Distributed service traffic scheduling method, device, equipment, medium and program product

By obtaining user multi-dimensional network indicator data and historical data, determining group location and performance characteristics, and selecting appropriate scheduling models for distributed service traffic scheduling, the problem of inaccurate distributed service traffic scheduling in the existing technology is solved, and the problem of inaccurate distributed service traffic scheduling is achieved. Accurate traffic scheduling and user experience improvement.

CN119031040AActive Publication Date: 2024-11-26CHINA MOBILE GRP BEIJING +1
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411199007.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-11-26
Estimated Expiration
2044-08-29

AI Technical Summary

Technical Problem

In the prior art, the distributed service traffic scheduling method is not accurate enough, and it is difficult to adapt to the dynamic changes in business traffic in distributed and cloud deployment environments, affecting user experience and system efficiency.

Method used

By obtaining the user's multi-dimensional network indicator data and historical data, determining the group location characteristics and performance characteristics, selecting appropriate scheduling models for business traffic scheduling, and dynamically adjusting traffic allocation to achieve more accurate traffic scheduling.

Benefits of technology

It improves the accuracy of distributed service traffic scheduling, enhances the advance perception of business situations, reduces sudden pressure and security risks, and improves user satisfaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119031040A_ABST
    Figure CN119031040A_ABST
Patent Text Reader

Abstract

The invention provides a distributed service flow scheduling method, device and equipment, a medium and a program product, and the method comprises the steps: determining the group position features of a user based on the obtained multi-dimensional network index data of the user and a plurality of pieces of multi-dimensional network index historical data; based on the historical data of the plurality of multi-dimensional network indexes, determining group performance characteristics of the users; selecting a plurality of target scheduling models based on the group position features and the group performance features; obtaining a target service flow scheduling baseline through a plurality of target scheduling models; and performing flow scheduling dynamic adjustment on the distributed service based on the target service flow scheduling baseline. According to the distributed service flow scheduling method provided by the invention, comprehensive scheduling is carried out through a plurality of target scheduling models based on relatively comprehensive multi-dimensional network index data, and an accurate target service flow scheduling baseline is obtained, so that flow scheduling dynamic adjustment is carried out on the distributed service, and the accuracy of distributed service flow scheduling is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of business scheduling, and in particular to a distributed business traffic scheduling method, device, equipment, medium and program product. Background Art

[0002] An enterprise business system refers to a subsystem of an enterprise that brings its products to market and maximizes profits. It is divided into modules, including marketing planning, sales platform, sales process management, customer service management, customer relationship management, and risk prevention. Among them, users can interact with the enterprise business system through the user end according to their needs. The smoothness of user access directly affects the user experience and the business efficiency of the enterprise. During the user access process, the enterprise business system manages and distributes the received user requests through traffic scheduling. Traffic scheduling includes strategies and technologies such as load balancing, data synchronization, and service degradation, with the aim of ensuring that the system can efficiently and stably handle a large number of concurrent requests.

[0003] In the existing technology, user access and traffic scheduling are mostly based on static rules for one-time matching and segmentation. According to the user's geographical location, the traffic is distributed to different server clusters. For example, the user traffic in the eastern region is directed to the eastern data center, and the user traffic in the western region is directed to the western data center. This is a static rule because the user's geographical location is relatively fixed and does not change frequently. However, as more and more enterprise business systems adopt distributed and cloud deployment, it is difficult for static scheduling algorithms to more reasonably schedule business traffic, which ultimately affects the user's access experience. Summary of the invention

[0004] The present invention provides a distributed service traffic scheduling method, device, equipment, medium and program product, which are used to solve the problem of inaccuracy in the distributed service traffic scheduling method in the prior art.

[0005] In a first aspect, the present invention provides a distributed service traffic scheduling method, comprising: Acquire real-time multi-dimensional network indicator data of the user and multi-dimensional network indicator historical data of the user at multiple historical time points; Determine the group location characteristics of the user based on the multi-dimensional network indicator data and a plurality of the multi-dimensional network indicator historical data; the group location characteristics are used to reflect the characteristic performance of the network location of the user; Determine the group performance characteristics of the user based on the plurality of multi-dimensional network indicator historical data; the group performance characteristics are used to reflect the characteristic performance of the user on network performance; Based on the group location characteristics and the group performance characteristics, multiple target scheduling models are selected from multiple types of scheduling models; any of the scheduling models is obtained by model training based on multi-dimensional network indicator samples and their corresponding service traffic scheduling baseline labels; Based on the multi-dimensional network indicator data, the target service traffic scheduling baseline is obtained by respectively training the multiple target scheduling models; Based on the target service traffic scheduling baseline, traffic scheduling of distributed services is dynamically adjusted.

[0006] In one embodiment, after obtaining the real-time multi-dimensional network indicator data of the user and the multi-dimensional network indicator historical data of the user at multiple historical time points, and before determining the group location characteristics of the user based on the multi-dimensional network indicator data and multiple multi-dimensional network indicator historical data, the following steps are performed for the multi-dimensional network indicator data: Determine whether each dimensional network indicator data satisfies a preset weight update trigger rule corresponding to the dimensional network indicator data; If the dimensional network indicator data satisfies the preset weight update trigger rule corresponding to the dimensional network indicator data, then the preset weight value corresponding to the dimensional network indicator data is increased to obtain the target weight value corresponding to each dimensional network indicator data; According to the target weight value corresponding to each dimensional network indicator data, the multi-dimensional network indicator data is sorted according to the weight value to obtain a multi-dimensional network indicator sequence.

[0007] In one embodiment, the target scheduling model includes a first target scheduling model and a second target scheduling model; the selecting multiple target scheduling models from multiple types of scheduling models based on the group location characteristics and the group performance characteristics includes: Determine a first performance indicator of each type of scheduling model on the group location characteristics and a second performance indicator of each type of scheduling model on the group performance characteristics; Determine a scheduling model corresponding to an optimal performance indicator among the plurality of first performance indicators as a first target scheduling model; The scheduling model corresponding to the optimal performance indicator among the multiple second performance indicators is determined as the second target scheduling model.

[0008] In one embodiment, the step of training the plurality of target scheduling models based on the multi-dimensional network indicator data to obtain a target service traffic scheduling baseline includes: Extracting features from the multi-dimensional network indicator sequence to obtain multi-dimensional network indicator representation data; Inputting the multi-dimensional network indicator characterization data into the first target scheduling model to obtain a first service traffic scheduling baseline output by the first target scheduling model; Inputting the multi-dimensional network indicator characterization data into the second target scheduling model to obtain a second service traffic scheduling baseline output by the second target scheduling model; A mean calculation is performed based on the first service traffic scheduling baseline and the second service traffic scheduling baseline to obtain a target service traffic scheduling baseline.

[0009] In one embodiment, the dynamically adjusting the traffic scheduling of the distributed service based on the target service traffic scheduling baseline includes: Obtaining the real-time first access behavior flow data of the user; If the first access behavior traffic data deviates from the target service traffic scheduling baseline, the distributed service and user access are dynamically scheduled.

[0010] In one embodiment, after dynamically adjusting the traffic scheduling of the distributed service based on the target service traffic scheduling baseline, the method includes: Obtaining real-time second access behavior flow data of the user; Performing a comparative analysis based on the second access behavior traffic data and the target service traffic scheduling baseline to obtain a comparative analysis result; Iteratively executing the step of obtaining the real-time second access behavior flow data of the user until a plurality of comparative analysis results are obtained after executing the continuous time period; Based on the multiple comparative analysis results, generate historical dynamic month-on-month data; Based on the historical dynamic month-on-month data, the strategy for distributed business traffic scheduling is optimized.

[0011] In one embodiment, the distributed service traffic scheduling method further includes: Obtain business support capability data; Performing performance bottleneck analysis based on the business support capability data to obtain performance bottleneck analysis results; Based on the performance bottleneck analysis result, determine the time point for distributed service traffic scheduling; At the time point of the distributed service traffic scheduling, the distributed services and user access are dynamically scheduled.

[0012] In a second aspect, the present invention further provides a distributed service flow scheduling device, comprising: An acquisition module, used to acquire real-time multi-dimensional network indicator data of a user and multi-dimensional network indicator historical data of the user at multiple historical time points; A first determination module is used to determine the group location characteristics of the user based on the multi-dimensional network indicator data and a plurality of multi-dimensional network indicator historical data; the group location characteristics are used to reflect the characteristic performance of the network location of the user; A second determination module is used to determine the group performance characteristics of the user based on the plurality of multi-dimensional network indicator historical data; the group performance characteristics are used to reflect the characteristic performance of the user on the network performance; A scheduling model selection module, used to select multiple target scheduling models from multiple types of scheduling models based on the group location characteristics and the group performance characteristics; any of the scheduling models is obtained by model training based on multi-dimensional network indicator samples and their corresponding service traffic scheduling baseline labels; A scheduling model prediction module, used to obtain a target service traffic scheduling baseline by training the multiple target scheduling models respectively based on the multi-dimensional network indicator data; The scheduling module is used to dynamically adjust the traffic scheduling of distributed services based on the target service traffic scheduling baseline.

[0013] In a third aspect, the present invention provides a device, comprising an electronic device, wherein the electronic device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the distributed service traffic scheduling method as described in any one of the above are implemented.

[0014] In a fourth aspect, the present invention further provides a medium, comprising a non-transitory computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the distributed service traffic scheduling method as described in any one of the above are implemented.

[0015] In a fifth aspect, the present invention also provides a product, comprising a computer program product, wherein the computer program product comprises a computer program, wherein the computer program can be stored on a non-transitory computer-readable storage medium, and wherein when the computer program is executed by the processor, the steps of the distributed business traffic scheduling method as described in any one of the above are implemented.

[0016] The distributed business traffic scheduling method, device, equipment, medium and program product provided by the present invention obtain relatively comprehensive multi-dimensional network indicator data, and at the same time combine the multi-dimensional network indicator historical data to determine the group location characteristics and group performance characteristics of the current user, comprehensively consider the group location characteristics and group performance characteristics of the current user, select multiple target scheduling models suitable for the current user from two different feature dimensions, and perform comprehensive scheduling based on the relatively comprehensive multi-dimensional network indicator data through multiple target scheduling models to obtain an accurate target business traffic scheduling baseline, and then based on the accurate target business traffic scheduling baseline, dynamically adjust the traffic scheduling of distributed services, improve the accuracy of distributed business traffic scheduling, and at the same time enhance the ability to perceive business situations in advance, reduce the pressure and security risks brought by business emergencies, thereby improving user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is one of the flow charts of the distributed service traffic scheduling method provided by the present invention.

[0019] Figure 2 This is the second flow chart of the distributed service traffic scheduling method provided by the present invention.

[0020] Figure 3 It is a schematic diagram of data sorting provided by the present invention.

[0021] Figure 4 It is a schematic diagram of the scheduling model selection provided by the present invention.

[0022] Figure 5 It is a structural diagram of the distributed service flow scheduling device provided by the present invention.

[0023] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein.

[0026] Combine the following Figure 1-Figure 6 The invention describes the distributed service flow scheduling method, device, equipment, medium and program product provided by the invention.

[0027] It should be noted that the distributed service traffic scheduling method provided by the embodiment of the present invention is implemented based on a distributed service traffic scheduling device. The distributed service traffic scheduling method provided by the embodiment of the present invention collects the real-time multi-dimensional network indicator data of the user, and then sorts and extracts features of these full-factor real-time data to obtain the corresponding characterization data, and further uses the full-factor historical data of the user to select two scheduling models for the user, and comprehensively predicts the full-factor real-time data based on the two scheduling models to obtain the distributed service traffic scheduling baseline of the user, and performs distributed service traffic scheduling according to the distributed service traffic scheduling baseline. The distributed service traffic scheduling method provided by the embodiment of the present invention can adapt to the development of distributed cloud, meet the needs of high availability and flexible and elastic deployment of services, realize the refined and dynamic scheduling of user access traffic, strengthen the ability to perceive business situations in advance, reduce the pressure and security risks brought by business emergencies, and thus improve user satisfaction.

[0028] The embodiment of the present invention describes the distributed service traffic scheduling method by taking a distributed service traffic scheduling device as an execution subject as an example.

[0029] Combination Figure 1 and Figure 2 , Figure 1 This is one of the flow charts of the distributed service traffic scheduling method provided by the present invention. Figure 2 This is the second flow chart of the distributed service traffic scheduling method provided by the present invention.

[0030] like Figure 1 As shown, the method includes the following: Step 101: Acquire real-time multi-dimensional network indicator data of a user and multi-dimensional network indicator historical data of the user at multiple historical time points; Step 102: determining the group location characteristics of the user based on the multi-dimensional network indicator data and a plurality of multi-dimensional network indicator historical data; Step 103: determining the group performance characteristics of the user based on the plurality of multi-dimensional network indicator historical data; Step 104: Select multiple target scheduling models from multiple types of scheduling models based on the group location characteristics and the group performance characteristics; Step 105: Based on the multi-dimensional network indicator data, the plurality of target scheduling models are trained respectively to obtain a target service traffic scheduling baseline; Step 106: Based on the target service traffic scheduling baseline, dynamically adjust the traffic scheduling of the distributed service.

[0031] When the user and the business system form a client-server relationship, a network connection will be established between the user terminal and the intelligent scheduling server in the business system, and the user can communicate and interact with the intelligent scheduling server through the user terminal.

[0032] Specifically, Figure 2 As shown, the distributed business traffic scheduling device obtains the user's real-time user access traffic full-factor data.

[0033] It should be noted that since the amount of data in the full-factor data of user access traffic is large, a large amount of data will be generated if it is accessed in parallel. Therefore, it is necessary to screen the full-factor data of user access traffic to determine the data that has a greater impact on the traffic scheduling results.

[0034] Furthermore, based on the retrieval method, the distributed business traffic scheduling device retrieves the acquired user access traffic full-factor data one by one, filters out the data that is worthless, duplicated data, and missing data contained in the user access traffic full-factor data for distributed business traffic scheduling, so as to obtain multi-dimensional network indicator data that is valuable and useful for distributed business traffic scheduling. The purpose of this step is to filter the data, remove worthless, duplicated or missing data, and improve data quality.

[0035] Among them, the multi-dimensional network indicator data includes but is not limited to the user's network location information, user network delay and jitter information, application resource availability, application response rate and success rate, which are all important for distributed business traffic scheduling. Specifically, in the process of distributed business traffic scheduling, the user's network location information can help the system better understand the user's geographical area and network topology, which is helpful for load balancing, fault tolerance and optimization of user experience. User network delay and jitter information is one of the key factors affecting user experience and application performance. High delay and jitter may lead to slow data transmission speed and long application response time, thereby affecting the user's experience and application stability. Application resource availability is crucial to the stability and reliability of the application. If resources are not available, the application will not be able to run normally. Application response rate and success rate are directly related to user experience and application performance. Fast response and high success rate mean that users can use the application smoothly, while slow response and low success rate may lead to user loss or dissatisfaction.

[0036] In one embodiment, multi-dimensional network indicator data such as user network location information, user network delay and jitter information, application resource availability, application response rate and success rate can be obtained in the following manner.

[0037] User's network location information: When the user terminal communicates with the intelligent scheduling server, the intelligent scheduling server is used to automatically obtain the user terminal's network location information, where the network location information can be an Internet Protocol Address (IP) address, Global Positioning System (GPS) coordinates, base station positioning, and wireless network Wi-Fi (Wireless Fidelity) positioning, etc. After the intelligent scheduling server obtains the network location information of the user terminal, the intelligent scheduling server sends a confirmation instruction to the user terminal to check the obtained network location information of the user terminal. After the user terminal receives the network location information instruction sent by the intelligent scheduling server, the user terminal responds to the confirmation instruction and checks the network location information of the user terminal obtained by the intelligent scheduling server. After the verification is successful, it sends a location confirmation feedback to the intelligent scheduling server. After the intelligent scheduling server receives the location confirmation feedback sent by the user terminal, the intelligent scheduling server automatically displays the network location information of the user terminal and determines the network location information of the user.

[0038] User network latency and jitter information: Measures the round-trip time between the user terminal and the server. Latency is evaluated by the round-trip time between the user terminal and the server, and network jitter is detected by continuously measuring the change in the round-trip time.

[0039] Application resource availability: Use application performance management tools to monitor application resource usage, including monitoring the CPU, memory, and storage to confirm application resource availability.

[0040] Application response rate and success rate: Use real-time monitoring tools to track application response time and business completion rate.

[0041] In addition, while obtaining the user's real-time user access traffic full-factor data, the distributed business traffic scheduling device will also obtain the user's user access traffic full-factor historical data at multiple historical time points. Furthermore, the distributed business traffic scheduling device performs data screening on the user access traffic full-factor historical data at each historical time point, and filters out data that is of no value to the distributed business traffic scheduling, duplicate data, and missing data contained in the user access traffic full-factor historical data, so as to obtain the multi-dimensional network indicator historical data of multiple historical time points after screening. Usually, the multi-dimensional network indicator historical data corresponds to each dimension of the multi-dimensional network indicator data.

[0042] Furthermore, the distributed service traffic scheduling device sorts the network indicator data of each dimension based on an adaptive sorting method, puts the data that is more valuable to the distributed service traffic scheduling in front, and obtains a sorted multi-dimensional network indicator sequence.

[0043] Similarly, the distributed business traffic scheduling device sorts the data of each dimension in the multi-dimensional network indicator historical data at each historical time point based on an adaptive sorting method, obtains the sorted multi-dimensional network indicator historical sequence at each historical time point, and arranges the multi-dimensional network indicator historical sequence at each historical time point in chronological order, thereby obtaining multiple multi-dimensional network indicator historical sequences arranged in sequence, which can be called a multi-dimensional network indicator historical sequence set.

[0044] Furthermore, the distributed service traffic scheduling device determines the group location characteristics of users based on the multi-dimensional network indicator sequence and the multi-dimensional network indicator historical sequence set.

[0045] It should be noted that since the servers of the distributed business system are distributed in multiple different locations, different users are located at different locations relative to the servers, which results in different scheduling delays during distributed scheduling. In other words, the user's network location can be used to determine the user's group location characteristics by geographical location partitioning. Therefore, first of all, the user's current location can be used as the main factor of the user's group location characteristics. The user's current location belongs to a certain area, which may correspond to a specific server cluster or data center, and can reflect the characteristic performance of the user's network location. In addition, the user's historical data will also be further used to analyze the user's behavior patterns and performance requirements, and the analyzed behavior patterns and performance requirements will be used as other factors of the user's group location characteristics. Therefore, the user's group location characteristics can be determined by the user's current location and the user's behavior patterns and performance requirements.

[0046] Therefore, it can be understood that the distributed business traffic scheduling device determines the user's current location based on the multi-dimensional network indicator sequence, and analyzes the user's behavior pattern and performance requirements based on the multi-dimensional network indicator historical sequence set. Furthermore, the distributed business traffic scheduling device determines the user's group location characteristics based on the user's current location and the user's behavior pattern and performance requirements.

[0047] Furthermore, the distributed service traffic scheduling device determines the group performance characteristics of users based on a multi-dimensional network indicator historical sequence set.

[0048] It should be noted that since changes in users' network data can change the sorting results described above, users are divided into high-delay sensitive users, high-throughput demand users, stable connection users, etc. according to the changes in network data corresponding to these sortings. These types can be used to determine the group performance characteristics of users.

[0049] Therefore, it can be understood that the distributed business traffic scheduling device determines the user's network data changes based on the multi-dimensional network indicator historical sequence set, further analyzes the user's network data changes, and determines the user's group performance characteristics.

[0050] Furthermore, the distributed business traffic scheduling device selects a target scheduling model with the best indicators of group location characteristics from multiple types of scheduling models based on the group location characteristics, and selects a target scheduling model with the best indicators of group performance characteristics from multiple types of scheduling models based on the group performance characteristics, so as to select the most suitable scheduling model for the user based on his or her historical data.

[0051] Among them, various types of scheduling models include but are not limited to time series prediction scheduling models, time series prediction scheduling models and reinforcement learning scheduling models.

[0052] Furthermore, the distributed service traffic scheduling device is based on the multi-dimensional network indicator data, and is trained through multiple target scheduling models to obtain the target service traffic scheduling baseline. It should be noted that each type of scheduling model is obtained by model training based on multi-dimensional network indicator samples and their low-frequency service traffic scheduling baseline labels, which is no different from the existing model training process and will not be elaborated here.

[0053] Furthermore, the distributed service traffic scheduling device dynamically adjusts the traffic scheduling of the distributed service based on the target service traffic scheduling baseline.

[0054] The distributed service traffic scheduling method provided by the present invention obtains relatively comprehensive multi-dimensional network indicator data, and at the same time combines the multi-dimensional network indicator historical data to determine the group location characteristics and group performance characteristics of the current user, comprehensively considers the group location characteristics and group performance characteristics of the current user, selects multiple target scheduling models suitable for the current user from two different feature dimensions, and performs comprehensive scheduling based on the relatively comprehensive multi-dimensional network indicator data through multiple target scheduling models to obtain an accurate target service traffic scheduling baseline, and then based on the accurate target service traffic scheduling baseline, dynamically adjusts the traffic scheduling of the distributed service, improves the accuracy of the distributed service traffic scheduling, and at the same time strengthens the ability to perceive the service situation in advance, reduces the pressure and security risks brought by service bursts, thereby improving user satisfaction.

[0055] Further, after obtaining the real-time multi-dimensional network indicator data of the user and the multi-dimensional network indicator historical data of the user at multiple historical time points, and before determining the group location characteristics of the user based on the multi-dimensional network indicator data and multiple multi-dimensional network indicator historical data, the following steps are performed for the multi-dimensional network indicator data: Determine whether each dimensional network indicator data satisfies a preset weight update trigger rule corresponding to the dimensional network indicator data; If the dimensional network indicator data satisfies the preset weight update trigger rule corresponding to the dimensional network indicator data, then the preset weight value corresponding to the dimensional network indicator data is increased to obtain the target weight value corresponding to each dimensional network indicator data; According to the target weight value corresponding to each dimensional network indicator data, the multi-dimensional network indicator data is sorted according to the weight value to obtain a multi-dimensional network indicator sequence.

[0056] The following description Figure 2 The refined content of step S2 in .

[0057] It should be noted that, combined with Figure 3 , Figure 3 It is a schematic diagram of data sorting provided by the present invention. Before the sorting process is carried out, a preset weight will be defined for each dimension of network indicator data, that is, the user's network location information, user network delay and jitter information, application resource availability, application response rate and success rate each have a preset weight, which can be defined as the same basic weight, such as 0.5. At the same time, a preset weight update trigger rule will be defined for each dimension of network indicator data. Since the type of each dimension of network indicator data is different, the preset weight update trigger rule defined for each dimension of network indicator data is different. After the preset weight update trigger rule corresponding to any dimension of network indicator data is triggered, its corresponding preset weight will be increased, and then the network indicator data of each dimension will be sorted from large to small according to the adjusted weight value. If the preset weight update trigger rule corresponding to any dimension of network indicator data is not triggered, the corresponding preset weight will not be updated.

[0058] Specifically, the distributed service traffic scheduling device determines whether the network indicator data of each dimension satisfies the preset weight update trigger rule corresponding to the network indicator data of this dimension.

[0059] Furthermore, if the dimensional network indicator data satisfies the preset weight update trigger rule corresponding to the dimensional network indicator data, the distributed business traffic scheduling device increases the preset weight value corresponding to the dimensional network indicator data to obtain the target weight value corresponding to the dimensional network indicator data.

[0060] If the dimensional network indicator data does not satisfy the preset weight update trigger rule corresponding to the dimensional network indicator data, the distributed business traffic scheduling device will not update the preset weight value corresponding to the dimensional target indicator data, and will determine it as the target weight value corresponding to the dimensional network indicator data.

[0061] Through the above method, the target weight value corresponding to each dimension of network indicator data can be obtained.

[0062] Furthermore, the distributed service traffic scheduling device sorts the multi-dimensional network indicator data according to the target weight value corresponding to each dimensional network indicator data and the size of the weight value to obtain a multi-dimensional network indicator sequence.

[0063] It should be noted that, in the sorting process, the larger the target weight value, the higher the corresponding network indicator data is ranked, and the network indicator data with the same target weight value can be randomly arranged.

[0064] In one embodiment, the preset weights of the user's network location information, the user's network delay and jitter information, the application resource availability, the application response rate and the success rate are all 0.5. Assume that the preset weight update trigger rule corresponding to the user's network delay and jitter information is: if the network delay exceeds a certain threshold or the jitter information exceeds a certain threshold, the weight of the network delay and jitter information is increased. At this time, if at least one of the user's network delay or jitter information exceeds the corresponding threshold, the basic weight corresponding to the user's network delay and jitter information is increased by 0.1. At this time, the target weight value of the user's network delay and jitter information is 0.6, and the target weight values ​​of the user's network location information, the application resource availability, the application response rate and the success rate are all 0.5. Then, when sorting, the user's network delay and jitter information is ranked first, and the user's network location information, the application resource availability, the application response rate and the success rate are randomly arranged.

[0065] Similarly, the historical data of multi-dimensional network indicators of users at multiple historical time points are also adaptively sorted according to the above sorting method to obtain a historical sequence set of multi-dimensional network indicators. It is understandable that the sorting results of the network location information, user network delay and jitter information, application resource availability, application response rate and success rate of the same user at different times or different users may be different.

[0066] In one embodiment, the multi-dimensional network indicator historical sequence set can be expressed as follows: Historical time 1: [user network location information, user network delay and jitter information, application resource availability, application response rate and success rate]; Historical time 2: [application resource availability, user network delay and jitter information, user network location information, application response rate and success rate]; Historical time 3: [user network delay and jitter information, application response rate and success rate, user network location information, application resource availability]; ……; Historical time n: [application response rate and success rate, user network delay and jitter information, user network location information, application resource availability].

[0067] The embodiment of the present invention can characterize the value of multi-dimensional data to distributed business traffic scheduling through multi-dimensional network indicator data, which is convenient for subsequent accurate prediction through the scheduling model. In addition, by sorting the multi-dimensional network indicator historical data of multiple historical time points, the network changes of users at different times can be determined, and then the group location characteristics and group performance characteristics of users can be determined in combination with the multi-dimensional network indicator data. The scheduling model that best suits the user is selected based on the user's group location characteristics and group performance characteristics to perform accurate prediction, thereby improving the prediction accuracy.

[0068] Further, based on step 104, multiple target scheduling models are selected from multiple types of scheduling models based on the group location characteristics and the group performance characteristics, including: Determine the scheduling model for each type a first performance indicator on the group position characteristic and a second performance indicator on the group performance characteristic for each type of scheduling model; Determine a scheduling model corresponding to an optimal performance indicator among the plurality of first performance indicators as a first target scheduling model; The scheduling model corresponding to the optimal performance indicator among the multiple second performance indicators is determined as the second target scheduling model.

[0069] The following description Figure 2 The detailed content of step S4 in .

[0070] It should be noted that, combined with Figure 4 , Figure 4 Schematic diagram of the scheduling model selection provided by the present invention. In the pre-training process of the scheduling model, the performance indicators of each type of scheduling model on each group position feature are recorded, so a scheduling model with the best performance indicator can be selected according to the group position feature of the user. Similarly, in the pre-training process of the scheduling model, the performance indicators of each type of scheduling model on each group performance feature are recorded, so a scheduling model with the best performance indicator can be selected according to the group performance feature of the user. Among them, the performance indicators include but are not limited to accuracy, precision, recall rate and F1 score.

[0071] Specifically, the distributed service flow scheduling device determines a first performance indicator of each type of scheduling model on the group location characteristics of users and a second performance indicator of each type of scheduling model on the group performance characteristics.

[0072] Furthermore, the distributed service traffic scheduling device determines an optimal performance indicator that satisfies the group location characteristics of the user from the multiple first performance indicators, and determines an optimal performance indicator that satisfies the group performance characteristics of the user from the second performance indicators.

[0073] Furthermore, the distributed service traffic scheduling device determines the scheduling model corresponding to the optimal performance indicator that meets the group location characteristics of the user as the first target scheduling model.

[0074] Furthermore, the distributed service traffic scheduling device determines the scheduling model corresponding to the optimal performance indicator that meets the group performance characteristics of the user as the second target scheduling model.

[0075] In one embodiment, assume that user A often uses services in city B, and city B corresponds to data center X. By analyzing the historical data of user A, it is found that user A is very sensitive to network latency in data center X. Therefore, it is necessary to select a scheduling model optimized for low latency in data center X and determine it as the first target scheduling model. At the same time, if user A's network usage patterns are different on weekdays and weekends, the scheduling strategy may also be adjusted according to these patterns to ensure the best service experience in different time periods.

[0076] In another embodiment, by analyzing the historical data of user A, it is found that the network used by user A usually has high throughput, indicating that the user is a user with high throughput requirements. Therefore, it is necessary to select a scheduling model optimized for high throughput and determine it as the second target scheduling model.

[0077] The embodiment of the present invention selects multiple target scheduling models from multiple model types based on group location characteristics and group performance characteristics determined by user historical data, and can select the target scheduling model that best suits the user according to characteristics of different dimensions, and then perform comprehensive scheduling through multiple target scheduling models to obtain a target business traffic scheduling baseline, which can improve the accuracy of target scheduling model prediction.

[0078] Further, based on step 105, the multi-dimensional network indicator data is based on which the multiple target scheduling models are trained respectively to obtain a target service traffic scheduling baseline, including: Extracting features from the multi-dimensional network indicator sequence to obtain multi-dimensional network indicator representation data; Inputting the multi-dimensional network indicator characterization data into the first target scheduling model to obtain a first service traffic scheduling baseline output by the first target scheduling model; Inputting the multi-dimensional network indicator characterization data into the second target scheduling model to obtain a second service traffic scheduling baseline output by the second target scheduling model; A mean calculation is performed based on the first service traffic scheduling baseline and the second service traffic scheduling baseline to obtain a target service traffic scheduling baseline.

[0079] The following description Figure 2 The detailed content of step S5 in .

[0080] Specifically, the distributed service traffic scheduling device extracts features from a multi-dimensional network indicator sequence to obtain multi-dimensional network indicator representation data.

[0081] Furthermore, the distributed service traffic scheduling device inputs the multi-dimensional network indicator characterization data into the first target scheduling model to obtain the first service traffic scheduling baseline output by the first target scheduling model.

[0082] Furthermore, the distributed service traffic scheduling device inputs the multi-dimensional network indicator characterization data into the second target scheduling model to obtain a second service traffic scheduling baseline output by the second target scheduling model.

[0083] Furthermore, the distributed business traffic scheduling device performs mean calculation based on the first business traffic scheduling baseline and the second business traffic scheduling baseline to obtain a target business traffic scheduling baseline. This baseline can be considered as a baseline for user access and computing power scheduling, and is subsequently used to measure the difference between actual user access behavior traffic and expected values.

[0084] The embodiment of the present invention uses a target scheduling model suitable for the user selected by different dimensional features to comprehensively predict the multi-dimensional network indicator sequence, and calculates the mean of the prediction results output by each target scheduling model to obtain an accurate target business traffic scheduling baseline, thereby improving the accuracy of the scheduling model prediction, thereby achieving accurate distributed business traffic scheduling based on the accurate target business traffic scheduling baseline.

[0085] Further, based on step 106, dynamically adjusting the traffic scheduling of the distributed service based on the target service traffic scheduling baseline includes: Obtaining the real-time first access behavior flow data of the user; If the first access behavior traffic data deviates from the target service traffic scheduling baseline, the distributed service and user access are dynamically scheduled.

[0086] The following description Figure 2 The detailed content of step S6 in .

[0087] Specifically, the distributed service traffic scheduling device obtains the user's real-time first access behavior traffic data, wherein the first access behavior traffic data records the access traffic generated by the user when accessing the system, including access frequency, data transmission volume, etc.

[0088] Furthermore, the distributed service traffic scheduling device compares and analyzes the first access behavior traffic data and the target service traffic scheduling baseline.

[0089] If the traffic data of the first access behavior deviates from the target service traffic scheduling baseline, the distributed service traffic scheduling device dynamically schedules the distributed service and user access.

[0090] If the first access behavior traffic data does not deviate from the target business traffic scheduling baseline, the distributed business traffic scheduling device continues to use the original distributed business and user access scheduling strategy, and records the user's first access behavior traffic data as the user's user access behavior traffic history data, which can be used for subsequent optimization of distributed business traffic scheduling.

[0091] When the embodiment of the present invention monitors that the user's first access behavior traffic data deviates from the target business traffic scheduling baseline, it will dynamically schedule distributed services and user access in a timely manner, which can adapt to the development of distributed clouds, meet the needs of high availability and flexible and elastic deployment of services, and achieve refined and dynamic scheduling of user access traffic. At the same time, it strengthens the ability to perceive business situations in advance, reduces the pressure and security risks caused by business emergencies, and thus improves user satisfaction.

[0092] Further, after dynamically adjusting the traffic scheduling of the distributed service based on the target service traffic scheduling baseline, the method includes: Obtaining real-time second access behavior flow data of the user; Performing a comparative analysis based on the second access behavior traffic data and the target service traffic scheduling baseline to obtain a comparative analysis result; Iteratively executing the step of obtaining the real-time second access behavior flow data of the user until a plurality of comparative analysis results are obtained after executing the continuous time period; Based on the multiple comparative analysis results, generate historical dynamic month-on-month data; Based on the historical dynamic month-on-month data, the strategy for distributed business traffic scheduling is optimized.

[0093] Specifically, the distributed service traffic scheduling device obtains the user's real-time second access behavior traffic data.

[0094] Furthermore, the distributed business traffic scheduling device performs comparative analysis based on the second access behavior traffic data and the target business traffic scheduling baseline to obtain a comparative analysis result, which reflects the deviation of the user access behavior traffic from the baseline and the trend of the user access behavior traffic.

[0095] Furthermore, the distributed service traffic scheduling device iteratively executes the step of obtaining the user's real-time second access behavior traffic data until a plurality of comparative analysis results are obtained after a continuous time period is executed. The continuous time period can be set according to actual conditions.

[0096] Furthermore, the distributed service traffic scheduling device generates historical dynamic month-on-month data based on multiple comparative analysis results.

[0097] Furthermore, the distributed service traffic scheduling device optimizes the distributed service traffic scheduling strategy based on historical dynamic month-on-month data.

[0098] In one embodiment, historical dynamic month-on-month data can be used to optimize the scheduling strategy. The historical dynamic month-on-month data records the changes in user access behavior traffic over time, and these data can help analyze user behavior patterns and traffic trends, thereby optimizing the scheduling strategy.

[0099] In another embodiment, the historical dynamic month-on-month data can be used to train and adjust the machine learning model. The historical dynamic month-on-month data can be used as input to train and adjust the machine learning model to improve the prediction accuracy and adaptability of the model.

[0100] In another embodiment, historical dynamic month-on-month data can be used to automatically adjust the scheduling algorithm. Based on the machine learning model, an automatic scheduling algorithm is added to use historical dynamic month-on-month data to adjust the scheduling of services and access in real time to adapt to the ever-changing business needs of the enterprise system.

[0101] In another embodiment, the historical dynamic year-on-year data can be used to predict and deal with traffic peaks. By analyzing the historical dynamic year-on-year data, traffic peak periods can be predicted, and resource allocation and scheduling can be performed in advance to avoid system overload.

[0102] The embodiment of the present invention generates historical dynamic month-on-month data by continuously obtaining comparative analysis results between user access behavior traffic data and the target business traffic scheduling baseline, and further optimizes the measurement of distributed business traffic scheduling based on the historical dynamic month-on-month data, so that the system can continuously learn and adapt to changes in user behavior and realize more intelligent and automated distributed business traffic scheduling.

[0103] The following description Figure 2 The detailed content of step S6 in .

[0104] Furthermore, the distributed service traffic scheduling method further includes: Obtain business support capability data; Performing performance bottleneck analysis based on the business support capability data to obtain performance bottleneck analysis results; Based on the performance bottleneck analysis result, determine the time point for distributed service traffic scheduling; At the time point of the distributed service traffic scheduling, the distributed services and user access are dynamically scheduled.

[0105] Specifically, the distributed service traffic scheduling device obtains service support capability data.

[0106] Among them, business support capability data include but are not limited to server load, response time, resource utilization (CPU, memory, storage, network), etc. These data reflect the performance and carrying capacity of the system.

[0107] Furthermore, the distributed service traffic scheduling device performs performance bottleneck analysis based on the service support capability data to obtain performance bottleneck analysis results, which can reflect the current state and performance bottleneck of the service system.

[0108] Furthermore, the distributed service traffic scheduling device determines the time point for distributed service traffic scheduling based on the performance bottleneck analysis result, so as to dynamically schedule distributed services and user access in advance before the service support capability data is overloaded.

[0109] Furthermore, the distributed service traffic scheduling device dynamically schedules distributed services and user access at the time point of distributed service traffic scheduling.

[0110] It should be noted that after dynamic scheduling of distributed services and user access based on business support capability data, historical dynamic month-on-month data will be gradually formed and accumulated. Based on the historical dynamic month-on-month data, an automatic adjustment scheduling algorithm will be added to the scheduling model to adapt to the ever-changing business needs of the business system.

[0111] The embodiments of the present invention can identify performance bottleneck problems in the system by acquiring business support capability data and performing performance bottleneck analysis, and further determine the appropriate time point for distributed business traffic scheduling based on the performance bottleneck analysis results, thereby optimizing the utilization of system resources, reducing the impact of performance bottlenecks, improving the response speed and stability of the overall system, and enhancing user experience.

[0112] The distributed service traffic scheduling device provided by the present invention is described below. The distributed service traffic scheduling device described below and the distributed service traffic scheduling method described above can be referenced to each other.

[0113] Reference Figure 5 , Figure 5 It is a structural diagram of the distributed service flow scheduling device provided by the present invention.

[0114] The distributed service flow scheduling device comprises: The acquisition module 510 is used to acquire the real-time multi-dimensional network indicator data of the user and the multi-dimensional network indicator historical data of the user at multiple historical time points.

[0115] The first determination module 520 is used to determine the group location characteristics of the users based on the multi-dimensional network indicator data and a plurality of multi-dimensional network indicator historical data; the group location characteristics are used to reflect the characteristic performance of the network location of the users.

[0116] The second determination module 530 is used to determine the group performance characteristics of the users based on the plurality of multi-dimensional network indicator historical data; the group performance characteristics are used to reflect the characteristic performance of the users on the network performance.

[0117] The scheduling model selection module 540 is used to select multiple target scheduling models from multiple types of scheduling models based on the group location characteristics and the group performance characteristics; any of the scheduling models is obtained by model training based on multi-dimensional network indicator samples and their corresponding business traffic scheduling baseline labels.

[0118] The scheduling model prediction module 550 is used to obtain a target business traffic scheduling baseline by training the multiple target scheduling models respectively based on the multi-dimensional network indicator data.

[0119] The scheduling module 560 is used to dynamically adjust the traffic scheduling of the distributed service based on the target service traffic scheduling baseline.

[0120] The distributed service traffic scheduling device provided by the present invention obtains relatively comprehensive multi-dimensional network indicator data, and combines the multi-dimensional network indicator historical data to determine the group location characteristics and group performance characteristics of the current user, comprehensively considers the group location characteristics and group performance characteristics of the current user, selects multiple target scheduling models suitable for the current user from two different feature dimensions, and performs comprehensive scheduling based on the relatively comprehensive multi-dimensional network indicator data through multiple target scheduling models to obtain an accurate target service traffic scheduling baseline, and then based on the accurate target service traffic scheduling baseline, dynamically adjusts the traffic scheduling of the distributed service, improves the accuracy of the distributed service traffic scheduling, and at the same time enhances the ability to perceive the service situation in advance, reduces the pressure and security risks brought by service bursts, and thus improves user satisfaction.

[0121] Furthermore, the distributed service flow scheduling device is also used for: Determine whether each dimensional network indicator data satisfies a preset weight update trigger rule corresponding to the dimensional network indicator data; If the dimensional network indicator data satisfies the preset weight update trigger rule corresponding to the dimensional network indicator data, then the preset weight value corresponding to the dimensional network indicator data is increased to obtain the target weight value corresponding to each dimensional network indicator data; According to the target weight value corresponding to each dimensional network indicator data, the multi-dimensional network indicator data is sorted according to the weight value to obtain a multi-dimensional network indicator sequence.

[0122] Furthermore, the scheduling model selection module 540 is also used for: Determine a first performance indicator of each type of scheduling model on the group location characteristics and a second performance indicator of each type of scheduling model on the group performance characteristics; Determine a scheduling model corresponding to an optimal performance indicator among the plurality of first performance indicators as a first target scheduling model; The scheduling model corresponding to the optimal performance indicator among the multiple second performance indicators is determined as the second target scheduling model.

[0123] Furthermore, the scheduling model prediction module 550 is also used for: Extracting features from the multi-dimensional network indicator sequence to obtain multi-dimensional network indicator representation data; Inputting the multi-dimensional network indicator characterization data into the first target scheduling model to obtain a first service traffic scheduling baseline output by the first target scheduling model; Inputting the multi-dimensional network indicator characterization data into the second target scheduling model to obtain a second service traffic scheduling baseline output by the second target scheduling model; A mean calculation is performed based on the first service traffic scheduling baseline and the second service traffic scheduling baseline to obtain a target service traffic scheduling baseline.

[0124] Furthermore, the scheduling module 560 is also used for: Obtaining the real-time first access behavior flow data of the user; If the first access behavior traffic data deviates from the target service traffic scheduling baseline, the distributed service and user access are dynamically scheduled.

[0125] Furthermore, the distributed service flow scheduling device is also used for: Obtaining real-time second access behavior flow data of the user; Performing a comparative analysis based on the second access behavior traffic data and the target service traffic scheduling baseline to obtain a comparative analysis result; Iteratively executing the step of obtaining the real-time second access behavior flow data of the user until a plurality of comparative analysis results are obtained after executing the continuous time period; Based on the multiple comparative analysis results, generate historical dynamic month-on-month data; Based on the historical dynamic month-on-month data, the strategy for distributed business traffic scheduling is optimized.

[0126] Furthermore, the distributed service flow scheduling device is also used for: Obtain business support capability data; Performing performance bottleneck analysis based on the business support capability data to obtain performance bottleneck analysis results; Based on the performance bottleneck analysis result, determine the time point for distributed service traffic scheduling; At the time point of the distributed service traffic scheduling, the distributed services and user access are dynamically scheduled.

[0127] It should be noted that the distributed service traffic scheduling device provided by the present invention can execute the distributed service traffic scheduling method described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0128] Figure 6 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 6 As shown, the electronic device may include: a processor (processor) 610 , a communication interface (Communications Interface) 620 , a memory (memory) 630 and a communication bus 640 , wherein the processor 610 , the communication interface 620 , and the memory 630 communicate with each other through the communication bus 640 . The processor 610 can call the logic instructions in the memory 630 to execute a distributed service traffic scheduling method, which includes: obtaining real-time multi-dimensional network indicator data of the user and the multi-dimensional network indicator historical data of the user at multiple historical time points; determining the group location characteristics of the user based on the multi-dimensional network indicator data and multiple multi-dimensional network indicator historical data; the group location characteristics are used to reflect the characteristic performance of the network location of the user; based on multiple multi-dimensional network indicator historical data, determining the group performance characteristics of the user; the group performance characteristics are used to reflect the characteristic performance of the user to network performance; based on the group location characteristics and the group performance characteristics, selecting multiple target scheduling models from multiple types of scheduling models; any of the scheduling models is obtained by model training based on multi-dimensional network indicator samples and their corresponding service traffic scheduling baseline labels; based on the multi-dimensional network indicator data, the multiple target scheduling models are trained separately to obtain a target service traffic scheduling baseline; based on the target service traffic scheduling baseline, the traffic scheduling of distributed services is dynamically adjusted.

[0129] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0130] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the distributed service traffic scheduling method provided by the above embodiments, the method comprising: obtaining real-time multi-dimensional network indicator data of a user and multi-dimensional network indicator historical data of the user at multiple historical time points; determining the group location characteristics of the user based on the multi-dimensional network indicator data and multiple multi-dimensional network indicator historical data; the group location characteristics are used to reflect the characteristic performance of the network location of the user; based on multiple multi-dimensional network indicator historical data, determining the group performance characteristics of the user; the group performance characteristics are used to reflect the characteristic performance of the user to network performance; based on the group location characteristics and the group performance characteristics, selecting multiple target scheduling models from multiple types of scheduling models; any of the scheduling models is obtained by model training based on multi-dimensional network indicator samples and their corresponding service traffic scheduling baseline labels; based on the multi-dimensional network indicator data, training is performed separately through the multiple target scheduling models to obtain a target service traffic scheduling baseline; based on the target service traffic scheduling baseline, dynamically adjusting the traffic scheduling of distributed services.

[0131] On the other hand, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it is implemented to execute the distributed service traffic scheduling method provided by the above embodiments, the method comprising: obtaining real-time multi-dimensional network indicator data of a user and multi-dimensional network indicator historical data of the user at multiple historical time points; determining the group location characteristics of the user based on the multi-dimensional network indicator data and multiple multi-dimensional network indicator historical data; the group location characteristics are used to reflect the characteristic performance of the network location of the user; determining the group performance characteristics of the user based on multiple multi-dimensional network indicator historical data; the group performance characteristics are used to reflect the characteristic performance of the user to network performance; based on the group location characteristics and the group performance characteristics, selecting multiple target scheduling models from multiple types of scheduling models; any of the scheduling models is obtained by model training based on multi-dimensional network indicator samples and their corresponding service traffic scheduling baseline labels; based on the multi-dimensional network indicator data, training is performed separately through the multiple target scheduling models to obtain a target service traffic scheduling baseline; based on the target service traffic scheduling baseline, dynamically adjusting the traffic scheduling of distributed services.

[0132] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Those of ordinary skill in the art may understand and implement the present invention without creative effort.

[0133] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A distributed service traffic scheduling method, characterized in that: include: Acquire real-time multi-dimensional network indicator data of the user and multi-dimensional network indicator historical data of the user at multiple historical time points; Determining group location characteristics of the user based on the multi-dimensional network indicator data and a plurality of multi-dimensional network indicator historical data; The group location feature is used to reflect the characteristic performance of the network location of the user; Determine the group performance characteristics of the user based on the plurality of multi-dimensional network indicator historical data; the group performance characteristics are used to reflect the characteristic performance of the user on the network performance; Based on the group location characteristics and the group performance characteristics, multiple target scheduling models are selected from multiple types of scheduling models; any of the scheduling models is obtained by model training based on multi-dimensional network indicator samples and their corresponding service traffic scheduling baseline labels; Based on the multi-dimensional network indicator data, the target service traffic scheduling baseline is obtained by respectively training the multiple target scheduling models; Based on the target service traffic scheduling baseline, traffic scheduling of distributed services is dynamically adjusted.

2. The distributed service traffic scheduling method according to claim 1, characterized in that: After obtaining the real-time multi-dimensional network indicator data of the user and the multi-dimensional network indicator historical data of the user at multiple historical time points, and before determining the group location characteristics of the user based on the multi-dimensional network indicator data and the multiple multi-dimensional network indicator historical data, the following steps are performed for the multi-dimensional network indicator data: Determine whether each dimensional network indicator data satisfies a preset weight update trigger rule corresponding to the dimensional network indicator data; If the dimensional network indicator data satisfies the preset weight update trigger rule corresponding to the dimensional network indicator data, then the preset weight value corresponding to the dimensional network indicator data is increased to obtain the target weight value corresponding to each dimensional network indicator data; According to the target weight value corresponding to each dimensional network indicator data, the multi-dimensional network indicator data is sorted according to the weight value to obtain a multi-dimensional network indicator sequence.

3. The distributed service traffic scheduling method according to claim 2, characterized in that: The target scheduling model includes a first target scheduling model and a second target scheduling model; the multiple target scheduling models are selected from multiple types of scheduling models based on the group location characteristics and the group performance characteristics, including: Determine a first performance indicator of each type of scheduling model on the group location characteristics and a second performance indicator of each type of scheduling model on the group performance characteristics; Determine a scheduling model corresponding to an optimal performance indicator among the plurality of first performance indicators as a first target scheduling model; The scheduling model corresponding to the optimal performance indicator among the multiple second performance indicators is determined as the second target scheduling model.

4. The distributed service traffic scheduling method according to claim 3, characterized in that: The step of training the plurality of target scheduling models based on the multi-dimensional network indicator data to obtain a target service traffic scheduling baseline includes: Extracting features from the multi-dimensional network indicator sequence to obtain multi-dimensional network indicator representation data; Inputting the multi-dimensional network indicator characterization data into the first target scheduling model to obtain a first service traffic scheduling baseline output by the first target scheduling model; Inputting the multi-dimensional network indicator characterization data into the second target scheduling model to obtain a second service traffic scheduling baseline output by the second target scheduling model; A mean calculation is performed based on the first service traffic scheduling baseline and the second service traffic scheduling baseline to obtain a target service traffic scheduling baseline.

5. The distributed service traffic scheduling method according to claim 1, characterized in that: The dynamically adjusting the traffic scheduling of the distributed service based on the target service traffic scheduling baseline includes: Obtaining the real-time first access behavior flow data of the user; If the first access behavior traffic data deviates from the target service traffic scheduling baseline, the distributed service and user access are dynamically scheduled.

6. The distributed service traffic scheduling method according to claim 5, characterized in that: After dynamically adjusting the traffic scheduling of the distributed service based on the target service traffic scheduling baseline, the method includes: Obtaining real-time second access behavior flow data of the user; Performing a comparative analysis based on the second access behavior traffic data and the target service traffic scheduling baseline to obtain a comparative analysis result; Iteratively executing the step of obtaining the real-time second access behavior flow data of the user until a plurality of comparative analysis results are obtained after executing the continuous time period; Based on the multiple comparative analysis results, generate historical dynamic month-on-month data; Based on the historical dynamic month-on-month data, the strategy for distributed business traffic scheduling is optimized.

7. The distributed service traffic scheduling method according to any one of claims 1 to 6, characterized in that: The distributed service traffic scheduling method further includes: Obtain business support capability data; Performing performance bottleneck analysis based on the business support capability data to obtain performance bottleneck analysis results; Based on the performance bottleneck analysis result, determine the time point for distributed service traffic scheduling; At the time point of the distributed service traffic scheduling, the distributed services and user access are dynamically scheduled.

8. A distributed service flow scheduling device, characterized in that: include: An acquisition module, used to acquire real-time multi-dimensional network indicator data of a user and multi-dimensional network indicator historical data of the user at multiple historical time points; A first determination module, configured to determine the group location characteristics of the user based on the multi-dimensional network indicator data and a plurality of multi-dimensional network indicator historical data; The group location feature is used to reflect the characteristic performance of the network location of the user; A second determination module is used to determine the group performance characteristics of the user based on the plurality of multi-dimensional network indicator historical data; the group performance characteristics are used to reflect the characteristic performance of the user on the network performance; A scheduling model selection module, used to select multiple target scheduling models from multiple types of scheduling models based on the group location characteristics and the group performance characteristics; any of the scheduling models is obtained by model training based on multi-dimensional network indicator samples and their corresponding service traffic scheduling baseline labels; A scheduling model prediction module, used to obtain a target service traffic scheduling baseline by training the multiple target scheduling models respectively based on the multi-dimensional network indicator data; The scheduling module is used to dynamically adjust the traffic scheduling of distributed services based on the target service traffic scheduling baseline.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the distributed service traffic scheduling method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, the computer-readable storage medium comprising a non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the distributed service traffic scheduling method as claimed in any one of claims 1 to 7 are implemented.

11. A computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the steps of the distributed service traffic scheduling method as claimed in any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Network traffic prediction method and device, equipment and storage medium

    CN113497717A

  • 5G network optimization method and system

    CN114245392A

  • Traffic scheduling method and device, equipment and storage medium

    CN116248603A

  • Network resource scheduling method and device, computer equipment and storage medium

    CN116916463A

  • User portrait scenarized operation method and system based on network information mirroring

    CN118102358A