System health assessment method, device and equipment based on dynamic migration assessment

Abstract

Embodiments of the present specification relate to a system health degree evaluation method and device based on dynamic migration evaluation. The method comprises: when a system scheduling request of a system is received, obtaining an index report of a current stage of the system and an index report of a historical stage corresponding to a last health degree evaluation result of the system; determining a health risk migration probability according to the index report of the current stage and the index report of the historical stage; and determining a final health degree evaluation result of a target system according to the health risk migration probability and the last health degree evaluation result. The method of the embodiments of the present specification solves the problem that the window period risk drift between the time point of the last health degree evaluation and the time point of the system scheduling request cannot be captured in real time in the prior art, thereby improving the system scheduling effect. In addition, the acquisition of the index report is triggered by the system scheduling request, thereby avoiding the problem of system performance degradation caused by active and frequent acquisition of the index report.

Description

Technical Field

[0001] The embodiments in this specification relate to the field of artificial intelligence technology, and in particular to a system health assessment method, apparatus, and device based on dynamic migration assessment. Background Technology

[0002] In various computer systems that rely on multi-stage data processing (such as banking business platforms, resource management systems, content service platforms, etc.), the stability of system operation and the accuracy of the final output results fundamentally depend on the result of the last health assessment. Once the last health assessment result is healthy, it is regarded as the benchmark for subsequent system operation and maintenance. If the last health assessment result is inaccurate, it will lead to poor system scheduling performance. Summary of the Invention

[0003] To address the problems existing in the prior art, embodiments of this specification provide a system health assessment method, apparatus, and device based on dynamic migration assessment. When scheduling the system, the method obtains the indicator report of the system in the current stage and the indicator report of the historical stage corresponding to the last health assessment result. The method determines the health risk migration probability based on the indicator report of the current stage and the indicator report of the historical stage, and determines the final health assessment result of the system during scheduling by combining the last health assessment result.

[0004] The specific technical solutions of the embodiments in this specification are as follows: On the one hand, embodiments of this specification provide a system health assessment method based on dynamic migration assessment, the method comprising: When a system scheduling request is received from the target system, the system obtains the indicator report of the target system in the current stage and the indicator report of the target system in the historical stage corresponding to the last health assessment result of the target system. The probability of health risk migration is determined based on the indicator reports of the current stage, the indicator reports of the historical stage, and the length of time between the last health assessment and the current time. The final health assessment result of the target system is determined based on the health risk migration probability and the result of the last health assessment.

[0005] Furthermore, the indicator report includes the values ​​of multiple indicators; Determining the probability of health risk migration based on the indicator reports of the current stage, the indicator reports of the historical stage, and the time between the last health assessment and the current time further includes: Extract the indicator values ​​of at least one predetermined indicator from the indicator report of the current stage and the indicator report of the historical stage, and use them as the current indicator value and the historical indicator value, respectively. The feature value corresponding to at least one feature of the predetermined indicator is calculated based on the current and historical indicator values ​​of the predetermined indicator and the time length between the last health assessment and the current time. The probability of health risk migration is calculated based on the characteristic values ​​of each predetermined indicator.

[0006] Furthermore, the features include at least difference features and trend features; Calculating the feature value corresponding to at least one feature of the predetermined indicator based on the current and historical indicator values ​​of the predetermined indicator and the time length between the last health assessment and the current time further includes: Calculate the difference between the current indicator value and the historical indicator value to obtain the indicator difference value in the feature value of the difference feature; Calculate the rate of change of the indicator in the feature value of the difference feature based on the indicator difference and the historical indicator value; The acceleration of indicator change in the characteristic value of the trend feature is calculated based on the difference between the indicators and the time between the last health assessment and the current time.

[0007] Furthermore, calculating the health risk migration probability based on the characteristic values ​​of each predetermined indicator further includes: The difference feature value and trend feature value are input into a pre-trained model for processing to obtain the health risk transfer probability.

[0008] Furthermore, the model is a logistic regression model; The formula for the logistic regression model is: P = 1 / (1+e (-z) ); z = Σ(β i,j ×X i,j ); Where P represents the probability of health risk migration, X i,j β represents the eigenvalue of the j-th feature of the i-th predetermined index. i,j This represents the coefficient of the j-th feature of the i-th predetermined indicator. The sample label Y is manually determined based on the system's operational status. For example, if the system's health status deteriorates within a certain period, Y=1 (health risk migration probability=1); if the system's health status remains unchanged within a certain period, Y=0 (health risk migration probability=0). Based on the manually determined sample labels according to the system's operational status, a certain number of system operational status samples (X,Y) are collected. A logistic regression model is constructed based on the labeled samples. Based on the constructed model, the probability of health risk migration within the system over a future period can be predicted.

[0009] Furthermore, determining the final health assessment result of the target system based on the health risk migration probability and the last health assessment result further includes: The health risk migration probability and the final health assessment result corresponding to the last health assessment result are determined based on a predetermined two-dimensional decision matrix.

[0010] Furthermore, when a system scheduling request from the target system is received, the method further includes: The evaluation strategy for the target system is determined based on the time interval between the last health assessment and the current time, as well as the result of the last health assessment.

[0011] Furthermore, the assessment strategies include exemption assessment, mandatory assessment, and sampling assessment.

[0012] On the other hand, embodiments of this specification also provide a system health assessment device based on dynamic migration assessment, the device comprising: The indicator report acquisition unit is used to acquire the indicator report of the target system in the current stage and the indicator report of the target system in the historical stage corresponding to the last health assessment result of the target system when a system scheduling request is received from the target system. The health risk migration probability determination unit is used to determine the health risk migration probability based on the indicator report of the current stage, the indicator report of the historical stage, and the time length between the time of the last health assessment and the current time. The final health assessment result determination unit is used to determine the final health assessment result of the target system based on the health risk migration probability and the last health assessment result.

[0013] On the other hand, embodiments of this specification also provide a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-described method.

[0014] On the other hand, embodiments of this specification also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0015] On the other hand, embodiments of this specification also provide a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method.

[0016] The method described in this specification, upon receiving a scheduling request from a target system, acquires the target system's current-stage indicator report and the historical-stage indicator report corresponding to the target system's last health assessment result. Then, it determines the health risk migration probability based on the current-stage and historical-stage indicator reports. Finally, it determines the target system's final health assessment result based on the health risk migration probability and the last health assessment result. This solves the problem in existing technologies where the window period risk drift between the last health assessment time and the system scheduling request time cannot be captured in real time, thereby improving system scheduling efficiency. Furthermore, in this specification's embodiments, the acquisition of indicator reports is triggered by the system scheduling request, thus avoiding system performance degradation caused by frequently and actively acquiring indicator reports. Compared to methods where a health assessment is performed manually every time a scheduling request is made, this method reduces the frequency of manual intervention. Staff only need to perform health assessments on the system according to the original cycle, eliminating the need for manual assessments every time a scheduling request is made, thus reducing the workload of staff. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 The figure shown is a schematic diagram of an implementation system for a system health assessment method based on dynamic migration assessment in an embodiment of this specification. Figure 2 The diagram shown is a flowchart illustrating how the probability of health risk migration is determined based on the indicator report of the current stage and the indicator report of the historical stage in an embodiment of this specification. Figure 3 The diagram shown is a flowchart illustrating the process of calculating the feature value corresponding to at least one feature of the predetermined indicator based on the current and historical indicator values ​​of the predetermined indicator in an embodiment of this specification. Figure 4 The diagram shown is a structural schematic of a system health assessment device based on dynamic migration assessment in an embodiment of this specification. Figure 5 The diagram shown is a structural schematic of the computer device in an embodiment of this specification.

[0019] [Explanation of Figure Markers]: 401. Indicator Report Acquisition Unit; 402. Unit for determining the probability of health risk migration; 403. Final Health Assessment Result Determination Unit; 502. Computer equipment; 504, Processor; 506. Memory; 508. Drive mechanism; 510. Input / output module; 512. Input devices; 514. Output devices; 516. Presentation equipment; 518. Graphical User Interface; 520. Network interface; 522. Communication link; 524. Communication bus. Detailed Implementation

[0020] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the embodiments of this specification.

[0021] It should be noted that the terms "first," "second," etc., in the description, claims, and accompanying drawings of the embodiments herein are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0022] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of the embodiments in this specification all comply with the relevant provisions of national laws and regulations.

[0023] It should be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the applicant has used or necessarily used the solution.

[0024] The inventors discovered that the reason for the poor system scheduling performance in existing technologies is that they do not consider the changes in system operation status during the time difference between the last health assessment and the current time. This time difference refers to the interval between the last health assessment and the actual system scheduling. During this interval, the system's operation status (e.g., data quality indicators, data processing indicators, security indicators, operational behavior indicators, system performance indicators, environmental consistency indicators, etc.) may change significantly. Therefore, there is a certain deviation between the last health assessment result and the actual health status. Using the last health assessment result as the benchmark for subsequent system scheduling will lead to poor system scheduling performance. Based on this discovery, embodiments of this specification provide a system health assessment method based on dynamic migration assessment. Figure 1 The diagram illustrates a system health assessment method based on dynamic migration evaluation, as described in an embodiment of this specification. While the diagram depicts the process of assessing the health of a target system, it may include more or fewer operational steps based on conventional or non-creative labor. The order of steps listed in the embodiment is merely one possible execution order among many and does not represent the only possible order. In actual system or device products, the method can be executed sequentially or in parallel, as shown in the embodiment or the accompanying drawings. Specifically, as... Figure 1 As shown, the method can be executed by a server and may include: Step 101: When a system scheduling request from the target system is received, obtain the indicator report of the target system in the current stage and the indicator report of the historical stage corresponding to the last health assessment result of the target system. Step 102: Determine the probability of health risk migration based on the indicator report of the current stage, the indicator report of the historical stage, and the time between the last health assessment and the current time; Step 103: Determine the final health assessment result of the target system based on the health risk migration probability and the last health assessment result.

[0025] The method described in this specification, upon receiving a scheduling request from a target system, acquires the target system's current-stage indicator report and the historical-stage indicator report corresponding to the target system's last health assessment result. Then, it determines the health risk migration probability based on the current-stage and historical-stage indicator reports. Finally, it determines the target system's final health assessment result based on the health risk migration probability and the last health assessment result. This solves the problem in existing technologies where the window period risk drift between the last health assessment time (time point) and the system scheduling request time (time point) cannot be captured in real time, thereby improving system scheduling efficiency. Furthermore, in this specification's embodiments, the acquisition of indicator reports is triggered by the system scheduling request, thus avoiding system performance degradation caused by frequently and actively acquiring indicator reports. Compared to methods where a health assessment is performed manually each time a scheduling request is made, this method reduces the frequency of manual intervention; staff only need to perform health assessments on the system according to the original cycle, reducing their workload.

[0026] In the embodiments of this specification, the target system can be a processing node in a distributed system. A strategy can be set to schedule each node in the distributed system. During scheduling, the health status of the processing nodes needs to be obtained, and tasks are assigned to the processing nodes based on their health status. Based on the existing environment, staff will periodically conduct health assessments of the processing nodes. The health assessment results can include a score for the processing node. Staff can also pre-divide multiple score levels and set corresponding decision actions for each score level. Decision actions can include "pass," "manual analysis," and / or "reject," thereby determining the decision action corresponding to the processing node, and determining whether to assign tasks to the processing node according to the decision action.

[0027] Because there is a certain time window between health assessment and scheduling of the target system, the health of the target system may change within this time window. Therefore, this specification proposes a system health assessment method based on dynamic migration assessment. In this specification embodiment, when a system scheduling request from the target system is received, the indicator report of the target system at the current stage (e.g., the current moment) and the indicator report of the historical stage corresponding to the last health assessment result of the target system are obtained. Then, the indicator report of the current stage and the indicator report of the historical stage are input into a pre-trained risk assessment model to obtain the health risk migration probability. The health risk migration probability represents the migration probability of the system's health changing from high to low within this time window. The higher the health risk migration probability, the higher the probability that the system's health will decrease.

[0028] Then, the final health assessment result of the system is determined based on the health risk migration probability and the result of the last health assessment. Specifically, the final health assessment result corresponding to the health risk migration probability and the result of the last health assessment can be determined according to a predetermined two-dimensional decision matrix.

[0029] In the embodiments of this specification, the two-dimensional decision matrix can be set by staff based on experience. The first dimension of the two-dimensional decision matrix can represent multiple levels of the probability of health risk migration, and the second dimension can represent multiple levels of the health assessment result. The elements in the two-dimensional decision matrix represent the decision actions in the final health assessment result.

[0030] For example, a two-dimensional decision matrix can be shown in Table 1: Table 1

[0031] In the embodiments of this specification, the level of health risk migration probability can be set by staff based on experience, including but not limited to high health risk migration probability and low health risk migration probability. In actual implementation, the actual level of health risk migration probability is determined based on the actual probability value of health risk migration. The level of health score result can also be set by staff based on experience, including but not limited to high score and low score. In actual implementation, the actual score level is determined based on the health score in the last health assessment result.

[0032] In the embodiments of this specification, the health score in the last health assessment result can be obtained by the staff analyzing the indicator reports of the historical stage corresponding to the last health assessment, which will not be elaborated in the embodiments of this specification.

[0033] In the embodiments of this specification, the indicator report includes the values ​​of multiple indicators. To save computational effort, according to one embodiment of this specification, the values ​​of representative indicators in the indicator report can be analyzed to obtain the probability of health risk migration. Specifically, as shown... Figure 2 As shown, determining the probability of health risk migration based on the indicator reports of the current stage, the indicator reports of the historical stage, and the time between the last health assessment and the current time further includes: Step 201: Extract the indicator values ​​of at least one predetermined indicator from the indicator report of the current stage and the indicator report of the historical stage, and use them as the current indicator value and the historical indicator value. Step 202: Calculate the feature value corresponding to at least one feature of the predetermined indicator based on the current and historical indicator values ​​of the predetermined indicator and the time length between the last health assessment and the current time; Step 203: Calculate the health risk migration probability based on the characteristic values ​​of each predetermined indicator.

[0034] In the embodiments of this specification, the indicators in the indicator report may include data quality indicators, data processing indicators, security indicators, operational behavior indicators, system real-time performance indicators, environmental consistency indicators, etc.

[0035] Data quality metrics can include data integrity (whether required fields are complete), data format compliance rate (such as image format, file size, etc.), and data duplication (whether it is duplicated with existing data in the system); system processing metrics can include data preprocessing time, data storage success rate, and data index creation status; security metrics can include data encryption strength and data transmission security score; operational behavior metrics can include operational sequence compliance (such as whether steps are skipped), operation frequency (number of operations per unit time), and operation latency (time consumed for each step); system real-time performance metrics can include CPU utilization, memory usage, and network latency; and environmental consistency metrics can include the consistency between the device used in this operation and historical devices, and changes in IP address geographical location.

[0036] In the embodiments of this specification, staff can select one or more representative indicators from multiple indicators based on their experience as predetermined indicators, or they can identify the top N indicators that are most important for predicting the migration probability of health risks through a pre-trained model as predetermined indicators. This ensures that the indicator system of the embodiments of this specification focuses on the core dimensions with the highest risk discrimination.

[0037] For example, a general health risk assessment model can be trained using a large number of samples, multiple indicators from a single point in time, and health assessment results over a future period as labels.

[0038] To further improve the performance of the health risk assessment model, a windowed modeling approach can be adopted, which divides the time between the last health assessment and the current time into multiple time windows, and trains an independent health risk assessment model for each time window.

[0039] In the embodiments of this specification, the indicator value of at least one predetermined indicator in the indicator report of the current stage is extracted as the current indicator value, and the indicator value of the predetermined indicator in the indicator report of the historical stage is extracted as the historical indicator value. Then, based on the current indicator value and the historical indicator value, the feature value corresponding to at least one feature of the predetermined indicator is calculated. Then, the feature value is used as input, and a pre-trained model is used to calculate the corresponding health risk migration probability.

[0040] To improve the accuracy of calculating the probability of health risk migration, the embodiments in this specification divide the features into difference features and trend features. Difference features include the difference between indicators and the rate of change of indicators, while trend features include the acceleration of indicator changes.

[0041] like Figure 3 As shown, calculating the feature value corresponding to at least one feature of the predetermined indicator based on the current and historical indicator values ​​of the predetermined indicator and the time length between the last health assessment and the current time further includes: Step 301: Calculate the difference between the current indicator value and the historical indicator value to obtain the indicator difference value in the feature value of the difference feature; Step 302: Calculate the rate of change of the indicator in the feature value of the difference feature based on the indicator difference and the historical indicator value; Step 303: Calculate the acceleration of indicator change in the feature value of the trend feature based on the difference between the indicators and the time between the last health assessment and the current time.

[0042] In the embodiments of this specification, for each predetermined indicator, the difference between the current indicator value and the historical indicator value is calculated as the indicator difference value of the predetermined indicator. Then, the ratio between the indicator difference value and the historical indicator value is calculated as the indicator change rate of the predetermined indicator. Then, the indicator difference value is used as the numerator, and the time length between the last health assessment time and the current time is used as the denominator to calculate the score, thus obtaining the indicator change acceleration of the predetermined indicator. Therefore, the indicator difference value, indicator change rate, and indicator change acceleration of each predetermined indicator can be obtained.

[0043] Then, the differences between all predetermined indicators, the rate of change of indicators, and the acceleration of change of indicators are input into the model to calculate the probability of health risk migration.

[0044] In the embodiments of this specification, the model type can be decision tree, random forest combined with SHAP analysis, etc., and the embodiments of this specification are not limited thereto.

[0045] Preferably, the model used in the embodiments of this specification is a logistic regression model. The formula for the logistic regression model is: P = 1 / (1+e (-z) ); z = Σ(β i,j ×X i,j ); Where P represents the probability of health risk migration, X i,j β represents the eigenvalue of the j-th feature of the i-th predetermined index. i,j This represents the coefficient of the j-th characteristic of the i-th predetermined index. Characteristic value X i,jIt has been normalized to avoid the influence of dimensions.

[0046] In the embodiments of this specification, each feature of each predetermined indicator is used as the independent variable, and the health risk migration probability determined by the staff based on experience is used as the dependent variable. The above-mentioned logistic regression model is trained to obtain the coefficient β of each feature in each indicator.

[0047] According to one embodiment of this specification, if the decision-making action is subject to manual review, in order to provide staff with systematic reference information, this embodiment of the specification can generate a contribution report for each predetermined indicator and provide the contribution report to the staff as reference information for manual review.

[0048] In the embodiments of this specification, the contribution report includes reference features selected from the features of multiple predetermined indicators based on the contribution, the contribution degree of the reference features, and the contribution direction.

[0049] The formula for calculating contribution is as follows:

[0050] Among them, S i,j This represents the contribution of the j-th feature of the i-th predetermined indicator.

[0051] Then, the top M features in terms of contribution are selected as reference features, and the contribution direction is determined based on the correlation between the reference features and the probability of health risk migration.

[0052] The selected reference features, their contribution level, and contribution direction are filled into the contribution report so that staff can determine the system's final decision action (pass or reject) based on the contribution report.

[0053] According to one embodiment of this specification, in order to further reduce the computational load, this embodiment abandons the method of comprehensive evaluation and selectively evaluates the target system, thereby reducing the total computational load of the evaluation. Specifically, when a system scheduling request from the target system is received, the method further includes: Based on the time elapsed between the last health assessment and the current time, and the result of the last health assessment, an assessment strategy for the target system is determined. The assessment strategy includes exemption assessment, mandatory assessment, and sampling assessment.

[0054] In the embodiments of this specification, "exempt evaluation" means that steps such as determining the health risk migration probability of the target system are not required, and the health of the target system is directly considered to meet the requirements for task allocation. "Forced evaluation" means that steps such as determining the health risk migration probability of the target system are required, and the health of the target system is determined based on the final health evaluation result to determine whether the health of the target system meets the requirements for task allocation. "Sampling evaluation" means that a sampling algorithm is used to select a portion of the processing nodes from all processing nodes in the distributed system to perform steps such as determining the health risk migration probability of the target system. Processing nodes not selected do not need to perform these steps, and the health of the target system is directly considered to meet the requirements for task allocation.

[0055] In the embodiments described in this specification, staff first establish a decision matrix based on experience. The first dimension of the decision matrix represents the time interval range, the second dimension represents the health level, and the elements of the decision matrix represent the assessment strategy. First, the time interval range corresponding to the length of time between the last health assessment and the current time is determined. Then, the health level corresponding to the health score in the last health assessment result is determined, thereby determining the corresponding assessment strategy in the decision matrix.

[0056] For example, the decision matrix can be as shown in Table 2, where r1 and r2 can be empirical values: Table 2

[0057] Based on the same inventive concept, embodiments of this specification also provide a system health assessment device based on dynamic migration assessment, such as... Figure 4 As shown, the device includes: The indicator report acquisition unit 401 is used to acquire the indicator report of the target system in the current stage and the indicator report of the target system in the historical stage corresponding to the last health assessment result of the target system when a system scheduling request of the target system is received. The health risk migration probability determination unit 402 is used to determine the health risk migration probability based on the indicator report of the current stage, the indicator report of the historical stage, and the time length between the time of the last health assessment and the current time. The final health assessment result determination unit 403 is used to determine the final health assessment result of the target system based on the health risk migration probability and the last health assessment result.

[0058] The beneficial effects obtained by the above-described device are the same as those obtained by the above-described method, and will not be described in detail in the embodiments of this specification.

[0059] like Figure 5As shown, a computer device provided in this embodiment can be used to execute the methods described herein. The computer device 502 may include one or more processors 504, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The computer device 502 may also include any memory 506 for storing information of any kind, such as code, settings, data, etc. Without limitation, for example, memory 506 may include any type of RAM, any type of ROM, flash memory, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent a fixed or removable component of the computer device 502. In one case, when processor 504 executes associated instructions stored in any memory or combination of memories, the computer device 502 may perform any operation of the associated instructions. The computer device 502 also includes one or more drive mechanisms 508 for interacting with any memory, such as hard disk drive mechanisms, optical disk drive mechanisms, etc.

[0060] Computer device 502 may also include an input / output module 510 (I / O) for receiving various inputs (via input device 512) and providing various outputs (via output device 514). A specific output mechanism may include a presentation device 516 and an associated graphical user interface (GUI) 518. In other embodiments, the input / output module 510 (I / O), input device 512, and output device 514 may be omitted, and the device may function solely as a computer device within a network. Computer device 502 may also include one or more network interfaces 520 for exchanging data with other devices via one or more communication links 522. One or more communication buses 524 couple the components described above together.

[0061] Communication link 522 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. Communication link 522 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0062] This specification also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0063] This specification also provides computer-readable instructions, wherein when a processor executes the instructions, the program therein causes the processor to perform the above-described method.

[0064] It should be understood that in the various embodiments of this specification, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0065] It should also be understood that, in the embodiments of this specification, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the embodiments of this specification, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0066] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the embodiments in this specification.

[0067] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0068] In the embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0069] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described in this specification, depending on actual needs.

[0070] Furthermore, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0071] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this specification, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this specification. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0072] This specification describes the principles and implementation methods of the embodiments using specific examples. The above descriptions of the embodiments are only for the purpose of helping to understand the methods and core ideas of the embodiments in this specification. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the embodiments in this specification. Therefore, the content of this specification should not be construed as a limitation on the embodiments in this specification.

Claims

1. A system health assessment method based on dynamic migration assessment, characterized in that, The method includes: When a system scheduling request is received from the target system, the system obtains the indicator report of the target system in the current stage and the indicator report of the target system in the historical stage corresponding to the last health assessment result of the target system. The probability of health risk migration is determined based on the indicator reports of the current stage, the indicator reports of the historical stage, and the length of time between the last health assessment and the current time. The final health assessment result of the target system is determined based on the health risk migration probability and the result of the last health assessment.

2. The method according to claim 1, characterized in that, The indicator report includes the values ​​of multiple indicators; Determining the probability of health risk migration based on the indicator reports of the current stage, the indicator reports of the historical stage, and the time between the last health assessment and the current time further includes: Extract the indicator values ​​of at least one predetermined indicator from the indicator report of the current stage and the indicator report of the historical stage, and use them as the current indicator value and the historical indicator value, respectively. The feature value corresponding to at least one feature of the predetermined indicator is calculated based on the current and historical indicator values ​​of the predetermined indicator and the time length between the last health assessment and the current time. The probability of health risk migration is calculated based on the characteristic values ​​of each predetermined indicator.

3. The method according to claim 2, characterized in that, The features include at least difference features and trend features; Calculating the feature value corresponding to at least one feature of the predetermined indicator based on the current and historical indicator values ​​of the predetermined indicator and the time length between the last health assessment and the current time further includes: Calculate the difference between the current indicator value and the historical indicator value to obtain the indicator difference value in the feature value of the difference feature; Calculate the rate of change of the indicator in the feature value of the difference feature based on the indicator difference and the historical indicator value; The acceleration of indicator change in the characteristic value of the trend feature is calculated based on the difference between the indicators and the time between the last health assessment and the current time.

4. The method according to claim 3, characterized in that, Calculating the health risk migration probability based on the characteristic values ​​of each predetermined indicator further includes: The feature values ​​of the difference feature and the feature values ​​of the trend feature are input into a pre-trained model for processing to obtain the health risk transfer probability.

5. The method according to claim 4, characterized in that, The model is a logistic regression model; The formula for the logistic regression model is: P = 1 / (1+e (-z) ); z = Σ(β i,j ×X i,j ); Where P represents the probability of health risk migration, X i,j β represents the eigenvalue of the j-th feature of the i-th predetermined index. i,j It represents the coefficient of the j-th characteristic of the i-th predetermined index.

6. The method according to claim 1, characterized in that, Determining the final health assessment result of the target system based on the health risk migration probability and the result of the last health assessment further includes: The health risk migration probability and the final health assessment result corresponding to the last health assessment result are determined based on a predetermined two-dimensional decision matrix.

7. The method according to claim 1, characterized in that, When a system scheduling request from the target system is received, the method further includes: The evaluation strategy for the target system is determined based on the time interval between the last health assessment and the current time, as well as the result of the last health assessment.

8. The method according to claim 7, characterized in that, The assessment strategies include exemption assessment, mandatory assessment, and sampling assessment.

9. A system health assessment device based on dynamic migration assessment, characterized in that, The device includes: The indicator report acquisition unit is used to acquire the indicator report of the target system in the current stage and the indicator report of the target system in the historical stage corresponding to the last health assessment result of the target system when a system scheduling request is received from the target system. The health risk migration probability determination unit is used to determine the health risk migration probability based on the indicator report of the current stage, the indicator report of the historical stage, and the time length between the time of the last health assessment and the current time. The final health assessment result determination unit is used to determine the final health assessment result of the target system based on the health risk migration probability and the last health assessment result.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 8.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 8.

Images