Business assurance method, apparatus, device, and storage medium

Abstract

Embodiments of the present application relate to the technical field of communication, in particular to a service guarantee method, device and equipment and storage medium, the method comprising: obtaining a first data set, the first data set being used to describe the running condition of a first service; determining the importance of M control factors according to the first data set, the control factors being used to guarantee the first service, M being a positive integer; determining a first script of the first service according to the importance of the M control factors, the first script representing a first control path of the first service, the first control path indicating the execution order of K control factors, K being less than or equal to M, K being a positive integer, and the K control factors being the control factors with the top K importance among the M control factors.

Description

Technical Field

[0001] This application relates to the field of communication technology, specifically to a service assurance method, apparatus, device, and storage medium. Background Technology

[0002] With the rapid development of information technology, enterprises are becoming increasingly reliant on networks, especially in terms of business continuity and performance requirements. Examples include front desk order processing in hotels, cashier operations in commercial services, and live streaming in online stores. The smooth operation of these services is crucial for business operations. However, various bandwidth networks typically suffer from issues such as session limits and uplink bandwidth throttling, and the quality of the outbound link (e.g., latency, packet loss, jitter) can also fluctuate dynamically. Summary of the Invention

[0003] This application provides a business assurance method, apparatus, device, and storage medium that can improve the assurance of critical business operations.

[0004] In a first aspect, embodiments of this application provide a service assurance method, the method comprising:

[0005] Obtain a first data set, which is used to describe the operation of the first service;

[0006] The importance of M control factors is determined based on the first data set. The control factors are used to ensure the first service. M is a positive integer.

[0007] The first script of the first service is determined based on the importance of the M control factors. The first script represents the first control path of the first service. The first control path indicates the execution order of the K control factors, where K ≤ M and K is a positive integer. The K control factors are the control factors with the highest importance among the M control factors.

[0008] In this embodiment of the application, the importance of multiple control factors can be determined by obtaining a first data set, and a control path for the first service can be planned and a first script can be generated based on the importance of the control factors. The above process can automatically ensure the first service, adjust the script used to ensure the first service in a timely manner, and meet the needs of dynamic changes in the network environment.

[0009] In one possible embodiment, the first data set is used to describe the operation of the first service under a second script of the first service; the second script is a pre-configured script, or the second script is a previously determined script.

[0010] Before obtaining the first data set, the process also includes:

[0011] Obtain the second script, which indicates the second control path of the first service. The second control path indicates the execution order of N control factors, where N is a positive integer. The first control path is different from the second control path, and the N control factors belong to the M control factors.

[0012] In one possible embodiment, the K control factors are the same as the N control factors, and the execution order of the K control factors indicated by the first control path is different from the execution order of the N control factors indicated by the second control path.

[0013] Alternatively, the K control factors may be different from the N control factors.

[0014] In one possible embodiment, obtaining the first data set includes:

[0015] Obtain a set of network environment monitoring parameters, which includes W network environment monitoring parameters at multiple times, where W is a positive integer;

[0016] Obtain a rating set, which includes the ratings of the first service at the plurality of times.

[0017] In one possible embodiment, obtaining the rating set includes:

[0018] For each of the plurality of time points, obtain the latency of the first service, the packet loss rate of the first service, or the jitter parameter of the first service;

[0019] The score of the first service is calculated based on the latency of the first service, the packet loss rate of the first service, or the jitter parameter of the first service.

[0020] In one possible embodiment, a mapping relationship is configured between the W network environment monitoring parameters and the M control factors, wherein each control factor corresponds to one or more network environment monitoring parameters among the W network environment monitoring parameters.

[0021] In this embodiment, a mapping relationship is established between network environment monitoring parameters and control factors. Each network environment monitoring parameter can correspond to one control factor, and one control factor can correspond to multiple network environment monitoring parameters.

[0022] In one possible embodiment, determining the importance of the M control factors based on the first dataset includes:

[0023] The importance of the W network environment monitoring parameters is determined based on the first data set;

[0024] The importance of the M control factors is determined based on the importance of the W network environment monitoring parameters and the mapping relationship.

[0025] In one possible embodiment, determining the importance of the W network environment monitoring parameters based on the first data set includes:

[0026] Calculate the first difference corresponding to each of the plurality of time points, where the first difference is the difference between the score of the first service and the predicted value of the score of the first service.

[0027] Calculate W second differences corresponding to the plurality of time points, wherein the W second differences correspond one-to-one with the W network environment monitoring parameters, the i-th second difference is the difference between the i-th network environment monitoring parameter and the predicted value of the i-th network environment monitoring parameter, the i-th network environment monitoring parameter is any one of the W network environment monitoring parameters, i is a positive integer, and i≤W;

[0028] The W ratios corresponding to the plurality of times are determined based on the first differences corresponding to the plurality of times and the W second differences corresponding to the plurality of times; wherein, the i-th ratio corresponding to the j-th time is the ratio of the i-th second difference corresponding to the j-th time to the first difference corresponding to the j-th time, and the j-th time is any one of the plurality of times, and j is a positive integer;

[0029] W reference values ​​are determined based on the W ratios corresponding to the plurality of times, wherein each of the W reference values ​​corresponds one-to-one with one of the W network environment monitoring parameters, and the i-th reference value is the sum of the i-th ratios corresponding to the plurality of times; wherein the W reference values ​​are proportional to the importance of the W network environment monitoring parameters.

[0030] In one possible embodiment, determining the importance of the M control factors based on the importance of the W network environment monitoring parameters and the mapping relationship includes:

[0031] The importance scores of the M control factors are determined, wherein the importance score of each control factor is determined based on the reference values ​​of one or more network environment monitoring parameters corresponding to that control factor; and wherein the importance scores of the M control factors are proportional to the importance of the M control factors.

[0032] Using the above embodiments, by calculating the importance scores of M control factors, the importance of the M control factors can be obtained, thereby optimizing the control path and generating a control path that effectively guarantees the performance of the first service.

[0033] In one possible embodiment, the importance score of each control factor is a weighted sum of reference values ​​of one or more network environment monitoring parameters corresponding to that control factor.

[0034] In one possible embodiment, a preset set of control operations corresponding to each of the M control factors is configured.

[0035] In one possible embodiment, the control operations corresponding to the K control factors are determined based on the preset control operation sets corresponding to the K control factors.

[0036] In one possible embodiment, determining the control operations corresponding to the K control factors based on the preset control operation sets corresponding to the K control factors includes:

[0037] Determine the rate of change of the W network environment monitoring parameters and the corresponding resource utilization rate based on the set of network environment monitoring parameters;

[0038] Based on the change rate of the W network environment monitoring parameters and the corresponding resource utilization rate, P network environment monitoring parameters are determined from the W network environment monitoring parameters. The change rate of each of the P network environment monitoring parameters is greater than a first threshold and the first resource utilization rate corresponding to each network environment monitoring parameter is greater than a second threshold. P is a positive integer, where P≤W.

[0039] Based on the mapping relationship and the P network environment monitoring parameters, S control factors are determined from the K control factors, where S is a positive integer and S≤K;

[0040] The control operation corresponding to the first control factor is determined according to the preset control operation set corresponding to the first control factor, and the control operation corresponding to the second control factor is determined according to the preset control operation set corresponding to the second control factor. The first control factor belongs to the S control factors, the second control factor belongs to the K control factors but does not belong to the S control factors, and the number of control operations corresponding to the second control factor is less than the number of control operations corresponding to the first control factor.

[0041] In this embodiment, by setting two thresholds, the rate of change of network environment monitoring parameters and the corresponding resource utilization rate are calculated. This allows the identification of the network environment monitoring parameters (P monitoring parameters) that have the greatest impact on network performance. The network environment monitoring parameters are then mapped to corresponding control factors. Based on this, the control operations corresponding to the control factors are adjusted. For the control factors corresponding to the P network environment monitoring parameters, more control operations are invoked, while for other control factors, fewer control operations are invoked. This approach reduces the resource consumption of other services, allowing more resources to be allocated to the first service, thereby effectively ensuring the performance of the first service.

[0042] In one possible embodiment, the M control factors include at least one of link uplink bandwidth, link session count, DNS resolution latency, or link packet loss.

[0043] In one possible embodiment, the preset control operation set corresponding to the uplink bandwidth of the link includes at least one of flow control and suppressing other service traffic;

[0044] The preset control operation set corresponding to the number of link sessions includes at least one of session control and suppressing other service sessions;

[0045] The preset set of control operations corresponding to the DNS resolution delay includes at least one of DNS domain name adjustment and enabling a DNS proxy; and

[0046] The preset set of control operations corresponding to the link packet loss includes at least one of the following: switching the outbound link and limiting the traffic rate of other services.

[0047] Secondly, embodiments of this application also provide a service assurance device, the device including a transceiver unit and a processing unit;

[0048] The transceiver unit is used to acquire a first data set, which is used to describe the operation of the first service.

[0049] The processing unit is configured to determine the importance of M control factors based on the first data set, wherein the control factors are used to guarantee the first service, and M is a positive integer; and to determine a first script for the first service based on the importance of the M control factors, wherein the first script represents a first control path for the first service, and the first control path indicates the execution order of K control factors, where K ≤ M, K is a positive integer, and the K control factors are the control factors with the highest importance among the M control factors.

[0050] Thirdly, this application provides a business support device, comprising:

[0051] Memory, used to store program instructions;

[0052] A processor is configured to invoke program instructions stored in the memory and execute the steps of the method described in any one of the first aspects according to the obtained program instructions.

[0053] Fourthly, this application provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a computer, cause the computer to perform the method described in any one of the first aspects.

[0054] Fifthly, this application provides a computer program product comprising: computer program code, which, when run on a computer, causes the computer to perform the method described in any one of the first aspects. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 Schematic diagrams illustrating the operation of multiple services provided in each embodiment;

[0057] Figure 2 A flowchart illustrating the service assurance method provided in the embodiments of this application;

[0058] Figure 3A A schematic diagram of the structure of the first script of the first service provided in the embodiments of this application;

[0059] Figure 3B A schematic diagram of the structure of the second script for the first service provided in the embodiments of this application;

[0060] Figure 4 Schematic diagram of the service assurance device provided in the embodiments of this application Figure 1 ;

[0061] Figure 5 Schematic diagram of the service assurance device provided in the embodiments of this application Figure 2 . Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0063] like Figure 1 As shown, multiple services connect to the egress device simultaneously through switches and wireless access points. When these services run at the same time, they compete for limited network resources, resulting in a deterioration and poor user experience.

[0064] The following explains the technical terms that may be involved in this application:

[0065] 1. Security Orchestration, Automation and Response (SOAR): This is a collection of technologies used to help enterprises and organizations collect various information monitored by security operations teams, perform event analysis and alert classification on this information, and then, guided by scripts, use a human-machine collaborative approach to help security operations personnel define, prioritize, and trigger standardized event response activities. Borrowing from the SOAR system and its concepts, the system internally breaks down into sets of atomic capabilities. Operations engineers then use these atomic capability sets to perform drag-and-drop orchestration, generating business assurance scripts that meet the requirements of specific scenarios. The general logic is as follows:

[0066] 1) Within the system, break down the system's atomic capability set. The atomic capability set can include: a collection of capabilities such as information collection and analysis, action handling and execution, etc.

[0067] 2) Operations engineers, based on the needs of actual application scenarios, either redesign and rearrange the script based on the template script to form a new script, or rearrange it based on the atomic capability set to build a new script.

[0068] 3) After the new script is completed, during system operation, based on the alarms and events detected, the system will handle them according to the process defined in the script to achieve automated protection of business operations.

[0069] 2. Critical Services: These refer to services that require priority protection in the network environment. For example, critical services can be understood as services that require guaranteed business continuity or services that require specific latency requirements. Examples include front desk order processing in a hotel setting, cashier operations in a commercial service setting, and livestreaming customer acquisition in a store setting. In this application, the network environment may include a home bandwidth network environment or a dedicated bandwidth network environment, etc., and this application does not limit this.

[0070] Current business assurance methods mainly rely on fixed control paths. Multiple business flows pass through various control nodes in sequence, and each control node performs control and adjustment according to its own logical strategy. There is a lack of linkage between multiple control nodes. With the dynamic changes of multiple businesses and the dynamic changes of the quality of the outbound link, it is impossible to achieve dynamic assurance of the entire process of business within the system.

[0071] In view of the above problems, this application provides a method for business assurance.

[0072] It is understood that the following method is illustrated using the example of ensuring the first service, which is a critical service. It is also understood that the following method can be applied to ensure other services. The following method is illustrated using a server as the executing entity. However, the executing entity can also be a chip in the server, a processor, or a chip in a processor; this application does not limit the executing entity.

[0073] like Figure 2 As shown, the method specifically includes:

[0074] Step 200: The server obtains the first data set, which is used to describe the operation of the first service.

[0075] The first service can be identified by a destination address, or by a source address and a destination address, or by a domain name, or by a source address, a destination address, and a domain name; this application does not limit the specific identification method. For example, in a scenario where a mobile phone is used for live streaming based on application A, the source address can be the mobile phone's Internet Protocol (IP) address, the destination address can be the IP address of application A's server, and the domain name can be the domain name of application A's live streaming service.

[0076] In one possible embodiment, when the server obtains the first data set, it may obtain, but is not limited to, the following two sets:

[0077] (1) Obtain the network environment monitoring parameter set, which includes W network environment monitoring parameters at multiple times, where W is a positive integer.

[0078] Here, "multiple moments" can be understood as multiple moments during the first service operation period. During the first service operation period, the server can periodically acquire W network environment monitoring parameters.

[0079] For example, the set of network environment monitoring parameters may include, but is not limited to, one or more of the following network environment monitoring parameters: uplink bandwidth occupied by the first service, downlink bandwidth occupied by the first service, number of sessions occupied by the first service, real-time uplink traffic of the link, real-time downlink traffic of the link, real-time number of sessions of the link, DNS resolution latency of the first service, etc. It is understood that the above parameters are only examples and are not intended to limit this application.

[0080] In one possible embodiment, the server can configure a mapping relationship between W network environment monitoring parameters and M control factors, wherein each control factor corresponds to one or more of the W network environment monitoring parameters.

[0081] Among them, the control factor is used to ensure the primary service. The control factor can also be called the influencing factor or the adjustment factor, etc., and the embodiments of this application do not limit it. For example, the set of control factors includes at least one of the following: link uplink bandwidth, link session count, DNS resolution latency, and link packet loss.

[0082] For example, assuming M=4, the set of control factors includes link uplink bandwidth, link session count, DNS resolution latency, and link packet loss. Network monitoring parameters include the above seven parameters. The mapping relationship between the W network environment monitoring parameters and the M control factors can be shown in Table 1. Here, the uplink bandwidth occupied by the first service, the downlink bandwidth occupied by the first service, the real-time uplink traffic of the link, and the real-time downlink traffic of the link correspond to the link uplink bandwidth; the number of sessions occupied by the first service and the real-time number of sessions of the link correspond to the number of link sessions; and the DNS resolution latency of the first service corresponds to the DNS resolution delay.

[0083] Table 1

[0084]

[0085] As can be seen from Table 1, each network environment monitoring parameter can correspond to a control factor, and each control factor can correspond to one or more network environment monitoring parameters.

[0086] (2) Obtain the rating set, which includes the rating of the first service at multiple time points.

[0087] For example, when obtaining a score set, the server can obtain the latency, packet loss rate, or jitter parameter of the first service for each of multiple time points, and calculate the score of the first service based on the latency, packet loss rate, or jitter parameter of the first service.

[0088] For example, the server can also detect the latency, packet loss rate, and jitter parameters of the first service at each of multiple moments, and use these parameters to calculate the score of the first service.

[0089] The score for the first business segment can be calculated using the following formula 1:

[0090] M = V1W1 + V2W2 + V3W3 (Formula 1);

[0091] Where M is the score of the first service, V1 is the latency of the first service, V2 is the packet loss rate of the first service, V3 is the jitter parameter of the first service, and W1, W2, and W3 are weight values ​​and are positive numbers. The weight values ​​can be empirical values, or they can be determined based on collected historical data (including latency, packet loss rate, and jitter parameter) and user feedback on the first service.

[0092] As shown in Formula 1, the lower the calculated score, the better the user experience of the first service, which means the lower the latency, the lower the packet loss rate, the lower the jitter parameter, and the lower M, the better the user experience of the first service.

[0093] In one embodiment, the first data set obtained by the server may be as shown in Table 2.

[0094] Table 2

[0095]

[0096]

[0097] Similarly, at multiple points in time, the server can obtain multiple data sets corresponding to various services, namely, the set of network environment monitoring parameters and scores for each service. Furthermore, Table 2 above can also be referred to as a multidimensional time-series data matrix table.

[0098] In one possible embodiment, the first data set is used to describe the operation of the first service under a second script of the first service; the second script is a pre-configured script, or the second script is a previously determined script.

[0099] For example, before obtaining the first data set, the server obtains a second script, which indicates the second control path of the first service. The second control path indicates the execution order of N control factors, where N is a positive integer and the N control factors belong to M control factors.

[0100] Step 210: The server determines the importance of M control factors based on the first dataset, where M is a positive integer.

[0101] For example, when the server determines the importance of M control factors based on the first data set, it can determine the importance of W network environment monitoring parameters based on the first data set, and determine the importance of the M control factors based on the importance and mapping relationship of the W network environment monitoring parameters.

[0102] The following is a detailed explanation of the above process:

[0103] First, when determining the importance of W network environment monitoring parameters based on the first dataset, the server can calculate the first difference corresponding to multiple time points. The first difference is the difference between the score of the first service and the predicted value of the score of the first service. The predicted value of the score of the first service can be obtained using an auto-regression and moving average (ARMA) model.

[0104] Furthermore, the server calculates W second differences corresponding to multiple time points, where each of the W second differences corresponds one-to-one with one of the W network environment monitoring parameters. The i-th second difference is the difference between the predicted value of the i-th network environment monitoring parameter and the predicted value of the i-th network environment monitoring parameter. The i-th network environment monitoring parameter is any one of the W network environment monitoring parameters, where i is a positive integer and i ≤ W. The predicted value of the i-th network environment monitoring parameter can be obtained using the Adtributor algorithm.

[0105] Next, the server can determine W ratios corresponding to multiple time points based on the first differences and W second differences corresponding to multiple time points. Here, the i-th ratio corresponding to the j-th time point is the ratio of the i-th second difference to the first difference at the j-th time point, where j is any one of the multiple time points and j is a positive integer. Based on the W ratios corresponding to the multiple time points, W reference values ​​are determined, each corresponding one-to-one with one of the W network environment monitoring parameters. The importance of each of the W reference values ​​is directly proportional to the importance of the network environment monitoring parameter; that is, the larger the reference value, the higher the importance of the network environment monitoring parameter.

[0106] For example, the i-th reference value is the sum of the i-th ratios corresponding to multiple time points, or the i-th reference value is the sum of the ratios of the i-th ratios corresponding to multiple time points that are greater than a set threshold. For example, the set threshold can be 1%.

[0107] Based on the above process, when determining the importance of M control factors according to the importance and mapping relationship of W network environment monitoring parameters, the server can determine the importance score of M control factors. The importance score of each control factor is determined based on the reference value of one or more network environment monitoring parameters corresponding to that control factor. The importance scores of the M control factors are directly proportional to the importance of the M control factors. In other words, the higher the importance score, the higher the importance of the control factor.

[0108] For example, the importance score of each control factor is a weighted sum of reference values ​​of one or more network environment monitoring parameters corresponding to that control factor. The weight value for each network environment monitoring parameter can be an empirical value.

[0109] Using the above method, the importance of M control factors can be obtained.

[0110] For example, the algorithm described above can be the multidimensional time series anomaly root cause analysis method proposed by Microsoft Research, or other algorithms can be used to determine the importance of the M control factors. This application does not limit the specific methods used.

[0111] In one embodiment, taking Table 2 as an example, the server can analyze and calculate the first data set in Table 2 according to the above algorithm to determine the reference values ​​corresponding to the seven network environment monitoring parameter sets respectively. Then, the importance order of the seven network environment monitoring parameters is determined as follows: downlink bandwidth occupied by the first service > uplink bandwidth occupied by the first service > real-time uplink traffic of the link > real-time downlink traffic of the link > DNS resolution latency of the first service > number of real-time sessions occupied by the first service > number of real-time sessions of the link. Furthermore, combined with Table 1, the importance scores of the four control factors are calculated, and the importance order of the four control factors can be obtained as follows: link uplink bandwidth > DNS resolution latency > number of link sessions > link packet loss.

[0112] Step 220: The server determines the first script of the first service based on the importance of the M control factors. The first script represents the first control path of the first service. The first control path indicates the execution order of the K control factors, where K ≤ M, K is a positive integer, and the K control factors are the control factors with the highest importance among the M control factors.

[0113] For example, the server can plan the control path of the first service based on the importance of the obtained M control factors, and obtain the first control path of the first service. The first control path is the execution order of the top K control factors in terms of importance among the M control factors. Here, K can be a preset value.

[0114] Among them, K control factors and N control factors can be the same, the execution order of K control factors indicated by the second control path is different from the execution order of N control factors indicated by the first control path, or K control factors and N control factors can be different.

[0115] In one embodiment, if the second control path indicated by the second script of the first service is link uplink bandwidth—link session count—DNS resolution latency—link packet loss, then the server obtains the control factors in the order of importance of the first data set as: link uplink bandwidth > DNS resolution latency > link session count > link packet loss. Then, the server can obtain the first control path of the first service based on the above four control factors in the order of importance. The first control path can be: link uplink bandwidth—DNS resolution latency—link session count—link packet loss. The control factors indicated by the first control path are the same as those indicated by the second control path, but the execution order is different.

[0116] In one embodiment, if the second control path indicated by the second script of the first service is the number of link sessions—link uplink bandwidth—DNS resolution latency, then the server obtains the control factors in the order of importance of the control factors obtained from the first data set as: number of link sessions > link uplink bandwidth > link packet loss > DNS resolution latency. The server can then obtain the first control path of the first service according to this order. The first control path can be: number of link sessions—link uplink bandwidth—link packet loss—DNS resolution latency, wherein the control factors indicated by the first control path are different from the control factors indicated by the second control path.

[0117] For example, such as Figure 3A As shown, taking the first service as the live streaming service as an example, the first control path indicated by the first script of the live streaming service is: link uplink bandwidth - link session count - DNS resolution latency - link packet loss.

[0118] Referring to Table 3 below, for a control factor of uplink bandwidth, the server can perform corresponding control operations, namely flow control; for a control factor of link session count, the server can perform corresponding control operations, namely session control; for a control factor of DNS resolution latency, the server can perform corresponding control operations, namely DNS domain name adjustment; and for a control factor of link packet loss, the server can perform corresponding control operations, namely outbound link switching. Alternatively, the server performs the following control operations sequentially: flow control, session control, DNS domain name adjustment, and outbound link switching.

[0119] like Figure 3B As shown, the second script for the live streaming service indicates the second control path as follows: link uplink bandwidth — DNS resolution latency — link session count — link packet loss.

[0120] Referring to Table 3 below, for a control factor of uplink bandwidth, the server can perform corresponding control operations, namely flow control and suppressing non-critical application traffic. For a control factor of DNS resolution latency, the server can perform corresponding control operations, namely enabling a DNS proxy. For a control factor of link session count, the server can perform corresponding control operations, namely session control. For a control factor of link packet loss, the server can perform corresponding control operations, namely outbound link switching. Alternatively, the server sequentially performs the following control operations: flow control, suppressing non-critical application traffic, enabling a DNS proxy, session control, and outbound link switching.

[0121] It should be noted that the above control factors and the corresponding control operations are merely examples and are not intended to limit the embodiments of this application.

[0122] Furthermore, after obtaining the first control path of the first service, the server can also determine the control operation corresponding to each control factor in the first control path. The control operations corresponding to each control factor can also be referred to as atomic capability items or atomic adjustment action items.

[0123] In one possible embodiment, the server can configure preset control operation sets corresponding to M control factors. Furthermore, the server can determine the control operations corresponding to the K control factors based on the preset control operation sets corresponding to the K control factors.

[0124] For example, if the control factors include at least one of link uplink bandwidth, link session count, DNS resolution latency, and link packet loss, the preset control operation set corresponding to link uplink bandwidth includes traffic control, suppressing traffic to other services, etc.; the preset control operation set corresponding to link session count includes session control, suppressing sessions to other services, etc.; the preset control operation set corresponding to DNS resolution latency includes DNS domain name adjustment, enabling DNS proxy, etc.; and the preset control operation set corresponding to link packet loss includes outbound link switching, traffic rate limiting for other services, etc.

[0125] The "other businesses" here can refer to non-critical applications or non-critical services, or in other words, services other than critical services. The following example uses non-critical applications as an example to illustrate this.

[0126] In one embodiment, each control factor and its corresponding control operation can be specifically shown in Table 3.

[0127] Table 3

[0128]

[0129] As shown in Table 3, each control factor corresponds to a control operation that can be assigned to an Application Program Interface (API). The corresponding control operation can be executed by calling the corresponding API.

[0130] In one possible embodiment, when the server determines the control operations corresponding to the K control factors based on the preset control operation set corresponding to the K control factors, the server can determine the rate of change of W network environment monitoring parameters and the corresponding resource utilization rate based on the network environment monitoring parameter set.

[0131] For example, the server can determine the rate of change of at least one network environment monitoring parameter and the corresponding resource utilization rate based on a first data set. Specifically, the server can calculate the rate of change of each monitoring parameter and the corresponding resource utilization rate at two adjacent time points.

[0132] In one embodiment, if the set of network environment monitoring parameters is as shown in Table 1 above, the server can obtain the rate of change of each monitoring parameter and the corresponding resource utilization rate, as shown in Table 4.

[0133] Table 4

[0134]

[0135] As shown in Table 4, taking the uplink bandwidth occupied by the first service as an example, the rate of change of the uplink bandwidth occupied by the first service at each time point can be expressed as shown in Formula (2):

[0136]

[0137] Among them, EPa n a represents the rate of change in uplink bandwidth used by the first service. n -a n-1 For T n The uplink bandwidth used by the first service at any given time is compared to that at T. n-1 The change in uplink bandwidth used by the primary service at any given time, T n -T n-1 This represents the difference between two points in time.

[0138] At each time point, the resource utilization rate of the uplink bandwidth occupied by the first service can be expressed as shown in formula (3):

[0139]

[0140] Among them, SRa n a represents the resource utilization rate of the uplink bandwidth used by the first service. n The uplink bandwidth used by the first service is in Tn The value at time t, where Q is the total bandwidth.

[0141] Similarly, Table 1 above includes 7 monitoring parameters, so the server can obtain the rate of change of the 7 monitoring parameters at multiple times and the corresponding resource utilization.

[0142] Furthermore, the server can determine P network environment monitoring parameters from the W network environment monitoring parameters based on their rate of change and corresponding resource utilization. Each of the P network environment monitoring parameters has a rate of change greater than a first threshold, and the corresponding resource utilization rate is greater than a second threshold, where P is a positive integer and P ≤ W. The first and second thresholds are preset values, for example, the first threshold is 30% and the second threshold is 40%, designed to select monitoring parameters with both high rate of change and high resource utilization. This application does not specifically limit the values ​​of the first and second thresholds.

[0143] Next, the server can determine S control factors out of K control factors based on the mapping relationship and P network environment monitoring parameters, where S is a positive integer and S≤K. The server can determine the control operation corresponding to the first control factor based on the preset control operation set corresponding to the first control factor, and determine the control operation corresponding to the second control factor based on the preset control operation set corresponding to the second control factor. Here, the first control factor belongs to the S control factors, the second control factor belongs to the K control factors but not to the S control factors, and the number of control operations corresponding to the second control factor is less than the number of control operations corresponding to the first control factor.

[0144] In one embodiment, taking live streaming as an example, if the first control path of the live streaming service is: link uplink bandwidth—DNS resolution latency—link session count—link packet loss, and the server selects the network environment monitoring parameter with a change rate greater than a first threshold and a resource utilization rate greater than a second threshold as the uplink bandwidth occupied by the first service, then the server can determine that more control operations need to be called for the link uplink bandwidth based on the mapping relationship and the uplink bandwidth occupied by the first service. The number of control operations required for the other three control factors can be less than the number of control operations required for the link uplink bandwidth. Specifically, taking Table 3 above as an example, the control operations corresponding to the link uplink bandwidth can be 2, while the control operations corresponding to the other control factors can be 1. Among them, the control operations corresponding to the link uplink bandwidth are traffic control and suppression of non-critical application traffic, the control operation corresponding to DNS resolution latency is enabling DNS proxy, the control operation corresponding to the link session count is session control, and the control operation corresponding to link packet loss is egress link switching.

[0145] In this embodiment, by setting two thresholds, the rate of change of network environment monitoring parameters and the corresponding resource utilization rate are calculated. This allows the identification of the network environment monitoring parameters (P monitoring parameters) that have the greatest impact on network performance. The network environment monitoring parameters are then mapped to corresponding control factors. Based on this, the control operations corresponding to the control factors are adjusted. For the control factors corresponding to the P network environment monitoring parameters, more control operations are invoked, while for other control factors, fewer control operations are invoked. This approach reduces the resource consumption of other services, allowing more resources to be allocated to the first service, thereby effectively ensuring the performance of the first service.

[0146] In one possible implementation, if there are multiple key services, after the server determines the corresponding scripts for the multiple key services, it can perform an impact significance analysis on the scores of the multiple services over a period of time to assess the interference or influence of adjusting each control factor on each service.

[0147] In one embodiment, if both live streaming service 1 based on application A and live streaming service 2 based on application B (hereinafter referred to as service 1 and service 2) operate in the same network environment, after adjusting the uplink bandwidth, a significance analysis is performed on the user experience scores of service 1 and service 2. If the analysis results show that the scores of both service 1 and service 2 have decreased significantly, for example, the score of service 1 has decreased from 50 to 30 and the score of service 2 has decreased from 60 to 40, it indicates that adjusting the uplink bandwidth has a significant impact on both service 1 and service 2, thus verifying the effectiveness of adjusting the uplink bandwidth. If the analysis results show that the score of service 1 has decreased significantly while the score of service 2 has increased significantly, for example, the score of service 1 has decreased from 50 to 30 and the score of service 2 has increased significantly, then the user experience score of service 1 has decreased significantly while the score of service 2 has increased significantly. If the live stream score rises from 60 to 70, it indicates that adjusting the uplink bandwidth has a significantly greater impact on Service 1, while having a less significant impact on Service 2. In this case, we can compare the importance levels (or service priorities) of Service 1 and Service 2, prioritizing the bandwidth requirements of the more important service to ensure that the performance of critical services is not affected. Alternatively, we can optimize network traffic through routing, sending the traffic of Service 1 and Service 2 through different link exits to reduce resource competition between Service 1 and Service 2. For example, if Service 1's live stream requires higher bandwidth and lower latency, its traffic can be routed to a link with higher bandwidth and lower latency, while the traffic of Service 2 can be transmitted through other links.

[0148] In addition, during the execution of the first script in the first business, the server can periodically monitor the running status of the first business, update the first data set according to a preset time interval, and readjust the control path and corresponding control operation in the first script through the updated first data set to form a new script. This process is repeated, and through this cyclical monitoring and dynamic adjustment, automated protection of critical business operations is achieved.

[0149] In summary, this application provides a service assurance method that can determine the importance of multiple control factors by obtaining a first data set, and plan the control path of the first service and generate a first script based on the importance of the control factors. The above process can automatically ensure the first service, adjust the script used to ensure the first service in a timely manner, and meet the needs of dynamic changes in the network environment.

[0150] Figure 4 and Figure 5 This is a schematic diagram of a possible service assurance device provided in an embodiment of this application. This service assurance device can be used to implement the server functions described in the above method embodiments.

[0151] like Figure 4 As shown, the service support device 400 includes a transceiver unit 410 and a processing unit 420.

[0152] When the business support device 400 is used to achieve Figure 1 The server function in the method embodiment shown is as follows:

[0153] The transceiver unit 410 is used to acquire a first data set, which is used to describe the operation of the first service.

[0154] Processing unit 420 is configured to determine the importance of M control factors based on the first data set, wherein the control factors are used to guarantee the first service, and M is a positive integer; and to determine a first script for the first service based on the importance of the M control factors, wherein the first script represents a first control path for the first service, and the first control path indicates the execution order of K control factors, where K≤M, K is a positive integer, and the K control factors are the control factors with the highest importance among the M control factors.

[0155] In one possible embodiment, the first data set is used to describe the operation of the first service under a second script of the first service; the second script is a pre-configured script, or the second script is a previously determined script.

[0156] The transceiver unit 410 is used to obtain the second script before obtaining the first data set. The second script indicates the second control path of the first service. The second control path indicates the execution order of N control factors, where N is a positive integer. The first control path is different from the second control path, and the N control factors belong to the M control factors.

[0157] In one possible embodiment, the K control factors are the same as the N control factors, and the execution order of the K control factors indicated by the first control path is different from the execution order of the N control factors indicated by the second control path.

[0158] Alternatively, the K control factors may be different from the N control factors.

[0159] In one possible embodiment, the transceiver unit 410 is configured to, when acquiring the first data set, acquire a network environment monitoring parameter set, the network environment monitoring parameter set including W network environment monitoring parameters at multiple times, where W is a positive integer; and acquire a score set, the score set including the score of the first service at the multiple times.

[0160] In one possible embodiment, the processing unit 420 is configured to acquire the latency of the first service, the packet loss rate of the first service, or the jitter parameter of the first service for each of the plurality of times when acquiring the score set.

[0161] The score of the first service is calculated based on the latency of the first service, the packet loss rate of the first service, or the jitter parameter of the first service.

[0162] In one possible embodiment, the processing unit 420 is configured to configure the mapping relationship between the W network environment monitoring parameters and the M control factors, wherein each control factor corresponds to one or more network environment monitoring parameters among the W network environment monitoring parameters.

[0163] In one possible embodiment, the processing unit 420 is configured to, when determining the importance of the M control factors based on the first data set, determine the importance of the W network environment monitoring parameters based on the first data set; and determine the importance of the M control factors based on the importance of the W network environment monitoring parameters and the mapping relationship.

[0164] In one possible embodiment, the processing unit 420 is configured to, when determining the importance of the W network environment monitoring parameters based on the first data set, calculate a first difference corresponding to each of the plurality of time points, wherein the first difference is the difference between the score of the first service and the predicted value of the score of the first service; calculate W second differences corresponding to each of the plurality of time points, wherein the W second differences correspond one-to-one with the W network environment monitoring parameters, the i-th second difference is the difference between the i-th network environment monitoring parameter and the predicted value of the i-th network environment monitoring parameter, the i-th network environment monitoring parameter being any one of the W network environment monitoring parameters, i being a positive integer, and i ≤ W; according to The first difference corresponding to each of the plurality of time points and the W second differences corresponding to each of the plurality of time points determine the W ratios corresponding to each of the plurality of time points; wherein, the i-th ratio corresponding to the j-th time point is the ratio of the i-th second difference corresponding to the j-th time point to the first difference corresponding to the j-th time point, and the j-th time point is any one of the plurality of time points, where j is a positive integer; W reference values ​​are determined based on the W ratios corresponding to each of the plurality of time points, wherein the W reference values ​​correspond one-to-one with the W network environment monitoring parameters, and the i-th reference value is the sum of the i-th ratios corresponding to each of the plurality of time points; wherein, the W reference values ​​are proportional to the importance of the W network environment monitoring parameters.

[0165] In one possible embodiment, the processing unit 420 is configured to determine the importance score of the M control factors when determining the importance of the M control factors based on the importance of the W network environment monitoring parameters and the mapping relationship, wherein the importance score of each control factor is determined based on the reference value of one or more network environment monitoring parameters corresponding to the control factor; wherein the importance score of the M control factors is proportional to the importance of the M control factors.

[0166] In one possible embodiment, the importance score of each control factor is a weighted sum of reference values ​​of one or more network environment monitoring parameters corresponding to that control factor.

[0167] In one possible embodiment, the processing unit 420 is configured to configure a set of preset control operations corresponding to the M control factors respectively.

[0168] In one possible embodiment, the processing unit 420 is configured to determine the control operations corresponding to the K control factors based on the preset control operation sets corresponding to the K control factors respectively.

[0169] In one possible embodiment, the processing unit 420 is configured to, when determining the control operations corresponding to the K control factors based on the preset control operation sets corresponding to the K control factors, determine the rate of change and corresponding resource utilization of the W network environment monitoring parameters based on the network environment monitoring parameter set; and determine P network environment monitoring parameters from the W network environment monitoring parameters based on the rate of change and corresponding resource utilization of the W network environment monitoring parameters, wherein the rate of change of each of the P network environment monitoring parameters is greater than a first threshold and the first resource utilization corresponding to each network environment monitoring parameter is greater than a second threshold, and P is positive. The integers, where P ≤ W; S control factors are determined from the K control factors according to the mapping relationship and the P network environment monitoring parameters, where S is a positive integer, and S ≤ K; the control operation corresponding to the first control factor is determined according to the preset control operation set corresponding to the first control factor, and the control operation corresponding to the second control factor is determined according to the preset control operation set corresponding to the second control factor, wherein the first control factor belongs to the S control factors, the second control factor belongs to the K control factors but not to the S control factors, and the number of control operations corresponding to the second control factor is less than the number of control operations corresponding to the first control factor.

[0170] In one possible embodiment, the M control factors include at least one of link uplink bandwidth, link session count, DNS resolution latency, or link packet loss.

[0171] In one possible embodiment, the preset control operation set corresponding to the uplink bandwidth of the link includes at least one of flow control and suppressing other service traffic;

[0172] The preset control operation set corresponding to the number of link sessions includes at least one of session control and suppressing other service sessions;

[0173] The preset set of control operations corresponding to the DNS resolution delay includes at least one of DNS domain name adjustment and enabling a DNS proxy; and

[0174] The preset set of control operations corresponding to the link packet loss includes at least one of the following: switching the outbound link and limiting the traffic rate of other services.

[0175] For a more detailed description of the transceiver unit 410 and the processing unit 420, please refer to [link / reference needed]. Figure 1 The relevant descriptions in the method embodiments shown are directly obtained and will not be repeated here.

[0176] like Figure 5As shown, the service assurance device 500 includes a processor 510 and a communication interface 520. The processor 510 and the communication interface 520 are coupled to each other. It is understood that the communication interface 520 can be a transceiver or an input / output interface. Optionally, the service assurance device 500 may also include a memory 530 for storing instructions executed by the processor 510, or storing input data required by the processor 510 to execute instructions, or storing data generated after the processor 510 executes instructions.

[0177] When the business support device 400 is used to achieve Figure 1 In the method shown, the processor 510 is used to implement the functions of the processing unit 420, and the communication interface 520 is used to implement the functions of the transceiver unit 410.

[0178] The unit division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into a single processor, exist as separate physical units, or be integrated into a single unit. The integrated units described above can be implemented in hardware or as software functional units.

[0179] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium. The computer program product includes computer program code, which, when executed on a computer, causes the computer to perform any of the business assurance methods discussed above. Since the principle by which the computer-readable storage medium solves the problem is similar to that of the business assurance methods, the implementation of the computer-readable storage medium can be found in the implementation of the methods, and repeated details will not be elaborated further.

[0180] Based on the same inventive concept, this application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, it causes the computer to execute any of the business assurance methods discussed above. Since the principle by which the above-described computer program product solves the problem is similar to that of the business assurance method, the implementation of the above-described computer program product can be referred to the implementation of the method, and repeated details will not be described again.

[0181] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0182] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0183] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0184] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A business assurance method, characterized in that, The method includes: Obtain a first data set, which is used to describe the operation of the first service; The importance of M control factors is determined based on the first data set. The control factors are used to ensure the first service. M is a positive integer. The first script of the first service is determined based on the importance of the M control factors. The first script represents the first control path of the first service. The first control path indicates the execution order of the K control factors, where K ≤ M and K is a positive integer. The K control factors are the control factors with the highest importance among the M control factors.

2. The method as described in claim 1, characterized in that, The first data set is used to describe the operation of the first service under the second script of the first service; the second script is a pre-configured script, or the second script is a previously determined script; Before obtaining the first data set, the process also includes: Obtain the second script, which indicates the second control path of the first service, and the second control path indicates the execution order of N control factors, where N is a positive integer; The first control path is different from the second control path, and the N control factors belong to the M control factors.

3. The method as described in claim 2, characterized in that, The K control factors are the same as the N control factors, but the execution order of the K control factors indicated by the first control path is different from the execution order of the N control factors indicated by the second control path. Alternatively, the K control factors may be different from the N control factors.

4. The method as described in claim 1, characterized in that, Obtaining the first data set includes: Obtain a set of network environment monitoring parameters, which includes W network environment monitoring parameters at multiple times, where W is a positive integer; Obtain a rating set, which includes the ratings of the first service at the plurality of times.

5. The method as described in claim 4, characterized in that, Get the rating set, including: For each of the plurality of time points, obtain the latency of the first service, the packet loss rate of the first service, or the jitter parameter of the first service; The score of the first service is calculated based on the latency of the first service, the packet loss rate of the first service, or the jitter parameter of the first service.

6. The method as described in claim 4, characterized in that, The method further includes: Configure the mapping relationship between the W network environment monitoring parameters and the M control factors, wherein each control factor corresponds to one or more network environment monitoring parameters among the W network environment monitoring parameters.

7. The method as described in claim 6, characterized in that, Determining the importance of the M control factors based on the first dataset includes: The importance of the W network environment monitoring parameters is determined based on the first data set; The importance of the M control factors is determined based on the importance of the W network environment monitoring parameters and the mapping relationship.

8. The method as described in claim 7, characterized in that, The importance of the W network environment monitoring parameters is determined based on the first dataset, including: Calculate the first difference corresponding to each of the plurality of time points, where the first difference is the difference between the score of the first service and the predicted value of the score of the first service. Calculate W second differences corresponding to the plurality of time points, wherein the W second differences correspond one-to-one with the W network environment monitoring parameters, the i-th second difference is the difference between the i-th network environment monitoring parameter and the predicted value of the i-th network environment monitoring parameter, the i-th network environment monitoring parameter is any one of the W network environment monitoring parameters, i is a positive integer, and i≤W; The W ratios corresponding to the plurality of times are determined based on the first differences corresponding to the plurality of times and the W second differences corresponding to the plurality of times; wherein, the i-th ratio corresponding to the j-th time is the ratio of the i-th second difference corresponding to the j-th time to the first difference corresponding to the j-th time, and the j-th time is any one of the plurality of times, and j is a positive integer; W reference values ​​are determined based on the W ratios corresponding to the plurality of times, wherein each of the W reference values ​​corresponds one-to-one with one of the W network environment monitoring parameters, and the i-th reference value is the sum of the i-th ratios corresponding to the plurality of times; wherein the W reference values ​​are proportional to the importance of the W network environment monitoring parameters.

9. The method as described in claim 8, characterized in that, The importance of the M control factors is determined based on the importance of the W network environment monitoring parameters and the mapping relationship, including: The importance scores of the M control factors are determined, wherein the importance score of each control factor is determined based on the reference values ​​of one or more network environment monitoring parameters corresponding to that control factor; and wherein the importance scores of the M control factors are proportional to the importance of the M control factors.

10. The method as described in claim 6, characterized in that, The method further includes: Configure the preset control operation sets corresponding to the M control factors respectively.

11. The method as described in claim 10, characterized in that, The method further includes: The control operations corresponding to the K control factors are determined based on the preset control operation sets corresponding to the K control factors.

12. The method as described in claim 11, characterized in that, The control operations corresponding to the K control factors are determined based on the preset control operation sets corresponding to the K control factors, including: Determine the rate of change of the W network environment monitoring parameters and the corresponding resource utilization rate based on the set of network environment monitoring parameters; Based on the change rate of the W network environment monitoring parameters and the corresponding resource utilization rate, P network environment monitoring parameters are determined from the W network environment monitoring parameters. The change rate of each of the P network environment monitoring parameters is greater than a first threshold and the first resource utilization rate corresponding to each network environment monitoring parameter is greater than a second threshold. P is a positive integer, where P≤W. Based on the mapping relationship and the P network environment monitoring parameters, S control factors are determined from the K control factors, where S is a positive integer and S≤K; The control operation corresponding to the first control factor is determined according to the preset control operation set corresponding to the first control factor, and the control operation corresponding to the second control factor is determined according to the preset control operation set corresponding to the second control factor. The first control factor belongs to the S control factors, the second control factor belongs to the K control factors but does not belong to the S control factors, and the number of control operations corresponding to the second control factor is less than the number of control operations corresponding to the first control factor.

13. The method as described in claim 10, characterized in that, The M control factors include at least one of the following: link uplink bandwidth, link session count, DNS resolution latency, or link packet loss.

14. The method as described in claim 13, characterized in that, The preset control operation set corresponding to the uplink bandwidth of the link includes at least one of flow control and suppressing other service traffic; The preset control operation set corresponding to the number of link sessions includes at least one of session control and suppressing other service sessions; The preset control operation set corresponding to the DNS resolution delay includes at least one of DNS domain name adjustment and enabling DNS proxy; as well as The preset set of control operations corresponding to the link packet loss includes at least one of the following: switching the outbound link and limiting the traffic rate of other services.

15. A business support device, characterized in that, The device includes: a transceiver unit and a processing unit; The transceiver unit is used to acquire a first data set, which is used to describe the operation of the first service. The processing unit is configured to determine the importance of M control factors based on the first data set, wherein the control factors are used to guarantee the first service, and M is a positive integer; and to determine a first script for the first service based on the importance of the M control factors, wherein the first script represents a first control path for the first service, and the first control path indicates the execution order of K control factors, where K ≤ M, K is a positive integer, and the K control factors are the control factors with the highest importance among the M control factors.

16. A business support device, characterized in that, include: Memory, used to store program instructions; A processor is configured to invoke program instructions stored in the memory and execute the steps of the method according to any one of claims 1-14.

17. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a computer, cause the computer to perform the method as described in any one of claims 1-14.

18. A computer program product, characterized in that, The computer program product includes: computer program code, which, when run on a computer, causes the computer to perform the method described in any one of claims 1-14.

Images