State determination method and device, equipment, program product and storage medium

Abstract

The embodiment of the invention discloses a state determination method, device and equipment, a program product and a storage medium, relates to the field of distributed technologies and can also be applied to the field of financial science and technology, and the method comprises the following steps: obtaining operation data of each monitoring point of a chaos engineering system; feature analysis is conducted on the operation data, input information of a pre-trained state judgment model is obtained, and the input information comprises steady-state features, unsteady-state features and dynamic features corresponding to the operation data; inputting the input information into a state judgment model, and obtaining the stability state of the chaotic engineering system according to the output information of the state judgment model; wherein the stability state is a steady state or an unsteady state; and displaying the stability state to the user. According to the method provided by the invention, the abnormal conditions in the operation of the chaos engineering system and the business system can be efficiently and accurately detected, the user is prompted in time when the system is abnormal, and the stability of the system is ensured.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of distributed technology and may also be applicable to the field of financial technology, and in particular, to a state determination method, apparatus, device, program product, and storage medium. Background Art

[0002] With the rapid development of the financial industry, the increase in transaction volume has driven the demand for digitalization, onlineization and mobility. In order to better handle various business data, distributed architecture has gradually replaced the monolithic architecture and become the mainstream system architecture in the financial industry. At the same time, with the surge in the number of users, the number and complexity of business systems have also continued to increase, and the calling relationship between systems has become more complex. The failure of a call in one link may trigger a chain avalanche effect. Therefore, the issue of system stability construction is imminent.

[0003] Current methods for determining system stability rely on predefined thresholds and historical data, which results in insufficient response to unknown faults or new abnormal modes. In addition, fixed thresholds may not be flexible enough to respond to dynamically changing system environments, resulting in inaccurate judgments of system stability and affecting the efficiency of determining system stability. Summary of the invention

[0004] Embodiments of the present invention provide a state determination method, apparatus, device, program product and storage medium, which can detect abnormal conditions in system operation in real time, efficiently and accurately, thereby accurately determining the stability of the system and improving the efficiency of determining the stability of the system.

[0005] In a first aspect, an embodiment of the present invention provides a state determination method, including:

[0006] Obtaining operation data of each monitoring point of the chaos engineering system, wherein the operation data includes each experimental indicator value of each monitoring point;

[0007] Performing feature analysis on the operation data to obtain input information of a pre-trained state judgment model, wherein the input information includes steady-state features, non-steady-state features, and dynamic features corresponding to the operation data;

[0008] Inputting the input information into the state judgment model, and obtaining the stability state of the chaos engineering system according to the output information of the state judgment model; wherein the stability state is a steady state or a non-steady state;

[0009] The stability status is presented to a user.

[0010] In a second aspect, an embodiment of the present invention provides a state determination device, the device comprising:

[0011] A data acquisition module is used to acquire the operating data of each monitoring point of the chaos engineering system, wherein the operating data includes the experimental indicator value of each monitoring point;

[0012] An information determination module, used to perform feature analysis on the operation data to obtain input information of a pre-trained state judgment model, wherein the input information includes steady-state features, non-steady-state features, and dynamic features corresponding to the operation data;

[0013] A state determination module, used for inputting the input information into the state judgment model, and obtaining the stability state of the chaos engineering system according to the output information of the state judgment model; wherein the stability state is a steady state or an unsteady state;

[0014] An information display module is used to display the stability status to the user.

[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a state determination method as described in any one of the embodiments of the present invention is implemented.

[0016] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a state determination method as described in any one of the embodiments of the present invention.

[0017] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements a state determination method as described in any one of the embodiments of the present invention.

[0018] In an embodiment of the present invention, the operation data of each monitoring point of the chaos engineering system is obtained, wherein the operation data includes the experimental index values ​​of each monitoring point; the operation data is feature analyzed to obtain the input information of the pre-trained state judgment model, wherein the input information includes the steady-state characteristics, non-steady-state characteristics and dynamic characteristics corresponding to the operation data; the input information is input into the state judgment model, and the stability state of the chaos engineering system is obtained according to the output information of the state judgment model; wherein the stability state is steady-state or non-steady-state; the stability state is displayed to the user. The method of the embodiment of the present invention can obtain the operation state and change trend of the business system more comprehensively and accurately through the steady-state characteristics, non-steady-state characteristics and dynamic characteristics corresponding to the operation data of each monitoring point of the chaos engineering system, thereby more accurately evaluating the stability of the chaos engineering system. It can further detect abnormal conditions in the operation of the chaos engineering system and the business system in real time, efficiently and accurately, and promptly remind the user when the system is abnormal, thereby ensuring the stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A first flow chart of a state determination method provided by an embodiment of the present invention;

[0021] Figure 2 A second flow chart of a state determination method provided by an embodiment of the present invention;

[0022] Figure 3 A schematic diagram of the structure of a state determination device provided by an embodiment of the present invention;

[0023] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0025] Figure 1 This is the first flow chart of a state determination method provided in an embodiment of the present invention. The method in the embodiment of the present invention can detect abnormal conditions in system operation in real time, efficiently and accurately, so as to accurately determine the stability of the system and improve the efficiency of determining the stability of the system. The information collected in the method in the embodiment of the present invention is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse. The method can be executed by a state determination device provided in an embodiment of the present invention, and the device can be implemented in software and / or hardware. The following embodiments will be described by taking the device integrated in an electronic device as an example. The electronic device can be a server or a computer device, etc., with reference to Figure 1 , the method may specifically include the following steps:

[0026] Step 101: Obtain the operating data of each monitoring point of the chaos engineering system.

[0027] Among them, the operation data includes the values ​​of each experimental indicator at each monitoring point. Chaos engineering is a practical method for conducting experiments in distributed systems, which is used to improve the ability of business systems to resist risks through experiments. Chaos engineering can discover and solve potential problems by randomly injecting various types of faults into the services of distributed systems, and ultimately improve the stability of the system. In this solution, the chaos engineering system is used to test and improve the resilience and stability of the business system. The existence of the chaos engineering system is to ensure that the business system can still maintain stable performance when facing various pressures and failures. Therefore, the stability of the business system can reflect the stability of the chaotic system. If the business system shows instability in the chaos engineering experiment, it can be determined that the chaos engineering system needs further optimization and improvement.

[0028] Each monitoring point is a specific location or component used by the chaos engineering system to collect business system operation data when conducting experiments. Different monitoring points can be distributed in different levels and modules of the business system to ensure that data reflecting the overall health of the business system can be collected comprehensively and accurately. The business system in this solution can be a banking business system, and the experimental indicator values ​​include but are not limited to CPU usage, memory consumption, network latency, service response time, and transaction throughput. Specifically, when it is necessary to determine the stability of the chaos engineering system, the experimental indicator values ​​generated by the business system during operation can be obtained at each monitoring point of the chaos engineering system.

[0029] Step 102: Perform feature analysis on the operating data to obtain input information of a pre-trained state judgment model.

[0030] Among them, the input information includes steady-state features, non-steady-state features and dynamic features corresponding to the operation data. Steady-state features are the characteristics of stability and consistency shown by the business system under normal operation. Steady-state features can reflect the ability of the business system to keep its core functions unaffected or quickly recover to normal state when facing various faults and pressures. For example, performance indicators such as CPU usage and memory consumption fluctuate within the normal range, and there are no significant abnormal peaks; network delay and service response time remain within the normal range and will not fluctuate violently due to fault injection. Non-steady-state features are unstable or abnormal states shown by the business system when it is affected by faults or pressure. Dynamic features are dynamic behaviors and trends shown by the business system during operation as time and environment change. Dynamic features can reflect the adaptability and responsiveness of the business system to external changes. For example, by monitoring the changing trend of transaction throughput, you can understand the load of the business system in different time periods; or by observing the changing trend of service response time, you can judge whether the business system is gradually becoming busy or idle. The state judgment model is a model pre-trained by the server and used to classify the operation data according to the input information.

[0031] Specifically, after obtaining the operation data of each monitoring point, the operation data is subjected to feature analysis to identify the stability and consistency features (steady-state features), as well as the instability or abnormal state (non-steady-state features). For example, the mean, maximum value, minimum value, standard deviation, kurtosis, skewness and time series trend of each operation data are counted, and the statistical data are analyzed to obtain steady-state features and non-steady-state features. At the same time, the dynamic characteristics of the system are extracted by analyzing the change trend of the data over time. In an optional embodiment, after obtaining the operation data, the operation data is preprocessed to obtain valid data of the operation data, wherein the data preprocessing includes data cleaning, data normalization and data noise reduction; stability features are identified for valid data according to pre-set feature statistical indicators to obtain initial steady-state features and initial non-steady-state features; dynamic features are identified for valid data according to pre-set business feature indicators and data change trend indicators to obtain initial dynamic features; initial steady-state features, initial non-steady-state features and initial dynamic features are respectively screened for importance features to obtain input information.

[0032] Step 103: Input the input information to the state judgment model, and obtain the stability state of the chaos engineering system according to the output information of the state judgment model.

[0033] Among them, the stability state is steady state or non-steady state. The state judgment model is used to classify the operation data according to the input information to obtain the stability state of the chaotic system. The state judgment model in this scheme can be a support vector machine. Specifically, after obtaining the input information, the input information is input into the state judgment model. The state judgment model processes the steady-state characteristics, non-steady-state characteristics and dynamic characteristics according to its internal classification algorithm to obtain the stability state of the business system. Further, the stability state of the chaos engineering system is determined according to the stability state of the business system.

[0034] In an optional implementation, feature mapping is performed on the input information through the kernel function of the state judgment model to obtain linear features corresponding to the input information; the optimal hyperplane corresponding to the input information is obtained based on the linear features, and the classification results of each data point corresponding to the input information are determined based on the optimal hyperplane; the stability state of the chaos engineering system is determined based on the classification results of each data point.

[0035] Step 104: Display the stability status to the user.

[0036] Specifically, the stability state is steady state or non-steady state. If the stability state of the chaos engineering system is steady state, it means that the chaos engineering system is currently running stably, and no significant instability or anomalies have been detected. It can be further determined that the business system can still maintain stable performance when facing various pressures and failures. If the stability state of the chaos engineering system is non-steady state, it means that there are unstable factors or anomalies in the chaos engineering, and the user needs to be reminded to deal with them in time. In this solution, optionally, when the stability state is non-steady state, abnormal prompt information is generated based on the stability state; and the abnormal prompt information is displayed to the user.

[0037] Specifically, when the stability state is non-steady, the server can determine the current problems or potential risk points of the chaos engineering system or business system based on the stability state. For example, determine the abnormal operation data of the monitoring point where the abnormality occurs, and the reason for the abnormal operation data (such as excessive CPU usage or memory leak, etc.). After determining the risk point or problem, generate abnormal prompt information based on the stability state and risk point, and display the abnormal prompt information to the user. This allows users to understand the stability status of the chaos engineering system in a timely manner and obtain valuable abnormal prompt information when non-steady states are detected. This method helps users quickly locate problems, take corresponding solutions, and ensure the stable operation of the business system.

[0038] The technical solution of this embodiment obtains the operating data of each monitoring point of the chaos engineering system, wherein the operating data includes the experimental index values ​​of each monitoring point; performs feature analysis on the operating data to obtain the input information of the pre-trained state judgment model, wherein the input information includes the steady-state characteristics, non-steady-state characteristics and dynamic characteristics corresponding to the operating data; inputs the input information into the state judgment model, and obtains the stability state of the chaos engineering system according to the output information of the state judgment model; wherein the stability state is steady-state or non-steady-state; and displays the stability state to the user. The technical solution of this embodiment can more comprehensively and accurately determine the operating state and change trend of the business system through the steady-state characteristics, non-steady-state characteristics and dynamic characteristics corresponding to the operating data of each monitoring point of the chaos engineering system, thereby more accurately evaluating the stability of the chaos engineering system. It can further detect abnormal conditions in the operation of the chaos engineering system and the business system in real time, efficiently and accurately, and promptly remind users when the system is abnormal, thereby ensuring the stability of the system.

[0039] Figure 2 This is a second flow chart of a state determination method provided by an embodiment of the present invention. This embodiment is a refinement based on the above embodiment. The specific method can be as follows Figure 2 As shown, the method may include the following steps:

[0040] Step 201: Obtain the operating data of each monitoring point of the chaos engineering system.

[0041] The operating data includes the experimental index values ​​of each monitoring point.

[0042] Step 202: pre-process the operation data to obtain valid data of the operation data.

[0043] Among them, data preprocessing includes data cleaning, data normalization and data denoising. Data cleaning is a key step to ensure data quality. Data cleaning can eliminate erroneous data in the data set. Data normalization is the process of mapping data of different dimensions to the same dimension range (such as 0 to 1) to eliminate the numerical differences between different indicators. Data denoising is used to reduce high-frequency noise in the data and retain the key trends of the data.

[0044] In an optional implementation, after obtaining the operating data of each monitoring point, the operating data is subjected to missing value processing, outlier processing, and duplicate data removal to obtain cleaned data. Missing value processing can be performed by deleting missing values ​​or using statistical methods (such as mean or median filling) to fill missing data. The cleaned data is normalized and denoised to obtain operating data with higher clarity and accuracy, that is, valid data.

[0045] Step 203: Perform stability feature identification on the valid data according to a preset feature statistical index to obtain initial steady-state features and initial non-steady-state features.

[0046] Among them, steady-state characteristics are the characteristics of stability and consistency exhibited by the business system under normal operating conditions. Steady-state characteristics reflect the ability of the business system to keep its core functions unaffected or quickly recover to normal status when facing various faults and pressures. After obtaining valid data, statistical analysis is performed on the valid data according to various pre-set indicators for evaluating data stability, such as analyzing the mean, maximum value, minimum value, standard deviation, kurtosis and skewness of the valid data of each monitoring point, identifying the stability characteristics therein, and obtaining the initial steady-state characteristics. Non-steady-state characteristics are the characteristics of unstable or abnormal states exhibited by the business system when it is affected by faults or pressures. After obtaining valid data, outliers, mutation points or data points that do not conform to the expected pattern in the valid data are identified to obtain non-steady-state characteristics.

[0047] Step 204: Obtain input information based on the valid data, the initial steady-state characteristics, and the initial non-steady-state characteristics.

[0048] Among them, the input data includes steady-state characteristics, non-steady-state characteristics and dynamic characteristics. Dynamic characteristics are the dynamic behaviors and trends exhibited by the business system during operation as time and environment change. Dynamic characteristics can reflect the adaptability and responsiveness of the business system to external changes. After obtaining the initial steady-state characteristics and initial non-steady-state characteristics, the initial dynamic characteristics are obtained according to the valid data, and the input information is obtained according to the initial dynamic characteristics, the initial steady-state characteristics and the initial non-steady-state characteristics. In this scheme, optionally, the input information is obtained based on the valid data, the initial steady-state characteristics and the initial non-steady-state characteristics, including the following steps A1-A2:

[0049] Step A1: Dynamic feature recognition is performed on valid data according to pre-set business feature indicators and data change trend indicators to obtain initial dynamic features.

[0050] Among them, dynamic characteristics are the characteristics of dynamic behaviors and trends exhibited by the business system during operation as time and environment change. For example, by monitoring the changing trend of transaction throughput, the load of the business system in different time periods can be understood; by observing the changing trend of service response time, it can be determined whether the business system is gradually becoming busy or idle. Business characteristic indicators are predetermined based on the business characteristics of the business system and the chaos engineering experiment demand information, and are used to indicate how the server determines the dynamic characteristics. For example, if the business system is a bank's transaction system, the business characteristic indicators may include the frequency of delays exceeding the service level agreement threshold. In this scheme, optionally, after obtaining the operating data of each monitoring point of the chaos engineering system, it also includes: performing stability state correlation analysis on the operating data, the pre-acquired business demand data, and the historical business data of the chaos engineering system to obtain the correlation analysis results; determining the business characteristic indicators based on the correlation analysis results.

[0051] The historical business data of the chaos engineering system refers to the data of the chaos engineering experiment conducted by the business system in the historical period. Taking the business system of a bank as an example, the business demand data may include transaction success rate, response time, and customer satisfaction. Business characteristic indicators can more accurately reflect the dynamic change trend characteristics of the operation data.

[0052] After obtaining the operation data, business demand data and historical business data, the operation data, business demand data and historical business data of the chaos engineering system are analyzed through statistical analysis methods (such as correlation analysis or regression analysis, etc.) to find out the correlation between different data. For example, the relationship between network delay and transaction success rate, or the relationship between CPU usage and response time is analyzed. According to the analysis results, the key factors affecting the stability of the system, namely the business characteristic indicators, are identified. For example, when the network delay exceeds a certain threshold, the transaction success rate drops significantly, and the network delay is determined as a business characteristic indicator. For example, for a banking system, "daily transaction volume", "average transaction response time" and "transaction failure rate" can be determined as business characteristic indicators. In addition to static business characteristic indicators, dynamic business characteristics can also be introduced, such as "daily transaction volume growth rate" or "change trend of transaction response time", and they can be determined as business characteristic indicators. Determining business characteristic indicators through correlation analysis helps to more accurately evaluate the stability status of the system and improve the efficiency and accuracy of determining the stability of the business system.

[0053] Specifically, after obtaining valid data, the server can analyze the changing trend of data over time by drawing a time series graph, calculating a moving average, or applying a trend detection algorithm, etc. According to the business characteristic indicators and data change trend indicators, key trend information is extracted to obtain the initial dynamic features.

[0054] Step A2: Perform importance feature screening on initial steady-state features, initial non-steady-state features and initial dynamic features respectively to obtain input information.

[0055] Among them, the input information is the information to be input into the state judgment model. To ensure the stability and reliability of the selected features in practical applications, a solid foundation is provided for subsequent state judgment. After obtaining the initial steady-state features, initial non-steady-state features and initial dynamic features, the initial steady-state features, initial non-steady-state features and initial dynamic features can be evaluated by information gain or chi-square test and other methods to obtain the degree of influence of each feature on distinguishing the stability of the system. Feature selection is performed according to the degree of influence, and the features that contribute less to the steady-state judgment among the initial steady-state features, initial non-steady-state features and initial dynamic features are removed to obtain steady-state features, non-steady-state features and dynamic features, that is, the input information of the state judgment model is obtained.

[0056] The extracted initial dynamic features are screened by importance, redundant and irrelevant features are removed, and the most representative and predictive features are retained, which ensures the validity and accuracy of the state judgment model input and improves the reliability of stability judgment.

[0057] Step 205: feature mapping is performed on the input information through the kernel function of the state judgment model to obtain linear features corresponding to the input information.

[0058] Among them, the state judgment model is used to classify the input information and determine whether the state of the corresponding business system is steady or non-steady. The state judgment model in this solution can be a support vector machine, and the kernel function of the support vector machine is used to perform feature mapping on the input information to obtain the linear features corresponding to the input information. The kernel function in this solution can be a radial basis function. After obtaining the input information, the following formula is used for feature mapping:

[0059]

[0060] Among them, σ is the kernel function parameter, k(x i ,x j ) is the mapping relationship, x i For any point in the feature space, x j is a certain center, and exp represents the exponential function.

[0061] Step 206: Obtain an optimal hyperplane corresponding to the input information based on the linear features, and determine the classification results of each data point corresponding to the input information based on the optimal hyperplane.

[0062] Among them, the optimal hyperplane is used to separate steady-state data points from non-steady-state data points. Specifically, linear features include monitoring indicators such as CPU usage, memory usage, and network latency, and all linear features together constitute a point set in a multidimensional space. The support vector machine can find an optimal hyperplane in the point set, and the optimal hyperplane can maximize the separation of steady-state data points and non-steady-state data points. The optimal hyperplane can be expressed as: f(x) = ω×x+b. Among them, ω is the normal vector of the hyperplane; b is the translation distance of the hyperplane; x is the linear feature. After obtaining the optimal hyperplane, the support vector machine can calculate the distance from each data point to the optimal hyperplane, and use its distance to determine the category of the data point, that is, to determine whether the data point belongs to a steady state or a non-steady state.

[0063] Step 207: Determine the stability state of the chaos engineering system based on the classification results of each data point.

[0064] After obtaining the classification results of each data point, the number or proportion of all data points classified as steady state and unstable state can be counted. The stability state of the business system and the stability state of the chaos engineering system can be determined based on their proportions. If most of the data points are classified as steady state, it can be determined that the business system is in a stable state; conversely, if a large number of data points are classified as unstable state, it can be determined that the business system is in an unstable state.

[0065] Step 208: Display the stability status to the user.

[0066] In the technical solution of this embodiment, the operation data of each monitoring point of the chaos engineering system is obtained. Among them, the operation data includes the experimental index values ​​of each monitoring point. The operation data is preprocessed to obtain valid data of the operation data, wherein the data preprocessing includes data cleaning, data normalization and data noise reduction; the stability characteristics of the valid data are identified according to the pre-set characteristic statistical indicators to obtain the initial steady-state characteristics and the initial non-steady-state characteristics. Input information is obtained based on the valid data, the initial steady-state characteristics and the initial non-steady-state characteristics. The optimal hyperplane corresponding to the input information is obtained based on the linear characteristics, and the classification results of each data point corresponding to the input information are determined based on the optimal hyperplane. The stability state of the chaos engineering system is determined based on the classification results of each data point. The stability state is displayed to the user. The technical solution of this embodiment can improve the quality of the input data, reduce noise and errors, and thus improve the accuracy of the analysis results and the performance of the state judgment model by preprocessing the operation data. By analyzing the input data through the support vector machine, abnormal conditions in the operation of the system can be detected in real time, efficiently and accurately, thereby accurately determining the stability of the system and improving the efficiency of determining the stability of the system.

[0067] Figure 3FIG. 1 is a schematic diagram of a state determination device provided in an embodiment of the present invention, and the device is suitable for executing the state determination method provided in an embodiment of the present invention. Figure 3 As shown, the device may specifically include:

[0068] The data acquisition module 301 is used to acquire the operation data of each monitoring point of the chaos engineering system, wherein the operation data includes the experimental indicator value of each monitoring point;

[0069] An information determination module 302 is used to perform feature analysis on the operation data to obtain input information of a pre-trained state judgment model, wherein the input information includes steady-state features, non-steady-state features, and dynamic features corresponding to the operation data;

[0070] The state determination module 303 is used to input the input information into the state judgment model, and obtain the stability state of the chaos engineering system according to the output information of the state judgment model; wherein the stability state is a steady state or an unsteady state;

[0071] The information display module 303 is used to display the stability status to the user.

[0072] Optionally, the information determination module 302 is specifically used to: perform data preprocessing on the operation data to obtain valid data of the operation data, wherein the data preprocessing includes data cleaning, data normalization and data noise reduction;

[0073] Perform stability feature identification on the valid data according to a preset feature statistical index to obtain an initial steady-state feature and an initial non-steady-state feature;

[0074] The input information is obtained based on the effective data, the initial steady-state characteristics and the initial non-steady-state characteristics.

[0075] Optionally, the information determination module 302 is further used to: perform dynamic feature recognition on the valid data according to a preset business feature index and a data change trend index to obtain an initial dynamic feature;

[0076] Importance feature screening is performed on the initial steady-state feature, the initial non-steady-state feature and the initial dynamic feature respectively to obtain the input information.

[0077] Optionally, the information determination module 302 is further used to: perform stability state correlation analysis on the operation data, the pre-acquired business demand data and the historical business data of the chaos engineering system to obtain a correlation analysis result;

[0078] The service characteristic index is determined based on the correlation analysis result.

[0079] Optionally, the state determination module 303 is specifically used to: perform feature mapping on the input information through the kernel function of the state judgment model to obtain linear features corresponding to the input information;

[0080] Obtaining an optimal hyperplane corresponding to the input information based on the linear features, and determining a classification result of each data point corresponding to the input information based on the optimal hyperplane;

[0081] The stability state of the chaos engineering system is determined based on the classification results of the data points.

[0082] Optionally, the information display module 303 is specifically used to: when the stability state is a non-stable state, generate abnormal prompt information based on the stability state; and display the abnormal prompt information to the user.

[0083] The state determination device provided in the embodiment of the present invention can execute the state determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For the contents not described in detail in this embodiment, reference can be made to the description in any method embodiment of the present invention.

[0084] An embodiment of the present invention also provides a computer program product.

[0085] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer program products, which can include one or more computer programs, which can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor, which can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0086] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, referring to Figure 4 , Figure 4 The electronic device 12 shown is only an example and should not limit the functions and scope of use of the embodiments of the present application. Figure 4As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0087] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0088] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0089] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0090] A program / utility 40 having a set (at least one) of program modules 46 may be stored, for example, in the memory 28, such program modules 46 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 46 generally perform the functions and / or methods of the embodiments described herein.

[0091] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0092] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing a state determination method provided by an embodiment of the present invention: obtaining the operating data of each monitoring point of the chaos engineering system, wherein the operating data includes the experimental indicator values ​​of each monitoring point; performing feature analysis on the operating data to obtain input information of a pre-trained state judgment model, wherein the input information includes steady-state features, non-steady-state features and dynamic features corresponding to the operating data; inputting the input information into the state judgment model, and obtaining the stability state of the chaos engineering system according to the output information of the state judgment model; wherein the stability state is steady-state or non-steady-state; and displaying the stability state to a user.

[0093] The embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, a state determination method provided by all the embodiments of the present invention is implemented: obtaining the operating data of each monitoring point of the chaos engineering system, wherein the operating data includes the experimental index values ​​of each monitoring point; performing feature analysis on the operating data to obtain input information of a pre-trained state judgment model, wherein the input information includes steady-state features, non-steady-state features and dynamic features corresponding to the operating data; inputting the input information into the state judgment model, and obtaining the stability state of the chaos engineering system according to the output information of the state judgment model; wherein the stability state is steady-state or non-steady-state; and displaying the stability state to the user. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electronic device, device or device of electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction-executing electronic device, apparatus, or device.

[0094] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction-executing electronic device, apparatus, or device.

[0095] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0096] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0097] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A state determination method, characterized in that: The method comprises: Obtaining operation data of each monitoring point of the chaos engineering system, wherein the operation data includes each experimental indicator value of each monitoring point; Performing feature analysis on the operation data to obtain input information of a pre-trained state judgment model, wherein the input information includes steady-state features, non-steady-state features, and dynamic features corresponding to the operation data; Inputting the input information into the state judgment model, and obtaining the stability state of the chaos engineering system according to the output information of the state judgment model; wherein the stability state is a steady state or a non-steady state; The stability status is presented to a user.

2. The method according to claim 1, characterized in that: Performing feature analysis on the operating data to obtain input information of a pre-trained state judgment model includes: Performing data preprocessing on the operation data to obtain valid data of the operation data, wherein the data preprocessing includes data cleaning, data normalization and data noise reduction; Perform stability feature identification on the valid data according to a preset feature statistical index to obtain an initial steady-state feature and an initial non-steady-state feature; The input information is obtained based on the effective data, the initial steady-state characteristics and the initial non-steady-state characteristics.

3. The method according to claim 2, characterized in that The input information is obtained based on the valid data, the initial steady-state characteristics and the initial non-steady-state characteristics, including: Performing dynamic feature recognition on the valid data according to pre-set business feature indicators and data change trend indicators to obtain initial dynamic features; Importance feature screening is performed on the initial steady-state feature, the initial non-steady-state feature and the initial dynamic feature respectively to obtain the input information.

4. The method according to claim 3, characterized in that Before performing feature analysis on the operation data, the method further includes: Performing stability state correlation analysis on the operation data, the pre-acquired business demand data, and the historical business data of the chaos engineering system to obtain a correlation analysis result; The service characteristic index is determined based on the correlation analysis result.

5. The method according to claim 1, characterized in that Inputting the input information into the state judgment model, and obtaining the stability state of the chaos engineering system according to the output information of the state judgment model, including: Performing feature mapping on the input information through the kernel function of the state judgment model to obtain linear features corresponding to the input information; Obtaining an optimal hyperplane corresponding to the input information based on the linear features, and determining a classification result of each data point corresponding to the input information based on the optimal hyperplane; The stability state of the chaos engineering system is determined based on the classification results of the data points.

6. The method according to claim 1, characterized in that Presenting the stability status to a user includes: When the stability state is a non-stable state, abnormal prompt information is generated based on the stability state; and the abnormal prompt information is displayed to the user.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements a state determination method according to any one of claims 1 to 6.

8. A state determination device, characterized in that: include: A data acquisition module is used to acquire the operating data of each monitoring point of the chaos engineering system, wherein the operating data includes the experimental indicator value of each monitoring point; An information determination module, used to perform feature analysis on the operation data to obtain input information of a pre-trained state judgment model, wherein the input information includes steady-state features, non-steady-state features, and dynamic features corresponding to the operation data; A state determination module, used for inputting the input information into the state judgment model, and obtaining the stability state of the chaos engineering system according to the output information of the state judgment model; wherein the stability state is a steady state or an unsteady state; An information display module is used to display the stability status to the user.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the state determination method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the state determination method according to any one of claims 1 to 6 is implemented.

Images