to the target doctor, the method further includes: After the user completes the consultation, the user's evaluation data on the consultation is collected; Obtain feedback from the target doctor regarding the traffic allocation corresponding to the user; Data analysis is performed on the evaluation data and the feedback opinions to obtain the corresponding data analysis results; The multi-flow factor allocation model is optimized based on the data analysis results.

5. The flow allocation method according to claim 1, characterized in that, After the step of selecting the target doctor with the highest traffic allocation priority value from all the doctors and assigning the user to the target doctor, the method further includes: Obtain the patient reception status of the target doctor and the patient consultation status of the user; Update the patient reception status of the target doctor; The user's consultation status is updated.

6. A flow distribution device, characterized in that, include: The judgment module is used to determine whether a consultation request submitted by the user has been received; The query module is used to obtain the user's account information if the condition is met, and to query the user's historical information based on the account information. The first processing module is used to collect the user's chief complaint information and obtain the consultation information of each doctor; The first generation module is used to perform factor generation processing on the historical information, the chief complaint information and the patient reception information based on a preset factor generation strategy to obtain the corresponding initial key factors. Specifically, the similarity coefficient between the user's current chief complaint and historical chief complaint is calculated using the aforementioned chief complaint information. Then, the historical information, chief complaint similarity, and consultation information are integrated to obtain the corresponding initial key factors. The filtering module is used to filter out target key factors related to the allocation of consultation traffic from the initial key factors based on a preset effectiveness filtering strategy; wherein, the number of target key factors includes multiple factors; The second generation module is used to generate target weights corresponding to the target key factors; The second processing module is used to construct a corresponding multi-flow factor allocation model based on the target key factors and the target weights, and to calculate the flow allocation priority value of each of the doctors based on the multi-flow factor allocation model. The allocation module is used to filter out the target doctor with the highest traffic allocation priority value from all the doctors, and allocate the user to the target doctor; The filtering module includes: The preprocessing submodule is used to preprocess the initial key factors to obtain the corresponding first factor; The analysis submodule is used to perform correlation analysis on the first factor to obtain the correlation coefficient value between the first factor and the quality of consultation. The evaluation submodule is used to evaluate the importance of the first factor based on a preset machine learning model and obtain the importance score of the first factor. A filtering submodule is used to filter out second factors that meet preset filtering conditions from all the first factors based on the correlation coefficient value and the importance score; The first generation submodule is used to generate target key factors related to the allocation of consultation traffic based on the second factor; The first generation submodule includes: A filtering unit is used to filter out a third factor from the second factor that meets a preset relevance threshold and a preset importance threshold. The processing unit is used to perform redundant factor removal processing on the third factor to obtain the corresponding fourth factor; The acquisition unit is used to acquire the business meaning information of all filtered specified factors; An extraction unit is used to extract important factors from the specified factors based on business significance information; important factors refer to factors that represent important business logic among the specified factors. The supplementary unit is used to supplement the fourth factor based on the important factors to obtain the corresponding fifth factor; A determining unit is used to identify the fifth factor as the target key factor.

7. A computer device, characterized in that, The device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the traffic allocation method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the traffic allocation method as described in any one of claims 1 to 5.

Images