Risk assessment method and device for unitized architecture, equipment, medium and product

Abstract

The invention provides a risk assessment method and device for a unitized architecture, equipment, a medium and a product, which can be applied to the fields of big data technology, distributed technology and financial science and technology. The risk assessment method for the unitized architecture comprises the steps that in response to a received risk assessment request, respective monitoring information of a plurality of units in the unitized architecture in M first time periods is acquired, the monitoring information comprises respective sub-monitoring information of S dimensions, and both M and S are positive integers larger than 1; for each unit, based on the respective index threshold range of the S dimensions, respectively evaluating the respective sub-monitoring information of the S dimensions to obtain respective sub-evaluation results of each unit in the M first time periods; and based on a preset decision-making mode, according to the respective sub-assessment results of each unit in the M first time periods, a risk assessment result is determined, and the risk assessment result comprises respective health degree assessment values and decision-making prompt information of the plurality of units.

Description

Technical Field

[0001] The present disclosure relates to the fields of big data technology, distributed technology and financial technology, and more specifically, to a risk assessment method and apparatus, equipment, medium and product for a unitized architecture. Background Art

[0002] With the development of big data technology, modular architecture has emerged. Modular architecture refers to an architecture that uses units as the basic unit of deployment and deploys key applications required for important customer services. How to effectively assess the faults of units in modular architecture and use the advantages of modularization to improve the level of operation and maintenance is an urgent problem to be solved.

[0003] In one example, a monitoring component, a liveness detection mechanism based on automatic health check, or a load liveness detection mechanism may be used to perform fault assessment on the units in the unitized architecture.

[0004] In the process of realizing the concepts disclosed herein, the inventors discovered that there are at least the following problems in the related art: the related art has poor predictability and integrated coordination for overall failures in a unitized architecture. For example, when a failure occurs and automatic traffic scheduling fails, it is impossible to assist in providing effective operation and maintenance decision-making solutions, making it difficult to ensure the efficiency and accuracy of risk assessment for the unitized architecture. Summary of the invention

[0005] In view of this, the present disclosure provides a risk assessment method and apparatus, device, medium and product for a unitized architecture.

[0006] According to one aspect of the present disclosure, a risk assessment method for a unitized architecture is provided, comprising: in response to receiving a risk assessment request, obtaining respective monitoring information of multiple units in the unitized architecture within M first time periods, wherein the monitoring information includes respective sub-monitoring information of S dimensions, and M and S are both positive integers greater than 1; for each of the above-mentioned units, based on respective indicator threshold ranges of the above-mentioned S dimensions, respectively evaluating the respective sub-monitoring information of the above-mentioned S dimensions to obtain respective sub-assessment results of each of the above-mentioned units in the above-mentioned M first time periods; and, based on a preset decision-making method, determining a risk assessment result according to the respective sub-assessment results of each of the above-mentioned units in the above-mentioned M first time periods, wherein the above-mentioned risk assessment result includes respective health assessment values ​​and decision prompt information of the above-mentioned multiple units.

[0007] According to another aspect of the present disclosure, a risk assessment device for a unitized architecture is provided, including: an acquisition module, for acquiring, in response to receiving a risk assessment request, respective monitoring information of multiple units in the unitized architecture within M first time periods, wherein the monitoring information includes respective sub-monitoring information of S dimensions, and M and S are both positive integers greater than 1; a first evaluation module, for evaluating, for each of the above-mentioned units, the respective sub-monitoring information of the above-mentioned S dimensions based on the respective indicator threshold ranges of the above-mentioned S dimensions, to obtain the respective sub-evaluation results of each of the above-mentioned units in the above-mentioned M first time periods; and a second evaluation module, for determining, based on a preset decision-making method and according to the respective sub-evaluation results of each of the above-mentioned units in the above-mentioned M first time periods, a risk assessment result, wherein the risk assessment result includes the respective health assessment values ​​and decision prompt information of the above-mentioned multiple units.

[0008] According to another aspect of the present disclosure, an electronic device is provided, comprising: one or more processors; and a memory for storing one or more instructions, wherein when the one or more instructions are executed by the one or more processors, the one or more processors implement the method described in the present disclosure.

[0009] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which executable instructions are stored. When the executable instructions are executed by a processor, the processor implements the method described in the present disclosure.

[0010] According to another aspect of the present disclosure, a computer program product is provided. The computer program product includes computer executable instructions. When the computer executable instructions are executed, they are used to implement the method described in the present disclosure.

[0011] According to an embodiment of the present disclosure, by responding to risk assessment requests to automatically obtain sub-monitoring information of multiple dimensions of multiple units in multiple time periods, not only the efficiency of data collection is improved, but also the comprehensiveness of the assessment is ensured. By evaluating the sub-monitoring information of each unit based on the indicator threshold range, detailed sub-assessment results can be generated, which provide quantitative indicators for the health status of each unit. On this basis, these sub-assessment results are combined through a preset decision-making method to determine the overall risk assessment result. This automated risk assessment method not only improves the accuracy of risk assessment of the unitized architecture, but also provides real-time decision support for administrators, optimizes the operating efficiency and stability of the unitized architecture, and further improves the overall maintainability and overall operation and maintenance capabilities of the unitized architecture. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0013] Figure 1 Schematically illustrates a system architecture to which a risk assessment method for a unitized architecture can be applied according to an embodiment of the present disclosure;

[0014] Figure 2 A flow chart of a risk assessment method for a unitized architecture according to an embodiment of the present disclosure is schematically shown;

[0015] Figure 3 An example schematic diagram of a unitized architecture according to an embodiment of the present disclosure is schematically shown;

[0016] Figure 4 An example schematic diagram schematically shows the training process of the first neural network and the second neural network according to an embodiment of the present disclosure;

[0017] Figure 5 A schematic diagram schematically shows an example process of evaluating the sub-monitoring information of the S dimensions based on the respective indicator threshold ranges of the S dimensions to obtain the respective sub-evaluation results of each unit in the M first time periods according to an embodiment of the present disclosure;

[0018] Figure 6 An example schematic diagram of a process of determining a risk assessment result based on a preset decision-making method and the respective sub-assessment results of each unit in M ​​first time periods according to an embodiment of the present disclosure is schematically shown;

[0019] Figure 7 An example schematic diagram schematically illustrates a process of displaying risk assessment results according to an embodiment of the present disclosure;

[0020] Figure 8 An example schematic diagram of a risk assessment process for a unitized architecture according to an embodiment of the present disclosure is schematically shown;

[0021] Fig. 9 A block diagram schematically shows a risk assessment device for a unitized architecture according to an embodiment of the present disclosure; and

[0022] Fig.10 A block diagram of an electronic device suitable for implementing a risk assessment method for a unitized architecture according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0023] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0024] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0025] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0026] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0027] In the technical solution of the present invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all 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 the relevant data comply with relevant laws, regulations and standards, 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.

[0028] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present invention provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0029] In one example, monitoring components can be used to achieve monitoring coverage on the application side to ensure that faults are discovered in the first place. However, due to the high requirements and restrictions of this approach, the enterprise-level unitized architecture requires the use of a complete underlying configuration management system and high-performance monitoring computing nodes, and there are many types of monitoring and indicators, lacking effective control over the overall situation.

[0030] In another example, the application layer can be probed based on the detection mechanism of automatic health check to ensure the isolation of problematic nodes. However, since this method lacks predictability, it is difficult to play a role in the security risks within the application itself.

[0031] In another example, based on the soft load detection mechanism, the minimum number of surviving application nodes can be set on the soft load to ensure that when a certain unit application node has a large-scale problem, the unit level can be automatically switched. However, although this method can achieve automatic unit level switching when a certain unit application node has a large-scale problem, it also has poor visibility and lacks controllability for unknown risks.

[0032] It can be seen that the relevant technologies have poor predictability and integrated coordination for overall failures in the unitized architecture, especially when a failure occurs and automatic traffic scheduling fails, and cannot assist in providing effective operation and maintenance decision-making solutions.

[0033] In order to at least partially solve the technical problems existing in the related art, the present disclosure provides a risk assessment method and device, equipment, medium and product for a unitized architecture, which can be applied to the fields of big data technology, distributed technology and financial technology. The risk assessment method for a unitized architecture includes: in response to receiving a risk assessment request, obtaining the respective monitoring information of multiple units in the unitized architecture in M ​​first time periods, the monitoring information includes the respective sub-monitoring information of S dimensions, and M and S are both positive integers greater than 1; for each unit, based on the respective indicator threshold ranges of the S dimensions, respectively evaluate the respective sub-monitoring information of the S dimensions, and obtain the respective sub-assessment results of each unit in the M first time periods; and, based on a preset decision-making method, determine the risk assessment result according to the respective sub-assessment results of each unit in the M first time periods, and the risk assessment result includes the respective health assessment values ​​and decision prompt information of the multiple units.

[0034] It should be noted that the risk assessment method and device for a unitized architecture provided in the embodiments of the present disclosure can be used in the fields of big data technology and distributed technology, for example, in risk assessment for a unitized architecture. The risk assessment method and device for a unitized architecture provided in the embodiments of the present disclosure can also be used in any field other than the fields of big data technology and distributed technology, for example, in the field of financial technology. The application field of the risk assessment method and device for a unitized architecture provided in the embodiments of the present disclosure is not limited.

[0035] Figure 1 The system architecture to which the risk assessment method for a unitized architecture can be applied according to an embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0036] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104 and a server 105. The network 104 is a medium for providing a communication link between different devices.

[0037] It should be noted that the risk assessment method for the unitized architecture provided in the embodiment of the present disclosure can generally be executed by the server 105 . Accordingly, the risk assessment device for the unitized architecture provided in the embodiment of the present disclosure can generally be set in the server 105 .

[0038] Alternatively, the risk assessment method for the unitized architecture provided in the embodiment of the present disclosure may also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103. Accordingly, the risk assessment apparatus for the unitized architecture provided in the embodiment of the present disclosure may also be disposed in the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0039] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0040] It should be noted that the sequence numbers of the operations in the following method are only used as representations of the operations for the purpose of description, and should not be regarded as representing the execution order of the operations. Unless explicitly stated, the method does not need to be executed completely in the order shown.

[0041] Figure 2 The flowchart of the risk assessment method for a unitized architecture according to an embodiment of the present disclosure is schematically shown.

[0042] like Figure 2 As shown, the risk assessment method 200 for a unitized architecture includes operations S210 - S230 .

[0043] In operation S210, in response to receiving a risk assessment request, respective monitoring information of a plurality of units in the unitized architecture in M ​​first time periods is obtained, wherein the monitoring information includes respective sub-monitoring information of S dimensions, and M and S are both positive integers greater than 1.

[0044] In operation S220, for each unit, based on the respective indicator threshold ranges of the S dimensions, the respective sub-monitoring information of the S dimensions is evaluated respectively to obtain the respective sub-evaluation results of each unit in the M first time periods.

[0045] In operation S230, based on a preset decision method, a risk assessment result is determined according to the respective sub-assessment results of each unit in the M first time periods, wherein the risk assessment result includes the health assessment values ​​and decision prompt information of the respective units.

[0046] According to an embodiment of the present disclosure, the code for generating a risk assessment request can be pre-written into a script, and in response to detecting that a scheduled task is triggered, the server can run the script to generate a risk assessment request on a regular basis. After detecting that a risk assessment request is generated, the monitoring information of each of the multiple units in the unitized architecture in the M first time periods can be obtained.

[0047] According to an embodiment of the present disclosure, a unitized architecture may include multiple units. A unit may refer to a self-contained set of operations related to a business processing link that can meet the needs of a certain type of business divided by a certain dimension, and the set includes most of the key services required for the business processing link of this type, as well as the data that this set needs to process.

[0048] According to the embodiments of the present disclosure, a unit may also refer to a partition unit (i.e., Rzone). Multiple partition units may be deployed downstream of the channel in the park according to the actual situation of the data center, and the units may be split according to user dimensions or other feature dimensions that are unified on the business link, or may be non-degradable applications in customer business links that are deployed peer-to-peer in each unit. Data from different shards may be processed by service nodes in different units.

[0049] According to an embodiment of the present disclosure, the monitoring information may include sub-monitoring information of each of the S dimensions. The dimensions may refer to different aspects or indicators used to evaluate the performance and health of the unitized architecture, and each dimension represents a specific performance indicator or system feature. In one example, the S dimensions include at least one of the following: CPU utilization, memory utilization, response time, business success rate, and key transaction success rate.

[0050] According to an embodiment of the present disclosure, the CPU utilization rate refers to the proportion of the central processing unit (CPU) used within a specific time, which can be used to evaluate the computing load and processing power of the unitized architecture. The memory utilization rate refers to the proportion of the system memory occupied, which can be used to evaluate the memory load and available resources of the unitized architecture. The response time refers to the time required for the unitized architecture to respond to a request, which can be used to evaluate the response speed and efficiency of the unitized architecture. The business success rate refers to the proportion of business requests successfully completed by the unitized architecture, which can be used to evaluate the reliability of the unitized architecture in processing business transactions. The key transaction success rate refers to the proportion of key or important transactions successfully completed by the unitized architecture, which can be used to evaluate the performance and reliability of the unitized architecture in processing key business processes.

[0051] According to the embodiments of the present disclosure, by covering key dimensions such as CPU utilization, memory utilization, response time, business success rate and key transaction success rate, the performance and health status of the unitized architecture can be comprehensively evaluated. The comprehensive evaluation of these dimensions not only provides a macro perspective of the operation of the unitized architecture, but also provides data support for targeted performance improvements and fault prevention, thereby improving the overall service quality and system stability.

[0052] According to an embodiment of the present disclosure, after obtaining respective monitoring information of multiple units in M ​​first time periods, for each unit, the respective sub-monitoring information of different dimensions can be evaluated based on the respective indicator threshold ranges of different dimensions to obtain respective sub-evaluation results of each unit in different first time periods. Evaluation can refer to the process of determining whether the sub-monitoring information of a certain dimension is within the indicator threshold range of the dimension.

[0053] According to an embodiment of the present disclosure, after obtaining the respective sub-assessment results of each unit in M ​​first time periods, the risk assessment results can be determined based on a preset decision-making method and according to the respective sub-assessment results of each unit in the M first time periods. The risk assessment results may include health assessment values ​​and decision prompt information for each of the multiple units. The health assessment value refers to a quantitative evaluation of the current state of the unit, which can be derived based on the comprehensive sub-assessment results of multiple dimensions. Decision prompt information refers to suggestions or warnings determined based on a preset decision-making method and according to the respective sub-assessment results of each unit in the M first time periods, which are intended to guide users or system administrators to take appropriate measures to optimize the performance of the unitized architecture or resolve potential problems.

[0054] According to an embodiment of the present disclosure, by responding to risk assessment requests to automatically obtain sub-monitoring information of multiple dimensions of multiple units in multiple time periods, not only the efficiency of data collection is improved, but also the comprehensiveness of the assessment is ensured. By evaluating the sub-monitoring information of each unit based on the indicator threshold range, detailed sub-assessment results can be generated, which provide quantitative indicators for the health status of each unit. On this basis, these sub-assessment results are combined through a preset decision-making method to determine the overall risk assessment result. This automated risk assessment method not only improves the accuracy of risk assessment of the unitized architecture, but also provides real-time decision support for administrators, optimizes the operating efficiency and stability of the unitized architecture, and further improves the overall maintainability and overall operation and maintenance capabilities of the unitized architecture.

[0055] In an embodiment of the present disclosure, before acquiring monitoring information, the user's consent or authorization may be obtained. For example, before operation S210, a request to acquire user information may be issued to the user. When the user agrees or authorizes that the user information may be acquired, operation S210 is performed.

[0056] In the embodiments of the present disclosure, a corresponding operation portal may be provided for the user to choose to agree or reject the automated decision result. That is, before the monitoring information is processed, the user may obtain an instruction to agree or reject the processing input through the corresponding operation portal. If the user agrees to process, the monitoring information is processed, that is, step S220 is executed. If the user rejects the processing, the expert decision process is entered.

[0057] Reference below Figure 3~Figure 8 , the risk assessment method 200 for a unitized architecture according to an embodiment of the present invention is further described.

[0058] According to an embodiment of the present disclosure, the risk assessment method 200 for a unitized architecture may further include the following operations.

[0059] According to the attribute information of each application, Q applications are divided into multiple units, wherein each unit is used to manage applications with the same attribute information, and the attribute information includes at least one of the following: channel attributes, data processing attributes and public service attributes.

[0060] According to an embodiment of the present disclosure, applications can be divided into a unitized architecture according to their own attribute information based on unitized planning. Attribute information refers to data that describes application features or characteristics, and this information is used to distinguish and classify different applications. For example, attribute information may include at least one of the following: channel attributes, data processing attributes, and public service attributes. Channel attributes refer to the channels or paths that applications rely on when they are distributed or deployed. Data processing attributes refer to the ability of applications to process user data. Public service attributes refer to the public service functions that applications can provide to users.

[0061] According to the embodiments of the present disclosure, after the applications are divided into the unitized architecture according to their own attribute information, P applications can be deployed in each unit, and each unit is used to manage applications with the same attribute information. For example, applications with channel attributes can be divided into partition units, applications with data processing attributes for processing user data can be divided into partition units, and applications with public service attributes for providing public services can be divided into public units.

[0062] According to the embodiments of the present disclosure, by classifying and managing applications according to channel attributes, data processing attributes, public service attributes, etc., each unit can centrally manage applications with the same attributes, thereby achieving efficient management of applications and optimized resource allocation, and improving the modularity, scalability and overall operational efficiency of the system.

[0063] According to an embodiment of the present disclosure, the risk assessment method 200 for a unitized architecture may further include the following operations.

[0064] The first software package for implementing unit monitoring is deployed to multiple units respectively, so that each unit obtains respective monitoring information in M ​​first time periods by running the first software package. The second software package for implementing bottom layer monitoring is deployed to the bottom layer environment for supporting the unitized architecture, so that the unitized architecture obtains bottom layer abnormality information by running the second software package.

[0065] According to the embodiments of the present disclosure, a monitoring system can be built by deploying software packages to achieve monitoring coverage of each node and underlying environment in a unitized environment and monitor application performance from multiple perspectives.

[0066] In one example, a first software package for implementing unit monitoring can be installed in different units of a unitized application to complete the coverage of application nodes. Unit monitoring refers to the process of real-time monitoring of the operating status of each independent unit in a unitized architecture. The first software package refers to a specific software tool or program package for implementing unit monitoring. By installing the first software package in each unit, each unit can independently run the monitoring program and collect monitoring information.

[0067] In another example, a second software package for implementing bottom-level monitoring can be installed at the infrastructure level to ensure full monitoring of bottom-level resources. Bottom-level monitoring refers to the process of real-time monitoring of the bottom-level environment of the unitized architecture. The bottom-level environment refers to the basic software and hardware environment that supports the unitized architecture. The second software package refers to a specific software tool or program package for implementing bottom-level monitoring. By installing the second software package in the bottom-level environment, the bottom-level environment can independently run the monitoring program and collect bottom-level abnormal information.

[0068] According to the embodiments of the present disclosure, by deploying the first software package for implementing unit monitoring to multiple units respectively, and deploying the second software package for implementing bottom-level monitoring to the bottom-level environment, comprehensive monitoring of the unitized architecture is achieved. This hierarchical monitoring strategy not only ensures the integrity and accuracy of monitoring information, but also enhances the abnormality detection capability of the unitized architecture, thereby improving the stability and reliability of the unitized architecture.

[0069] Figure 3 An example schematic diagram of a unitized architecture according to an embodiment of the present disclosure is schematically shown.

[0070] like Figure 3 As shown in 300, a user request 301 involving campus 302_1 and campus 302_2 is taken as an example to illustrate an example of a unitized architecture.

[0071] For the park 302_1, the access unit 303_1 can be used to perform routing control on the partition unit 304_1 and the partition unit 304_2 within the park. In addition, the access unit 303_1 can also be used to perform routing control on the partition unit 304_3 and the partition unit 304_4 outside the park. In the partition unit 304_1, the soft load balancing 305_1 can be used to perform load management on at least one application 306_1. In the partition unit 304_2, the soft load balancing 305_2 can be used to perform load management on at least one application 306_2.

[0072] For the park 302_2, the access unit 303_2 can be used to perform routing control on the partition unit 304_3 and the partition unit 304_4 within the park. In addition, the access unit 303_2 can also be used to perform routing control on the partition unit 304_1 and the partition unit 304_2 outside the park. In the partition unit 304_3, the soft load balancing 305_3 can be used to perform load management on at least one application 306_3. In the partition unit 304_4, the soft load balancing 305_4 can be used to perform load management on at least one application 306_4.

[0073] In one example, the first software package can be deployed in the partition unit 304_1, the partition unit 304_2, the partition unit 304_3 and the partition unit 304_4 respectively to obtain monitoring information. In another example, the second software package can be deployed in the underlying environment of the unitized architecture to obtain underlying abnormal information.

[0074] According to an embodiment of the present disclosure, the indicator threshold range of each of the S dimensions can be obtained in the following manner.

[0075] A historical data set is obtained, wherein the historical data set includes sample monitoring information of each of the multiple units in N second time periods, where the second time period is a historical time period relative to the first time period, wherein N is a positive integer greater than 1. The historical data set is input into the first neural network to obtain the indicator threshold range of each of the S dimensions.

[0076] According to the embodiments of the present disclosure, when the system is first launched, the various time-sharing monitoring indicator data of each unit in the unitized architecture and the operation and maintenance operations at the time of failure can be collected in advance, and a historical data set can be established based on different types of data, and machine learning can be used for classification to learn the possible corresponding types of failures of different indicator types and pass them into the neural network component. In subsequent use, the data stored in the Node can be input into the neural network component for training, and the trained model will be passed into the first neural network in batches at the end of the day.

[0077] According to an embodiment of the present disclosure, the historical data set may include sample monitoring information of each of the multiple units in N second time periods. The second time period is a historical time period relative to the first time period. For example, if the first time period includes multiple time periods on November 2, 2023, the second time period may include multiple time periods on November 1, 2023. The specific form of the historical data set may be shown in Table 1 below.

[0078] According to an embodiment of the present disclosure, by sequentially passing the data in the historical data set into the first neural network, the normal value range of each indicator is calculated according to the different time periods in Table 1 above. The specific structure of the first neural network can be configured according to actual business needs and is not limited here. For example, the first neural network may include at least one of the following: Backpropagation Neural Network (BP), Radial Basis Function Neural Network (RBF), General Regression Neural Network (GRNN), Probabilistic Neural Network (PNN), etc.

[0079] Table 1

[0080]

[0081] According to the embodiment of the present disclosure, taking the first neural network as a BP neural network as an example, the processing process of the BP neural network is mainly divided into two stages. The first stage is the forward propagation of the signal, from the input layer through the hidden layer, and finally to the output layer; the second stage is the reverse propagation of the error, from the output layer to the hidden layer, and finally to the input layer, and the weight and bias from the hidden layer to the output layer, and the weight and bias from the input layer to the hidden layer are adjusted in turn. The processing process of the BP neural network is shown in the following formula (1).

[0082]

[0083] in, represents the weight of the i-th neuron, represents the activation value of the i-th neuron, Represents the bias of the ith neuron.

[0084] According to the embodiments of the present disclosure, by acquiring a historical data set and inputting it into a first neural network to obtain the indicator threshold range of each of S dimensions, it is possible to utilize the powerful data support of the historical data set, combined with the nonlinear mapping capability and flexibility of the neural network, to accurately calculate the indicator threshold range of each dimension, which not only improves the accuracy of system monitoring, but also provides a basis for the system's anomaly detection and performance optimization, thereby helping to improve the overall operating efficiency and stability.

[0085] According to an embodiment of the present disclosure, the preset decision-making method is obtained in the following manner.

[0086] The historical data set is input into the second neural network to obtain a one-to-one correspondence between the decision operation and the candidate dimension matching information, wherein the candidate dimension matching information represents the relationship between the sub-sample monitoring information of each of the S dimensions and the indicator threshold range. The historical data set also includes sample decision information of each of the multiple units in the N second time periods, and the sample decision information includes the decision operation when the unit is abnormal.

[0087] According to the embodiments of the present disclosure, a form can be compiled based on the actual situation in combination with the maintenance experience of front-line production personnel, and the historical data set can be passed through the second neural network to learn a set of decision parameters. In one example, the first neural network and the second neural network can be simultaneously associated with the data storage node of the monitoring system, the first neural network is used to calculate the threshold conditions of different time periods, and the second neural network is used to calculate the decision to be made.

[0088] According to an embodiment of the present disclosure, the candidate dimension matching information characterizes the relationship between the subsample monitoring information of each of the S dimensions and the indicator threshold range. For example, the relationship may include one of the following: above the threshold, in line with the threshold, and below the threshold. The decision operation may include one of the following: unit node restart, service degradation, unit switching, version rollback, and normal operation. The one-to-one correspondence between the decision operation and the candidate dimension matching information may be shown in the following table (2).

[0089] Table 2

[0090]

[0091] According to the embodiments of the present disclosure, by inputting the historical data set into the second neural network, utilizing the powerful data processing capability of the neural network and combining the rich information of the historical data set, a one-to-one correspondence between the decision operation and the candidate dimension matching information is obtained, thereby achieving accurate detection of system anomalies and performance optimization, which not only improves the accuracy of anomaly detection, but also provides a scientific basis for performance optimization, thereby being able to better identify and warn of potential abnormal events and improve overall operating efficiency and stability.

[0092] Figure 4 An example schematic diagram schematically shows the training process of the first neural network and the second neural network according to an embodiment of the present disclosure.

[0093] like Figure 4 As shown, in 400, a historical data set 410 may be acquired, the acquired historical data set 410 including sample monitoring information 411 of each of the multiple units in N second time periods and sample decision information 412 of each of the multiple units in N second time periods.

[0094] In one example, the sample monitoring information 411 of each of the multiple units in N second time periods can be input into the first neural network 421 to obtain the indicator threshold range 430 of each of the S dimensions.

[0095] The sample decision information 412 of each unit in N second time periods and the indicator threshold range 430 of each dimension are input into the second neural network to obtain a one-to-one correspondence 440 between the decision operation 441 and the candidate dimension matching information 442.

[0096] According to an embodiment of the present disclosure, operation S220 may include the following operations.

[0097] For each dimension, the sub-monitoring information of the dimension is evaluated according to the indicator threshold range of the dimension to obtain an intermediate evaluation result. For each first period, the intermediate evaluation results of the S dimensions in the first period are determined as sub-evaluation results.

[0098] According to an embodiment of the present disclosure, the output result model of the first neural network can be put into the production environment, and the monitoring information on the production can be analyzed, and the monitoring results can be summarized into the unit health index. The indicator threshold range refers to the normal value range of the indicator used to evaluate a certain dimension. The intermediate evaluation result characterizes the relationship between the sub-monitoring information and the indicator threshold range. For example, the relationship may include one of the following: above the threshold, in line with the threshold, and below the threshold.

[0099] According to the embodiments of the present disclosure, for each dimension, the sub-monitoring information of the dimension can be evaluated according to the indicator threshold range of the dimension to obtain an intermediate evaluation result. For example, taking the monitoring information including sub-monitoring information of 2 dimensions, sub-monitoring information 1 of dimension 1 is 15%, sub-monitoring information 2 of dimension 1 is 95ms, indicator threshold range 1 for dimension 1 is 10%~20%, and indicator threshold range 2 for dimension 2 is 80ms~90ms as an example: for dimension 1, it can be determined that sub-monitoring information 1 (15%) is within indicator threshold range 1 (10%~20%), thereby obtaining an intermediate evaluation result that dimension 1 meets the threshold; for dimension 2, it can be determined that sub-monitoring information 2 (95ms) is outside indicator threshold range 2 (80ms~90ms), thereby obtaining an intermediate evaluation result that dimension 2 is higher than the threshold.

[0100] According to the embodiments of the present disclosure, by carefully evaluating the sub-monitoring information for the indicator threshold range of each dimension, an intermediate evaluation result reflecting the relationship between the sub-monitoring information and the threshold is generated, thereby achieving accurate monitoring and analysis of the unit status. On this basis, by integrating the intermediate evaluation results of all dimensions in each first time period into sub-evaluation results, not only the timeliness of the evaluation is improved, but also the responsiveness to changes in the unit status is enhanced, thereby improving the reliability and operating efficiency of the unitized structure.

[0101] Figure 5 It schematically shows an example schematic diagram of the process of evaluating the sub-monitoring information of each of the S dimensions based on the respective indicator threshold ranges of the S dimensions according to an embodiment of the present disclosure, and obtaining the respective sub-evaluation results of each unit in M ​​first time periods.

[0102] like Figure 5 As shown, in 500, taking the sub-monitoring information of S dimensions including sub-monitoring information 501_1, sub-monitoring information 501_2, ..., sub-monitoring information 501_X, where X is a positive integer greater than 1 as an example, the process of obtaining the sub-evaluation results of each unit in M ​​first time periods is explained.

[0103] For sub-monitoring information 501_1, sub-monitoring information 501_1 can be evaluated according to the indicator threshold range 502_1 of the dimension to obtain an intermediate evaluation result 503_1. For sub-monitoring information 501_2, sub-monitoring information 501_2 can be evaluated according to the indicator threshold range 502_2 of the dimension to obtain an intermediate evaluation result 503_2. Similarly, for sub-monitoring information 501_X, sub-monitoring information 501_X can be evaluated according to the indicator threshold range 502_X of the dimension to obtain an intermediate evaluation result 503_X.

[0104] On this basis, the intermediate evaluation result 503_1, the intermediate evaluation result 503_2, ..., the intermediate evaluation result 503_X may be determined as the sub-evaluation result 504 of the unit in the first time period.

[0105] According to an embodiment of the present disclosure, operation S230 may include the following operations.

[0106] According to the sub-evaluation results, multiple candidate dimension matching information is matched to obtain target dimension matching information. According to the decision operation corresponding to the target dimension matching information, decision prompt information is determined.

[0107] According to an embodiment of the present disclosure, the preset decision method may include a one-to-one correspondence between the decision operation and the candidate dimension matching information. The candidate dimension matching information characterizes the relationship between the sub-sample monitoring information of each of the S dimensions and the indicator threshold range. The following takes the example of S dimensions including CPU usage, memory usage, system response time, business success rate and key transaction success rate to illustrate the candidate dimension matching information.

[0108] For example, when the CPU usage is higher than the threshold, the memory usage is higher than the threshold, the system response time meets the threshold, the business success rate meets the threshold, and the key transaction success rate meets the threshold, the corresponding decision operation may be restarting the unit node.

[0109] Alternatively, when the CPU usage meets the threshold, the memory usage meets the threshold, the system response time meets the threshold, the business success rate meets the threshold and the key transaction success rate is lower than the threshold, the corresponding decision operation may be service downgrade.

[0110] Alternatively, when the CPU usage meets the threshold, the memory usage meets the threshold, the system response time is higher than the threshold, the business success rate is lower than the threshold and the key transaction success rate is lower than the threshold, the corresponding decision operation can be unit switching.

[0111] Alternatively, when the CPU usage meets the threshold, the memory usage meets the threshold, the system response time meets the threshold, the business success rate is lower than the threshold and the key transaction success rate is lower than the threshold, the corresponding decision operation can be version rollback.

[0112] Alternatively, when the CPU usage meets the threshold, the memory usage meets the threshold, the system response time meets the threshold, the business success rate meets the threshold, and the key transaction success rate meets the threshold, the corresponding decision operation may be running normally.

[0113] According to the embodiments of the present disclosure, multiple candidate dimension matching information are matched according to the sub-evaluation results to obtain the target dimension matching information, and the decision prompt information is determined according to the decision operation corresponding to the target dimension matching information. This not only optimizes the decision-making process, but also enhances the unitized architecture's ability to identify and handle abnormal situations, thereby ensuring the stable operation and efficient management of the unitized architecture.

[0114] According to an embodiment of the present disclosure, operation S230 may further include the following operations.

[0115] For each first time period, a first evaluation value is determined according to a first weight and a first health impact value for sub-abnormal information. A second evaluation value is determined according to a second weight and a second health impact value for decision operation. A health evaluation value is determined according to the first evaluation value and the second evaluation value.

[0116] According to an embodiment of the present disclosure, in response to receiving a risk assessment request, the underlying exception information of the unitized architecture is also obtained, and the underlying exception information includes sub-exception information of at least one unit. The underlying exception information refers to non-urgent problems in the unitized application that need to be rectified, and may include, for example, configuration management system data configuration errors, modifications that have not been completed according to the architecture plan, hidden dangers that may cause production problems, unitized information configuration errors, and prohibited mutual access between units. The underlying exception information can be aggregated from each platform to the monitoring system in a daily batch manner, and through the background calculation of the monitoring system, the sub-exception information of at least one unit can be obtained after differentiation by unit dimension.

[0117] According to the embodiments of the present disclosure, the index interval of the health evaluation value is 0%~100%, and the stability of the unit production operation can be judged according to the level of the health evaluation value. In one example, the result model of machine learning can be put into the production environment, the monitoring information on production can be analyzed, and the monitoring results can be summarized into the health evaluation value; at the same time, the underlying abnormal information can also be summarized into the health evaluation value.

[0118] According to an embodiment of the present disclosure, a corresponding first health impact value is set for different sub-abnormal information, and the first health impact value can represent the degree of influence of the sub-abnormal information on the health of the unit. A corresponding second health impact value is set for different decision operations, and the second health impact value can represent the degree of influence of the decision operation on the health of the unit. For example, the second health impact value corresponding to the restart of the unit node is 10, the second health impact value corresponding to the service degradation is 20, the second health impact value corresponding to the unit switch is 30, and the second health impact value corresponding to the version rollback is 30.

[0119] According to an embodiment of the present disclosure, after determining the first health impact value for the sub-abnormal information and the second health impact value for the decision-making operation, the first evaluation value can be determined according to the first weight and the first health impact value for the sub-abnormal information, and the second evaluation value can be determined according to the second weight and the second health impact value for the decision-making operation. On this basis, the health evaluation value is determined according to the first evaluation value and the second evaluation value. The first weight and the second weight can be configured according to actual business needs and are not limited here. For example, the first weight can be 10% and the second weight can be 90%.

[0120] According to the embodiments of the present disclosure, by analyzing the sub-abnormal information in the underlying abnormal information, potential risks can be identified more meticulously. By combining the first weight and the first health impact value to calculate the first evaluation value, and the second weight and the second health impact value to calculate the second evaluation value, these evaluation values ​​are finally combined to obtain the health evaluation value, which not only optimizes the risk assessment process, but also enhances the ability to respond to abnormal situations, ensuring the stable operation and efficient management of the unitized architecture.

[0121] Figure 6 An example schematic diagram of a process of determining a risk assessment result based on a preset decision-making method and according to respective sub-assessment results of each unit in M ​​first time periods according to an embodiment of the present disclosure is schematically shown.

[0122] like Figure 6 As shown, in 600, multiple candidate dimension matching information 602 can be matched according to the sub-evaluation result 601 to obtain target dimension matching information 603. Multiple candidate dimension matching information 602 can include candidate dimension matching information 602_1, candidate dimension matching information 602_2, ..., candidate dimension matching information 602_U, where U is a positive integer. After obtaining the target dimension matching information 603, decision prompt information 605 can be determined according to the decision operation 604 corresponding to the target dimension matching information 603.

[0123] The second evaluation value 607 is determined according to the second weight 606 and the second health impact value for the decision operation 604. The first evaluation value 610 is determined according to the first weight 609 and the first health impact value for the sub-abnormal information 608. On this basis, the health evaluation value 611 can be determined according to the first evaluation value 610 and the second evaluation value 607.

[0124] According to an embodiment of the present disclosure, the risk assessment method 200 for a unitized architecture may further include the following operations.

[0125] The health assessment values ​​of the respective units are visualized to obtain a risk assessment view, wherein the range of the health assessment values ​​is represented by multiple colors in the risk assessment view. At least one unit with an abnormality is determined according to the color characteristics of the risk assessment diagram. Based on the risk assessment view, decision prompt information is displayed at a preset position away from at least one unit with an abnormality.

[0126] According to an embodiment of the present disclosure, the health of different units can be set according to the unitized application attribution and displayed in the production line monitoring view to obtain a risk assessment view. The risk assessment view refers to an interface or chart that displays the health assessment value in a visual form, which is used to intuitively identify system risks.

[0127] According to an embodiment of the present disclosure, the color feature refers to using different colors in the risk assessment view to characterize different ranges of health assessment values ​​to facilitate identification of abnormalities. An abnormal unit refers to a unit whose health assessment value exceeds the normal range identified by the color feature in the risk assessment view.

[0128] According to an embodiment of the present disclosure, when a unit has an abnormality, decision prompt information can be displayed at a preset position away from at least one unit with the abnormality. The preset position can be configured according to actual business needs and is not limited here. For example, the preset position can be 5 mm. The decision prompt information can be used to characterize the decision operation suggestion for the unit.

[0129] According to the embodiments of the present disclosure, decision prompt information refers to suggestions or warnings provided based on the risk assessment view, which is intended to guide users or system administrators to prompt different operations when the health assessment value reaches different thresholds. For example, for the decision operation of restarting a unit node, the decision prompt information may be "it is recommended to restart the unit node in combination with the alarm"; for the decision operation of downgrading the service, the decision prompt information may be "it is recommended to downgrade the hotspot function"; for the decision operation of switching a unit, the decision prompt information may be "it is recommended to switch at the unit level"; for the decision operation of rolling back a version, the decision prompt information may be "please pay attention to the recent version to determine whether to roll back".

[0130] According to the embodiments of the present disclosure, by visualizing the health evaluation values ​​of multiple units, generating a risk assessment view, and identifying abnormal units through color features and displaying decision prompt information, the intuitiveness of risk identification and the accuracy of decision-making are improved. By displaying decision prompt information at the preset position of the unit with abnormalities, the abnormality handling process is further optimized, ensuring the stable operation and efficient management of the unitized architecture.

[0131] Figure 7 An example schematic diagram schematically illustrates a process of displaying risk assessment results according to an embodiment of the present disclosure.

[0132] like Figure 7 As shown, in 700, the unitized architecture involving campus 702_1 and campus 702_2 is taken as an example to illustrate the display process of the risk assessment results.

[0133] By visualizing the health evaluation values ​​of the multiple units, a risk evaluation view 701 can be obtained. In the risk evaluation view 701, the ranges to which the health evaluation values ​​belong can be represented by multiple colors.

[0134] For example, for partition unit 703_2, its health assessment value is 50%, so it can be displayed in a darker gray; for partition unit 703_3, its health assessment value is 60%, so it can be displayed in a lighter gray; for partition units 703_1 and 703_4, their health assessment values ​​are 90%, so they can be displayed in a transparent color.

[0135] In addition, decision prompt information is displayed at a preset position away from at least one unit with an abnormality based on the risk assessment view 701. For example, for partition unit 703_2, whose health assessment value is 50%, decision prompt information can be displayed at a preset position away from partition unit 703_2.

[0136] Figure 8 An example schematic diagram of a risk assessment process for a unitized architecture according to an embodiment of the present disclosure is schematically shown.

[0137] like Figure 8 As shown, the modular architecture 800 may include a plurality of modules (eg, module 801_1 , module 801_2 , . . . , module 801_V) and an underlying environment 802 .

[0138] In one example, a historical data set 810 of the unitized architecture 800 may be obtained in advance, and the historical data set 810 may include sample monitoring information and sample decision information of each of the multiple units in N second time periods. The historical data set 810 is input into the first neural network 821 to obtain the index threshold range 830 of each of the S dimensions. The historical data set 810 and the index threshold range 830 are input into the second neural network 822 to obtain a one-to-one correspondence 840 between the decision operation 841 and the candidate dimension matching information 842.

[0139] In another example, respective monitoring information 850 and underlying abnormal information 880 of multiple units in the unitized architecture 800 in M ​​first time periods may be obtained. Based on respective indicator threshold ranges 830 of the S dimensions, respective sub-monitoring information of the S dimensions included in the monitoring information 850 is evaluated respectively, and respective sub-evaluation results 860 of each unit in the M first time periods are obtained.

[0140] According to the sub-evaluation result 860, multiple candidate dimension matching information 842 are matched to obtain target dimension matching information; according to the decision operation 841 corresponding to the target dimension matching information, the decision prompt information 870 is determined. On this basis, the first evaluation value can be determined according to the first weight and the first health impact value of the sub-abnormal information included in the underlying abnormal information 880; the second evaluation value can be determined according to the second weight and the second health impact value used for the decision operation 841; the health evaluation value 890 can be determined according to the first evaluation value and the second evaluation value.

[0141] The above are only exemplary embodiments, but are not limited thereto and may also include other risk assessment methods for unitized architecture known in the art, as long as they can improve the overall maintainability and overall operation and maintenance capabilities of the unitized architecture.

[0142] Fig. 9 A block diagram of a risk assessment device for a unitized architecture according to an embodiment of the present disclosure is schematically shown.

[0143] like Fig. 9 As shown, the risk assessment apparatus 900 for a unitized architecture may include an acquisition module 910 , a first assessment module 920 , and a second assessment module 930 .

[0144] The acquisition module 910 is used to obtain, in response to receiving a risk assessment request, respective monitoring information of multiple units in the unitized architecture within M first time periods, wherein the monitoring information includes respective sub-monitoring information of S dimensions, and M and S are both positive integers greater than 1. In one embodiment, the acquisition module 910 can be used to perform the operation S210 described above, which will not be described in detail herein.

[0145] The first evaluation module 920 is used to evaluate the sub-monitoring information of each of the S dimensions based on the respective indicator threshold ranges of the S dimensions for each unit, and obtain the respective sub-evaluation results of each unit in the M first time periods. In one embodiment, the first evaluation module 920 can be used to perform the operation S220 described above, which will not be repeated here.

[0146] The second evaluation module 930 is used to determine the risk evaluation result based on the preset decision-making method and the sub-evaluation results of each unit in the M first time periods, wherein the risk evaluation result includes the health evaluation values ​​and decision prompt information of each of the multiple units. In one embodiment, the second evaluation module 930 can be used to perform the operation S230 described above, which will not be repeated here.

[0147] According to an embodiment of the present disclosure, the first evaluation module 920 may include an evaluation unit and a first determination unit.

[0148] The evaluation unit is used to evaluate the sub-monitoring information of each dimension according to the indicator threshold range of the dimension to obtain an intermediate evaluation result, wherein the intermediate evaluation result represents the relationship between the sub-monitoring information and the indicator threshold range.

[0149] The first determining unit is used to determine, for each first time period, respective intermediate evaluation results of the S dimensions within the first time period as sub-evaluation results.

[0150] According to an embodiment of the present disclosure, the preset decision method includes a one-to-one correspondence between the decision operation and the candidate dimension matching information.

[0151] According to an embodiment of the present disclosure, the second evaluation module 930 may include a matching unit and a second determining unit.

[0152] The matching unit is used to match multiple candidate dimension matching information according to the sub-evaluation results to obtain target dimension matching information.

[0153] The second determination unit is used to determine the decision prompt information according to the decision operation corresponding to the target dimension matching information.

[0154] According to an embodiment of the present disclosure, in response to receiving a risk assessment request, underlying exception information of the unitized architecture is also acquired, and the underlying exception information includes sub-exception information of each of at least one unit.

[0155] According to an embodiment of the present disclosure, the second evaluation module 930 may include a third determination unit, a fourth determination unit, and a fifth determination unit.

[0156] The third determining unit is used to determine, for each first time period, a first evaluation value according to the first weight and a first health impact value for the sub-abnormality information.

[0157] The fourth determining unit is used to determine a second evaluation value according to the second weight and a second health impact value used for decision-making operation.

[0158] The fifth determining unit is used to determine the health evaluation value according to the first evaluation value and the second evaluation value.

[0159] According to an embodiment of the present disclosure, the risk assessment device 900 for a unitized architecture may further include a visualization module, a determination module, and a display module.

[0160] The visualization module is used to visualize the health assessment values ​​of each of the multiple units to obtain a risk assessment view, wherein the range of the health assessment values ​​is represented by multiple colors in the risk assessment view.

[0161] The determination module is used to determine at least one unit with an abnormality according to the color characteristics of the risk assessment schematic diagram.

[0162] The display module is used to display decision prompt information at a preset position of at least one unit with an abnormality based on the risk assessment view.

[0163] According to an embodiment of the present disclosure, each unit is deployed with P applications.

[0164] According to an embodiment of the present disclosure, the risk assessment device 900 for a unitized architecture may further include a partitioning module.

[0165] The partitioning module is used to partition Q applications according to the attribute information of each application to obtain multiple units, wherein each unit is used to manage applications with the same attribute information, and the attribute information includes at least one of the following: channel attributes, data processing attributes and public service attributes.

[0166] According to an embodiment of the present disclosure, the risk assessment device 900 for a unitized architecture may further include a first deployment module and a second deployment module.

[0167] The first deployment module is used to deploy the first software package for implementing unit monitoring to multiple units respectively, so that each unit can obtain respective monitoring information in M ​​first time periods by running the first software package.

[0168] The second deployment module is used to deploy a second software package for implementing bottom-level monitoring to a bottom-level environment for supporting the unitized architecture, so that the unitized architecture can obtain bottom-level abnormality information by running the second software package.

[0169] According to an embodiment of the present disclosure, the indicator threshold range of each of the S dimensions is obtained in the following manner: a historical data set is obtained, wherein the historical data set includes sample monitoring information of multiple units in N second time periods, and the second time period is a historical time period relative to the first time period, wherein N is a positive integer greater than 1; the historical data set is input into the first neural network to obtain the indicator threshold range of each of the S dimensions.

[0170] According to an embodiment of the present disclosure, the historical data set also includes sample decision information of each of the multiple units in N second time periods, and the sample decision information includes decision operations when an abnormality occurs in the unit.

[0171] According to an embodiment of the present disclosure, the preset decision-making method is obtained by the following method: the historical data set is input into the second neural network to obtain a one-to-one correspondence between the decision operation and the candidate dimension matching information, wherein the candidate dimension matching information represents the relationship between the sub-sample monitoring information of each of the S dimensions and the indicator threshold range.

[0172] According to an embodiment of the present disclosure, the S dimensions include at least one of the following: CPU utilization, memory utilization, response time, business success rate, and key transaction success rate.

[0173] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging circuits, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0174] For example, the acquisition module 910, the first evaluation module 920, and the second evaluation module 930. Any multiple of them can be combined in one module / unit / sub-unit for implementation, or any one of them can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of these modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to an embodiment of the present disclosure, the acquisition module 910, the first evaluation module 920, and the second evaluation module 930. At least one of them can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware or in any appropriate combination of any of them. Alternatively, the acquisition module 910, the first evaluation module 920, and the second evaluation module 930. At least one of the embodiments may be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function may be performed.

[0175] It should be noted that the risk assessment device part for the unitized architecture in the embodiments of the present disclosure corresponds to the risk assessment method part for the unitized architecture in the embodiments of the present disclosure. The description of the risk assessment device part for the unitized architecture specifically refers to the risk assessment method part for the unitized architecture, which will not be repeated here.

[0176] Fig.10 A block diagram of an electronic device suitable for implementing a risk assessment method for a unitized architecture according to an embodiment of the present disclosure is schematically shown. Fig.10 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0177] like Fig.10 As shown, the computer electronic device 1000 according to the embodiment of the present disclosure includes a processor 1001, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1002 or the program loaded from the storage part 1009 to the random access memory (RAM) 1003. The processor 1001 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 1001 may also include an onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0178] In the RAM 1003, various programs and data necessary for the operation of the electronic device 1000 are stored. The processor 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004.

[0179] According to an embodiment of the present disclosure, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to the bus 1004. The electronic device 1000 may further include one or more of the following components connected to the input / output (I / O) interface 1005: an input portion 1006 including a keyboard, a mouse, etc.; an output portion 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 1008 including a hard disk, etc.; and a communication portion 1009 including a network interface card such as a LAN card, a modem, etc. The communication portion 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the input / output (I / O) interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage portion 1008 as needed.

[0180] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the risk assessment method for the unitized architecture according to the embodiment of the present disclosure is implemented.

[0181] In the present disclosure, a computer readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0182] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains a program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the risk assessment method for a unitized architecture provided by the embodiment of the present disclosure.

[0183] When the computer program is executed by the processor 1001, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0184] According to the embodiments of the present disclosure, program codes for executing the computer programs provided by the embodiments of the present disclosure may be written in any combination of one or more programming languages.

[0185] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. It should also be noted that in some alternative implementations, the functions marked in the blocks may also occur in an order different from that marked in the accompanying drawings.

[0186] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A risk assessment method for a unitized architecture, comprising: In response to receiving the risk assessment request, obtaining respective monitoring information of a plurality of units in the unitized architecture in M ​​first time periods, wherein the monitoring information includes respective sub-monitoring information of S dimensions, where M and S are both positive integers greater than 1; For each of the units, based on the respective indicator threshold ranges of the S dimensions, respectively evaluate the respective sub-monitoring information of the S dimensions to obtain respective sub-evaluation results of each of the units in the M first time periods; and Based on a preset decision-making method, a risk assessment result is determined according to the respective sub-assessment results of each of the units in the M first time periods, wherein the risk assessment result includes the respective health assessment values ​​and decision prompt information of the multiple units.

2. The method according to claim 1, wherein: The evaluating the sub-monitoring information of the S dimensions respectively based on the respective indicator threshold ranges of the S dimensions to obtain the respective sub-evaluation results of each of the units in the M first time periods includes: For each of the dimensions, according to the indicator threshold range of the dimension, the sub-monitoring information of the dimension is evaluated to obtain an intermediate evaluation result, wherein the intermediate evaluation result represents the relationship between the sub-monitoring information and the indicator threshold range; and For each of the first time periods, the intermediate evaluation results of the S dimensions within the first time period are determined as the sub-evaluation results.

3. The method according to claim 1, wherein: The preset decision mode includes a one-to-one correspondence between the decision operation and the candidate dimension matching information; The determining of the risk assessment result based on the preset decision-making method and according to the respective sub-assessment results of each of the units in the M first time periods includes: According to the sub-evaluation results, matching the plurality of candidate dimension matching information is performed to obtain target dimension matching information; and The decision prompt information is determined according to the decision operation corresponding to the target dimension matching information.

4. The method according to claim 3, wherein: In response to receiving the risk assessment request, underlying exception information of the unitized architecture is also obtained, the underlying exception information including sub-exception information of at least one unit; The method further comprises: For each of the first time periods, determining a first evaluation value according to the first weight and a first health impact value for the sub-abnormal information; determining a second evaluation value according to the second weight and the second health impact value for the decision operation; and The health evaluation value is determined according to the first evaluation value and the second evaluation value.

5. The method according to any one of claims 1 to 4, further comprising, after determining the risk assessment result based on the preset decision-making method and according to the respective sub-assessment results of each of the units in the M first time periods: The health evaluation values ​​of each of the multiple units are visualized to obtain a risk assessment view, wherein: In the risk assessment view, a plurality of colors are used to represent the range to which the health assessment value belongs; Determining at least one unit having an abnormality according to a color feature of the risk assessment schematic diagram; as well as Based on the risk assessment view, the decision prompt information is displayed at a preset position away from the at least one unit having the abnormality.

6. The method according to any one of claims 1 to 4, wherein: Each of the units is deployed with P applications; The method further includes, before obtaining respective monitoring information of multiple units in the unitized architecture in M ​​first time periods in response to receiving the risk assessment request: According to the attribute information of each of the applications, the Q applications are divided to obtain the multiple units, wherein each of the units is used to manage applications with the same attribute information, and the attribute information includes at least one of the following: channel attributes, data processing attributes and public service attributes.

7. The method according to claim 6, further comprising: Deploy a first software package for implementing unit monitoring to the multiple units respectively, so that each of the units obtains respective monitoring information in the M first time periods by running the first software package; as well as A second software package for implementing bottom-level monitoring is deployed to a bottom-level environment for supporting the unitized architecture, so that the unitized architecture obtains bottom-level abnormality information by running the second software package.

8. The method according to any one of claims 1 to 4, wherein: The indicator threshold ranges of the S dimensions are obtained in the following manner: Acquire a historical data set, wherein the historical data set includes sample monitoring information of each of the plurality of units in N second time periods, the second time period being a historical time period relative to the first time period, wherein N is a positive integer greater than 1; and The historical data set is input into the first neural network to obtain the indicator threshold range of each of the S dimensions.

9. The method according to claim 8, wherein: The historical data set also includes sample decision information of each of the plurality of units in N second time periods, the sample decision information including decision operations when an abnormality occurs in the unit; The preset decision-making method is obtained by: The historical data set is input into a second neural network to obtain a one-to-one correspondence between the decision operation and the candidate dimension matching information, wherein the candidate dimension matching information represents the relationship between the sub-sample monitoring information of each of the S dimensions and the indicator threshold range.

10. The method according to claim 1, wherein: The S dimensions include at least one of the following: CPU utilization, memory utilization, response time, business success rate, and key transaction success rate.

11. A risk assessment device for a unitized architecture, comprising: An acquisition module, configured to, in response to receiving a risk assessment request, acquire respective monitoring information of a plurality of units in the unitized architecture within M first time periods, wherein the monitoring information includes respective sub-monitoring information of S dimensions, where M and S are both positive integers greater than 1; A first evaluation module is used to evaluate, for each of the units, the respective sub-monitoring information of the S dimensions based on the respective indicator threshold ranges of the S dimensions, to obtain the respective sub-evaluation results of each of the units in the M first time periods; and The second assessment module is used to determine the risk assessment result based on a preset decision-making method and according to the respective sub-assessment results of each of the units in the M first time periods, wherein the risk assessment result includes the health assessment values ​​and decision prompt information of each of the multiple units.

12. An electronic device comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 10.

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

14. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images