Data processing method and related device

Abstract

The invention discloses a data processing method and a related device, and the method comprises the steps: building a target structure tree of a to-be-monitored system, enabling each node in the target structure tree to correspond to a performance index of the to-be-monitored system, and enabling a hierarchical structure between the nodes in the target structure tree to correspond to an incidence relation of the performance index; on the basis of a hierarchical structure between nodes of the target structure tree, determining influence parameters of nodes of a next hierarchy of the current hierarchy on the nodes of the current hierarchy; based on the influence parameters and the initial weights of the nodes, target weights of the nodes of each level of a target structure tree are determined according to a target sequence, the target structure tree comprises n layers of nodes, and the target sequence represents a sequence of determining the target weights of the nodes of each level upwards layer by layer from the nth layer of nodes, the target weights of the nodes of the first level are obtained; the weight represents the influence degree of the performance index corresponding to the node on the monitoring result.

Description

Technical Field

[0001] The present application relates to a data processing method and related devices. Background Art

[0002] The health status of the monitored system is the main indicator for measuring the system's operating status. The system health that evaluates the system's health status is usually determined by the evaluation indicators of each level of the system. However, the importance of each evaluation indicator is usually determined by empirical values. For different monitored system constructions or different evaluation indicators, the corresponding empirical values ​​need to be re-determined by professionals, which reduces the efficiency and accuracy of system status evaluation. Summary of the invention

[0003] In view of this, this application provides the following technical solutions:

[0004] A data processing method, comprising:

[0005] Constructing a target structure tree for the system to be monitored, wherein each node in the target structure tree corresponds to a performance indicator of the system to be monitored, and the hierarchical structure between the nodes in the target structure tree corresponds to the association relationship between the performance indicators;

[0006] Based on the hierarchical structure between the nodes of the target structure tree, determining the influence parameters of the nodes of the next level of the current level on the nodes of the current level;

[0007] Based on the influencing parameters and the initial weights of the nodes, the target weights of the nodes at each level of the target structure tree are determined in a target order, wherein the target structure tree includes n layers of nodes, the nth layer of nodes does not include the nodes of the next layer, and the target order represents the order of determining the target weights of the nodes at each level from the nth layer of nodes upward layer by layer until the target weights of the nodes at the first level are obtained; the weight represents the degree of influence of the performance indicators corresponding to the nodes on the monitoring results.

[0008] Optionally, the method further comprises:

[0009] Obtaining a current performance score of each node of the target structure tree;

[0010] Determining a target performance score for each node based on the target weight of each node and the current performance score;

[0011] Based on the target performance score of each node, the monitoring result of the system to be monitored is determined.

[0012] Optionally, the determining, based on the hierarchical structure between the nodes of the target hierarchical tree, an influence parameter of the nodes of the next level of the current level on the nodes of the current level includes:

[0013] Obtaining monitoring data corresponding to the system to be monitored within a target time period, wherein the monitoring data includes a performance score of a performance indicator corresponding to each monitoring period;

[0014] Obtaining deviation data of performance scores of each node at a level below the current level in the monitoring data;

[0015] Based on the deviation data, influence parameters of nodes of the next level of the current level on nodes of the current level are determined.

[0016] Optionally, determining the target performance score of each node based on the target weight of each node and the current performance score includes:

[0017] Obtaining monitoring data corresponding to the system to be monitored within a target time period, wherein the monitoring data includes a performance score of a performance indicator corresponding to each monitoring period;

[0018] Determining a performance correction parameter for each node based on the performance score of each node in the monitoring data;

[0019] Determining an initial performance score for each node based on the target weight of each node and the current performance score;

[0020] Based on the performance correction parameter and the initial performance score, a target performance score for each node is determined.

[0021] Optionally, obtaining deviation data of performance scores of each node at a level below the current level in the monitoring data includes:

[0022] Based on the performance scores of the nodes of the next level of the current level in the monitoring data, determine the average performance score, the maximum performance score and the minimum performance score of the nodes of the next level corresponding to the monitoring data;

[0023] Deviation data is determined based on the performance average score, the maximum performance score and the minimum performance score.

[0024] Optionally, determining the performance correction parameter of each node based on the performance score of each node in the monitoring data includes:

[0025] Determine performance score grouping information based on the performance score of each node in the monitoring data, wherein the grouping information includes at least one score group, and each score group has a corresponding performance score range;

[0026] Determine the performance score parameter of each node according to the corresponding relationship between the performance score of each node and the score group;

[0027] Based on the performance score parameter and the number of nodes, a performance correction parameter for each node is determined.

[0028] Optionally, the step of constructing a target structure tree of the system to be monitored includes:

[0029] Obtain candidate performance indicators of the system to be monitored;

[0030] Screening the candidate performance indicators to obtain performance indicators;

[0031] Based on the correlation relationship between the various performance indicators, determine the hierarchical relationship and the parallel relationship of the performance indicators, wherein the hierarchical relationship represents the inclusion relationship of the performance indicators, and the parallel relationship represents that the performance indicators belong to the same category;

[0032] A target structure tree is constructed according to the hierarchical relationship and parallel relationship of the performance indicators.

[0033] A data processing device, comprising:

[0034] A construction unit, used to construct a target structure tree for the system to be monitored, each node in the target structure tree corresponds to a performance indicator of the system to be monitored, and the hierarchical structure between the nodes in the target structure tree corresponds to the association relationship between the performance indicators;

[0035] A first determining unit, configured to determine, based on the hierarchical structure between the nodes of the target structure tree, an influence parameter of the nodes of the next level of the current level on the nodes of the current level;

[0036] The second determination unit is used to determine the target weights of nodes at each level of the target structure tree according to the target order based on the influencing parameters and the initial weights of the nodes, wherein the target structure tree includes n layers of nodes, the nth layer of nodes does not include the nodes of the next layer, and the target order represents the order of determining the target weights of nodes at each level from the nth layer of nodes upward layer by layer until the target weights of the nodes at the first level are obtained; the weight represents the degree of influence of the performance indicators corresponding to the nodes on the monitoring results.

[0037] A readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the data processing method described in any one of the above is implemented.

[0038] An electronic device, comprising:

[0039] A memory, used to store applications and data generated by the operation of the applications;

[0040] The processor is used to execute the application program to implement the data processing method as described in any one of the above. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0042] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0043] Figure 2 A schematic diagram of a target structure tree provided in an embodiment of the present application;

[0044] Figure 3 A schematic diagram of a monitoring health topology tree of a system to be monitored provided in an embodiment of the present application;

[0045] Figure 4 A schematic diagram of a basic service server node provided in an embodiment of the present application;

[0046] Figure 5 A schematic diagram of a basic service server node weight comparison provided in an embodiment of the present application;

[0047] Figure 6 A schematic diagram of a basic module health tree structure provided in an embodiment of the present application;

[0048] Figure 7 A schematic diagram of a basic module health weight comparison provided in an embodiment of the present application;

[0049] Figure 8 A schematic diagram of a weight comparison of network access server nodes provided in an embodiment of the present application;

[0050] Fig. 9 A schematic diagram of a health tree score curve provided in an embodiment of the present application;

[0051] Fig.10 A schematic diagram of an average weighted health tree score curve provided in an embodiment of the present application;

[0052] Fig.11 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] The terms "first" and "second" in this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may include steps or units that are not listed.

[0055] The embodiment of the present application provides a data processing method, which is a method for processing monitoring data in a system to be monitored, so as to obtain relevant data for evaluating the status of the system to be monitored. The system to be monitored may be a business system in the monitoring field, or a data system in a data platform, etc. The method can fully analyze the performance indicators in the system to be monitored, and based on the correlation and related influence between each performance indicator, accurately obtain the weight of each performance indicator, so as to accurately evaluate the performance status of the system to be monitored.

[0056] See also Figure 1 , is a flow chart of a data processing method provided in an embodiment of the present application, the method may include the following steps:

[0057] S101. Construct a target structure tree for the system to be monitored.

[0058] S102: Based on the hierarchical structure between the nodes of the target structure tree, determine the influence parameters of the nodes of the next level of the current level on the nodes of the current level.

[0059] S103 . Based on the influencing parameters and the initial weights of the nodes, determine the target weights of the nodes at each level of the target receiving number in a target order.

[0060] In order to accurately evaluate the status of the system to be monitored, it is necessary to determine the performance indicators used to evaluate the system to be monitored, wherein evaluating the status of the system to be monitored may include: evaluating whether the current system to be monitored is in a stable operating state, or evaluating whether the current system to be monitored is in a healthy state, or evaluating whether the current system to be monitored is in a preset working state, etc. Performance indicators are key factors used to measure whether the system to be monitored is operating effectively. Different types of systems to be monitored have different corresponding performance indicators. For example, if the system to be monitored is a data processing system, the performance indicators may include indicators such as data transmission efficiency indicators, data processing efficiency indicators, data storage capacity, and data processing threads. If the system to be monitored is a business system, the performance indicators may include business layer indicators, user layer indicators, application layer indicators, infrastructure layer indicators, etc.

[0061] Since there are usually multiple performance indicators of the system to be monitored, and there are certain relationships between the various performance indicators, in order to facilitate the analysis of each performance indicator, in the embodiment of the present application, each performance indicator is represented by a target structure tree, wherein the target structure tree can adopt a multi-branch tree structure, each node in the target structure tree corresponds to the performance indicator of the system to be monitored, and the hierarchical structure between the nodes in the target structure tree corresponds to the association relationship of the performance indicators. In one implementation of the embodiment of the present application, a target structure tree for the system to be monitored is constructed, including: obtaining candidate performance indicators of the system to be monitored; screening the candidate performance indicators to obtain performance indicators; based on the association relationship of each performance indicator, determining the hierarchical relationship and parallel relationship of the performance indicators, the hierarchical relationship represents the inclusion relationship of the performance indicators, and the parallel relationship represents that the performance indicators belong to the same category; constructing a target structure tree according to the hierarchical relationship and parallel relationship of the performance indicators. Among them, since there are many performance indicators of the system, in order to improve the processing efficiency, the performance indicators can be screened according to the importance of the performance indicators in the system and the utilization rate, and the target structure tree can be constructed according to the screened performance indicators. The hierarchical relationship refers to the inclusion relationship between nodes, and the nodes in the parallel relationship are nodes of the same level. See Figure 2, is a schematic diagram of a target structure tree provided in an embodiment of the present application. In the target structure tree, the node 1 of the first level represents the total performance index of the state to be evaluated of the system to be monitored, such as node 1 identifies the health of the system to be detected, and the nodes of the second level are child nodes of node 1 (also referred to as child nodes), that is, the performance index dimension corresponding to node 1 includes the performance index dimension of each child node of the second level, such as the nodes of the second level include nodes 10, nodes 11, nodes 12 and nodes 13, such as in the system to be detected, node 10 can represent the business layer performance index, node 11 can represent the user layer performance index, node 12 can represent the application layer performance index, and node 13 can represent the business index of the infrastructure layer. The nodes of the second level can be in parallel relationship. Furthermore, the nodes of the third level are child nodes of the corresponding nodes of the second level, such as nodes 101 and 102 are child nodes of node 10, indicating that the business layer performance index includes business index cluster 1 and business index cluster 2. Furthermore, the nodes of the fourth level are child nodes of the corresponding nodes of the third level, such as nodes 1011 and 1012 representing child nodes of node 101, which can specifically represent the specific business indicators included in business indicator cluster 1. By constructing a target structure tree with the system to be monitored, the correlation between the various performance indicators of the system to be monitored can be clarified, and the mutual influence between the performance indicators can be better analyzed based on the correlation, thereby determining the performance status of the system to be monitored.

[0062] After constructing the target structure tree, the mutual influence parameters between nodes at each level can be determined according to the hierarchical relationship between nodes, and then the target weights of nodes at each level can be determined according to the target order. Among them, the target structure tree includes n layers of nodes, n is a positive integer, and the nth-level nodes are nodes that do not include the next level (also called leaf nodes). The target order represents the order of determining the target weights of nodes at each level from the nth-level nodes layer by layer until the target weight of the previous level is obtained. The weight represents the degree of influence of the performance indicator corresponding to the node on the monitoring result. If the weight value of a node is large, it means that the performance indicator corresponding to the node is more important in evaluating the status of the system to be monitored.

[0063] When determining target weight for each node of this target structure tree, because the score of parent node (node ​​of current level) is obtained by weighted calculation of the current score of its directly connected child node (node ​​of next level of current level).The score of parent node will lose a part of numerical fluctuation like this, as parent node has 10 child nodes, assuming that these child node initial weights are all 0.1, if the score of a certain child node is 0, when all the other are full marks 100 points, the score of parent node at this time is 90.This can cause when calculating weight layer by layer, the node closer to the upper layer of target structure tree, its numerical value can be more regionally stable, causes the weight of upper layer node to be averaged, loses the index information of important node.In order to solve the above problem, in the process of calculating weight in the embodiment of the present application, when the weight of node, all can determine based on the influence parameter of the node of next level to it, can make the weight obtained more accurate like this, and meet the assessment scene of system to be monitored, make subsequent assessment result more accurate.

[0064] Furthermore, when determining the state of the system to be monitored, the method further includes: obtaining the current performance score of each node in the target structure tree, determining the target performance score of each node based on the target weight and current performance score of each node, and determining the monitoring result of the system to be monitored based on the target performance score of each node. Wherein, the performance score is a score determined according to the monitoring data of the performance index corresponding to the node in the current system to be monitored. If the monitoring index is a network transmission index, the score of the network transmission index can be determined according to the current data upload and download efficiency and network status of the system to be monitored, and then the target performance score of the network transmission index is calculated according to the weight of the network transmission index, and the health of the current system to be monitored is determined in combination with the target performance scores corresponding to other performance indicators, so as to obtain the corresponding monitoring result. Wherein, since the information of the next layer of nodes is reflected in the information of the nodes of the previous layer, when determining the target performance index of the node, only the target performance score of the performance index corresponding to the node under the maximum dimension can be determined, so that computing resources can be saved. It should be noted that the weight calculation process of the previous layer of nodes fully considers the influence of the next layer of nodes on it, so as to ensure the accuracy of the calculation.

[0065] The data processing method of the embodiment of the present application is described below in combination with actual application scenarios. Figure 3 , is a schematic diagram of a monitoring health topology tree of a system to be monitored provided in an embodiment of the present application. Figure 3This is a schematic diagram of system health from the perspective of system monitoring. The application system collects the underlying infrastructure monitoring indicators, application layer monitoring indicators, user experience monitoring indicators and business core monitoring indicators, and the nodes corresponding to all performance indicators can be calculated using a percentage system to obtain the node health status (100 points means that the node where the indicator is located is completely normal, and 0 points means that the node where the indicator is located is completely invalid). These monitoring indicators (i.e. performance indicators) can come from different monitoring tools, and the health of the system to be monitored can be evaluated by uniformly summarizing the monitoring indicators.

[0066] First, construct the target structure tree corresponding to the system to be detected, and obtain Figure 3 The monitoring health topology tree is shown. Then, when calculating the node weights of the tree, it is necessary to optimize the weights according to the association relationship of the nodes, and finally obtain an indicator tree model suitable for the application itself, which can more accurately realize the health evaluation of this application.

[0067] In one implementation of the embodiment of the present application, based on the hierarchical structure between nodes of the target number of hierarchical levels, determining the influence parameters of the nodes of the next level of the current level on the nodes of the current level includes:

[0068] Obtain monitoring data corresponding to the system to be monitored within the target time period; obtain deviation data of the performance scores of each node of the next level of the current level in the monitoring data; based on the deviation data, determine the influence parameters of the nodes of the next level of the current level on the nodes of the current level.

[0069] The target time period can be a specified monitoring cycle, or it can be between the current moments, that is, the monitoring data corresponding to the system to be monitored within the target time period is historical monitoring data, that is, the relevant data of all performance indicators of the system to be monitored in the past period of time is obtained, such as the monitoring data of 150 sample points, where each sample point can correspond to a monitoring moment. In this way, the performance scores corresponding to each monitoring indicator can be determined by analyzing the historical monitoring data, which is used to analyze the influencing parameters between subsequent nodes. The deviation data of the performance score can determine the differentiation of the performance indicators corresponding to the nodes at the same level during the evaluation, thereby determining the influencing parameters of the nodes at the upper level. Further, the deviation data of the performance score of each node at the next level of the current level in the monitoring data is obtained, including: based on the performance scores of each node at the next level of the current level in the monitoring data, determining the average performance score, the maximum performance score and the minimum performance score corresponding to each node at the next level and the monitoring data; based on the average performance score, the maximum performance score and the minimum performance score, the deviation data is determined.

[0070] For example, Figure 3Taking the bottom part as an example, the bottom performance indicators corresponding to the business layer performance indicators are respectively represented as business monitoring indicator 1, business monitoring indicator 2, ..., business monitoring indicator n, that is, n performance indicators of business indicator cluster 1 corresponding to the business layer are obtained. The scores of historical time statistics are recorded as m objects to be evaluated, that is, m dimensions, and the business layer is one of the dimensions. The comparative performance σ of the jth performance indicator is calculated by the following formula (1): j ,in, Represents the average performance score of j indicators.

[0071]

[0072] The contradiction parameter f of the jth performance indicator can be calculated by the following formula (2): j , where r ij It represents the correlation coefficient between performance index i and performance index j. Here, the Pearson correlation coefficient is used, which is a linear correlation coefficient:

[0073]

[0074] The weight score w of the jth performance indicator is calculated by formula (3): j :

[0075]

[0076] The initial weights of each performance indicator can be obtained through the above historical data, as shown in formula (3): j .

[0077] The score S of business indicator cluster 1 at the i-th moment can be calculated by formula (4): i ,in, represents the highest score among all leaf nodes (i.e., the corresponding nodes of the next level) of business indicator cluster 1 at time i; represents the lowest score among all leaf nodes of business indicator cluster 1 at time i; the value range of L is 0-1, which indicates the difference degree of scores of all leaf nodes of business indicator cluster 1 at time i. The larger the value of L, the greater the difference of scores of leaf nodes of business indicator cluster 1. The final score S of business indicator cluster 1 is i will be lower (S i The minimum value of is 0), where the calculation formula of L is as shown in formula (5).

[0078]

[0079] Repeat the above process until the target weights of all nodes in the target structure tree are calculated. In the above formula (5), the average performance score, maximum performance score and minimum performance score of the nodes at the next level (i.e., business monitoring indicators) corresponding to business indicator cluster 1 are used to calculate the parameters that characterize the influence of the nodes at the next level on the nodes at the current level, which can also be called the node attenuation coefficient L, that is, the value of L is mainly related to the difference between the maximum performance score and the minimum performance score of the child nodes connected to the node. In this way, the weights of the upper nodes can be optimized through the performance characteristics of the lower nodes. This solves the problem that the weights of the upper nodes tend to be averaged and the information of important nodes is lost.

[0080] Furthermore, in order to be able to more accurately calculate the target performance score of the node, the performance score of the node is also corrected by the performance correction parameter of the node in the embodiment of the present application. This is because nodes with large numerical fluctuations and large conflicts with other nodes in historical data are given higher weights. For example, when calculating the target performance score that represents the health of the system to be monitored, the negative impact of a node with a score of 0 is often more serious than the impact of two nodes with a score of 50. Therefore, in the embodiment of the present application, the impact of low-scoring nodes is increased by performance correction parameters when calculating the final score of the node, where the performance correction parameter can also be called a penalty coefficient in some application scenarios.

[0081] In one implementation of the present application, based on the target weight and current performance score of each node, the target performance score of each node is determined, including: obtaining monitoring data corresponding to the system to be monitored within the target time period; determining the performance correction parameters of each node based on the performance score of each node in the monitoring data; determining the initial performance score of each node based on the target weight of each node and the current performance score; determining the target performance score of each node based on the performance correction parameters and the initial performance score. Wherein, the monitoring data includes the performance score of the performance indicator corresponding to each monitoring period. Further, the performance correction parameters of each node are determined based on the performance score of each node in the monitoring data, including: determining the performance score grouping information based on the performance score of each node in the monitoring data, determining the performance score parameters of each node according to the corresponding relationship between the performance score of each node and the score group; determining the performance correction parameters of each node based on the performance score parameters and the number of nodes. Wherein, the grouping information includes at least one grouping value, and each grouping value has a corresponding performance grouping range.

[0082] In the embodiment of the present application, by grouping the performance scores of nodes at the same level and then determining the performance correction coefficient based on the grouping information, it is possible to ensure that the data is evenly distributed and avoid excessive data processing volume in certain groups, thereby affecting the accuracy of the results.

[0083] Still Figure 3 For example, in the actual calculation of the target performance score that represents the state of the system to be monitored (such as health), the performance correction parameter (also called the node attenuation coefficient) can be calculated first, represented by P. According to the performance score of each node in the monitoring data, the performance score is grouped, and each group has corresponding grouping information. The grouping information can guarantee the number of nodes in the group. For example, when the score is 90-100, the grouping information B=3; the group corresponding to 60-90 points, B=2; the group corresponding to 30-60 points, B=1; the group corresponding to 0-20 points, B=0. The performance correction parameter P is calculated according to formula (6), where B j Represents the grouping information of the j-th performance indicator.

[0084]

[0085] Then, the score S of business indicator cluster 1 can be calculated. The calculation formula is shown in formula (7), where P is the performance correction parameter, w j is the target weight of the jth evaluation index, x j Represents the score of the jth performance indicator.

[0086]

[0087] By repeating the above process, the scores of other business indicator clusters can be calculated. Similarly, the scores of the upper level, namely the business layer, are calculated, and then the scores of the user layer, the application layer, and the infrastructure layer are calculated in sequence until the final system health is calculated.

[0088] The data processing method provided in the embodiment of the present application can accurately analyze the hierarchical relationship of various performance indicators in the system to be monitored and the related influences between each other, so as to be more accurate and more in line with actual application scenarios when evaluating the system status.

[0089] See also Figure 4 , is a schematic diagram of a basic service server node provided in an embodiment of the present application, and the basic service server node is composed of 12 leaf nodes. When verifying the technical solution of the embodiment of the present application, experts score the importance of all 12 leaf nodes, with a full score of 100. The higher the score, the higher the importance of the node. The expert scoring results are finally mapped to weights for comparison. The results are as follows: Figure 5As shown in the figure, the blue line indicates the average weight method; the yellow line is the weight result converted after expert scoring; and the green line is the weight result automatically calculated by this application. It can be found that this application can match the expert experience results well in the weights of more important nodes such as Net (network), OS (operating system), and Process (process).

[0090] At the same time, Figure 3 The weight analysis is performed on the subtree structure close to the upper level in the healthy tree shown. The tree structure is also evaluated and scored based on expert experience and converted into corresponding weights for comparison and review. Figure 6 For the tree structure of the basic module health, it can be found that this node is affected by 6 child nodes. Figure 7 The figure shows the weight scores calculated for different solutions. The blue line indicates the average weight method; the yellow line is the weight result after expert scoring; the green line indicates the solution without node score attenuation (i.e., without performance correction parameter); and the red line indicates the solution with performance correction parameter L. Figure 7 It can be seen that when the node-free attenuation scheme calculates the weight of the tree structure, the final result tends to be average, which cannot effectively reflect the importance of the node. After adding the calculation result of the performance correction parameter L, the overall weight calculation result is more differentiated and can better reflect the importance of the child node.

[0091] Correspondingly, in the embodiment of the present application, automatic calculation can also solve the situation of continuous abnormal value of the node. In the actual scenario, the node of the network access server (such as Linux-Disk) has a low score for a long time in the historical data due to data collection or calculation problems, as shown in Table 1. In the embodiment of the present application, if it is detected that the score of the node has not changed for a long time, the weight will be automatically reduced, which is more in line with the actual application scenario.

[0092] Table 1

[0093]

[0094] See also Figure 8 , is a schematic diagram of the weight of the network access server node provided in the embodiment of the present application. The system health and system abnormality status calculated by the scheme in the actual scenario are compared, and the results are as follows Fig. 9 and Fig.10As shown. The weight calculation method of the embodiment of the present application can clearly analyze the system abnormality in Table 2, and give a lower health tree score to remind the system abnormality. Due to the influence of the Linux-Disk node data connected to the network, the average weight method has a low overall system health score, and when the system abnormality occurs at 19:45, the system health score obviously cannot reflect the problems in the system well, which also verifies the effectiveness of the present application.

[0095] Table 2

[0096] Time Node Fault conditions 2:00 Abnormal alarm 19:45 Abnormal alarm 22:50 Abnormal alarm

[0097] Correspondingly, a data processing device is also provided in the embodiment of the present application, see Fig.11 ,include:

[0098] A construction unit 201 is used to construct a target structure tree for the system to be monitored, each node in the target structure tree corresponds to a performance indicator of the system to be monitored, and the hierarchical structure between the nodes in the target structure tree corresponds to the association relationship between the performance indicators;

[0099] A first determining unit 202 is used to determine the influence parameters of the nodes of the next level of the current level on the nodes of the current level based on the hierarchical structure between the nodes of the target structure tree;

[0100] The second determination unit 203 is used to determine the target weights of the nodes at each level of the target structure tree according to the target order based on the influencing parameters and the initial weights of the nodes, wherein the target structure tree includes n layers of nodes, the nth layer nodes do not include the nodes of the next layer, and the target order represents the order of determining the target weights of the nodes of each layer from the nth layer nodes upward layer by layer until the target weights of the nodes of the first layer are obtained; the weight represents the degree of influence of the performance indicators corresponding to the nodes on the monitoring results.

[0101] Optionally, the device further comprises:

[0102] A first acquisition unit, configured to obtain a current performance score of each node in the target structure tree;

[0103] A third determining unit, configured to determine a target performance score for each node based on the target weight of each node and the current performance score;

[0104] The fourth determining unit is used to determine the monitoring result of the system to be monitored based on the target performance score of each node.

[0105] Optionally, the first determining unit includes:

[0106] A first acquisition subunit is used to obtain monitoring data corresponding to the system to be monitored within a target time period, wherein the monitoring data includes a performance score of a performance indicator corresponding to each monitoring period;

[0107] A second acquisition subunit is used to obtain deviation data of performance scores of each node in the next level of the current level in the monitoring data;

[0108] The first determination subunit is used to determine, based on the deviation data, an influence parameter of the nodes of the next level of the current level on the nodes of the current level.

[0109] Optionally, the third determining unit includes:

[0110] A third acquisition subunit is used to obtain monitoring data corresponding to the system to be monitored within a target time period, wherein the monitoring data includes a performance score of a performance indicator corresponding to each monitoring period;

[0111] A second determination subunit is used to determine a performance correction parameter of each node based on the performance score of each node in the monitoring data;

[0112] a third determining subunit, configured to determine an initial performance score of each node based on the target weight of each node and the current performance score;

[0113] The fourth determining subunit is used to determine a target performance score of each node based on the performance correction parameter and the initial performance score.

[0114] Optionally, the second acquiring subunit is configured to:

[0115] Based on the performance scores of the nodes of the next level of the current level in the monitoring data, determine the average performance score, the maximum performance score and the minimum performance score of the nodes of the next level corresponding to the monitoring data;

[0116] Deviation data is determined based on the performance average score, the maximum performance score and the minimum performance score.

[0117] Optionally, the second determining subunit is configured to:

[0118] Determine performance score grouping information based on the performance score of each node in the monitoring data, wherein the grouping information includes at least one score group, and each score group has a corresponding performance score range;

[0119] Determine the performance score parameter of each node according to the corresponding relationship between the performance score of each node and the score group;

[0120] Based on the performance score parameter and the number of nodes, a performance correction parameter for each node is determined.

[0121] Optionally, the construction unit comprises:

[0122] A fourth acquisition subunit, used to obtain candidate performance indicators of the system to be monitored;

[0123] A screening subunit, used to screen the candidate performance indicators to obtain performance indicators;

[0124] A fifth determining subunit, configured to determine a hierarchical relationship and a parallel relationship of the performance indicators based on the association relationship of the various performance indicators, wherein the hierarchical relationship represents an inclusion relationship of the performance indicators, and the parallel relationship represents that the performance indicators belong to the same category;

[0125] The construction subunit is used to construct a target structure tree according to the hierarchical relationship and parallel relationship of the performance indicators.

[0126] It should be noted that the specific implementation of each unit and sub-unit in this embodiment can refer to the corresponding content in the previous text and will not be described in detail here.

[0127] In another embodiment of the present application, a readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the data processing method as described in any one of the above items is implemented.

[0128] In another embodiment of the present application, an electronic device is further provided, and the electronic device may include:

[0129] A memory, used to store applications and data generated by the operation of the applications;

[0130] The processor is used to execute the application program to implement the data processing method as described in any one of the above.

[0131] It should be noted that the specific implementation of the processor in this embodiment can refer to the corresponding content in the previous text and will not be described in detail here.

[0132] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0133] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0134] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0135] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing method, comprising: Constructing a target structure tree for the system to be monitored, wherein each node in the target structure tree corresponds to a performance indicator of the system to be monitored, and the hierarchical structure between the nodes in the target structure tree corresponds to the association relationship between the performance indicators; Based on the hierarchical structure between the nodes of the target structure tree, determining the influence parameters of the nodes of the next level of the current level on the nodes of the current level; Based on the influencing parameters and the initial weights of the nodes, the target weights of the nodes at each level of the target structure tree are determined in a target order, wherein the target structure tree includes n-level nodes, the n-th-level nodes are nodes that do not include the next level, and the target order represents the order of determining the target weights of the nodes at each level from the n-th-level nodes upwards layer by layer until the target weights of the nodes at the first level are obtained; The weight represents the degree of influence of the performance indicator corresponding to the node on the monitoring result.

2. The method according to claim 1, further comprising: Obtaining a current performance score of each node of the target structure tree; Determining a target performance score for each node based on the target weight of each node and the current performance score; Based on the target performance score of each node, the monitoring result of the system to be monitored is determined.

3. The method according to claim 1, wherein determining the influence parameter of the node of the next level of the current level on the node of the current level based on the hierarchical structure between the nodes of the target hierarchical tree comprises: Obtaining monitoring data corresponding to the system to be monitored within a target time period, wherein the monitoring data includes a performance score of a performance indicator corresponding to each monitoring period; Obtaining deviation data of performance scores of each node at a level below the current level in the monitoring data; Based on the deviation data, influence parameters of nodes of the next level of the current level on nodes of the current level are determined.

4. The method according to claim 2, wherein determining the target performance score of each node based on the target weight of each node and the current performance score comprises: Obtaining monitoring data corresponding to the system to be monitored within a target time period, wherein the monitoring data includes a performance score of a performance indicator corresponding to each monitoring period; Determining a performance correction parameter for each node based on the performance score of each node in the monitoring data; Determining an initial performance score for each node based on the target weight of each node and the current performance score; Based on the performance correction parameter and the initial performance score, a target performance score for each node is determined.

5. According to the method of claim 3, the step of obtaining deviation data of performance scores of nodes at a level below the current level in the monitoring data comprises: Based on the performance scores of the nodes of the next level of the current level in the monitoring data, determine the average performance score, the maximum performance score and the minimum performance score of the nodes of the next level corresponding to the monitoring data; Deviation data is determined based on the performance average score, the maximum performance score and the minimum performance score.

6. The method according to claim 4, wherein determining the performance correction parameter of each node based on the performance score of each node in the monitoring data comprises: Determine performance score grouping information based on the performance score of each node in the monitoring data, wherein the grouping information includes at least one score group, and each score group has a corresponding performance score range; Determine the performance score parameter of each node according to the corresponding relationship between the performance score of each node and the score group; Based on the performance score parameter and the number of nodes, a performance correction parameter for each node is determined.

7. The method according to claim 1, wherein the step of constructing a target structure tree for the system to be monitored comprises: Obtain candidate performance indicators of the system to be monitored; Screening the candidate performance indicators to obtain performance indicators; Based on the correlation relationship between the various performance indicators, determine the hierarchical relationship and the parallel relationship of the performance indicators, wherein the hierarchical relationship represents the inclusion relationship of the performance indicators, and the parallel relationship represents that the performance indicators belong to the same category; A target structure tree is constructed according to the hierarchical relationship and parallel relationship of the performance indicators.

8. A data processing device, comprising: A construction unit, used to construct a target structure tree for the system to be monitored, each node in the target structure tree corresponds to a performance indicator of the system to be monitored, and the hierarchical structure between the nodes in the target structure tree corresponds to the association relationship between the performance indicators; A first determining unit, configured to determine, based on the hierarchical structure between the nodes of the target structure tree, an influence parameter of the nodes of the next level of the current level on the nodes of the current level; a second determining unit, configured to determine the target weights of the nodes at each level of the target structure tree according to a target order based on the influencing parameters and the initial weights of the nodes, wherein the target structure tree includes n-layer nodes, the n-th-layer nodes are nodes that do not include the next-layer nodes, and the target order represents an order of determining the target weights of the nodes at each level from the n-th-layer nodes upward layer by layer until the target weights of the nodes at the first level are obtained; The weight represents the degree of influence of the performance indicator corresponding to the node on the monitoring result.

9. A readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the data processing method according to any one of claims 1 to 8 is implemented.

10. An electronic device, comprising: A memory, used to store applications and data generated by the operation of the applications; A processor, configured to execute the application program to implement the data processing method according to any one of claims 1 to 8.

Images