Traffic distribution method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of intelligent decision, and discloses a traffic distribution method and device, computer equipment and a storage medium, and the method comprises the steps: determining a current progress factor and a current priority factor according to a current traffic value and a target traffic value, and then generating a target traffic distribution strategy, and adjusting the flow value of the current task based on the target flow distribution strategy. Through the above mode, through the initial flow distribution strategy, the target flow value of the task is calculated, the current flow value is obtained and compared with the target flow value for analysis, the progress condition of the task is determined in real time, the deviation between flow obtaining and an expected target is found in time, and the flow is obtained according to the change of the progress factor and the priority factor. And the target flow distribution strategy is generated, flow regulation and control are performed on the current task through the target flow classification strategy, and the accuracy of configuring the task flow through the task flow distribution system is improved in a system management platform in the business fields of financial science and technology, medical care and health and the like.

Description

Technical Field

[0001] The present application relates to the field of intelligent decision-making technology, and in particular to a flow distribution method, device, computer equipment and storage medium. Background Art

[0002] With the rapid development of information technology, electronic channels such as online banking and mobile banking have flourished in the financial field, providing customers with convenient financial services. Customers can handle some services such as remittance, account inquiry, and financial purchase through the Internet, which has greatly improved the convenience and availability of financial services. Financial institutions have also keenly captured this trend, using big data to analyze customer behavior and preferences, and through in-depth mining and analysis of massive customer data, to achieve precision marketing and personalized recommendations. For example, according to the consumption habits, asset status and risk preferences of different customers, tailor-made exclusive financial products and service solutions for them, such as personalized financial product portfolios, exclusive loan solutions, etc., to effectively improve customer satisfaction and loyalty.

[0003] In the field of medical care, elderly care and health, information technology has also spawned a series of changes. Electronic channels such as telemedicine and mobile medical applications are gradually emerging. Users can conduct online consultations, make appointments, view examination reports and other operations through online platforms, making medical services more convenient and efficient. Medical institutions also use big data to analyze patient health data, such as medical records, examination results, and living habits, to achieve precision medicine and personalized health management. For example, personalized treatment and follow-up plans are formulated for patients with chronic diseases to improve the quality of medical services and patient treatment effects.

[0004] However, in the current traffic distribution mechanism, whether in the financial field or the medical field, most of them adopt the method of manual traffic control. This method has many disadvantages, such as the control target is not clear enough, it is difficult to accurately meet different business scenarios and customer needs; the control granularity is relatively coarse, and it is impossible to finely distribute and manage the traffic; the control effect is delayed, and it is impossible to adjust it in time according to the actual situation. In the financial field, it may cause congestion in electronic channels such as online banking and mobile banking during business peaks, affecting customer experience, or marketing resources cannot be accurately delivered to the target customer group; in the medical field, it may affect the stability and response speed of the telemedicine platform, resulting in patients unable to obtain medical services in time, or medical resources cannot be reasonably allocated to patients in need. Therefore, how to improve the accuracy of configuration task traffic in the system management platform of business fields such as financial technology, medical care and health has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a traffic allocation method, device, computer device, and storage medium to improve the accuracy of configuring task traffic in system management platforms in business fields such as fintech, medical care, and elderly care and health.

[0006] In a first aspect, the present application provides a traffic allocation method, and the method includes:

[0007] Obtain the initial traffic allocation strategy of the current task, and determine the target traffic value of the current task according to the initial traffic allocation strategy;

[0008] Obtain the current traffic value of the current task, and determine the current progress factor and the current priority factor of the current task according to the current traffic value and the target traffic value;

[0009] Generate the target traffic allocation strategy of the current task according to the current progress factor and the current priority factor, and adjust the traffic value of the current task based on the target traffic allocation strategy.

[0010] In a second aspect, the present application further provides a traffic allocation device, and the device includes:

[0011] A target traffic value determination module, configured to obtain the initial traffic allocation strategy of the current task, and determine the target traffic value of the current task according to the initial traffic allocation strategy;

[0012] A factor determination module, configured to obtain the current traffic value of the current task, and determine the current progress factor and the current priority factor of the current task according to the current traffic value and the target traffic value;

[0013] A traffic allocation module, configured to generate the target traffic allocation strategy of the current task according to the current progress factor and the current priority factor, and adjust the traffic value of the current task based on the target traffic allocation strategy.

[0014] In a third aspect, the present application further provides a computer device, and the computer device includes a memory and a processor; the memory is used to store a computer program; the processor is configured to execute the computer program and implement the traffic allocation method as described above when executing the computer program.

[0015] In a fourth aspect, the present application further provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to implement the traffic allocation method as described above.

[0016] The present application discloses a traffic allocation method, apparatus, computer device, and storage medium. The traffic allocation method includes obtaining an initial traffic allocation policy for a current task and determining a target traffic value for the current task according to the initial traffic allocation policy; obtaining a current traffic value of the current task and determining a current progress factor and a current priority factor of the current task according to the current traffic value and the target traffic value; generating a target traffic allocation policy for the current task according to the current progress factor and the current priority factor, and adjusting the traffic value of the current task based on the target traffic allocation policy. By the above method, the present application calculates the target traffic value of a task through the initial traffic allocation policy, obtains the current traffic value of the current task, compares and analyzes it with the target traffic value, determines the progress of the task in real time, discovers the deviation between the traffic acquisition and the expected target in a timely manner, generates a dynamic target traffic allocation policy according to the changes of the progress factor and the priority factor, and adjusts the traffic of the current task through the target traffic classification policy, improving the accuracy of configuring the task traffic of the system management platform in business fields such as fintech and medical and elderly care and health. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 is a schematic flowchart of a traffic allocation method provided by the first embodiment of the present application;

[0019] Figure 2 is a schematic flowchart of a traffic allocation method provided by the second embodiment of the present application;

[0020] Figure 3 is a schematic flowchart of a traffic allocation method provided by the third embodiment of the present application;

[0021] Figure 4 is a schematic block diagram of a traffic allocation apparatus provided by the embodiments of the present application;

[0022] Figure 5 is a schematic block diagram of the structure of a computer device provided by the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0024] The flowcharts shown in the accompanying drawings are only illustrative, not necessarily including all contents and operations / steps, nor necessarily executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged, so the actual execution order may change according to the actual situation.

[0025] It should be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0026] It should also be understood that the term "and / or" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0027] The following will describe in detail some embodiments of the present application with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0028] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a traffic allocation method provided by the first embodiment of the present application. This traffic allocation method can be applied to a traffic allocation system, used to calculate the target traffic value of a task through an initial traffic allocation strategy, obtain the current traffic value of the current task, compare and analyze it with the target traffic value, determine the progress of the task in real time, timely discover the deviation between the traffic acquisition and the expected target, generate a dynamic target traffic allocation strategy according to the changes of the progress factor and the priority factor, and regulate the traffic of the current task through the target traffic classification strategy, improving the accuracy of the system management platform in configuring task traffic in business fields such as fintech and medical and elderly care and health.

[0029] As Figure 1 shown, this traffic allocation method specifically includes steps S10 to S30.

[0030] Step S10: Obtain the initial traffic allocation strategy of the current task, and determine the target traffic value of the current task according to the initial traffic allocation strategy;

[0031] Specifically, the traffic distribution system includes a traffic task configuration module, a traffic prediction module, a traffic monitoring module, and a traffic regulation module. Specifically:

[0032] Traffic data pool: Different from the normal recommendation data pool, it is for materials that need to be regulated, such as text, pictures, links, videos, etc.;

[0033] The task configuration module is used to configure traffic configuration information, such as configuring traffic task names, target cities, target populations, configured push materials, configured display positions, configured task priorities, and other information;

[0034] Traffic prediction module: Calculate the target traffic value of the task based on the configured traffic task name, target city or target population, task priority, etc.;

[0035] Traffic monitoring module: Calculate and display in real time the achievement status of each indicator (exposure, click, etc.) of each traffic regulation task;

[0036] Traffic regulation module: Generate a task progress factor and a task priority factor based on the traffic prediction result and the current achievement progress result of the monitored task, and generate a corresponding target traffic configuration strategy based on the progress factor and the priority factor.

[0037] The initial traffic distribution strategy includes information such as traffic task name, target city, target population, configured push materials, configured display position, configured task priority, etc. The target traffic value and the current traffic value can be reflected in various ways, specifically depending on business requirements and application scenarios, and can be the exposure volume, click volume, conversion volume, etc., which are not limited here.

[0038] In a specific embodiment, establish a connection with the corresponding task configuration database or configuration file according to the task source, including inputting information such as username, password, server address, etc., to obtain access rights to the configuration information, and read various configuration parameters related to the current task from the task configuration database or file, such as task type, task priority, task cycle, task target audience scale, traffic distribution strategy, etc.

[0039] According to the specific meaning and use of the target traffic value, and according to the task type and configuration information, select an appropriate traffic calculation model. For example, for a website promotion task, a linear growth model, an exponential growth model, or a prediction model based on market trends can be used to calculate the target traffic value according to historical data and the target audience scale.

[0040] Substitute the relevant parameters obtained from the task configuration information into the calculation model for calculation to obtain the target traffic value. When calculating the target traffic value, historical data (such as city, time period, population distribution performance, version distribution, etc.) will be combined for time series prediction to predict the future traffic performance. Calculate the Wilson score of the material using the historical exposure click data, and combine the priority configured in the task with the person-goods-place label score to split the total available traffic to obtain a target traffic value.

[0041] The Wilson algorithm is based on the binomial nature of a user's certain decision, solves the accuracy of small samples, inputs the confidence level, outputs the confidence interval, performs data sorting and comparison, and selects the lower limit data of the confidence interval.

[0042] According to the initial traffic allocation strategy, determine the key factors involved in traffic estimation, such as task type, task cycle, target audience size, historical traffic data, etc. Construct these factors into a network model, where each factor is a node, and the relationships and influences between them are connection edges. For example, the task type may be connected to the historical traffic data of different types of tasks, and the task cycle is connected to the traffic conditions in each cycle stage, etc.

[0043] Select a starting node from the network model, usually a node with known traffic data or having an important impact on traffic estimation, such as the historical average traffic node or the traffic node in the initial stage of the task. Create an empty list to store the visited nodes, and add the starting node to the list.

[0044] Randomly select an unmarked node as the current node, and randomly select an adjacent node from the current node. According to the relationships and influences between the nodes, calculate the traffic transfer probability or influence coefficient from the current node to the adjacent node.

[0045] Repeat the above steps until the next node is a visited node. When reaching a visited node, check if there is a loop in the path. If there is a loop, remove the loop, record the nodes and their traffic influence relationships in the path to form a traffic estimation path, and mark the nodes in the path as visited.

[0046] Based on the constructed multiple traffic estimation paths, combine the traffic data and transfer probabilities or influence coefficients of the nodes in each path to establish a traffic estimation model. Use this model to calculate the target traffic value. Methods such as Monte Carlo simulation can be used for a large number of random samplings and calculations to obtain a more accurate target traffic estimate.

[0047] Step S20: Obtain the current traffic value of the current task, and determine the current progress factor and current priority factor of the current task according to the current traffic value and the target traffic value;

[0048] Specifically, according to the type and characteristics of the task, select an appropriate traffic monitoring tool or method. For example, website traffic can be obtained through analysis tools, network service traffic can be obtained through server logs or network monitoring software, and application traffic can be obtained through the traffic statistics module within the application, etc.

[0049] Use the selected traffic monitoring tool or method to collect the traffic data of the current task in real time. Ensure that the collection frequency and accuracy can meet the requirements of task progress evaluation and traffic allocation strategy adjustment. For example, for tasks with high real-time requirements, a higher collection frequency can be adopted, such as collecting traffic data every minute or every second; for relatively stable tasks, the collection frequency can be appropriately reduced, such as collecting once every hour or every day.

[0050] Exemplarily, determine the progress factor according to the traffic progress ratio and the preset progress evaluation rule. The preset progress evaluation rule can be a function, table, or algorithm for mapping the traffic progress ratio to the progress factor. For example, when the traffic progress ratio is less than 0.5, the progress factor is 0.8; when the traffic progress ratio is between 0.5 and 0.7, the progress factor is 1.0; when the traffic progress ratio is between 0.7 and 1.0, the progress factor is 1.2; when the traffic progress ratio is greater than 1.0, the progress factor is 1.5.

[0051] Step S30: Generate the target traffic allocation strategy for the current task according to the current progress factor and the current priority factor, and adjust the traffic value of the current task based on the target traffic allocation strategy.

[0052] Specifically, determine the goal of traffic allocation, such as improving task completion efficiency, ensuring task quality, optimizing resource utilization, etc. For example, if the goal is to improve task completion efficiency, the traffic requirements of tasks with lagging progress should be prioritized; if the goal is to ensure task quality, the traffic can be appropriately tilted towards high-priority tasks.

[0053] Set the weights for traffic allocation according to the progress factor and priority factor of the task. Methods such as the linear weighting method and the analytic hierarchy process can be used to set the weights. For example, different weights can be assigned to the progress factor and the priority factor, such as a weight of 0.6 for the progress factor and a weight of 0.4 for the priority factor, and then the comprehensive weight is obtained through weighted calculation.

[0054] Normalize the progress factors and priority factors of all traffic tasks to be allocated, and map them to the same numerical range (such as between 0 and 1) for unified comparison and calculation. According to the set allocation weight, the normalized progress factor and priority factor are weighted and fused to obtain the comprehensive weight of each task. The formula is: Comprehensive weight = progress factor weight * normalized progress factor + priority factor weight * normalized priority factor. According to the comprehensive weight of each task, calculate the proportion of the total traffic that should be allocated. The formula is: Traffic allocation ratio = task comprehensive weight / sum of the comprehensive weights of all traffic tasks to be allocated.

[0055] Clearly define the total amount of traffic available for allocation, and determine it based on actual conditions and resource constraints, such as the bandwidth capacity of the server, the forwarding capacity of the network equipment, etc. Allocate a certain amount of basic traffic to each task to ensure the minimum operating requirements of the task. The basic traffic can be set according to the basic requirements and importance of the task. For example, the basic traffic ratio can be appropriately increased for high-priority tasks. Dynamically allocate the remaining traffic according to the calculated traffic allocation ratio, and adjust the traffic allocation ratio in real time according to changes in the real-time progress factor and priority factor of the task.

[0056] For tasks with high priority factors, such as limited-time promotions of financial products and important customer service notifications, the traffic allocation strategy will allocate more traffic resources to such tasks. For example, a larger proportion of the total traffic will be allocated, such as 60%-70% or even higher of the total traffic, to ensure that they can quickly reach the target audience and achieve business goals.

[0057] For tasks with low priority factors, the remaining traffic will be allocated, but a certain amount of basic traffic will be reserved according to their own characteristics and business needs to ensure basic visibility of the tasks.

[0058] The traffic quality and cost of different channels are different. For example, mobile traffic has high accuracy but high cost, while web traffic has low cost but slightly lower accuracy. The traffic allocation strategy will dynamically adjust the proportion of each channel based on its characteristics. For example, for the promotion of high-value financial products, the proportion of mobile channel traffic will be increased to improve the conversion rate; for the basic financial information popularization task, the focus will be on low-cost channel traffic allocation.

[0059] In addition, when the initial traffic allocation strategy targets high-net-worth customers, for example, more traffic will be allocated to users who visit private banking pages and participate in high-end financial lectures to improve the accurate reach of traffic. After determining the core target population, tentative traffic allocation will also be made to potential target populations. For example, when promoting credit card business, in addition to the target young office workers, a small amount of traffic will also be allocated to some college students who are about to graduate to tap into potential customers.

[0060] In one embodiment, this embodiment can also be applied to the field of medical care, elderly care, and health. The system management platform can be a hospital information system. When there are multiple medical tasks (such as medical record data processing tasks, remote medical diagnosis tasks, etc.) in the hospital information system that need to allocate traffic resources, first obtain the initial traffic allocation strategy for the current task (subsequently taking the medical record data processing task as an example). The initial traffic allocation strategy can be set based on past experience. For example, pre-allocate according to the average traffic demand for each medical record data processing, and determine the target traffic value for the current task. For example, comprehensively evaluate factors such as the amount of medical record data and the expected processing efficiency, and set the target traffic value (taking 3000 as an example).

[0061] After determining the target traffic value, obtain the current traffic value of the current task (taking 1200 as an example). Based on the current traffic value (1200) and the target traffic value (3000), calculate and determine the current progress factor of the current task (i.e., 1200 / 3000 = 0.4) and the current priority factor (which can be quantified by comprehensively considering factors such as the urgency of medical record data processing and the impact on subsequent medical processes. The priority can be set from 1 to 5, where 1 represents the lowest priority and 5 represents the highest priority. Assume that the priority of this task is relatively high, and the priority factor is set to 5).

[0062] According to the current progress factor (0.4) and the current priority factor (5), generate a target traffic allocation strategy. For example, a new target traffic allocation strategy may be to increase the traffic allocation on the existing basis to ensure that the target traffic is reached as soon as possible to accelerate the progress of medical record data processing. Based on this target traffic allocation strategy, adjust the current traffic value of the current task, such as gradually adjusting the current traffic value to be closer to the target traffic value to ensure that the medical record data processing task can be completed efficiently as expected.

[0063] This embodiment discloses a traffic allocation method, device, computer device, and storage medium. The traffic allocation method includes obtaining an initial traffic allocation policy for a current task and determining a target traffic value for the current task according to the initial traffic allocation policy; obtaining a current traffic value of the current task and determining a current progress factor and a current priority factor of the current task according to the current traffic value and the target traffic value; generating a target traffic allocation policy for the current task according to the current progress factor and the current priority factor, and adjusting the traffic value of the current task based on the target traffic allocation policy. By the above method, this application calculates the target traffic value of a task through the initial traffic allocation policy, obtains the current traffic value of the current task, compares and analyzes it with the target traffic value, determines the progress of the task in real time, discovers the deviation between the traffic acquisition and the expected target in a timely manner, generates a dynamic target traffic allocation policy according to the changes in the progress factor and the priority factor, and adjusts the traffic of the current task through the target traffic classification policy, improving the accuracy of configuring task traffic in the system management platform in business fields such as fintech, medical care, and elderly care and health.

[0064] Please refer to Figure 2 , Figure 2 FIG. is a schematic flowchart of a traffic allocation method provided by the second embodiment of this application. This traffic allocation method can be applied to a traffic allocation system, and is used to obtain an initial traffic allocation policy and a target traffic value, collect the current traffic value, calculate the traffic ratio with the target traffic value, determine the current progress factor, and then combine the initial priority factor to determine the current priority factor, providing an accurate quantitative basis for traffic allocation, and improving the accuracy of allocating task traffic in the system management platform in business fields such as fintech, medical care, and elderly care and health.

[0065] Based on Figure 1 the embodiment shown, this embodiment is as Figure 2 shown, step S20 includes steps S201 to S204.

[0066] Step S201: Collect the current traffic value at a preset time interval;

[0067] Specifically, select a suitable traffic collection tool according to the task type and traffic source. For example, for website traffic, for server traffic, a server log analysis tool or network traffic monitoring software can be used; for application traffic, an internal statistics module of the application or a third-party application performance monitoring tool can be used.

[0068] According to the requirements and importance of the task, determine the preset time interval. For tasks with high real-time requirements, a shorter time interval can be set, such as collecting data once per minute or per second; for relatively stable tasks, a longer time interval can be set, such as collecting data once per hour or per day.

[0069] Step S202: Calculate the flow ratio between the current flow value and the target flow value;

[0070] Specifically, obtain the currently collected current flow value from a flow collection tool or data storage location. Ensure that the obtained data is the latest and comparable to the target flow value within the same time range. For example, if the target flow value is the daily number of visits, then the current flow value should also be the number of visits within the corresponding time period.

[0071] Step S203: Determine the current progress factor according to the flow ratio;

[0072] Specifically, determine a reasonable flow evaluation period according to the cycle and target of the task. The evaluation period can be a fixed time period (such as daily, weekly, monthly, etc.), or it can be dynamically adjusted according to the progress of the task.

[0073] Within each evaluation period, compare the current flow value with the target flow value and calculate the flow progress ratio. Flow progress ratio = current flow value / target flow value. For example, if the target flow value is 10,000 visits and the current flow value is 5,000 visits, then the flow progress ratio is 0.5.

[0074] Step S204: Determine the current priority factor according to the current progress factor and the initial priority factor.

[0075] Specifically, determine the priority of the task according to factors such as the business importance, urgency, and resource requirements of the current task. The task priority can be divided into three levels: high, medium, and low, or a more refined grading method can be adopted (such as levels 1 to 10).

[0076] Assign a corresponding priority weight value to each task priority, that is, the initial priority factor. The weight value of high-priority tasks is relatively high, and the weight value of low-priority tasks is relatively low. For example, the weight value of high-priority tasks is 1.5, the weight value of medium-priority tasks is 1.0, and the weight value of low-priority tasks is 0.5.

[0077] This embodiment discloses a traffic allocation method. The traffic allocation method includes obtaining an initial traffic allocation strategy for the current task and determining the target traffic value of the current task according to the initial traffic allocation strategy; collecting the current traffic value at preset time intervals; calculating the traffic ratio between the current traffic value and the target traffic value; determining the current progress factor according to the traffic ratio; determining the current priority factor according to the current progress factor and the initial priority factor; generating a target traffic allocation strategy for the current task according to the current progress factor and the current priority factor, and adjusting the traffic value of the current task based on the target traffic allocation strategy. By the above method, this application provides an accurate quantitative basis for traffic allocation by obtaining the initial traffic allocation strategy and the target traffic value, collecting the current traffic value and calculating the traffic ratio with the target traffic value, determining the current progress factor, and then combining the initial priority factor to determine the current priority factor, thereby improving the accuracy of allocating task traffic.

[0078] Based on Figure 2 the embodiment shown, in this embodiment, step S204 includes:

[0079] Analyze the initial priority factor to generate the priority level information, task type information, and task deadline information of the current task;

[0080] Quantify the initial priority factor according to the priority level information, the task type information, and the task deadline information to generate a priority quantification value;

[0081] Perform a weighted sum of the priority quantification value and the current progress factor to determine the current priority factor.

[0082] Specifically, comprehensively consider the traffic progress ratio and the priority weight value to calculate the priority factor. The following formula can be used: Priority factor = Priority weight value * (1 + function of traffic progress ratio). Among them, the function of the traffic progress ratio can be designed according to the actual situation. For example, when the traffic progress ratio is lower than expected, the priority factor is appropriately reduced; when the traffic progress ratio is higher than expected, the priority factor is appropriately increased to encourage the rapid progress of the task.

[0083] Please refer to Figure 3 , Figure 3It is a schematic flowchart of a traffic allocation method provided by the third embodiment of the present application. This traffic allocation method can be applied to a traffic allocation system, which is used to classify factors according to a preset classification rule, more finely divide the task status, generate a fusion classification interval by weighted fusion of the progress classification interval and the priority classification interval according to a preset weight, and generate a target traffic allocation strategy in combination with a preset classification strategy list, comprehensively considering the resource allocation method of multiple factors, so that the traffic resources can be more reasonably allocated. For tasks with high priority and high progress, sufficient traffic can be preferentially allocated to ensure their rapid progress; for other tasks, traffic can be reasonably allocated without affecting the overall task progress, improving the accuracy of allocating task traffic in business fields such as fintech, medical care, and elderly care and health.

[0084] Based on Figure 1 the embodiments shown, this embodiment is as Figure 3 shown, step S30 includes steps S301 to S303.

[0085] Step S301: Classify the current progress factor and the current priority factor respectively according to the preset classification rule, and determine the progress classification interval of each current progress factor and the priority classification interval of each current priority factor;

[0086] Specifically, determine how many levels the progress factor and the priority factor are divided into according to requirements, such as 3 levels, 5 levels, etc. The number of levels should not be too many or too few, and sufficient discrimination should be ensured within each level interval, and clear upper and lower limits or ranges should be set for each level. For example, for the progress factor, 0 - 0.3 can be set as the low progress level, 0.3 - 0.7 as the medium progress level, and 0.7 - 1.0 as the high progress level; for the priority factor, 0 - 0.5 can be set as the low priority level, 0.5 - 0.8 as the medium priority level, and 0.8 - 1.0 as the high priority level.

[0087] Step S302: Perform weighted fusion on the progress classification interval and the priority classification interval according to the preset weight to generate a fusion classification interval;

[0088] Specifically, assign weights to the progress classification interval and the priority classification interval respectively. The weight value is between 0 and 1, and the sum of the two is 1. For example, if it is considered that the progress is more important, the weight of the progress classification interval can be set to 0.6, and the weight of the priority classification interval can be set to 0.4.

[0089] Collect the upper and lower limit data of the progress grading interval and the priority grading interval respectively. For example, the progress grading intervals are [0, 0.3), [0.3, 0.7), [0.7, 1], and the priority grading intervals are [0, 0.5), [0.5, 0.8), [0.8, 1]. Calculate the midpoint value of each grading interval as the representative value of that interval. For example, the midpoint of the progress grading interval [0, 0.3) is 0.15, the midpoint of [0.3, 0.7) is 0.5, and the midpoint of [0.7, 1] is 0.85; the same applies to the priority grading intervals.

[0090] For each progress grading interval and priority grading interval, use the weighted average formula to calculate the lower and upper limits after fusion. The formula is: Value after fusion = Representative value of progress grading interval * Progress weight + Representative value of priority grading interval * Priority weight. For example, if the representative value of the progress grading interval [0, 0.3) is 0.15 and the weight is 0.6, and the representative value of the priority grading interval [0, 0.5) is 0.25 and the weight is 0.4, then the lower limit after fusion is 0.15 * 0.6 + 0.25 * 0.4 = 0.19. Calculate the fusion values for all combinations in the same way. After sorting these fusion values, the adjacent values form new fusion grading intervals.

[0091] Step S303: Determine the target traffic allocation strategy from the preset grading strategy list according to the fusion grading interval.

[0092] Specifically, the preset grading strategy list contains all necessary information, such as the traffic allocation ratio, adjustment measures, etc. corresponding to each grading interval. Process each fusion grading interval in order and find the matching strategy from the preset grading strategy list. If the upper and lower limits of the fusion grading interval are exactly the same as a certain strategy interval in the preset grading strategy list, directly apply that strategy; if the fusion grading interval is between two strategy intervals, you can choose to match the lower-level strategy according to business rules or perform interpolation calculations to determine the applicable strategy. Organize all fusion grading intervals and their corresponding preset grading strategies into a complete strategy list to determine the target traffic allocation strategy.

[0093] This embodiment discloses a traffic allocation method, device, computer device, and storage medium. The traffic allocation method includes obtaining an initial traffic allocation policy for a current task and determining a target traffic value for the current task according to the initial traffic allocation policy; obtaining a current traffic value of the current task and determining a current progress factor and a current priority factor of the current task according to the current traffic value and the target traffic value; classifying the current progress factor and the current priority factor respectively according to a preset classification rule to determine a progress classification interval for each current progress factor and a priority classification interval for each current priority factor; performing weighted fusion on the progress classification interval and the priority classification interval according to a preset weight to generate a fusion classification interval; and determining the target traffic allocation policy from a preset classification policy list according to the fusion classification interval. By the above method, this application classifies factors according to a preset classification rule, divides task states more meticulously, performs weighted fusion on the progress classification interval and the priority classification interval according to a preset weight to generate a fusion classification interval, and generates a target traffic allocation policy in combination with a preset classification policy list, comprehensively considering a resource allocation method with multiple factors, so that traffic resources are more reasonably allocated. For tasks with high priority and high progress, sufficient traffic can be preferentially allocated to ensure their rapid progress; for other tasks, traffic can be reasonably allocated without affecting the overall task progress, improving the accuracy of allocating task traffic in business fields such as fintech, medical care, and elderly care.

[0094] Based on Figure 3 the embodiment shown, in this embodiment, step S303 includes:

[0095] Traverse the preset classification policy list and determine the preset traffic allocation policy that matches the fusion classification interval as the traffic allocation policy to be verified;

[0096] Verify the traffic allocation policy to be verified;

[0097] Determine the traffic allocation policy to be verified that passes the verification as the target traffic allocation policy.

[0098] Specifically, the verification is generally divided into the following aspects:

[0099] 1. Legality verification:

[0100] Check whether the traffic allocation policy to be verified complies with basic rules and constraint conditions. For example, ensure that the total traffic allocated to each task does not exceed the total available traffic; whether the traffic allocation ratio of each task is within a reasonable range (such as not less than 0% and not higher than 100%). If the legality conditions are not met, mark it as an invalid policy and enter the adjustment link;

[0101] 2. Consistency verification:

[0102] Verify whether the preliminary strategy is consistent with the integrated grading range according to the rules in the preset grading strategy list. For example, if the integrated grading range indicates that the task priority is high and the progress is behind, the preset strategy should tend to increase the traffic allocation. If the preliminary strategy is contrary to this, it needs to be adjusted. Compare the traffic allocation strategies of historical similar tasks to check whether the preliminary strategy is consistent with the historical reasonable strategies and whether there are obvious deviations.

[0103] 3. Validation of effectiveness:

[0104] Through a simulation or prediction model, evaluate whether the implementation of the preliminary strategy can effectively improve the task progress and make it approach the target traffic value. For example, predict the estimated completion time and traffic gap of the task under this strategy. According to the task priority and business objectives, judge whether the traffic allocation can maximize the overall task completion effect and business value.

[0105] 4. Validation of balance:

[0106] Check whether the traffic allocation strategy achieves a reasonable balance among different tasks, avoid a certain task obtaining too much traffic and causing other important tasks to be ignored, consider the mutual influence among tasks, and ensure that the traffic allocation will not cause adverse chain reactions to other tasks.

[0107] Based on Figure 1 the illustrated embodiment, in this embodiment, step S10 includes:

[0108] Obtain historical tasks matching the current task, and determine the historical traffic allocation strategy corresponding to the historical tasks from the preset configuration database;

[0109] According to the historical traffic allocation strategy, determine the historical traffic value of the historical task;

[0110] Through the preset traffic prediction model, the historical traffic value and the initial traffic allocation strategy, determine the target traffic value.

[0111] Specifically, retrieve historical tasks with similar characteristics to the current task from the historical task database. The similar characteristics include but are not limited to task type, target city, target population, material type, task priority, etc. Task matching algorithms such as those based on cosine similarity and Euclidean distance can be used to quantify the similarity between tasks and screen out the top N historical tasks with the highest matching degree. Extract the detailed configuration information of the above-mentioned matched historical tasks from the preset configuration database, including task name, target city, target population, push materials, display positions, task priority, etc.

[0112] According to the historical traffic allocation strategy, obtain the actual traffic data of each historical task during execution from the traffic monitoring database, including exposure volume, click volume, conversion volume, etc. Clean and preprocess the obtained traffic data to remove outliers and missing values to ensure the accuracy and consistency of the data.

[0113] Select a suitable machine learning algorithm to build a traffic prediction model, such as linear regression, time series analysis, decision tree, random forest, neural network, etc. The preset traffic prediction model calculates and outputs the target traffic value of the current task according to the input historical traffic values and the initial traffic allocation strategy, combined with the model parameters obtained through training.

[0114] In a specific embodiment, after step S10, it further includes:

[0115] Determine whether the target traffic value belongs to a reasonable traffic range;

[0116] If the target traffic value does not belong to the reasonable traffic range, then trigger an alarm signal.

[0117] Specifically, perform a rationality verification on the predicted target traffic value, for example, compare it with the traffic values of historical similar tasks to check whether there are obvious deviations.

[0118] According to the verification result, adjust and optimize the traffic prediction model if necessary, and re - predict until a reasonable target traffic value is obtained.

[0119] Please refer to Figure 4 , Figure 4 FIG. is a schematic block diagram of a traffic allocation device provided by an embodiment of the present application. The traffic allocation device is used to execute the foregoing traffic allocation method. Among them, the traffic allocation device can be configured in a server.

[0120] As Figure 4 shown, the traffic allocation device 400 includes:

[0121] A target traffic value determination module 410, configured to obtain the initial traffic allocation strategy of the current task and determine the target traffic value of the current task according to the initial traffic allocation strategy;

[0122] A factor determination module 420, configured to obtain the current traffic value of the current task and determine the current progress factor and the current priority factor of the current task according to the current traffic value and the target traffic value;

[0123] A traffic allocation module 430, configured to generate a target traffic allocation strategy for the current task according to the current progress factor and the current priority factor, and adjust the traffic value of the current task based on the target traffic allocation strategy.

[0124] Further, the factor determination module 420 includes:

[0125] A current flow value acquisition unit, configured to acquire the current flow value at a preset time interval;

[0126] A flow ratio calculation unit, configured to calculate a flow ratio between the current flow value and the target flow value;

[0127] A current progress factor determination unit, configured to determine the current progress factor according to the flow ratio;

[0128] A current priority factor determination unit, configured to determine the current priority factor according to the current progress factor and the initial priority factor.

[0129] Further, the current priority factor determination unit includes:

[0130] An initial priority factor parsing subunit, configured to parse the initial priority factor to generate priority level information, task type information, and task deadline information of the current task;

[0131] A priority quantization value generation subunit, configured to perform quantization processing on the initial priority factor according to the priority level information, the task type information, and the task deadline information to generate a priority quantization value;

[0132] A current priority factor determination subunit, configured to perform weighted summation on the priority quantization value and the current progress factor to determine the current priority factor.

[0133] Further, the flow allocation module 430 includes:

[0134] A grading interval determination unit, configured to grade the current progress factor and the current priority factor respectively according to a preset grading rule to determine a progress grading interval of each current progress factor and a priority grading interval of each current priority factor;

[0135] A fusion grading interval generation unit, configured to perform weighted fusion on the progress grading interval and the priority grading interval according to a preset weight to generate a fusion grading interval;

[0136] A target flow allocation strategy determination unit, configured to determine the target flow allocation strategy from a preset grading strategy list according to the fusion grading interval.

[0137] Further, the target flow allocation strategy determination unit includes:

[0138] A traffic allocation policy determination subunit to be verified, configured to traverse the preset hierarchical policy list and determine the preset traffic allocation policy that matches the fusion hierarchical interval as the traffic allocation policy to be verified;

[0139] A verification subunit, configured to verify the traffic allocation policy to be verified;

[0140] A traffic allocation policy determination subunit, configured to determine the traffic allocation policy to be verified that passes the verification as the target traffic allocation policy.

[0141] Furthermore, the target traffic value determination module 410 includes:

[0142] A historical traffic allocation policy determination unit, configured to obtain a historical task that matches the current task and determine the historical traffic allocation policy corresponding to the historical task from a preset configuration database;

[0143] A historical traffic value determination unit, configured to determine the historical traffic value of the historical task according to the historical traffic allocation policy;

[0144] A target traffic value determination unit, configured to determine the target traffic value through a preset traffic prediction model, the historical traffic value, and the initial traffic allocation policy.

[0145] Furthermore, the target traffic value determination module 410 includes:

[0146] A reasonable traffic interval judgment unit, configured to judge whether the target traffic value belongs to a reasonable traffic interval;

[0147] An alarm signal trigger unit, configured to trigger an alarm signal if the target traffic value does not belong to the reasonable traffic interval.

[0148] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0149] The above device can be implemented in the form of a computer program, and the computer program can run on a computer device as shown in Figure 5 shown.

[0150] Please refer to Figure 5 , Figure 5 which is a schematic block diagram of the structure of a computer device provided by an embodiment of the present application. The computer device can be a server.

[0151] Refer to Figure 5, the computer device includes a processor, a memory, and a network interface connected via a system bus. Among them, the memory may include a non-volatile storage medium and an internal memory.

[0152] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, which when executed, can cause the processor to execute any one of the traffic allocation methods.

[0153] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0154] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, it can cause the processor to execute any one of the traffic allocation methods.

[0155] The network interface is used for network communication, such as sending the assigned tasks, etc. Those skilled in the art can understand that Figure 5 the structure shown in

[0156] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0157] Among them, in one embodiment, the processor is used to run the computer program stored in the memory to implement the following steps:

[0158] Obtain the initial traffic allocation policy of the current task, and determine the target traffic value of the current task according to the initial traffic allocation policy;

[0159] Obtain the current traffic value of the current task, and determine the current progress factor and the current priority factor of the current task according to the current traffic value and the target traffic value;

[0160] Generate a target traffic allocation policy for the current task according to the current progress factor and the current priority factor, and adjust the traffic value of the current task based on the target traffic allocation policy.

[0161] In one embodiment, the initial traffic allocation policy includes an initial priority factor. Obtain the current traffic value of the current task, and determine the current progress factor and the current priority factor of the current task according to the current traffic value and the target traffic value, for the purpose of:

[0162] Collect the current traffic value at a preset time interval;

[0163] Calculate the traffic ratio between the current traffic value and the target traffic value;

[0164] Determine the current progress factor according to the traffic ratio;

[0165] Determine the current priority factor according to the current progress factor and the initial priority factor.

[0166] In one embodiment, determine the current priority factor according to the current progress factor and the initial priority factor, for the purpose of:

[0167] Parse the initial priority factor to generate the priority level information, task type information, and task deadline information of the current task;

[0168] Quantify the initial priority factor according to the priority level information, the task type information, and the task deadline information to generate a priority quantification value;

[0169] Perform a weighted sum of the priority quantification value and the current progress factor to determine the current priority factor.

[0170] In one embodiment, generate a target traffic allocation policy for the current task according to the current progress factor and the current priority factor, and adjust the traffic value of the current task based on the target traffic allocation policy, for the purpose of:

[0171] Classify the current progress factor and the current priority factor respectively according to a preset classification rule to determine the progress classification interval of each current progress factor and the priority classification interval of each current priority factor;

[0172] Perform a weighted fusion of the progress classification interval and the priority classification interval according to a preset weight to generate a fusion classification interval;

[0173] Determine the target traffic allocation policy from a preset classification policy list according to the fusion classification interval.

[0174] In one embodiment, the target traffic allocation policy is determined from a preset grading policy list according to the fusion grading interval, for the purpose of achieving:

[0175] Traverse the preset grading policy list, and determine the preset traffic allocation policy that matches the fusion grading interval as the traffic allocation policy to be verified;

[0176] Verify the traffic allocation policy to be verified;

[0177] Determine the traffic allocation policy to be verified that passes the verification as the target traffic allocation policy.

[0178] In one embodiment, the target traffic value of the current task is determined according to the initial traffic allocation policy, for the purpose of achieving:

[0179] Obtain a historical task that matches the current task, and determine the historical traffic allocation policy corresponding to the historical task from a preset configuration database;

[0180] According to the historical traffic allocation policy, determine the historical traffic value of the historical task;

[0181] Determine the target traffic value through a preset traffic prediction model, the historical traffic value, and the initial traffic allocation policy.

[0182] In one embodiment, after determining the target traffic value through a preset traffic prediction model, the historical traffic value, and the initial traffic allocation policy, it is further used to achieve:

[0183] Judge whether the target traffic value belongs to a reasonable traffic interval;

[0184] If the target traffic value does not belong to the reasonable traffic interval, then trigger an alarm signal.

[0185] In an embodiment of the present application, there is also provided a computer-readable storage medium, which stores a computer program. The computer program includes program instructions, and the processor executes the program instructions to implement any one of the traffic allocation methods provided in the embodiments of the present application.

[0186] Among them, the computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device.

[0187] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A flow distribution method, characterized in that, Including: Obtain the initial traffic allocation strategy of the current task, and determine the target traffic value of the current task according to the initial traffic allocation strategy; Obtain the current traffic value of the current task, and determine the current progress factor and the current priority factor of the current task according to the current traffic value and the target traffic value; Generate the target traffic allocation strategy of the current task according to the current progress factor and the current priority factor, and adjust the traffic value of the current task based on the target traffic allocation strategy.

2. The flow distribution method according to claim 1, wherein The initial traffic allocation strategy includes an initial priority factor. The step of obtaining the current traffic value of the current task and determining the current progress factor and the current priority factor of the current task according to the current traffic value and the target traffic value includes: Collect the current traffic value at a preset time interval; Calculate the traffic ratio between the current traffic value and the target traffic value; Determine the current progress factor according to the traffic ratio; Determine the current priority factor according to the current progress factor and the initial priority factor.

3. The flow rate distribution method according to claim 2, wherein The step of determining the current priority factor according to the current progress factor and the initial priority factor includes: Analyze the initial priority factor to generate the priority level information, task type information, and task deadline information of the current task; Quantify the initial priority factor according to the priority level information, the task type information, and the task deadline information to generate a priority quantization value; Perform weighted summation on the priority quantization value and the current progress factor to determine the current priority factor.

4. The flow rate distribution method according to claim 1, characterized in that The step of generating the target traffic allocation strategy of the current task according to the previous progress factor and the current priority factor includes: Classify the current progress factor and the current priority factor respectively according to a preset classification rule to determine the progress classification interval of each current progress factor and the priority classification interval of each current priority factor; Perform weighted fusion on the progress classification interval and the priority classification interval according to a preset weight to generate a fusion classification interval; Determine the target traffic allocation strategy from a preset classification strategy list according to the fusion classification interval.

5. The flow rate distribution method according to claim 4, wherein The preset classification strategy list includes at least one preset traffic allocation strategy. The step of determining the target traffic allocation strategy from the preset classification strategy list according to the fusion classification interval includes: Traverse the preset classification strategy list, and determine the preset traffic allocation strategy that matches the fusion classification interval as the traffic allocation strategy to be verified; Verify the traffic allocation strategy to be verified; Determine the traffic allocation strategy to be verified that passes the verification as the target traffic allocation strategy.

6. The flow rate distribution method according to claim 1, wherein The step of determining the target traffic value of the current task according to the initial traffic allocation strategy includes: Obtain a historical task that matches the current task, and determine the historical traffic allocation strategy corresponding to the historical task from a preset configuration database; Determine the historical traffic value of the historical task according to the historical traffic allocation strategy; Determine the target traffic value based on the preset traffic prediction model, the historical traffic value, and the initial traffic allocation policy.

7. The flow rate distribution method according to claim 6, wherein After determining the target traffic value based on the preset traffic prediction model, the historical traffic value, and the initial traffic allocation policy, the method further includes: Judge whether the target traffic value belongs to a reasonable traffic range; If the target traffic value does not belong to the reasonable traffic range, trigger an alarm signal.

8. A flow distribution device, characterized in that, It includes: A target traffic value determination module, configured to obtain the initial traffic allocation policy of the current task and determine the target traffic value of the current task according to the initial traffic allocation policy; A factor determination module, configured to obtain the current traffic value of the current task and determine the current progress factor and the current priority factor of the current task according to the current traffic value and the target traffic value; A traffic allocation module, configured to generate a target traffic allocation policy for the current task according to the current progress factor and the current priority factor, and adjust the traffic value of the current task based on the target traffic allocation policy.

9. A computer device, characterized in that, The computer device includes a memory and a processor; The memory is used to store a computer program; The processor is configured to execute the computer program and, when executing the computer program, implement the traffic allocation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the processor is caused to implement the traffic allocation method according to any one of claims 1 to 7.

Images