Evaluation method and device and electronic equipment

Abstract

The invention discloses an evaluation method and apparatus, and an electronic device. The evaluation method comprises the steps of obtaining normalized data of a first number of indexes of a target device in a preset time period; wherein the indexes represent the operation state of the target equipment, and each index comprises a second number of normalized data in a preset time period; determining a discrete degree value of each index in the first number of indexes according to the second number of normalized data; the dispersion degree numerical value reflects the volatility of the evaluation data corresponding to the index; dynamically allocating a weight corresponding to each index in the first number of indexes according to the dispersion degree value by adopting a dynamic adjustment strategy; and according to the second number of normalized data and the weight corresponding to each index, determining the health degree of the target equipment so as to evaluate the health state of the target equipment.

Description

Technical Field

[0001] The present application relates to the field of electronic technology, and in particular to an evaluation method, device, and electronic equipment. Background Art

[0002] Hybrid cloud platforms typically involve operating systems, databases, middleware, hardware servers, network devices, storage devices, Docker, Kubernetes and other infrastructure, which require comprehensive monitoring to ensure high availability, performance and security of the system.

[0003] Currently, infrastructure-related performance monitoring data is often only displayed statically, or problems are categorized based on threshold alarms, or the health status of infrastructure equipment is assessed by simply presetting fixed weights based on monitoring indicator priorities. However, these methods lack in-depth analysis and cannot provide accurate decision-making basis for operation and maintenance personnel. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide an evaluation method, device, and electronic device.

[0005] In a first aspect, this embodiment provides an evaluation method, including:

[0006] Obtaining normalized data of a first number of indicators of the target device within a preset time period; wherein the indicators represent an operating state of the target device, and each indicator includes a second number of normalized data within the preset time period;

[0007] Determining a dispersion value of each indicator in the first number of indicators based on the second number of normalized data; the dispersion value reflects the volatility of the evaluation data corresponding to the indicator;

[0008] Adopting a dynamic adjustment strategy to dynamically assign a weight corresponding to each indicator in the first number of indicators according to the discrete degree value;

[0009] The health of the target device is determined based on the second number of normalized data and the weight corresponding to each indicator to evaluate the health status of the target device.

[0010] In a possible implementation, the weight corresponding to the indicator is positively correlated with the discrete degree value corresponding to the indicator.

[0011] In a possible implementation, dynamically allocating a weight corresponding to each indicator in the first number of indicators according to the discrete degree value includes:

[0012] Adding the dispersion degree values ​​of each indicator in the first number of indicators to obtain a first value;

[0013] A weight corresponding to each indicator in the first number of indicators is dynamically assigned according to the first value and the discrete degree value of each indicator.

[0014] In one possible implementation, determining the health of the target device according to the second number of normalized data and the weight corresponding to each indicator includes:

[0015] Determining the health level corresponding to each indicator of the target device based on the second amount of normalized data;

[0016] The health of the target device is determined based on the health of each indicator of the target device and the weight of each indicator.

[0017] In one possible implementation, determining the health level corresponding to each indicator of the target device based on the second number of normalized data includes:

[0018] Determining a mean of the second number of normalized data based on the second number of normalized data;

[0019] The health level corresponding to each indicator of the target device is determined based on the second number of normalized data and the mean.

[0020] In one possible implementation, determining the health level corresponding to each indicator of the target device based on the second number of normalized data and the mean value includes:

[0021] Subtracting each normalized data in the second number of normalized data from the mean value one by one to obtain a second number of difference values;

[0022] According to the second number of differences, establishing an exponential decay relationship between the health level corresponding to each indicator of the target device and the square of the second number of differences;

[0023] Determine the health of each indicator of the target device based on the exponential decay relationship.

[0024] In one possible implementation, determining the health of the target device according to the health corresponding to each indicator of the target device and the weight corresponding to each indicator includes:

[0025] The health of each indicator in the first number of indicators is multiplied by the weight of each indicator one by one and then added together to obtain the health of the target device.

[0026] In a possible implementation, before obtaining normalized data of a first number of indicators of the target device within a preset time period, the method includes:

[0027] Obtaining raw data of a first number of indicators of the target device within a preset time period;

[0028] Normalize the original data of each indicator separately to obtain the normalized data of each indicator within a preset time period.

[0029] In a second aspect, an embodiment of the present application provides an evaluation device, comprising:

[0030] A first acquisition module is configured to acquire normalized data of a first number of indicators of the target device within a preset time period; wherein the indicators represent the operating state of the target device, and each indicator includes a second number of normalized data within the preset time period;

[0031] The first determining module is configured to determine a dispersion value of each indicator in the first number of indicators based on the second number of normalized data; the dispersion value reflects the volatility of the evaluation data corresponding to the indicator;

[0032] An allocation module is configured to adopt a dynamic adjustment strategy to dynamically allocate a weight corresponding to each indicator in the first number of indicators according to the discrete degree value;

[0033] The second determination module is configured to determine the health of the target device according to the second number of normalized data and the weight corresponding to each indicator to evaluate the health status of the target device.

[0034] In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores an executable program, and the processor executes the executable program to implement the following steps:

[0035] Obtaining normalized data of a first number of indicators of the target device within a preset time period; wherein the indicators represent an operating state of the target device, and each indicator includes a second number of normalized data within the preset time period;

[0036] Determining a dispersion value of each indicator in the first number of indicators based on the second number of normalized data; the dispersion value reflects the volatility of the evaluation data corresponding to the indicator;

[0037] Adopting a dynamic adjustment strategy to dynamically assign a weight corresponding to each indicator in the first number of indicators according to the discrete degree value;

[0038] The health of the target device is determined based on the second number of normalized data and the weight corresponding to each indicator to evaluate the health status of the target device. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flowchart of an evaluation method provided in an embodiment of the present application;

[0040] Figure 2 This is a flow chart of step S300 of an embodiment of the present application;

[0041] Figure 3 This is a flow chart of step S400 of an embodiment of the present application;

[0042] Figure 4 A schematic diagram of the structure of an evaluation device provided in an embodiment of the present application;

[0043] Figure 5 It is a diagram showing the fluctuation of raw data of the metric CPU usage percentage in "I / O wait" mode (priority 1);

[0044] Figure 6 It is a diagram showing the volatility of raw data of the indicator free space (in bytes) of the file system (priority 2);

[0045] Figure 7 The figure below shows the volatility of the raw data of the number of disk read operations completed (priority 3). DETAILED DESCRIPTION

[0046] Various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0047] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but merely as an example of an embodiment. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.

[0048] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0049] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0050] It should also be understood that although the present application has been described with reference to certain specific examples, those skilled in the art will readily be able to implement many other equivalent forms of the present application.

[0051] The above and other aspects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings.

[0052] Specific embodiments of the present application will be described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments described are merely examples of the present application and may be implemented in a variety of ways. Familiar and / or repetitive functions and structures are not described in detail to avoid obscuring the present application with unnecessary or redundant details. Therefore, the specific structural and functional details described herein are not intended to be limiting, but rather serve merely as a basis and representative basis for the claims to teach those skilled in the art to variously utilize the present application with substantially any suitable detailed structure.

[0053] This specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may all refer to one or more of the same or different embodiments according to the present application.

[0054] With the development of information technology, the scale of monitoring equipment on hybrid cloud platforms has increased, making equipment operation and maintenance more difficult. Some existing evaluation methods fail to fully consider the volatility of evaluation data for different indicators. As a result, when the evaluation data of some indicators fluctuates significantly, the evaluation results may not be accurate or timely, and cannot provide accurate decision-making basis for operation and maintenance personnel.

[0055] Taking Linux devices as an example, there are 15 indicators in total. Linux devices can be divided into three levels according to the priority of the indicators. This priority level is already divided for Linux devices.

[0056] There are three indicators with priority 1, including: disk I / O operation time (in seconds), CPU usage percentage in "busy" mode, and CPU usage percentage in "I / O wait" mode.

[0057] There are 10 indicators with a priority of 2, including: available space in the file system (in bytes), memory usage, swap space usage, file node (inode) usage in the file system, number of bytes read from the disk, number of bytes written to the disk, disk read efficiency, disk write efficiency, amount of data received and sent by the network (in bytes), and bandwidth rate of data transmitted by the network interface.

[0058] There are two indicators with a priority of 3, including the number of completed disk read operations and the number of completed disk write operations.

[0059] Figure 5 、 Figure 6 and Figure 7 The raw data (i.e., evaluation data) corresponding to some indicators are shown, taking three indicators of different priorities as an example. Figure 5It is a diagram showing the fluctuation of raw data of the metric CPU usage percentage in "I / O wait" mode (priority 1); Figure 6 It is a diagram showing the volatility of raw data of the indicator free space (in bytes) of the file system (priority 2); Figure 7 The figure below shows the volatility of the raw data of the number of disk read operations completed (priority 3). Figure 5 、 Figure 6 and Figure 7 The horizontal axis is time, and the vertical axis is the indicator value, that is, the value of the original data (i.e., evaluation data) corresponding to the indicator.

[0060] from Figure 5 、 Figure 6 and Figure 7 As can be observed, the changes in the evaluation data corresponding to each indicator are different. Existing equipment health assessment methods generally rely on preset fixed weights to calculate the impact of each indicator on the equipment health score. For example, for the 15 indicators mentioned above, fixed weights are preset for indicators of different priorities. This method does not fully consider the volatility of the evaluation data of different indicators. As a result, when the evaluation data of some indicators fluctuates significantly, the evaluation results may not be accurate or timely, and cannot provide accurate decision-making basis for operation and maintenance personnel.

[0061] To this end, the embodiments of the present application provide an evaluation method, device, and electronic device that comprehensively consider the impact of different indicators on the health of the target device, can automatically adapt to changes in actual original data, and pay more attention to key indicators with greater volatility, thereby improving the sensitivity and adaptability of target device health monitoring and enhancing the refinement of target device health assessment.

[0062] The evaluation method of this application is described in detail below with reference to the accompanying drawings. Figure 1 A flow chart of the evaluation method provided in the embodiment of the present application is shown in FIG. Figure 1 As shown, the evaluation method is applied to infrastructure equipment, and the evaluation method includes:

[0063] S100, obtaining normalized data of a first number of indicators of a target device within a preset time period; wherein the indicators represent an operating state of the target device, and each indicator includes a second number of normalized data within the preset time period;

[0064] The target device may be a hybrid cloud platform infrastructure device, such as a Linux device.

[0065] The indicators can be the time of disk I / O operations (in seconds), the percentage of CPU usage in "busy" mode, the percentage of CPU usage in "I / O wait" mode, the free space in the file system (in bytes), the usage of memory, the usage of swap space, the usage of file nodes (inodes) in the file system, the number of bytes read from the disk, the number of bytes written to the disk, the disk read efficiency, the disk write efficiency, the amount of data received and sent by the network (in bytes), the bandwidth rate of the network interface to transmit data, the number of completed disk read operations, the number of completed disk write operations, etc.

[0066] The preset time period is the time period between the historical moment and the current moment, for example, the past 30 days, the past 60 days, etc. Normalized data refers to the data after normalization processing of the original data (i.e., evaluation data).

[0067] S200, determining the dispersion value of each indicator in the first number of indicators based on the second number of normalized data; the dispersion value reflects the volatility of the evaluation data corresponding to the indicator, that is, the dispersion value reflects the volatility of the indicator value corresponding to the indicator.

[0068] The dispersion degree value may be a standard deviation calculated based on the second number of normalized numbers.

[0069] The number of indicators is m (i.e., the first number), and the number of normalized data is n (i.e., the second number). Both m and n are integers greater than 0.

[0070] For example, each normalized data is denoted as x i ′ , i∈{1, 2, ...n}; according to n normalized data x i ′ , calculate the mean μ of a single index iddex and standard deviation σ index ,as follows;

[0071]

[0072] The number of indicators is m, that is, index∈{1, 2,…m}.

[0073] S300, using a dynamic adjustment strategy to dynamically assign a weight corresponding to each indicator in the first number of indicators according to the discrete degree value;

[0074] The discrete degree value of each indicator is determined based on the normalized data of each indicator within a preset time period. By dynamically adjusting the weight, it can be distributed according to the volatility of each indicator value (that is, the evaluation data corresponding to each indicator), so that the system pays more attention to key indicators with greater volatility in the calculation of health status, and enhances sensitivity to abnormal conditions.

[0075] S400 : Determine the health of the target device according to the second number of normalized data and the weight corresponding to each indicator to evaluate the health status of the target device.

[0076] The health of the target device is determined based on the n normalized data and the weight corresponding to each indicator to evaluate the health status of the target device.

[0077] The evaluation method provided in this embodiment dynamically adjusts the weights of various indicators, flexibly assigning weights based on the volatility of the target device's status, thereby more accurately reflecting the health status of the target device. Compared to traditional fixed-weight methods, this application can flexibly adjust weights based on the volatility of each indicator value, improving the accuracy and timeliness of target device health assessments, thereby providing accurate decision-making basis for operations and maintenance personnel.

[0078] In some embodiments, the weight corresponding to the indicator is positively correlated with the discreteness value corresponding to the indicator, that is, the weight corresponding to the indicator increases as the discreteness value corresponding to the indicator increases.

[0079] In some embodiments, as Figure 2 As shown, according to the discrete degree value, the weight corresponding to each indicator in the first number of indicators is dynamically assigned, including:

[0080] S301, adding the discrete degree values ​​of each indicator in the first number of indicators to obtain a first value;

[0081] S302: Dynamically assign a weight corresponding to each indicator in the first number of indicators according to the first value and the discrete degree value of each indicator.

[0082] Specifically, the standard deviation σ of each indicator in the m indicators index Add up to get the first value, according to the first value and the standard deviation σ of each indicator index , dynamically assign the weight w corresponding to each indicator in m indicators index

[0083] For example, according to the standard deviation σ of each indicator index The weight w corresponding to a single indicator can be calculated by the following formula index .

[0084]

[0085] This embodiment uses a dynamic weight adjustment strategy based on the weight influence of a single indicator on the health of the target device, and dynamically allocates the weight w according to the volatility of the evaluation data corresponding to the indicator. index , which improves the accuracy and timeliness of health assessment of target devices.

[0086] In some embodiments, as Figure 3 As shown, determining the health of the target device based on the second amount of normalized data and the weight corresponding to each indicator includes:

[0087] S401, determining the health level corresponding to each indicator of the target device based on a second number of normalized data;

[0088] S402 : Determine the health of the target device according to the health corresponding to each indicator of the target device and the weight corresponding to each indicator.

[0089] Specifically, based on n normalized data, the health degree corresponding to each indicator of the target device is determined, and then the health degree of the target device is determined based on the health degree corresponding to each indicator of the target device and the weight corresponding to each indicator. This application can flexibly adjust the weight according to the volatility of the evaluation data corresponding to each indicator, thereby improving the accuracy and timeliness of the health assessment of the target device.

[0090] In some embodiments, determining the health level corresponding to each indicator of the target device based on the second amount of normalized data includes:

[0091] Determining a mean of the second number of normalized data based on the second number of normalized data;

[0092] The health level corresponding to each indicator of the target device is determined based on the second number of normalized data and the mean.

[0093] Specifically, n normalized data x i ′ Substituting into the formula of the above embodiment, the mean μ of the single index index can be calculated index , then according to n normalized data x i ′ and mean μ index , determine the health level corresponding to each indicator of the target device.

[0094] In some embodiments, determining the health level corresponding to each indicator of the target device based on the second number of normalized data and the mean value includes:

[0095] Subtracting each normalized data in the second number of normalized data from the mean value one by one to obtain a second number of difference values;

[0096] According to the second number of differences, establishing an exponential decay relationship between the health level corresponding to each indicator of the target device and the square of the second number of differences;

[0097] Determine the health of each indicator of the target device based on the exponential decay relationship.

[0098] Specifically, for the health calculation of a single indicator, the sensitivity to extreme indicator values ​​can be improved by introducing exponential decay.

[0099] According to n normalized data x i ′ and mean μ index , the health degree f(index) corresponding to a single indicator of the target device is calculated using the following formula.

[0100]

[0101] The embodiment of the present application introduces exponential decay to calculate the health corresponding to each indicator, which can improve the sensitivity to extreme indicator values, that is, improve the sensitivity to indicators with greater volatility, and can further improve the accuracy of determining the health of the target device.

[0102] In some embodiments, determining the health of the target device according to the health corresponding to each indicator of the target device and the weight corresponding to each indicator includes:

[0103] The health of each indicator in the first number of indicators is multiplied by the weight of each indicator one by one and then added together to obtain the health of the target device.

[0104] Specifically, for the target device m indicators, according to the health degree f (index) corresponding to each indicator of the target device and the weight w corresponding to each indicator index , use the following formula to determine the health_score of the target device.

[0105]

[0106] In some embodiments, before obtaining normalized data of a first number of indicators of the target device within a preset time period, the method includes:

[0107] Obtaining raw data of a first number of indicators of the target device within a preset time period;

[0108] Normalize the original data of each indicator separately to obtain the normalized data of each indicator within a preset time period.

[0109] For example, the preset time period may be the latest 30 days, 60 days, etc., and the following description will be made taking the latest 30 days as an example.

[0110] Specifically, raw data (evaluation data) of m indicators of the target device within a preset time period is collected; the raw data content may include a timestamp and the indicator value (the value of the evaluation data). For example, for each indicator, raw data can be collected every 5 minutes for the past 30 days, for a total of 288 points of historical data (raw data) per day, for a total of 8640 raw data points, denoted as n, i.e., n = 8640 in this example.

[0111] Then, the original data of the m indicators within a preset time period are preprocessed; optionally, the original data can be preprocessed using a linear interpolation method to fill in missing data in the original data.

[0112] Then, the pre-processed original data of the m indicators within the preset time period are normalized to obtain the normalized data of the m indicators within the preset time period.

[0113] For example, the original data of a single indicator is standardized using Min-Max Scaling, and the normalized data x of a single indicator within a preset time period is obtained by the following formula: i ′ .

[0114]

[0115] x i is the original data, x i ′ is the normalized data (i.e. normalized data), x min is the minimum value in the original data, x max is the maximum value in the original data.

[0116] In the embodiment of the present application, the original data is normalized to scale the value of the original data to a target range, for example, the target range may be [0, 1] or [1, 1], so that the weight and health corresponding to each indicator can be determined based on the normalized data.

[0117] Based on the same inventive concept, the embodiment of the present application provides an evaluation device, Figure 4 This is a schematic diagram of the structure of the evaluation device provided in the embodiment of the present application, as shown in FIG. Figure 4 As shown, the evaluation device includes:

[0118] A first acquisition module is configured to acquire normalized data of a first number of indicators of the target device within a preset time period; wherein the indicators represent the operating state of the target device, and each indicator includes a second number of normalized data within the preset time period;

[0119] The first determining module is configured to determine a dispersion value of each indicator in the first number of indicators based on the second number of normalized data; the dispersion value reflects the volatility of the evaluation data corresponding to the indicator;

[0120] An allocation module is configured to adopt a dynamic adjustment strategy to dynamically allocate a weight corresponding to each indicator in the first number of indicators according to the discrete degree value;

[0121] The second determination module is configured to determine the health of the target device according to the second number of normalized data and the weight corresponding to each indicator to evaluate the health status of the target device.

[0122] The evaluation device provided in the embodiments of this application dynamically adjusts the weights of various indicators, flexibly assigning weights based on the volatility of the target device's status, thereby more accurately reflecting the health status of the target device. Compared to traditional fixed-weight methods, this application can flexibly adjust weights based on the volatility of each indicator value, improving the accuracy and timeliness of target device health assessments, thereby providing accurate decision-making basis for operations and maintenance personnel.

[0123] In some embodiments, the weight corresponding to the indicator is positively correlated with the discrete degree value corresponding to the indicator.

[0124] In some embodiments, the first determining module is specifically configured to:

[0125] Adding the dispersion degree values ​​of each indicator in the first number of indicators to obtain a first value;

[0126] A weight corresponding to each indicator in the first number of indicators is dynamically assigned according to the first value and the discrete degree value of each indicator.

[0127] In some embodiments, the second determining module is further specifically configured to:

[0128] Determining the health level corresponding to each indicator of the target device based on the second amount of normalized data;

[0129] The health of the target device is determined based on the health of each indicator of the target device and the weight of each indicator.

[0130] In some embodiments, the second determining module is further specifically configured to:

[0131] Determining a mean of the second number of normalized data based on the second number of normalized data;

[0132] The health level corresponding to each indicator of the target device is determined based on the second number of normalized data and the mean.

[0133] In some embodiments, the second determining module is further specifically configured to:

[0134] Subtracting each normalized data in the second number of normalized data from the mean value one by one to obtain a second number of difference values;

[0135] According to the second number of differences, establishing an exponential decay relationship between the health level corresponding to each indicator of the target device and the square of the second number of differences;

[0136] Determine the health of each indicator of the target device based on the exponential decay relationship.

[0137] In some embodiments, the second determining module is further specifically configured to:

[0138] The health of each indicator in the first number of indicators is multiplied by the weight of each indicator one by one and then added together to obtain the health of the target device.

[0139] In some embodiments, the evaluation device further comprises:

[0140] A second acquisition module is configured to acquire raw data of a first number of indicators of the target device within a preset time period;

[0141] The normalization module is configured to perform normalization processing on the original data of each indicator respectively to obtain the normalized data of each indicator within a preset time period.

[0142] The implementation and effects of the evaluation device provided in the embodiments of the present application can be referred to in the aforementioned embodiments and will not be described in detail here.

[0143] Based on the same inventive concept, an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores an executable program, and the processor executes the executable program to implement the following steps:

[0144] Obtaining normalized data of a first number of indicators of the target device within a preset time period; wherein the indicators represent an operating state of the target device, and each indicator includes a second number of normalized data within the preset time period;

[0145] Determining a dispersion value of each indicator in the first number of indicators based on the second number of normalized data; the dispersion value reflects the volatility of the evaluation data corresponding to the indicator;

[0146] Adopting a dynamic adjustment strategy to dynamically assign a weight corresponding to each indicator in the first number of indicators according to the discrete degree value;

[0147] The health of the target device is determined based on the second number of normalized data and the weight corresponding to each indicator to evaluate the health status of the target device.

[0148] The implementation and effects of the electronic device provided in the embodiments of the present application can be referred to the aforementioned embodiments and will not be described in detail here.

[0149] The above embodiments are merely exemplary embodiments of the present application and are not intended to limit the scope of the present application. The scope of protection of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and scope of protection of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the scope of protection of the present application.

Claims

1. An evaluation method comprising: Obtaining normalized data of a first number of indicators of a target device within a preset time period; wherein the indicators represent an operating state of the target device, and each indicator includes a second number of normalized data within the preset time period; Determining a dispersion value of each of the first number of indicators based on the second number of normalized data; the dispersion value reflects the volatility of the evaluation data corresponding to the indicator; Adopting a dynamic adjustment strategy to dynamically assign a weight corresponding to each indicator in the first number of indicators according to the discrete degree value; The health of the target device is determined according to the second number of normalized data and the weight corresponding to each indicator to evaluate the health status of the target device.

2. The method according to claim 1, The weight corresponding to the indicator is positively correlated with the discrete degree value corresponding to the indicator.

3. The method according to claim 1, dynamically assigning a weight corresponding to each of the first number of indicators based on the discrete degree value, comprises: Adding the dispersion degree value of each indicator in the first number of indicators to obtain a first value; A weight corresponding to each indicator in the first number of indicators is dynamically allocated according to the first value and the discrete degree value of each indicator.

4. The method according to claim 1, determining the health of the target device based on the second number of normalized data and the weight corresponding to each indicator, comprising: Determining the health level corresponding to each indicator of the target device based on the second number of normalized data; The health of the target device is determined based on the health of each indicator of the target device and the weight of each indicator.

5. The method according to claim 4, wherein determining the health level corresponding to each indicator of the target device based on the second number of normalized data comprises: Determining a mean of the second number of normalized data according to the second number of normalized data; The health level corresponding to each indicator of the target device is determined according to the second number of normalized data and the mean.

6. The method according to claim 5, wherein determining the health level corresponding to each indicator of the target device based on the second number of normalized data and the mean value comprises: Subtracting each normalized data in the second number of normalized data from the mean value one by one to obtain a second number of difference values; According to the second number of differences, establishing an exponential decay relationship between the health level corresponding to each indicator of the target device and the square of the second number of differences; The health level corresponding to each indicator of the target device is determined according to the exponential decay relationship.

7. The method according to claim 4, wherein determining the health of the target device based on the health corresponding to each indicator of the target device and the weight corresponding to each indicator comprises: The health of each indicator in the first number of indicators is multiplied by the weight of each indicator one by one and then added together to obtain the health of the target device.

8. The method according to claim 1, before obtaining normalized data of a first number of indicators of the target device within a preset time period, comprising: Obtaining raw data of a first number of indicators of the target device within a preset time period; Normalize the original data of each indicator separately to obtain the normalized data of each indicator within a preset time period.

9. An evaluation device comprising: a first acquisition module configured to acquire normalized data of a first number of indicators of a target device within a preset time period; wherein the indicators represent an operating state of the target device, and each indicator includes a second number of normalized data within the preset time period; A first determining module is configured to determine a dispersion value of each of the first number of indicators based on the second number of normalized data; the dispersion value reflects the volatility of the evaluation data corresponding to the indicator; An allocation module is configured to adopt a dynamic adjustment strategy to dynamically allocate a weight corresponding to each indicator in the first number of indicators according to the discrete degree value; The second determination module is configured to determine the health of the target device according to the second number of normalized data and the weight corresponding to each indicator to evaluate the health status of the target device.

10. An electronic device comprising a memory and a processor, wherein the memory stores an executable program, and the processor executes the executable program to implement the following steps: Obtain normalized data of a first number of indicators of the target device within a preset time period; wherein, The indicator represents the operating state of the target device, and each indicator includes a second number of normalized data within a preset time period; Determining a dispersion value of each of the first number of indicators based on the second number of normalized data; the dispersion value reflects the volatility of the evaluation data corresponding to the indicator; Adopting a dynamic adjustment strategy to dynamically assign a weight corresponding to each indicator in the first number of indicators according to the discrete degree value; The health of the target device is determined according to the second number of normalized data and the weight corresponding to each indicator to evaluate the health status of the target device.

Images