Electronic equipment health degree assessment method and system

Abstract

The invention discloses an electronic equipment health degree assessment method and system, and relates to the technical field of Internet. And the more scientific and accurate health degree of the electronic equipment can be adaptively obtained. The method comprises the steps of determining at least one health degree assessment object of target electronic equipment according to fault statistical information of multiple pieces of electronic equipment and a hardware component type of the target electronic equipment; determining the health degree of the target electronic equipment according to the evaluation parameters of the at least one health degree evaluation object in the historical preset time period; wherein the evaluation parameter values of the evaluation parameter of at least one health degree evaluation object in different historical preset time periods are different.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a method and system for evaluating the health of electronic equipment. Background Art

[0002] In cluster scenarios where multiple servers are combined into one logical server, such as supercomputing clouds and public clouds, users often demand that services be orchestrated and scheduled based on the health of the servers, with the priority given to deploying services of important customers or important services on servers with higher health. Therefore, operators need to evaluate the health of the servers and orchestrate and schedule services based on the health of the servers.

[0003] In the related technology, the operator receives the fault information of the server and determines the health of the server based on the fault information. Alternatively, the operator determines the health of the server based on the resource utilization rate of the server. When the health of the server is too low, a warning is issued. However, the server health result obtained in this way is not accurate enough and deviates too much from the actual server health. Summary of the invention

[0004] The present application provides a method and system for evaluating the health of an electronic device, which can adaptively obtain a more scientific and accurate health status of the electronic device.

[0005] In order to achieve the above objectives, the embodiments of the present application provide the following technical solutions:

[0006] In a first aspect, the present application provides a method for evaluating the health of an electronic device, the method comprising: determining at least one health evaluation object of a target electronic device based on fault statistical information of a plurality of electronic devices and types of hardware components of the target electronic device; determining the health of the target electronic device based on evaluation parameters of at least one health evaluation object within a historical preset time period; wherein the evaluation parameters of at least one health evaluation object have different evaluation parameter values ​​in different historical preset time periods.

[0007] That is to say, the present application determines at least one health assessment object of the target electronic device from the types of hardware components of the target electronic device according to the fault statistics information of multiple electronic devices. The health of the target electronic device is determined according to the evaluation parameter value of the evaluation parameter of at least one health assessment object within a historical preset time period. Different target electronic devices correspond to different health assessment objects, and different historical preset time periods correspond to different evaluation parameter values. In this way, the health assessment object and evaluation parameter value of the target electronic device can be adaptively determined, and the evaluation parameter value changes over time, so that the health of the target electronic device obtained is more scientific and accurate.

[0008] The electronic device may be a server. Optionally, the electronic device may also be a notebook, a mobile phone, or other device, which is not specifically limited in the present embodiment of the application.

[0009] Exemplarily, when the target electronic device is a server, the health assessment object of the server can be determined based on the fault statistics of multiple servers and the types of hardware components of the server. For example, the health assessment object is CPU, memory, hard disk, network card, PCIE card, power module, and fan module. The indicator that has a greater impact on the health assessment object is selected as the health index (assessment parameter). The health of the server is calculated based on the specific parameters (assessment parameter values) of the health assessment object within a historical week (historical preset period).

[0010] Among them, the specific parameters of the health indicators of the health assessment objects within the historical week are different from different moments.

[0011] Exemplarily, if the current time is 14:37:32 of the day, the server health evaluation system calculates the CPU health according to the specific parameters corresponding to the CPU health index in the past week from 14:37:32 of the day. If the current time is 14:37:33 of the day, the server health evaluation system calculates the CPU health according to the specific parameters corresponding to the CPU health index in the past week from 14:37:33 of the day.

[0012] In a possible implementation, the method further includes: prompting first information, where the first information is used to indicate the health of the target electronic device.

[0013] In this way, the user can learn about the health of the target electronic device in real time, and thus schedule services and target electronic device maintenance according to the health of the target electronic device, thereby improving the user experience.

[0014] For example, Figure 5 As shown, the server health evaluation system sends a text message (first message) of the current health level of server A to the user's mobile phone. The text message includes the title of the text message "Server Health Reminder" and the content of the text message "The current health level of server A is a mild sub-health level." to prompt the health level of server A.

[0015] For example, Figure 7As shown, when the server health assessment system assesses the health level of server A as a mild sub-health level, the server health assessment system can issue an audio and visual prompt through server A. The server health assessment system sends the assessment result to server A. There are three prompt lights in server A. When the assessment result is a mild sub-health level, the first prompt light flashes (first information) to prompt the user of the current health of server A. And / or, server A issues a voice prompt "The current health level of server A is a mild sub-health level, please perform maintenance as soon as possible" (first information). To prompt the user of the current health of server A.

[0016] Optionally, the first information may also be a log, an alarm, an event, an email, a push message within an application, etc. The embodiment of the present application does not impose any specific limitation on this.

[0017] In one possible implementation, the first information includes the second information or the third information, and the first information is prompted. The first information is used to indicate the health of the target electronic device, including: when the health of the target electronic device is lower than a first threshold, the second information is prompted; when the health of the target electronic device is lower than a second threshold, the third information is prompted, the first threshold is greater than the second threshold, and the second information is different from the third information.

[0018] In this way, different health levels of target electronic devices prompt different information, and users can classify and deal with problems according to different prompt information. When the health level of the target server is low, users can perform server maintenance in advance, further improving user experience.

[0019] Exemplarily, the server health status is divided into multiple levels according to different server warning thresholds (threshold values). The server health assessment system can prompt the user of the current level of the server. When the server health is between [0, 20] (the first threshold is 20), it is a critical sub-health level. When the server health is between [20, 65] (the second threshold is 65), it is a severe sub-health level. Or, when the server health is between [65, 85] (the second threshold is 85), it is a mild sub-health level. Or, when the server health is between [85, 100] (the second threshold is 100), it is a healthy level.

[0020] For example, when the second threshold is 85, the server health evaluation system calculates that the server health is 81.2, and the server health level is slightly sub-healthy. The server health evaluation system can prompt the user that the server health level is slightly sub-healthy (third information) this week.

[0021] In one possible implementation, at least one health assessment object of the target electronic device is determined based on fault statistical information of multiple electronic devices and the types of hardware components of the target electronic device, including: determining the failure rate of each hardware component in the multiple electronic devices based on the fault statistical information of the multiple electronic devices; sorting the multiple hardware components from high to low based on the failure rate of each hardware component in the multiple electronic devices, and determining the hardware component whose failure rate is ranked greater than a preset ranking and belongs to the type of hardware component of the target electronic device as a health assessment object.

[0022] The hardware components with higher failure rates in the target electronic device are determined as health evaluation objects. The hardware components with higher failure rates have a greater impact on the health of the target electronic device, thus further improving the accuracy of the health of the target electronic device. The failure rate ranking of the hardware components is determined for subsequent weight allocation.

[0023] For example, if the statistical analysis results of multiple server failure information are: the mainboard failure rate is 4%, the CPU failure rate is 15%, the memory failure rate is 15%, the hard disk failure rate is 20%, the network card failure rate is 10%, the PCIE card failure rate is 10%, the remote management card failure rate is 2%, the power module failure rate is 5%, and the fan module failure rate is 25%. The server health assessment system detects that the server includes hardware components such as the mainboard, central processing unit (CPU), memory, hard disk, network card, high-speed serial computer expansion (Peripheral Component Interconnect Express, PCIE) card, remote management card, power module and fan module. The server health assessment system can select seven hardware components with higher failure rates as the server health assessment objects. In other words, the server health assessment system selects CPU, memory, hard disk, network card, PCIE card, power module and fan module as the server health assessment objects.

[0024] In a possible implementation, determining the health of a target electronic device according to evaluation parameters of at least one health evaluation object within a preset period of history includes: determining a fault prediction result of the health evaluation object using a first prediction algorithm according to the evaluation parameters of the health evaluation object within a preset period of history; determining the health of the target electronic device according to the evaluation parameters of at least one health evaluation object within a preset period of history and the fault prediction result of at least one health evaluation object. In this way, the accuracy of the health of the target electronic device is further improved.

[0025] The first prediction algorithm may be a random forest prediction algorithm, etc. For example, the server health evaluation system may use a prediction algorithm to obtain the probability of a CPU failure within a preset time based on the number of CPU CEs and CPU UCEs within a certain period of time. Then, the health of the server is calculated based on the probability of a CPU failure within a preset time and the health index.

[0026] In one possible implementation, the health of a target electronic device is determined based on evaluation parameters of at least one health evaluation object within a preset historical period, including: determining the health of the health evaluation object based on evaluation parameters of at least one health evaluation object within a preset historical period; determining the health of the target electronic device based on the health of at least one health evaluation object.

[0027] Exemplarily, the health of the CPU, memory, hard disk, network card, PCIE card, power module and fan module in the server is calculated respectively, and the health of the server is calculated based on the health of the CPU, memory, hard disk, network card, PCIE card, power module and fan module.

[0028] In a possible implementation, the method further includes: determining the weight of the health evaluation object of the target electronic device according to the failure rate of each hardware component of the multiple electronic devices; the failure rate of each hardware component of the multiple electronic devices is obtained according to the failure statistics of the multiple electronic devices; the failure rate of each hardware component of the multiple electronic devices is positively correlated with the weight of the health evaluation object of the target electronic device; when there are multiple health objects of the target electronic device, determining the health of the target electronic device according to the health of at least one health evaluation object, including: determining the health of the target electronic device according to the health of the multiple health evaluation objects and the corresponding weights of the multiple health evaluation objects. In this way, the weight of the health evaluation object with a higher failure rate is larger, and the health of the target electronic device can be accurately obtained.

[0029] For example, if the CPU failure rate is 15%, the weight of the CPU is 15% / (15%+15%+20%+10%+10%+5%+25%)=15%; if the memory failure rate is 15%, the weight of the memory is 15% / (15%+15%+20%+10%+10%+5%+25%)=15%; if the hard disk failure rate is 20%, the weight of the hard disk is 20% / (15%+15%+20%+10%+10%+5%+25%)=20%; if the network card failure rate is 10%, the weight of the network card is 10% / (15%+15%+20%+10%+10%+5%+25%)=20%. +20%+10%+10%+10%+5%+25%)=10%; the failure rate of PCIE card is 10%, and the weight of PCIE card is 10% / (15%+15%+20%+10%+10%+5%+25%)=10%; the failure rate of power module is 5%, and the weight of power module is 5% / (15%+15%+20%+10%+10%+5%+25%)=5%; the failure rate of fan module is 25%, and the weight of fan module is 25% / (15%+15%+20%+10%+10%+5%+25%)=25%.

[0030] The server health evaluation system can perform weighted average calculation according to the health of each of the above health evaluation objects and the weight of each health evaluation object to determine the server health. That is, server health = CPU health * CPU health weight + memory health * memory health weight + hard disk health * hard disk health weight + network card health * network card health weight + PCIE card health * PCIE card health weight + power module health * power module health weight + fan module health * fan module health weight = 54*15% + 87*15% + 84*20% + 79*10% + 90*10% + 67*5% + 92*25% = 81.2.

[0031] In one possible implementation, the health of a health assessment object is determined based on evaluation parameters within a preset historical period of time of at least one health assessment object, including: calculating a first health loss within a preset historical period of time of the health assessment object based on evaluation parameters within a preset historical period of time of at least one health assessment object; and calculating the health of the health assessment object based on the number of health assessment objects, a preset full score health and the first health loss.

[0032] Exemplarily, the health of a single memory (the health of the health assessment object) is 100 (the preset full score health) minus the health loss of the abnormal memory page and the health loss of the memory alarm (the first health loss).

[0033] In one possible implementation, the health of a health assessment object is determined based on evaluation parameters within a historical preset time period of at least one health assessment object, including: calculating a first health loss of the health assessment object within a historical preset time period based on evaluation parameters within a historical preset time period of at least one health assessment object; determining a second health loss of the health assessment object based on an average usage rate and an average load of the health assessment object; and calculating the health of the health assessment object based on the number of health assessment objects, a preset full score health, the first health loss, and the second health loss.

[0034] Exemplarily, the health of a single CPU is 100 (preset full score health) minus the CPU abnormal core loss and CPU alarm health loss (first health loss). Afterwards, the average health of the CPU is obtained based on the health of the single CPU and the number of CPUs (the number of health assessment objects). The CPU health (the health of the health assessment object) is the difference between the average health of the CPU and the average CPU usage and the normalized average CPU load health loss (second health loss).

[0035] In one possible implementation, the method further includes: calculating the predicted health of the target electronic device using a second prediction algorithm based on the historical health of the target electronic device; and prompting a third information, where the third information is used to indicate the predicted health. In this way, the user can determine the health development trend of the target server based on the predicted health of the target electronic device, and can intervene in advance to promptly troubleshoot and handle target electronic device failures, and better arrange work. For example, when the server health assessment system predicts that the server will enter a critical sub-health level in 10 days, the server may be about to be scrapped. The user can back up the data in the server in time, or replace or repair components in the server to improve the health of the server. Delay server usage time.

[0036] In a possible implementation, the health assessment object includes at least one of a central processing unit, a memory, a hard disk, a network card, a high-speed serial computer expansion card, a remote management card, a power module, or a fan module.

[0037] In a possible implementation, the evaluation parameter includes: at least one of the number of each health evaluation object, a correctable error count, an uncorrectable error count, and an alarm count.

[0038] In the second aspect, the present application provides an electronic device health assessment device, including: a processing module, which is used to determine at least one health assessment object of the target electronic device based on the fault statistics of multiple electronic devices and the types of hardware components of the target electronic device; the processing module is also used to determine the health of the target electronic device based on the assessment parameters of at least one health assessment object in a historical preset time period; wherein the assessment parameter values ​​of at least one health assessment object are different in different historical preset time periods. In this way, the health assessment object and the assessment parameter value of the target electronic device can be adaptively determined, and the assessment parameter value changes over time, so that the health of the target electronic device obtained is more scientific and accurate.

[0039] In a possible implementation, the device further includes: a communication module, configured to prompt first information, where the first information is used to indicate the health of the target electronic device.

[0040] In one possible implementation, the first information includes the second information or the third information, and the communication module is further used to prompt the second information when the health of the target electronic device is lower than a first threshold; the communication module is further used to prompt the third information when the health of the target electronic device is lower than a second threshold, the first threshold is greater than the second threshold, and the second information is different from the third information.

[0041] In one possible implementation, the processing module is also used to determine the failure rate of each hardware component in multiple electronic devices based on failure statistics of multiple electronic devices; sort the multiple hardware components from high to low according to the failure rate of each hardware component in the multiple electronic devices, and determine the hardware component whose failure rate ranking is greater than a preset ranking and belongs to the type of hardware component of the target electronic device as a health assessment object.

[0042] In one possible implementation, the processing module is also used to determine a fault prediction result of the health assessment object using a first prediction algorithm based on evaluation parameters of the health assessment object within a historical preset period of time; and determine the health of the target electronic device based on evaluation parameters of at least one health assessment object within a historical preset period of time and the fault prediction result of at least one health assessment object.

[0043] In a third aspect, the present application provides an electronic device health assessment system, comprising: a processor, the processor being coupled to a memory; the processor being used to execute a computer program stored in the memory so that the electronic device health assessment system performs the method described in the first aspect.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium, which includes a computer program or instructions. When the computer program or instructions are executed on a vehicle control device, the vehicle control device executes the method described in the first aspect.

[0045] In a fifth aspect, the present application provides a chip system comprising at least one processor and at least one interface circuit, wherein the at least one interface circuit is used to perform transceiver functions and send instructions to at least one processor, and when the at least one processor executes the instructions, the at least one processor executes a method as described in any one of the above-mentioned first aspects.

[0046] In a sixth aspect, the present application also provides a computer program product, comprising instructions, which, when executed on a computer, enables the computer to execute the method as described in any one of the first aspects.

[0047] In a seventh aspect, an embodiment of the present application provides a circuit system, the circuit system includes a processing circuit, and the processing circuit is configured to execute the method of the first aspect or any one of the implementations of the first aspect.

[0048] The technical effects corresponding to the second to seventh aspects and any one of the implementation methods of the second to seventh aspects can be referred to the technical effects corresponding to the above-mentioned first aspect and any one of the implementation methods of the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A schematic diagram of the structure of an electronic device health assessment system provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of a module of an electronic device provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of the structure of a server provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of an interface of an electronic device provided in an embodiment of the present application;

[0054] Figure 6 A schematic diagram of an interface of another electronic device provided in an embodiment of the present application;

[0055] Figure 7 A schematic diagram of the structure of a server provided in an embodiment of the present application;

[0056] Figure 8A schematic diagram of an interface of another electronic device provided in an embodiment of the present application;

[0057] Fig. 9 A schematic diagram of an interface of another electronic device provided in an embodiment of the present application;

[0058] Fig.10 A schematic diagram of a flow chart of a method for evaluating the health of an electronic device provided in an embodiment of the present application;

[0059] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0060] Fig.12 A schematic diagram of the structure of a chip system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] An operating method and an electronic device provided in an embodiment of the present application are described in detail below with reference to the accompanying drawings.

[0062] The terms "including" and "having" and any variations thereof mentioned in the description of the embodiments of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0063] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0064] In the description of the embodiments of the present application, unless otherwise specified, the meaning of "multiple" refers to two or more. The "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0065] The current method of evaluating server health is to obtain server fault information. When a server fails, the current health value of the server is deducted to calculate the final health value of the server. The fault information of different server components and the deduction scores of different fault levels are different. However, it is too one-sided to evaluate server health based solely on server fault information. When the server does not fail, users cannot know the health status of the server, and the server health evaluation results are inaccurate.

[0066] In the related art, the resource utilization rate of each part of the server is obtained, and the health of the server is calculated according to the resource utilization rate of each part of the server. The higher the resource utilization rate of the server, the lower the health. When the health of the server is lower than the threshold, an alarm is issued to the user. However, this evaluation method only evaluates the health of the server based on the resource utilization rate, which is too one-sided and the evaluation result is inaccurate. Users can only passively receive alarm prompts, and the user experience is poor.

[0067] To solve the above problems, an embodiment of the present application provides a method for evaluating the health of an electronic device. The method can adaptively determine at least one health assessment object (such as a component in an electronic device) for evaluating the health of a target electronic device (electronic device) through the statistical analysis results of multiple electronic device fault information and the types of hardware components of the target electronic device, the weight of the health assessment object, and the health index of the health assessment object. The health of the electronic device can be determined according to the health assessment object, the weight of the health assessment object, and the health index of the health assessment object. Among them, each health assessment object includes at least one health index. The health index refers to the operating status information (such as operating information, status information or attribute information) of the health assessment object obtained during the operation of the electronic device. The health index can be used to diagnose and quantify the health status of the health assessment object. The present application adaptively evaluates the health of the electronic device from multiple aspects based on the fault analysis results, and the evaluation results are scientific and accurate.

[0068] The embodiment of the present application can also divide multiple electronic equipment health warning thresholds to determine the current electronic equipment health level. The embodiment of the present application can also predict the future server health level of the electronic equipment. Periodically prompt the electronic equipment's current electronic equipment health level and future electronic equipment health level. Periodic prompts can enable users to obtain the current electronic equipment health level and future electronic equipment health level of the electronic equipment in a timely manner. Different from the passive reception method of fault reporting, users can intervene in advance to promptly troubleshoot and handle electronic equipment faults and eliminate or reduce the resulting losses. Differentiated prompts for different levels of electronic equipment health can enable operation and maintenance personnel to classify and solve them according to different electronic equipment health levels, improve efficiency, and enhance user experience.

[0069] like Figure 1 As shown in FIG. 1 , a schematic diagram of the architecture of an electronic device health assessment system is shown. Figure 1 As shown in (a), the electronic device health assessment system may include an electronic device 101 and an electronic device health assessment device 102. The electronic device health assessment device 102 may be located outside the electronic device 101. Alternatively, Figure 1 As shown in (b), the electronic device health assessment device 102 is located inside the electronic device 101. This embodiment of the application does not make any specific limitation to this.

[0070] In a possible implementation, the embodiment of the present application can use an electronic device health assessment device to assess the health of an electronic device, and the electronic device can be a server, a personal computer (PC), a mobile phone, a tablet computer (Pad), a laptop computer, a desktop computer, a laptop computer, a computer with a transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, a wearable device, a vehicle-mounted device, and other terminal devices. The embodiment of the present application does not impose any special restrictions on the specific form of the electronic device.

[0071] The embodiment of the present application is introduced by taking the use of a server health assessment device in a server health assessment system to perform health assessment on a server as an example.

[0072] Figure 2 The hardware structure diagram of the server provided in the embodiment of the present application is shown in FIG. The server includes at least one processor 201 , a communication line 202 , a memory 203 , and at least one communication interface 204 . The memory 203 may also be included in the processor 201 .

[0073] The processor 201 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0074] The communication link 202 may include a pathway to transmit information between the above-mentioned components.

[0075] The communication interface 204 is used to communicate with other devices. In the embodiment of the present application, the communication interface can be a module, a circuit, a bus, an interface, a transceiver or other device capable of realizing a communication function, and is used to communicate with other devices. Optionally, when the communication interface is a transceiver, the transceiver can be an independently arranged transmitter, which can be used to send information to other devices, and the transceiver can also be an independently arranged receiver, which is used to receive information from other devices. The transceiver can also be a component that integrates the functions of sending and receiving information, and the embodiment of the present application does not limit the specific implementation of the transceiver.

[0076] In some embodiments, the media interface may be a communication interface, that is, an interface may be used as both a communication interface and a media interface.

[0077] The memory 203 may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. Among them, the nonvolatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM) or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but not limited to this. The memory can be independent and connected to the processor 201 via the communication line 202. The memory 203 can also be integrated with the processor 201.

[0078] The memory 203 is used to store computer-executable instructions for implementing the solution of the present application, and the execution is controlled by the processor 201. The processor 201 is used to execute the computer-executable instructions stored in the memory 203, thereby implementing the electronic device health assessment method provided in the following embodiments of the present application.

[0079] Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application code, instructions, computer program or other names, which are not specifically limited in the embodiments of the present application.

[0080] In a specific implementation, as an embodiment, the processor 201 may include one or more CPUs, such as Figure 2 CPU0 and CPU1 in.

[0081] In a specific implementation, as an embodiment, the server may include multiple processors, such as Figure 2 201 and processor 205 in the embodiment of the present invention. Each of these processors may be a single-CPU processor or a multi-CPU processor. The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0082] The above-mentioned server can be a general server or a dedicated server, and the embodiment of the present application does not limit the type of server.

[0083] It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the server. In other embodiments of the present application, the electronic device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0084] like Figure 3 The module diagram of the server health evaluation system provided by the embodiment of the present application is shown in FIG. The server health evaluation system includes a server health index acquisition module 301 , a server health calculation module 302 , a server health output module 303 , and a server health management module 304 .

[0085] The server health index acquisition module 301 is used to acquire the health index of each health evaluation object of the server and send the health index of each health evaluation object of the server to the server health calculation module 302 .

[0086] The server health calculation module 302 is used to calculate the server health according to the weight of the health evaluation object and the health index. The health index comes from the server health index acquisition module 301, and the weight of the health evaluation object comes from the server health management module 304. The server health calculation module 302 is also used to send the server health to the server health output module 303.

[0087] The server health output module 303 is used to obtain the server health from the server health calculation module 302, determine the server health level, and prompt the user of the server health level of the server. The server health output module 303 is also used to obtain the server health, predict the future server health level trend of the server, and prompt the user of the predicted server health level of the server.

[0088] The server health management module 304 is used to determine the server health assessment object and the weight of the health assessment object according to the type and quantity of each actual component of the server and the statistical analysis results of the server fault information. And send it to the server health calculation module 302. The server health management module 304 is also used to adaptively adjust the server health assessment object when the server components change. And instruct the server health index acquisition module 301 to obtain the health index of the server health assessment object. The server health management module 304 is also used to manage the server health assessment cycle, server health assessment method, etc. The server health management module 304 is also used to manage the server health output cycle, output status, etc.

[0089] The following is an introduction to the server health evaluation of an embodiment of the present application.

[0090] Optionally, the server health assessment system can detect the hardware components of the server. It can also perform statistical analysis on the massive amount of failure information of each server hardware to obtain the failure rate (or return rate) of each hardware component in the server. The hardware components of the server with the highest failure rate are used as the health assessment object of the server.

[0091] For example, Figure 4 As shown, the server health assessment system detects that the server includes hardware components such as a motherboard, a central processing unit (CPU), a memory, a hard disk, a network card, a high-speed serial computer expansion (Peripheral Component Interconnect Express, PCIE) card, a remote management card, a power module, and a fan module. Optionally, the server may also include other server components, which are not specifically limited in the embodiments of the present application.

[0092] For example, if the statistical analysis results of server fault information are: mainboard failure rate is 4%, CPU failure rate is 15%, memory failure rate is 15%, hard disk failure rate is 20%, network card failure rate is 10%, PCIE card failure rate is 10%, remote management card failure rate is 2%, power module failure rate is 5%, and fan module failure rate is 25%. The server health assessment system can select seven hardware components with higher failure rates as the server health assessment objects. In other words, the server health assessment system selects CPU, memory, hard disk, network card, PCIE card, power module and fan module as the server health assessment objects.

[0093] For another example, if the statistical analysis results of server fault information are: mainboard failure rate is 4%, CPU failure rate is 15%, memory failure rate is 15%, hard disk failure rate is 20%, network card failure rate is 10%, PCIE card failure rate is 10%, remote management card failure rate is 12%, power module failure rate is 5%, and fan module failure rate is 25%. The server health assessment system can select seven hardware components with higher failure rates as the server health assessment objects. In other words, the server health assessment system selects CPU, memory, hard disk, network card, PCIE card, remote management card and fan module as the server health assessment objects.

[0094] In a possible implementation, the embodiment of the present application may also use other components that affect the performance of the server as the health evaluation object of the server. For example, the embodiment of the present application may also use the software of the server as the health evaluation object of the server. The higher the software performance of the software in the server, the higher the health of the server; the lower the software performance of the software in the server, the lower the health of the server. The embodiment of the present application does not impose any specific restrictions on this.

[0095] Optionally, the embodiment of the present application is introduced by taking the CPU, memory, hard disk, network card, PCIE card, power module and fan module as the server health assessment objects as an example.

[0096] Optionally, the server health assessment system may calculate the health of each health assessment object.

[0097] Each health assessment object includes at least one health indicator. The health indicator refers to the operating status information of the health assessment object obtained during the operation of the server, which can be used to diagnose and quantify the health status of the health assessment object. The server health assessment system can select a significant indicator in the health assessment object (for example, an indicator that has a greater impact on the health assessment object) as a health indicator.

[0098] Optionally, when the health assessment object is a CPU, memory, hard disk, network card, PCIE card, power module, or fan module, each health assessment object corresponds to a different health indicator. The server health assessment system can determine the indicator that has a greater impact on the health assessment object as the health indicator of the health assessment object. When the server is upgraded or downgraded, the impact of each indicator in the health assessment object on the health assessment object may change, and the health indicator of the health assessment object will also change accordingly.

[0099] Optionally, the server health evaluation system may adaptively calculate the health of the health evaluation object according to specific parameters of the health evaluation object's health indicator within a certain period of time.

[0100] The specific parameters of the health indicator may include the number of health indicators, the running status information of the health indicator (the alarm count of the health indicator, etc., see below for details), etc.

[0101] For example, the server health evaluation system can calculate the health of the health evaluation object according to the specific parameters of the health evaluation object's health index within a week of history. The embodiment of the present application does not specifically limit the length of time.

[0102] Optionally, when the health assessment object is a CPU, the CPU health index may include the number of CPU core isolations, CPU correctable error (CE) counts, CPU uncorrectable error (UCE) counts, CPU alarm counts, CPU average usage, CPU average load, CPU failure prediction results, etc. Optionally, the CPU health index may also include other parameters, which are not specifically limited in the embodiments of the present application. Optionally, there are usually multiple CPUs in a server. Exemplarily, the server in the embodiment of the present application includes four CPUs, namely CPU1, CPU2, CPU3 and CPU4.

[0103] CPU core isolation refers to isolating a CPU core by taking it offline, etc., to prevent the core failure from affecting the services running on other cores.

[0104] The number of CPU core isolations indicates the number of cores isolated within a certain period of time. For example, from the current moment, the number of CPU1 core modules isolated within a week is 2.

[0105] CPU CE indicates the errors that the CPU can correct. For example, when a single-bit error occurs in the cache memory in the CPU, the CPU can correct the error through error checking and correcting (ECC) without affecting any process in the system. This error is CE. The CPU CE count indicates the number of times the CPU has CE in a certain period of time. For example, from the current moment, CPU1 has CE twice in the past week.

[0106] CPU UCE indicates the CPU errors that cannot be corrected by the CPU. For example, when a multi-bit error occurs in the CPU cache, the CPU cannot directly correct the error through error checking and correcting (ECC), and this error is UCE. The CPU UCE count indicates the number of times the CPU has UCE in a certain period of time. For example, from the current moment, CPU1 has had 1 UCE in the past week.

[0107] CPU alarm indicates the alarm signal sent out when the CPU fails. CPU alarm count indicates the number of times the CPU alarm occurs within a certain period of time. Each time the CPU alarm occurs, a certain health loss will occur. Optionally, CPU alarms can be divided into CPU minor alarms, CPU major alarms, and CPU emergency alarms, and the CPU health loss corresponding to each alarm level is also different. Exemplarily, from the current moment, within a week of history, CPU1 has 2 minor alarms, and each CPU1 minor alarm generates a unit CPU minor alarm health loss of 0.1; 1 major alarm, each CPU1 major alarm generates a unit CPU major alarm health loss of 1; 1 emergency alarm, each CPU1 emergency alarm generates a unit CPU emergency alarm health loss of 10.

[0108] CPU usage indicates the ratio of CPU resources occupied by programs running in the CPU to all CPU resources, indicating the current status of programs running in the CPU. A server usually has multiple CPUs, and the average CPU usage indicates the average usage of multiple CPUs in the server. For example, the server includes four CPUs, the usage of CPU1 is 60%; the usage of CPU2 is 50%; the usage of CPU3 is 55%; and the usage of CPU4 is 65%. The average CPU usage is 55%.

[0109] The CPU load average refers to the average number of processes in the CPU running / runnable and uninterruptible state per unit time, that is, the average number of active processes. For example, the CPU load average may be 2.88.

[0110] The CPU failure prediction result indicates the probability of a CPU failure occurring within a preset time in the future. Optionally, the server health evaluation system can obtain the probability of a CPU failure occurring within a preset time in the future using a prediction algorithm based on the number of CPU CEs and the number of CPU UCEs within a certain period of time.

[0111] For example, from the current moment, in the past week, the number of CPU1 CEs is 6 and the number of CPU1 UCEs is 1. According to the random forest prediction algorithm, it can be predicted that the probability of CPU1 failure in the next week is 0.15.

[0112] It should be understood that the above method of using the random forest prediction method to obtain the probability of CPU1 predicting a failure within the next week is only an example, and other prediction algorithms can also be used to obtain the probability of CPU1 predicting a failure within the next week, or to obtain the probability of CPU1 predicting a failure within the next month. The embodiment of the present application does not specifically limit the method for obtaining the probability of CPU1 predicting a failure within a preset time in the future and the length of the preset time.

[0113] Optionally, the server health assessment system can calculate the CPU health based on the above-mentioned CPU health indicators and the corresponding specific parameters. Since there are usually multiple CPUs in a server, it is necessary to calculate the health of each CPU, and then calculate the average CPU health of the server based on the health of each CPU. The server CPU health can be the server average CPU health minus the average CPU usage and the standardized CPU average load health loss. Among them, the server average CPU health is the average health of multiple CPUs in the server. The health of a single CPU is 100 minus the CPU abnormal core loss and the CPU alarm health loss.

[0114] Among them, CPU abnormal core loss = CPU core failure basic loss + CPU unit core failure loss * CPU abnormal core number.

[0115] For example, the basic loss of CPU1 core failure may be 15, and the unit core failure loss of CPU1 is 15. The number of abnormal cores of CPU1 includes the number of isolated cores of CPU1 and the number of abnormal cores of non-isolated cores of CPU1. The server health evaluation system can directly obtain the number of isolated cores of CPU1.

[0116] Optionally, the number of abnormal cores of the unisolated cores of CPU1 is the number of CPU1 cores multiplied by the probability of CPU1 core failure predicted within the next week. For example, the number of CPU1 cores is 4, the probability of CPU1 core failure predicted within the next week is 0.15, and the number of abnormal cores of the unisolated cores of CPU1 is 0.6.

[0117] The number of CPU1 core isolations plus the number of abnormal cores of CPU1 non-isolated cores is the number of abnormal cores of CPU1. For example, the number of CPU1 core isolations is 2, the number of abnormal cores of CPU1 non-isolated cores is 0.6, and the number of abnormal cores of CPU1 is 2.6.

[0118] Afterwards, it can be calculated that the abnormal core loss of CPU1 is 15+15*2.6=54.

[0119] Optionally, if the number of abnormal cores of CPU1 is 0, the loss of abnormal cores of CPU1 is 0.

[0120] Optionally, the server health evaluation system can determine the CPU1 alarm health loss according to the CPU1 alarm count and the corresponding alarm loss. Alarm health loss = CPU1 minor alarm count * unit CPU minor alarm health loss + CPU1 severe alarm count * unit CPU severe alarm health loss + CPU1 emergency alarm count * unit CPU emergency alarm health loss. Exemplarily, from the current moment, the CPU1 alarm health loss in the historical week is 2*0.1+1*1+1*10=11.2.

[0121] Optionally, the health of CPU1 is 100-54-11.2=34.8.

[0122] The server health evaluation system can calculate the health of other CPUs in the server. For example, the health of CPU2 is 65.2, the health of CPU3 is 84, and the health of CPU4 is 72.

[0123] Optionally, the server health evaluation system may obtain an average CPU health value of (34.8+65.2+84+72) / 4=64.

[0124] Optionally, the server health evaluation system may obtain the busyness of the CPU and the overload degree of the CPU, and determine the CPU usage and the standardized CPU average load health loss according to the busyness of the CPU and the overload degree of the CPU as shown in Table 1 below.

[0125] The CPU can be divided into different busyness levels according to the average CPU usage. For example, when the average CPU usage is between [0%, 5%), the CPU busyness is "idle". When the average CPU usage is between [5%, 75%), the CPU busyness is "normal". When the average CPU usage is between [75%, 95%), the CPU busyness is "busy". When the average CPU usage is between [95%, 100%), the CPU busyness is "overloaded".

[0126] The CPU average load is standardized, and the CPU can be divided into different overload levels according to the standardized CPU average load. Among them, the standardized CPU average load = CPU average load / number of CPU cores. Optionally, the number of CPU cores can be 4. When the CPU average load is 2.88, the standardized CPU average load = CPU average load / number of CPU cores = 2.88 / 4 = 0.72.

[0127] When the standardized average CPU load is between [0, 0.7], the CPU overload level is "normal load". When the standardized average CPU load is between (0.7, 1], the CPU overload level is "slight overload". When the standardized average CPU load is between (1, 5], the CPU overload level is "normal overload". When the standardized average CPU load is greater than 5, the CPU overload level is "severe overload".

[0128] Optionally, the average CPU usage and the normalized average CPU load health loss may be obtained as shown in Table 1 below.

[0129] Table 1

[0130]

[0131] As shown in Table 1, when the CPU busyness is low, if the CPU overload is high, the average CPU usage and the normalized average CPU load health loss are high. This means that the CPU is not normal, and the CPU may be faulty at this time, and the server health is low.

[0132] Specifically, when the CPU busyness is "idle" and the CPU overload degree is "normal load"; or, the CPU busyness is "normal" and the CPU overload degree is "normal load" or "slight overload"; or, the CPU busyness is "busy" and the CPU overload degree is "normal load", "slight overload" or "general overload"; or, the CPU busyness is "overload" and the CPU overload degree is "normal load", "slight overload", "general overload" or "severe overload", the CPU average usage rate and the standardized CPU average load health loss are 0. When the CPU busyness is "idle" and the CPU overload degree is "normal load"; or, the CPU busyness is "normal" and the CPU overload degree is "general overload"; or, the CPU busyness is "busy" and the CPU overload degree is "severe overload", the CPU average usage rate and the standardized CPU average load health loss are 10. When the CPU busyness is "idle" and the CPU overload level is "normal overload"; or when the CPU busyness is "normal" and the CPU overload level is "severe overload", the CPU average usage and the normalized CPU average load health loss are 20. When the CPU busyness is "idle" and the CPU overload level is "severe overload", the CPU average usage and the normalized CPU average load health loss are 30.

[0133] For example, when the average CPU usage is 55%, the CPU busyness is "normal". When the standardized average CPU load is 0.72, the CPU overload is "normal overload". According to Table 1 above, the health loss of the average CPU usage and the standardized average CPU load is 10.

[0134] Optionally, the CPU health is the difference between an average CPU health value and an average CPU usage and a normalized average CPU load health loss.

[0135] For example, when the average health value of the CPU is 64, and the average CPU usage and the normalized average load health loss are 10, the CPU health is 64-10=54.

[0136] Optionally, the specific parameters corresponding to the above CPU health indicators can be adaptively changed according to the upgrade, downgrade, and time of the server.

[0137] For example, after the server is upgraded, the number of CPUs increases, and the server includes 8 CPUs. The server health evaluation system calculates the CPU health according to the specific parameters corresponding to the health indicators of the upgraded CPUs. Specifically, if the number of CPUs in the past week is 8 from the current moment, the server health evaluation system can calculate the CPU health according to the health indicators of the CPU in the past week and the corresponding specific parameters using the formula described above.

[0138] Alternatively, if the number of CPUs from the seventh to the fourth day in history from the current moment is 4, and the number of CPUs from the third day in history to the current moment is 8. The server health evaluation system can calculate the health of the CPU 1 using the formula described above based on the health index of the CPU from the seventh to the fourth day in history and the corresponding specific parameters. The health of the CPU 2 is calculated using the formula described above based on the health index of the CPU from the third day in history to the current moment and the corresponding specific parameters. Then the health of the CPU in the past week can be the average of health 1 and health 2.

[0139] As another example, when the current time changes, the server health assessment system calculates the CPU health based on the specific parameters corresponding to the CPU health index within the historical week starting from the time after the change. Specifically, if the current time is 14:37:32 on the same day, the server health assessment system calculates the CPU health based on the specific parameters corresponding to the CPU health index within the historical week starting from 14:37:32 on the same day. If the current time is 14:37:33 on the same day, the server health assessment system calculates the CPU health based on the specific parameters corresponding to the CPU health index within the historical week starting from 14:37:33 on the same day.

[0140] Optionally, when the health assessment object is memory, the memory health index may include the number of memory page isolations, memory CE count, memory UCE count, memory alarm count, memory fault prediction results, etc. Optionally, the memory health index may also include other parameters, which are not specifically limited in the embodiments of the present application. Optionally, there are usually multiple memories in a server. Exemplarily, the server includes 8 memories, namely memory 1, memory 2, memory 3, memory 4, memory 5, memory 6, memory 7, and memory 8.

[0141] Among them, memory page isolation is used to isolate faulty memory pages. When a memory error occurs, the operating system will call the interface to copy the content of this page to a new physical page frame to isolate the faulty memory page and avoid more memory errors. The number of memory page isolations indicates the number of memory pages isolated within a certain period of time. For example, from the current moment, the number of memory pages isolated in memory 1 within a week is 2.

[0142] Memory CE indicates a correctable error in memory. Memory CE count indicates the number of times memory CE occurs within a certain period of time. For example, from the current moment, memory 1 has 2 CEs in the past week.

[0143] Memory UCE indicates an uncorrectable error that occurs in the memory. Memory UCE count indicates the number of times that memory UCE occurs within a certain period of time. For example, from the current moment, memory 1 has one UCE in the past week.

[0144] Memory alarm indicates the alarm signal sent out when the memory fails. Memory alarm count indicates the number of times the memory alarm occurs within a certain period of time. Each time the memory alarm occurs, a certain health loss will be generated. Optionally, memory alarms can be divided into memory minor alarms, memory major alarms, and memory emergency alarms, and the memory health loss generated corresponding to each alarm level is also different. Exemplarily, from the current moment, within a week of history, memory 1 has 2 minor alarms, and each memory 1 minor alarm generates a unit memory minor alarm health loss of 0.1; 3 major alarms, and each memory 1 major alarm generates a unit memory major alarm health loss of 1; 0 emergency alarms, and each memory 1 emergency alarm generates a unit memory emergency alarm health loss of 10.

[0145] The memory failure prediction result indicates the probability of the memory failing within a preset time in the future. Optionally, the server health assessment system can obtain the probability of the memory failing within a preset time in the future based on the number of memory CEs and memory UCEs within a certain period of time by using random forest prediction or other methods. For example, from the current moment, within a week in history, the number of memory 1CEs is 2 and the number of memory 1UCEs is 0. According to the random forest prediction algorithm, it can be predicted that the probability of memory 1 failing within the next week is 0.01.

[0146] Optionally, the server health evaluation system can calculate the memory health based on the above-mentioned memory health index. Since a server usually has multiple memories, it is necessary to calculate the health of each memory, and then calculate the average memory health of the server based on the health of each memory. The server memory health can be the average memory health of the server. Among them, the average memory health of the server is the average health of multiple memories in the server. The health of a single memory is 100 minus the memory abnormal page health loss and the memory alarm health loss.

[0147] The memory abnormal page health loss of the memory may be the memory abnormal page capacity / the total memory capacity*100.

[0148] Optionally, the total memory capacity can be directly obtained. Exemplarily, the total capacity of memory 1 is 128 megabytes. The memory exception page capacity of memory 1 includes the isolated memory page capacity and the non-isolated memory page exception capacity. The isolated memory page capacity can be directly obtained. Exemplarily, the isolated memory page capacity of memory 1 is 6.72 megabytes. The non-isolated memory page exception capacity of memory 1 is obtained according to the memory failure prediction result. Exemplarily, the non-isolated memory page exception capacity of memory 1 is equal to the memory page capacity multiplied by the probability of memory 1 predicted to fail within the next week. The non-isolated memory page exception capacity of memory 1 is 1.28.

[0149] Afterwards, it can be calculated that the health loss of the abnormal memory page of memory 1 is (6.72+1.28) / 128*100=6.25.

[0150] Optionally, the server health evaluation system can determine the memory alarm health loss according to the memory alarm count and the corresponding alarm loss. That is, memory alarm health loss = memory minor alarm count * unit memory minor alarm health loss + memory major alarm count * unit memory major alarm health loss + memory emergency alarm count * unit memory emergency alarm health loss. Exemplarily, from the current moment, the memory alarm health loss of memory 1 in the past week is 2*0.1+3*1+0*10=3.2.

[0151] Optionally, the health of memory 1 is 100-the health loss of abnormal memory page-the health loss of memory alarm. That is, 100-6.25-3.2=90.55. The server health evaluation system can calculate the health of other memories in the server. Exemplarily, the health of memory 2 is 90.55, the health of memory 3 is 72, the health of memory 4 is 88, the health of memory 5 is 90, the health of memory 6 is 85, the health of memory 7 is 92, and the health of memory 8 is 89.

[0152] Optionally, the server health evaluation system may obtain an average health of the memory as (90.55+90.55+72+88+90+85+92+89) / 8=87.

[0153] Optionally, the server memory health is the average health of the memory, that is, the server memory health is 87.

[0154] Optionally, specific parameters corresponding to the above memory health indicators may be adaptively changed according to server upgrades, downgrades, and time.

[0155] Optionally, when the health assessment object is a hard disk, the hard disk health index may include hard disk self-monitoring, analysis and reporting technology (SMART) information, hard disk alarm count, etc. Optionally, the hard disk health index may also include other parameters, which are not specifically limited in the embodiments of the present application. Optionally, there are usually multiple hard disks in a server. Exemplarily, the server in the embodiments of the present application includes four hard disks, namely hard disk 1, hard disk 2, hard disk 3 and hard disk 4.

[0156] Among them, the hard disk SMART information corresponding to different types of hard disks is different. Exemplarily, the hard disk types are mainly divided into mechanical hard disks (hard disk drive, HDD), solid state drives (solid state drive, SSD) and solid state hybrid drives (solid state hybrid drive, SSHD). The solid state drive remaining life (SSDlife left) and remaining empty blocks (spare block left) in the hard disk SMART information are only applicable to solid state drives. Only solid state drives can use the solid state drive remaining life and remaining empty blocks as hard disk SMART information.

[0157] Optionally, the present application takes the hard disk as a solid state disk as an example, and selects the solid state disk remaining life (SSD life left), the underlying data read error rate (read error rate), and the reallocated sector count (reallocated sector count) in the solid state disk as the hard disk SMART information. Optionally, the solid state disk SMART information may also include other parameters, which are not specifically limited in the embodiments of the present application.

[0158] The hard disk alarm indicates the alarm signal sent out when the hard disk fails. The hard disk alarm count indicates the number of hard disk alarms within a certain period of time. Each time the hard disk alarm occurs, a certain health loss will be generated. Optionally, hard disk alarms can be divided into hard disk minor alarms, hard disk major alarms, and hard disk emergency alarms, and the hard disk health loss generated corresponding to each alarm level is also different. For example, from the current moment, within a week of history, hard disk 1 has 5 minor alarms, and each minor alarm of hard disk 1 generates a unit hard disk minor alarm health loss of 0.1; 0 major alarms, each major alarm of hard disk 1 generates a unit hard disk major alarm health loss of 1; 1 emergency alarm, each emergency alarm of hard disk 1 generates a unit hard disk emergency alarm health loss of 10.

[0159] Optionally, the server health assessment system can calculate the hard disk health based on the above hard disk health index. Since there are usually multiple hard disks in a server, it is necessary to calculate the health of each hard disk, and then calculate the average hard disk health of the server based on the health of each hard disk. The server hard disk health can be the average hard disk health of the server. Among them, the average hard disk health of the server is the average health of multiple hard disks in the server. The health of a single hard disk is 100 minus the hard disk SMART health loss and the hard disk alarm health loss.

[0160] The hard disk SMART health loss can be calculated based on the hard disk SMART information.

[0161] Specifically, first, the server health assessment system calculates the "SMART distance" between the current value of each hard disk's SMART information and the threshold. The ratio of the "SMART distance" to the "total SMART information distance" of the hard disk is calculated as the health loss of the hard disk's SMART information, that is, the health loss of the hard disk's SMART information is (1-"SMART distance" / "total SMART information distance")*100. Among them, the threshold is determined by the hard disk manufacturer. When the current value of the hard disk's SMART information is less than the threshold, the hard disk is a faulty hard disk and cannot be used. The health of the hard disk is 0.

[0162] Exemplarily, the current value of the remaining life of the solid state drive of hard disk 1 is 119, the threshold value is 6, and the total distance of the remaining life of the solid state drive is 150, then the health loss of the remaining life of the solid state drive of hard disk 1 is (1-(119-6) / 150)*100=24.67. The current value of the underlying data read error rate of hard disk 1 is 2, the threshold value is 50, and the total distance of the underlying data read error rate is 60, then the health loss of the underlying data read error rate of hard disk 1 is (1-(50-2) / 60)*100=20. The current value of the relocation sector count of hard disk 1 is 1, the threshold value is 45, and the total distance of the relocation sector count is 50, then the health loss of the relocation sector count of hard disk 1 is (1-(45-1) / 50)*100=12.

[0163] Optionally, the server health assessment system can also calculate the distance between the worst value of each hard disk SMART information and the threshold as the "SMART distance". The worst value is the value closest to the threshold in the history of the hard disk SMART information within one week. The embodiment of the present application takes the "SMART distance" as the distance between the current value of the hard disk SMART information and the threshold as an example for introduction.

[0164] Afterwards, the weight of the SMART information of each hard disk in hard disk 1 is obtained. The weight of the SMART information of each hard disk is sorted by the manufacturer from high to low according to the importance of the hard disk SMART information and numbered from 1. The weight of the SMART information of each hard disk is calculated according to the number of the hard disk SMART information.

[0165] Exemplarily, the remaining life of the solid state drive has a high impact on hard disk 1, is of high importance, and can be set to number 2. The underlying data read error rate has a high impact on hard disk 1, is of high importance, and can be set to number 1. The relocation sector count has a high impact on hard disk 1, is of high importance, and can be set to number 2.

[0166] Optionally, the weight of the hard disk SMART information is calculated by subtracting the quotient of the hard disk SMART information number and the sum of all hard disk SMART information numbers from 1.

[0167] Exemplarily, the weight of the remaining life of the solid state drive of Hard Drive 1 is 1-2 / (2+1+2)=0.6; the weight of the underlying data read error rate of Hard Drive 1 is 1-1 / (2+1+2)=0.8; and the weight of the relocation sector count of Hard Drive 1 is 1-2 / (2+1+2)=0.6.

[0168] Finally, the server health evaluation system calculates the hard disk SMART health loss based on the health of each hard disk SMART information and weight.

[0169] Exemplarily, the hard disk SMART health loss of hard disk 1 can be the health of the remaining life of the solid state drive * the weight of the remaining life of the solid state drive + the health of the underlying data read error rate * the weight of the underlying data read error rate + the health of the relocated magnetic sector count + the weight of the relocated magnetic sector count. That is, the hard disk SMART health loss of hard disk 1 is 24.67*(0.6 / (0.6+0.8+0.6))+20*(0.8 / (0.6+0.8+0.6))+12*(0.6 / (0.6+0.8+0.6))=19.

[0170] Optionally, the server health evaluation system can determine the hard disk alarm health loss according to the hard disk alarm count and the corresponding alarm loss. That is, hard disk alarm health loss = hard disk minor alarm count * unit hard disk minor alarm health loss + hard disk major alarm count * unit hard disk major alarm health loss + hard disk emergency alarm count * unit hard disk emergency alarm health loss. Exemplarily, from the current moment, the hard disk alarm health loss of hard disk 1 in the past week is 5*0.1+0*1+1*10=10.5.

[0171] Optionally, the hard disk health of hard disk 1 is 100-hard disk SMART health loss-hard disk warning health loss, that is, 100-19-10.5=70.5. The server health evaluation system can calculate the health of other hard disks in the server. Exemplarily, the health of hard disk 2 is 85.5, the health of hard disk 3 is 92, and the health of hard disk 4 is 88.

[0172] Optionally, the server health evaluation system may obtain the average health of the hard disk as (70.5+85.5+92+88) / 4=84.

[0173] Optionally, the specific parameters corresponding to the hard disk health indicators can be adaptively changed according to the upgrade, downgrade, and time of the server.

[0174] Optionally, when the health assessment object is a network card, the network card health index may include the network interface (network port) connection (link) status, network card CE count, network card UCE count, network card alarm count, etc. Optionally, the network card health index may also include other parameters, which are not specifically limited in the embodiments of the present application. Optionally, a server usually has multiple network cards. Exemplarily, the server in the embodiments of the present application includes two network cards, namely network card 1 and network card 2.

[0175] The network port link state may be a network port connection (linkup) or a network port disconnection (linkdown) state. The network port is an electrical port. A network card may include multiple network ports. Exemplarily, in an embodiment of the present application, each network card includes two network ports, for example, network card 1 includes network port 1 and network port 2.

[0176] The network card CE indicates a correctable error that occurs on the network card. The network card CE count indicates the number of times the network card CE occurs within a certain period of time. For example, from the current moment, network card 1 has 20 CEs in the past week. Among them, network port 1 has 10 CEs and network port 2 has 10 CEs.

[0177] The network card UCE indicates an uncorrectable error that occurs in the network card. The network card UCE count indicates the number of times the network card has UCE within a certain period of time. For example, from the current moment, network card 1 has UCE 5 times in the past week. Among them, network port 1 has UCE 2 times, and network port 2 has UCE 3 times.

[0178] The network card alarm indicates the alarm signal sent out when the network card fails. The network card alarm count indicates the number of times the network card alarm occurs within a certain period of time. Among them, each time the network card alarm occurs, a certain health loss will be generated. Optionally, the network card alarm can be divided into network card minor alarm, network card serious alarm, and network card emergency alarm, and the network card health loss corresponding to each alarm level is also different. Exemplarily, from the current moment, within a week of history, network card 1 has 5 minor alarms, and the unit network card minor alarm health loss generated by each network card 1 minor alarm is 0.1; 2 serious alarms, each network card 1 serious alarm generates a unit network card serious alarm health loss of 1; 0 emergency alarms, each network card 1 emergency alarm generates a unit network card emergency alarm health loss of 10.

[0179] Optionally, the server health evaluation system can calculate the health of the network card according to the above network card health index. Since there are usually multiple network cards in a server, it is necessary to calculate the health of each network card, and then calculate the average health of the server's network card according to the health of each network card. The server network card health can be the average network card health of the server. Among them, the average network card health of the server is the average health of multiple network cards in the server. The health of a single network card is 100 minus the health loss of the abnormal port of the network card and the health loss of the network card alarm.

[0180] The abnormal port health loss of the network card can be calculated based on the network port link status, the network card CE count, and the network card UCE count.

[0181] Specifically, the server health evaluation system can calculate the abnormality level of each network port of the network card 1. The link state of the network port is connected (linkup).

[0182] Optionally, the network port CE standard count = MIN (network port CE count, network port CE maximum allowable threshold). MIN is the minimum value. For example, the maximum allowable threshold of network port CE within a week is 50, the network port 1 CE count is 10, and the network port 1 CE count = MIN (10, 50) = 10.

[0183] Network port UCE standard count = MIN (network port UCE count, network port UCE maximum allowable threshold). MIN is the minimum value. For example, the maximum allowable threshold of network port UCE within a week is 10, the network port 1 UCE count is 2, and the network port 1 UCE count = MIN (2, 10) = 2.

[0184] The abnormality degree of the network port = MAX (network port 1 CE standard count / network port CE maximum allowable threshold, network port 1 UCE standard count / network port UCE maximum allowable threshold). MAX is the maximum value, and the abnormality degree of the network port is a floating point number between [0,1]. For example, the abnormality degree of network port 1 = MAX (10 / 50, 2 / 10) = 0.2.

[0185] Optionally, according to the method, the abnormality degree of network port 2 can be calculated to be 0.3. Then the number of abnormal network ports of the network card is the sum of the abnormality degree of network port 1 and the abnormality degree of network port 2, that is, 0.2+0.3=0.5.

[0186] Optionally, if the network port link status is disconnected (linkdown) or the network port type is an optical port (the network port optical module is not in place or the optical module signal is lost (loss of signal, LOS)), the abnormality level of network port 1 is 1.

[0187] Optionally, the health loss of the abnormal network port of the network card 1 is the number of abnormal network ports of the network card / the number of network card ports*100, that is, the health loss of the abnormal network port of the network card 1 is 0.5 / 2*100=25.

[0188] Optionally, the server health evaluation system can determine the network card alarm health loss according to the network card alarm count and the corresponding alarm loss. That is, the network card alarm health loss = network card minor alarm count * unit network card minor alarm health loss + network card serious alarm count * unit network card serious alarm health loss + network card emergency alarm count * unit network card emergency alarm health loss. Exemplarily, from the current moment, the network card alarm health loss of network card 1 in the past week is 5*0.1+2*1+0*10=2.5.

[0189] Optionally, the network card health of network card 1 is 100-network card abnormal port health loss-network card alarm health loss, that is, the network card health of network card 1 is 100-25-2.5=72.5.

[0190] The server health evaluation system can calculate the health of other network cards in the server. For example, the health of network card 2 is 85.5.

[0191] Optionally, the server health evaluation system may obtain an average health of the network card as (72.5+85.5) / 2=79.

[0192] Optionally, the server network card health is the average health of the network card, that is, the server network card health is 79.

[0193] Optionally, the specific parameters corresponding to the above network card health indicators can be adaptively changed according to the upgrade, downgrade and time of the server.

[0194] Optionally, when the health assessment object is a PCIE card, the PCIE card health index may include a PCIE card CE count, a PCIE card UCE count, a PCIE card alarm count, etc. Optionally, the PCIE card health index may also include other parameters, which are not specifically limited in the embodiment of the present application. Optionally, a server usually has multiple PCIE cards. Exemplarily, the server in the embodiment of the present application includes three PCIE cards, namely PCIE card 1, PCIE card 2, and PCIE card 3.

[0195] PCIE card CE indicates a correctable error that occurs in the PCIE card. PCIE card CE count indicates the number of CEs that occur in the PCIE card within a certain period of time. For example, from the current moment, PCIE card 1 has 3 CEs in the past week.

[0196] PCIE card UCE indicates an uncorrectable error that occurs in a PCIE card. PCIE card UCE count indicates the number of times a PCIE card has UCE within a certain period of time. For example, from the current moment, PCIE card 1 has 0 UCEs in the past week.

[0197] The PCIE card alarm indicates the alarm signal issued when a PCIE card fails. The PCIE card alarm count indicates the number of times the PCIE card alarms within a certain period of time. Among them, each alarm of the PCIE card will cause a certain health loss. Optionally, the PCIE card alarm can be divided into PCIE card minor alarm, PCIE card serious alarm, and PCIE card emergency alarm, and the PCIE card health loss corresponding to each alarm level is also different. Exemplarily, from the current moment, within a week of history, PCIE card 1 has 5 minor alarms, and each minor alarm of PCIE card 1 generates a unit PCIE card minor alarm health loss of 0.1; 2 serious alarms, each serious alarm of PCIE card 1 generates a unit PCIE card serious alarm health loss of 1; 0 emergency alarms, each emergency alarm of PCIE card 1 generates a unit PCIE card emergency alarm health loss of 10.

[0198] Optionally, the server health evaluation system can calculate the PCIE card health based on the above PCIE card health index. Since there are usually multiple PCIE cards in a server, it is necessary to calculate the health of each PCIE card, and then calculate the average PCIE card health of the server based on the health of each PCIE card. The server PCIE card health can be the average PCIE card health of the server. Among them, the average PCIE card health of the server is the average health of multiple PCIE cards in the server. The health of a single PCIE card is 100 minus the PCIE card CE and UCE error health loss and the PCIE card alarm health loss.

[0199] The PCIE card CE and UCE error health losses may be calculated based on the PCIE card CE count and the PCIE card UCE count.

[0200] Specifically, PCIE card CE standard count = MIN (PCIE card CE count, PCIE card CE maximum allowable threshold). Wherein, MIN is the minimum value. Exemplarily, the maximum allowable threshold of PCIE card CE within a week is 50, the PCIE card 1 CE count is 10, and the PCIE card 1 CE count = MIN (10, 50) = 10. PCIE card CE error health loss = PCIE card CE count / PCIE card CE maximum allowable threshold * 100. Exemplarily, PCIE card 1 CE error health loss = 3 / 50*100 = 6.

[0201] PCIE card UCE standard count = MIN (PCIE card UCE count, network port UCE maximum allowable threshold). MIN is the minimum value. Exemplarily, the maximum allowable threshold of PCIE card UCE within a week is 1, the PCIE card 1 UCE count is 0, and the PCIE card 1 UCE count = MIN (0, 1) = 0. PCIE card UCE error health loss = PCIE card UCE count / PCIE card UCE maximum allowable threshold * 100. Exemplarily, PCIE card 1 UCE error health loss = 0 / 1*100 = 0.

[0202] PCIE card CE and UCE error health loss = MAX (PCIE card CE error health loss + PCIE card UCE error health loss). MAX is the maximum value. For example, PCIE card 1 CE and UCE error health loss = MAX (6, 0) = 6.

[0203] Optionally, the server health evaluation system can determine the PCIE card alarm health loss according to the PCIE card alarm count and the corresponding alarm loss. That is, PCIE card alarm health loss = PCIE card minor alarm count * unit PCIE card minor alarm health loss + PCIE card serious alarm count * unit PCIE card serious alarm health loss + PCIE card emergency alarm count * unit PCIE card emergency alarm health loss. Exemplarily, from the current moment, the PCIE card alarm health loss of PCIE card 1 in the past week is 5*0.1+2*1+0*10=2.5.

[0204] Optionally, the health of the PCIE card 1 is 100 minus the health loss of the CE and UCE errors of the PCIE card and the health loss of the PCIE card alarm, that is, the health of the PCIE card 1 = 100 - 6 - 2.5 = 91.5.

[0205] The server health evaluation system can calculate the health of other PCIE cards in the server. For example, the health of PCIE card 2 is 85.5, and the health of PCIE card 3 is 93.

[0206] Optionally, the server health evaluation system may obtain an average health of the PCIE card as (91.5+85.5+93) / 3=90.

[0207] Optionally, the health of the server PCIE card is the average health of the PCIE card, that is, the health of the server PCIE card is 90.

[0208] Optionally, the specific parameters corresponding to the above PCIE card health indicators can be adaptively changed according to the upgrade, downgrade and time of the server.

[0209] Optionally, when the health assessment object is a power module, the power module health index may include the power module in-place status, power alarm count, etc. Optionally, the power module health index may also include other parameters, which are not specifically limited in the embodiments of the present application. Optionally, there are usually multiple power modules in a server. Exemplarily, the server in the embodiment of the present application includes four power modules, namely power module 1, power module 2, power module 3, and power module 4.

[0210] The power module in-place state is divided into an online state and an offline state. When the power module in-place state is an online state, the power module works normally. When the power module in-place state is an offline state, the power module does not work.

[0211] The power module alarm indicates the alarm signal issued when the power module fails. The power module alarm count indicates the number of times the power module alarms within a certain period of time. Among them, each time the power module alarms, a certain health loss will occur. Optionally, the power module alarm can be divided into a power module minor alarm, a power module serious alarm, and a power module emergency alarm, and the power module health loss corresponding to each alarm level is also different. Exemplarily, from the current moment, within a week of history, power module 1 has 5 minor alarms, and the unit power module minor alarm health loss generated by each minor alarm of power module 1 is 0.1; 2 serious alarms, each unit power module serious alarm health loss generated by each serious alarm of power module 1 is 1; 0 emergency alarms, each unit power module emergency alarm health loss generated by the emergency alarm of power module 1 is 10.

[0212] Optionally, the server health assessment system can calculate the health of the power module based on the above-mentioned power module health index. Since there are usually multiple power modules in a server, it is necessary to calculate the health of each power module, and then calculate the average health of the server's power modules based on the health of each power module. The server power module health can be the server average power module health - 100*(NM) / N. Where M is the number of power modules in place, and N is the number of power modules. The health of a single power module is 100 minus the power module alarm health loss.

[0213] Optionally, the server health evaluation system may obtain the status of the power modules. Exemplarily, power module 1 is online, power module 2 is online, power module 3 is online, and power module 4 is offline.

[0214] Optionally, the server health assessment system can determine the power module alarm health loss based on the power module alarm count and the corresponding alarm loss. That is, the power module alarm health loss = power module minor alarm count * unit power module minor alarm health loss + power module serious alarm count * unit power module serious alarm health loss + power module emergency alarm count * unit power module emergency alarm health loss. Exemplarily, from the current moment, the PCIE card alarm health loss of power module 1 in the past week is 5*0.1+2*1+0*10=2.5.

[0215] Optionally, the health of the power module of the power module 1 is 100 minus the power module alarm health loss, that is, the health of the power module of the power module 1 = 100 - 2.5 = 97.5.

[0216] The server health evaluation system can calculate the health of other power modules in the server. For example, the health of power module 2 is 85.5, the health of power module 3 is 93, and the health of power module 4 is 92.

[0217] Optionally, the server health evaluation system may obtain an average health of the power module as (97.5+85.5+93+92) / 4=92.

[0218] Optionally, the health of the server power module may be the server average power module health - 100*(NM) / N, that is, 92-100*(4-3) / 4=67.

[0219] Optionally, specific parameters corresponding to the above power module health indicators can be adaptively changed according to server upgrades, downgrades, and time.

[0220] Optionally, when the health assessment object is a fan module, the fan module health index may include the fan module in-place status, fan alarm count, etc. Optionally, the fan module health index may also include other parameters, which are not specifically limited in the embodiment of the present application. Optionally, there are usually multiple fan modules in a server. Exemplarily, the server in the embodiment of the present application includes four fan modules, namely fan module 1, fan module 2, fan module 3, and fan module 4.

[0221] The fan module in-place state is divided into an online state and an offline state. When the fan module in-place state is an online state, the fan module works normally. When the fan module in-place state is an offline state, the fan module does not work.

[0222] The fan module alarm indicates the alarm signal sent out when the fan module fails. The fan module alarm count indicates the number of times the fan module alarms within a certain period of time. Each time the fan module alarms, a certain health loss will be generated. Optionally, the fan module alarm can be divided into a fan module minor alarm, a fan module serious alarm, and a fan module emergency alarm, and the fan module health loss generated corresponding to each alarm level is also different. Exemplarily, from the current moment, within a week of history, fan module 1 has 15 minor alarms, and each minor alarm of fan module 1 generates a unit fan module minor alarm health loss of 0.1; 1 serious alarm, each severe alarm of fan module 1 generates a unit fan module serious alarm health loss of 1; 0 emergency alarms, each emergency alarm of fan module 1 generates a unit fan module emergency alarm health loss of 10.

[0223] Optionally, the server health assessment system can calculate the fan module health based on the above-mentioned fan module health index. Since there are usually multiple fan modules in a server, it is necessary to calculate the health of each fan module, and then calculate the average health of the server's fan modules based on the health of each fan module. The server fan module health can be the server average fan module health - 100*(NM) / N. Where M is the number of fan modules in place, and N is the number of fan modules. The health of a single fan module is 100 minus the fan module alarm health loss.

[0224] Optionally, the server health evaluation system may obtain the in-place status of the fan modules. Exemplarily, fan module 1 is in an online state, fan module 2 is in an online state, fan module 3 is in an online state, and fan module 4 is in an online state.

[0225] Optionally, the server health assessment system can determine the fan module alarm health loss based on the fan module alarm count and the corresponding alarm loss. That is, fan module alarm health loss = fan module minor alarm count * unit fan module minor alarm health loss + fan module severe alarm count * unit fan module severe alarm health loss + fan module emergency alarm count * unit fan module emergency alarm health loss. Exemplarily, from the current moment, the alarm health loss of fan module 1 in the past week is 15*0.1+1*1+0*10=2.5

[0226] Optionally, the health of the fan module of the fan module 1 is 100 minus the fan module alarm health loss, that is, the fan module health of the fan module 1 = 100 - 2.5 = 97.5.

[0227] The server health evaluation system can calculate the health of other fan modules in the server. For example, the health of fan module 2 is 85.5, the health of fan module 3 is 93, and the health of fan module 4 is 92.

[0228] Optionally, the server health evaluation system may obtain an average health of the fan modules as (97.5+85.5+93+92) / 4=92.

[0229] Optionally, the health of the server fan module may be the server average fan module health - 100*(NM) / N, that is, 92-100*(4-4) / 4=92.

[0230] Optionally, the specific parameters corresponding to the above fan module health indicators can be adaptively changed according to the upgrade, downgrade and time of the server.

[0231] Optionally, the server health evaluation system can perform weighted average calculation based on the health of each of the above health evaluation objects and the weight of each health evaluation object to determine the server health. That is, server health = CPU health * CPU health weight + memory health * memory health weight + hard disk health * hard disk health weight + network card health * network card health weight + PCIE card health * PCIE card health weight + power module health * power module health weight + fan module health * fan module health weight.

[0232] The weight of each health assessment object may be calculated based on the failure rate of each health assessment object.

[0233] Specifically, the weight of the health assessment object is the failure rate of the health assessment object / the sum of the failure rates of all health assessment objects.

[0234] For example, if the CPU failure rate is 15%, the weight of the CPU is 15% / (15%+15%+20%+10%+10%+5%+25%)=15%; if the memory failure rate is 15%, the weight of the memory is 15% / (15%+15%+20%+10%+10%+5%+25%)=15%; if the hard disk failure rate is 20%, the weight of the hard disk is 20% / (15%+15%+20%+10%+10%+5%+25%)=20%; if the network card failure rate is 10%, the weight of the network card is 10% / (15%+15%+20%+10%+10%+5%+25%)=20%. +20%+10%+10%+10%+5%+25%)=10%; the failure rate of PCIE card is 10%, and the weight of PCIE card is 10% / (15%+15%+20%+10%+10%+5%+25%)=10%; the failure rate of power module is 5%, and the weight of power module is 5% / (15%+15%+20%+10%+10%+5%+25%)=5%; the failure rate of fan module is 25%, and the weight of fan module is 25% / (15%+15%+20%+10%+10%+5%+25%)=25%.

[0235] Exemplarily, according to the failure rates of the above-mentioned health assessment objects and the corresponding healths, it can be obtained that server health=54*15%+87*15%+84*20%+79*10%+90*10%+67*5%+92*25%=81.2.

[0236] Optionally, the server health may be calculated in other ways, such as calculating the average health of multiple health evaluation objects as the server health. This embodiment of the present application does not impose any specific limitation on this.

[0237] In one embodiment, the server health evaluation system may prompt the user based on the server health.

[0238] Optionally, the developer can divide multiple server health warning thresholds, and divide the server health status into multiple levels according to different server warning thresholds. The server health evaluation system prompts the user with the current level of the server.

[0239] For example, when the server health is between [0, 20), it is a critical sub-health level; when the server health is between [20, 65), it is a severe sub-health level; when the server health is between [65, 85), it is a mild sub-health level; when the server health is between [85, 100], it is a healthy level. The server health warning threshold can also be other threshold values, and the embodiments of the present application do not specifically limit this.

[0240] Exemplarily, when the server health is 81.2, the server health level is a slightly sub-healthy level.

[0241] Optionally, the server health evaluation system may periodically prompt the user of the server's health level. Exemplarily, the server health evaluation system may prompt the user of the server's health level every day, and the server's health level this week is a mild sub-health level.

[0242] The server A evaluated by the server health evaluation system is taken as an example for introduction.

[0243] For example, the server health evaluation system may send a text message to the user's mobile phone to remind the user of the server's health level. Figure 5 As shown in FIG. 1 , the server health evaluation system sends a text message of the current health level of server A to the user's mobile phone. After the user's mobile phone receives the text message, it can display the following information: Figure 5 The user's mobile phone text message interface 401 is shown, and the text message interface 401 includes a text message 402, the sender of the text message "Server Health Assessment System" and the receiving time of the text message "Today's morning 8:00". Among them, the text message 402 includes the title of the text message "Server Health Reminder" and the text message content "The current health level of server A is a mild sub-health level."

[0244] Optionally, the server health assessment system can also issue an early warning prompt to the user only when the server enters the sub-health level. Exemplarily, when the server health level is a mild sub-health level, the server health assessment system issues an early warning prompt to the user that the server has entered the mild sub-health level and needs maintenance.

[0245] For example, Figure 6As shown in the figure, the server health assessment system sends an alarm prompt SMS to the user's mobile phone. After the user's mobile phone receives the alarm prompt SMS, it can display the following Figure 6 The user's mobile phone text message interface 501 is shown, and the text message interface 501 includes a text message 502, the sender of the text message "Server Health Assessment System" and the receiving time of the text message "Today's morning 8:00". Among them, the text message 502 includes the title of the text message "Server Health Alarm Reminder" and the text message content "The current health level of server A is a mild sub-health level, please maintain it as soon as possible."

[0246] In another exemplary embodiment, when the server health evaluation system evaluates that the health level of server A is a mild sub-health level, the server health evaluation system may issue an audible and visual prompt through server A. Figure 7 As shown, the server health evaluation system sends the evaluation result to server A. There are three prompt lights in server A. When the evaluation result is a mild sub-health level, the first prompt light flashes to remind the user that the current health level of server A is a mild sub-health level. And / or, server A issues a voice prompt "The current health level of server A is a mild sub-health level, please perform maintenance as soon as possible."

[0247] Optionally, when the health level of the server is different, the way the prompt light flashes and the content of the voice prompt are also different. For example, when the evaluation result is a healthy level, the prompt light does not flash. And / or, server A issues a voice prompt "The current health level of server A is a healthy level." To prompt the user that the current health level of server A is a healthy level. When the evaluation result is a severe sub-health level, the second prompt light flashes. And / or, server A issues a voice prompt "The current health level of server A is a severe sub-health level, please perform maintenance as soon as possible." To prompt the user that the current health level of server A is a severe sub-health level. When the evaluation result is a critical sub-health level, the third prompt light flashes. And / or, server A issues a voice prompt "The current health level of server A is a critical sub-health level, please perform maintenance as soon as possible." To prompt the user that the current health level of server A is a critical sub-health level.

[0248] Alternatively, there is a prompt light in server A, which prompts the user of the current health level of server A through different colors or different flashing frequencies. For example, when the evaluation result is a healthy level, the prompt light is green. When the evaluation result is a mild sub-health level, the prompt light is yellow. When the evaluation result is a severe sub-health level, the prompt light is orange. When the evaluation result is a critical sub-health level, the prompt light is orange. For another example, when the evaluation result is a healthy level, the prompt light is off. When the evaluation result is a mild sub-health level, the prompt light flashes once per second. When the evaluation result is a severe sub-health level, the prompt light flashes three times per second. When the evaluation result is a critical sub-health level, the prompt light is always on.

[0249] Optionally, the flashing mode of the prompt light and the voice prompt content may also be other modes, and this application does not impose any specific restrictions on this.

[0250] Optionally, the above-mentioned prompting method may also be a log, an alarm, an event, an email, a push in an application, etc. The embodiment of the present application does not impose any specific limitation on this.

[0251] In this way, users can determine the current server health and schedule services according to the server health. For example, if the current server health is 92, which is a healthy level, the server health is relatively high, and users can assign more important or more services to this server. If the current server health is 72, which is a mild sub-health level, the server health is relatively low, and users can assign less important or less services to this server.

[0252] Optionally, the server health evaluation system can also predict future server health level trends of the server.

[0253] Optionally, the server health evaluation system can periodically evaluate and calculate the server health to form a server health sequence, and use a trend prediction algorithm model to perform trend prediction on future server health levels based on the server health sequence.

[0254] The trend prediction algorithm model may be an autoregressive integrated moving average model (ARIMA), a long short-term memory model (LSTM), etc. The embodiment of the present application does not impose any specific limitation on this.

[0255] Exemplarily, the server health assessment system can evaluate and calculate the server health every day. From the current moment, the server health of the historical four days is: the server health of the first day before was 88, the server health of the second day before was 92, the server health of the third day before was 92, and the server health of the fourth day before was 96.

[0256] Optionally, the server health evaluation system may use ARIMA to perform trend prediction on the server health level of the server based on the server health over the past four days.

[0257] Exemplarily, the prediction result obtained according to the above server health sequence may be: the server will enter a mild sub-health level after 10 days; the server will enter a severe sub-health level after 40 days; and the server will enter a critical sub-health level after 200 days.

[0258] For example, the server health level is 82 on the first day before, 88 on the second day before, 92 on the third day before, and 96 on the fourth day before. The prediction result may be: the server will enter a severe sub-health level after 40 days; and the server will enter a critical sub-health level after 200 days.

[0259] Optionally, the server health evaluation system may evaluate and calculate the server health every week, and use ARIMA to perform trend prediction on the server health level of the server based on the server health at a historical preset time.

[0260] Exemplarily, the server health evaluation system may evaluate and calculate the server health every week. From the current moment, the server health of the three previous weeks is: the server health of the first week is 82, the server health of the second week is 92, and the server health of the third week is 95.

[0261] Optionally, the server health evaluation system may use ARIMA to perform trend prediction on the server health level of the server based on the server health over the past four weeks.

[0262] Exemplarily, the prediction result obtained according to the above server health sequence may be: the server will enter a mild sub-health level after 2 weeks; the server will enter a severe sub-health level after 10 weeks; and the server will enter a critical sub-health level after 40 weeks.

[0263] Alternatively, the server health evaluation system can also evaluate and calculate the server health every hour, and use ARIMA to perform trend prediction on the server health level of the server based on the server health at a historical preset time. This embodiment of the application does not impose specific restrictions on this.

[0264] Optionally, the server health assessment system can send the prediction results to the user for early warning.

[0265] For example, Figure 8 As shown in the figure, the server health assessment system sends a warning SMS to the user's mobile phone. After the user's mobile phone receives the warning SMS, it can display the following Figure 8 The user's mobile phone text message interface 601 is shown, and the text message interface 601 includes a text message 602, the sender of the text message "Server Health Assessment System" and the receiving time of the text message "Today's 8:00 am". Among them, the text message 602 includes the title of the text message "Server Health Warning Reminder" and the text message content "Server A will enter the mild sub-health level in 10 days; the server will enter the severe sub-health level in 40 days; the server will enter the critical sub-health level in 200 days, please maintain it as soon as possible."

[0266] Optionally, the server may also only prompt the next server health level that the server is about to enter.

[0267] For example, the server health level on the first day is 88, which is a healthy level. The user is prompted that the server will enter a mild sub-health level after 10 days;

[0268] For example, if the server health level on the first day is 82, which is a mild sub-health level, the user is prompted that the server will enter a severe sub-health level after 40 days.

[0269] For example, Fig. 9 The text message content shown may be "Server A will enter a mild sub-health level in 10 days, please perform maintenance as soon as possible." The embodiment of the present application does not impose any specific restrictions on this.

[0270] In this way, users can obtain the server health development trend for a period of time in the future, which is convenient for users to design solutions. For example, when the server health assessment system predicts that the server will enter the critical sub-health level in 10 days, the server may be scrapped. Users can back up the data in the server in time, or replace or repair the components in the server to improve the health of the server. Delay the use of the server.

[0271] Further, such as Fig.10 As shown, the server health evaluation method can be specifically implemented as the following steps S101-S102.

[0272] S101. A server health assessment system determines at least one health assessment object of a target server according to fault statistics of multiple servers and types of hardware components of the target server.

[0273] The health evaluation object is the hardware component of the server. The server health evaluation system selects hardware components with higher failure rates from among the hardware components included in the target server as the health evaluation object based on the failure statistics of multiple servers.

[0274] For example, if the statistical analysis results of multiple server failure information are: the mainboard failure rate is 4%, the CPU failure rate is 15%, the memory failure rate is 15%, the hard disk failure rate is 20%, the network card failure rate is 10%, the PCIE card failure rate is 10%, the remote management card failure rate is 2%, the power module failure rate is 5%, and the fan module failure rate is 25%. The server health assessment system detects that the server includes hardware components such as the mainboard, central processing unit (CPU), memory, hard disk, network card, high-speed serial computer expansion (Peripheral Component Interconnect Express, PCIE) card, remote management card, power module and fan module. The server health assessment system can select seven hardware components with higher failure rates as the server health assessment objects. In other words, the server health assessment system selects CPU, memory, hard disk, network card, PCIE card, power module and fan module as the server health assessment objects.

[0275] S102: The server health evaluation system determines the health of the target server according to evaluation parameters of the at least one health evaluation object within a preset historical time period.

[0276] The evaluation parameter in the historical preset time period may be an evaluation parameter in the historical week from the current moment. The evaluation parameter of at least one health evaluation object has different evaluation parameter values ​​in different historical preset time periods. For example, the specific parameters of the health index of the health evaluation object in the historical week are different from different moments.

[0277] Exemplarily, if the current time is 14:37:32 of the day, the server health evaluation system calculates the CPU health according to the specific parameters corresponding to the CPU health index in the past week from 14:37:32 of the day. If the current time is 14:37:33 of the day, the server health evaluation system calculates the CPU health according to the specific parameters corresponding to the CPU health index in the past week from 14:37:33 of the day.

[0278] The evaluation parameters include at least one of the number of each health evaluation object, the correctable error count, the uncorrectable error count, and the alarm count. For example, when the health evaluation object is a CPU, the CPU evaluation parameters may include the number of CPU core isolations, the CPU correctable error count, the CPU uncorrectable error count, the CPU alarm count, the CPU average usage, the CPU average load, the number of CPUs, etc.

[0279] Optionally, the evaluation parameters of the health evaluation object may also include predicted fault information of the health evaluation object. Exemplarily, when the health evaluation object is a CPU, the CPU evaluation parameters may include a CPU fault prediction result.

[0280] The server health evaluation system can also determine predicted fault information of the health evaluation object according to the evaluation parameters of the health evaluation object. Exemplarily, when the health evaluation object is a CPU, the server health evaluation system can determine the CPU fault prediction result according to the CPU evaluation parameters.

[0281] Optionally, the server health evaluation system may determine the health of the health evaluation object according to the evaluation parameters of the health evaluation object, and then determine the health of the server according to the health of the health evaluation object.

[0282] Exemplarily, the server health evaluation system determines the health of the CPU, memory, hard disk, network card, PCIE card, power module and fan module respectively according to the evaluation parameters, fault prediction results, etc. of the CPU, memory, hard disk, network card, PCIE card, power module and fan module. The health of the server is determined according to the health of the CPU, memory, hard disk, network card, PCIE card, power module and fan module.

[0283] Optionally, the server health evaluation system can also determine the weight of the health evaluation object of the server according to the failure statistics of the multiple servers, and then determine the health of the server according to the health of the health evaluation object and the weight of the health evaluation object. The failure rate of each hardware component of the multiple servers is positively correlated with the weight of the health evaluation object of the target server.

[0284] Exemplarily, the server health evaluation system determines that the weight of the CPU is 15%, the weight of the memory is 15%, the weight of the hard disk is 20%, the weight of the network card is 10%, the weight of the PCIE card is 10%, the weight of the power module is 5%, and the weight of the fan module is 25% according to the fault statistics of multiple servers. After that, the server health evaluation system calculates the health of the server according to the health of the health evaluation object and the weight of the health evaluation object. That is, server health = CPU health * CPU health weight + memory health * memory health weight + hard disk health * hard disk health weight + network card health * network card health weight + PCIE card health * PCIE card health weight + power module health * power module health weight + fan module health * fan module health weight = 54*15% + 87*15% + 84*20% + 79*10% + 90*10% + 67*5% + 92*25% = 81.2.

[0285] Optionally, the developer can divide multiple server health warning thresholds, and divide the server health status into multiple levels according to different server warning thresholds. The server health evaluation system can prompt the user with the current level of the server.

[0286] When the server health is between [0,20), it is a critical sub-health level; when the server health is between [20,65), it is a severe sub-health level; when the server health is between [65,85), it is a mild sub-health level; when the server health is between [85,100], it is a healthy level.

[0287] For example, the server health evaluation system calculates that the server health is 81.2, and the server health level is a mild sub-health level. The server health evaluation system can prompt the user that the server health level of the current week is a mild sub-health level.

[0288] Optionally, the server health assessment system may also determine a predicted health level of the server based on the health of the server.

[0289] Specifically, the server health evaluation system can periodically evaluate and calculate the server health to form a server health sequence, and use a trend prediction algorithm model to predict the future server health level trend based on the server health sequence.

[0290] For example, the server health level is 82 on the first day before, 88 on the second day before, 92 on the third day before, and 96 on the fourth day before. The prediction result may be: the server will enter a severe sub-health level after 40 days; and the server will enter a critical sub-health level after 200 days.

[0291] The above-mentioned server health evaluation method determines at least one health evaluation object based on the fault statistics of multiple servers and the types of hardware components of the target server, and uses the evaluation parameters in the historical period to calculate the health of the target server, and adaptively evaluates the server health from multiple aspects, and the evaluation results are scientific and accurate. In addition, the server health evaluation system can periodically provide differentiated prompts to users for different health levels of the target server. Or, when the health level of the target server is low, an alarm prompt is issued. Or, the health level of the target server is predicted, and the predicted health level is sent to the user for early warning prompts. In this way, users can intervene in advance to promptly troubleshoot and handle server failures, eliminating or reducing the losses caused thereby. And enable operation and maintenance personnel to classify and solve them according to different server health levels. It is also possible to obtain the server health development trend for a period of time in the future, which is convenient for users to design solutions. Improve efficiency and enhance user experience.

[0292] It should be noted that some operations in the processes of the above-mentioned method embodiments are optionally combined, and / or the order of some operations is optionally changed. In addition, the execution order between the steps of each process is only exemplary and does not constitute a limitation on the execution order between the steps. There may be other execution orders between the steps. It is not intended to indicate that the execution order is the only order in which these operations can be performed. A person of ordinary skill in the art will think of a variety of ways to reorder the operations described herein. In addition, it should be noted that the process details involved in a certain embodiment of this invention are also applicable to other embodiments in a similar manner, or different embodiments can be used in combination.

[0293] In addition, some steps in the method embodiment may be equivalently replaced by other possible steps. Alternatively, some steps in the method embodiment may be optional and may be deleted in certain usage scenarios. Alternatively, other possible steps may be added to the method embodiment.

[0294] Furthermore, the above method embodiments may be implemented separately or in combination.

[0295] Some other embodiments of the present application provide a device, which may be the above-mentioned electronic device or a component in the electronic device (such as a chip system).

[0296] The device may include: a memory and one or more processors. The memory is coupled to the processor. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device may execute the various functions or steps executed by the mobile phone in the above method embodiment.

[0297] Among them, the core structure of the electronic device can be expressed as Fig.11 As shown in the structure, the electronic device includes: a processing module 151, a communication module 152, and a storage module 153.

[0298] The processing module 151 may include at least one of a central processing unit (CPU), an application processor (AP) or a communication processor (CP). The processing module 151 may perform operations or data processing related to the control and / or communication of at least one of the other components of the user electronic device. Optionally, the processing module 151 is used to support the electronic device to perform Fig.10 S101-S102 in

[0299] The communication module 152 is used to support the electronic device to communicate with other electronic devices (through a communication network). For example, the communication module can be connected to the network via wireless communication or wired communication to communicate with other personal terminals or network servers. Wireless communication can adopt at least one of cellular communication protocols, such as Long Term Evolution (LTE), Advanced Long Term Evolution (LTE-A), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Universal Mobile Telecommunications System (UMTS), Wireless Broadband (WiBro) or Global System for Mobile Communications (GSM). Wireless communication may include, for example, short-range communication. Short-range communication may include at least one of wireless fidelity (Wi-Fi), Bluetooth, near field communication (NFC), magnetic stripe transmission (MST) or GNSS. For example, the server can send the server health level to other electronic devices.

[0300] The storage module 153 may include a volatile memory and / or a non-volatile memory. The storage module is used to store at least one instruction or data related to other modules of the user terminal device. Optionally, the storage module 153 is used by the electronic device to store the historical health level of the server, etc.

[0301] Fig.11 The device shown may also include more or fewer components, or split some components, or have other ways of arranging components, which is not limited in the embodiments of the present application.

[0302] The present application also provides a chip system, such as Fig.12As shown, the chip system includes at least one processor 161 and at least one interface circuit 162. The processor 161 and the interface circuit 162 can be interconnected via lines. For example, the interface circuit 162 can be used to receive signals from other devices (such as a memory of an electronic device). For another example, the interface circuit 162 can be used to send signals to other devices (such as the processor 161). Exemplarily, the interface circuit 162 can read instructions stored in the memory and send the instructions to the processor 161. When the instructions are executed by the processor 161, the electronic device can execute the various steps in the above embodiments. Of course, the chip system may also include other discrete devices, which are not specifically limited in the embodiments of the present application.

[0303] An embodiment of the present application also provides a computer storage medium, which includes computer instructions. When the computer instructions are executed on the above-mentioned electronic device, the electronic device executes each function or step executed by the mobile phone in the above-mentioned method embodiment.

[0304] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute each function or step executed by the mobile phone in the above method embodiment.

[0305] Through the description of the above implementation methods, technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and module described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0306] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0307] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0308] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0309] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0310] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for evaluating the health of an electronic device, characterized in that: include: Determining at least one health assessment object of the target electronic device according to the failure statistics of the plurality of electronic devices and the types of hardware components of the target electronic device; The health of the target electronic device is determined according to the evaluation parameters of the at least one health evaluation object in a historical preset time period; wherein the evaluation parameter values ​​of the at least one health evaluation object are different in different historical preset time periods.

2. The method according to claim 1, characterized in that The method further comprises: Prompt first information, where the first information is used to indicate the health of the target electronic device.

3. The method according to claim 2, characterized in that The first information includes the second information or the third information, and the prompting of the first information, wherein the first information is used to indicate the health of the target electronic device, includes: When the health of the target electronic device is lower than a first threshold, prompting the second information; When the health of the target electronic device is lower than a second threshold, the third information is prompted, the first threshold is greater than the second threshold, and the second information is different from the third information.

4. The method according to any one of claims 1 to 3, characterized in that: The step of determining at least one health evaluation object of the target electronic device according to the failure statistics of the plurality of electronic devices and the types of hardware components of the target electronic device comprises: Determining a failure rate of each hardware component in the plurality of electronic devices according to the failure statistics of the plurality of electronic devices; According to the failure rate of each hardware component in the multiple electronic devices, the multiple hardware components are sorted from high to low, and the hardware component whose failure rate ranking is greater than the preset ranking and belongs to the hardware component type of the target electronic device is determined as the health assessment object.

5. The method according to any one of claims 1 to 4, characterized in that: Determining the health of the target electronic device according to the evaluation parameters of the at least one health evaluation object within a preset historical period includes: Determining a fault prediction result of the health assessment object using a first prediction algorithm according to the assessment parameters of the health assessment object within a preset historical period; The health of the target electronic device is determined according to the evaluation parameters of the at least one health evaluation object within a preset historical period and the fault prediction result of at least one health evaluation object.

6. The method according to any one of claims 1 to 4, characterized in that: The determining the health of the target electronic device according to the evaluation parameter of the at least one health evaluation object within a preset historical period includes: Determining the health of the health assessment object according to the assessment parameters of the at least one health assessment object within a preset historical period; The health of the target electronic device is determined according to the health of at least one of the health assessment objects.

7. The method according to claim 6, characterized in that The method further comprises: Determining the weight of the health evaluation object of the target electronic device according to the failure rate of each hardware component of the multiple electronic devices; the failure rate of each hardware component of the multiple electronic devices is obtained according to the failure statistical information of the multiple electronic devices; the failure rate of each hardware component of the multiple electronic devices is positively correlated with the weight of the health evaluation object of the target electronic device; When there are multiple health objects of the target electronic device, determining the health of the target electronic device according to the health of at least one health assessment object includes: The health of the target electronic device is determined according to the health of the plurality of health assessment objects and the corresponding weights of the plurality of health assessment objects.

8. The method according to claim 6, characterized in that The determining the health of the health assessment object according to the assessment parameter of the at least one health assessment object in a preset historical period includes: Calculating a first health loss of the health assessment object within a preset historical period according to an assessment parameter of the at least one health assessment object within a preset historical period; The health of the health assessment object is calculated according to the number of the health assessment objects, the preset full score health and the first health loss.

9. The method according to claim 6, characterized in that The determining the health of the health assessment object according to the assessment parameter of the at least one health assessment object in a preset historical period includes: Calculating a first health loss of the health assessment object within a preset historical period according to an assessment parameter of the at least one health assessment object within a preset historical period; Determining a second health loss of the health assessment object according to an average usage rate and an average load of the health assessment object; The health of the health assessment object is calculated according to the number of the health assessment objects, the preset full score health, the first health loss, and the second health loss.

10. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: According to the historical health of the target electronic device, using a second prediction algorithm to calculate the predicted health of the target electronic device; Prompt third information, where the third information is used to indicate the predicted health level.

11. The method according to any one of claims 1 to 10, characterized in that: The health evaluation object includes at least one of a central processing unit, a memory, a hard disk, a network card, a high-speed serial computer expansion card, a remote management card, a power module or a fan module.

12. The method according to any one of claims 1 to 11, characterized in that: The evaluation parameters include: at least one of the number of each health evaluation object, a correctable error count, an uncorrectable error count, and an alarm count.

13. An electronic equipment health assessment device, characterized in that: include: A processing module, configured to determine at least one health assessment object of the target electronic device according to the failure statistics of the plurality of electronic devices and the types of hardware components of the target electronic device; The processing module is also used to determine the health of the target electronic device according to the evaluation parameters of the at least one health evaluation object within a historical preset time period; wherein the evaluation parameter values ​​of the at least one health evaluation object are different in different historical preset time periods.

14. The device according to claim 13, characterized in that The device also includes: The communication module is used to prompt first information, where the first information is used to indicate the health of the target electronic device.

15. The device according to claim 14, characterized in that The first information includes the second information or the third information, The communication module is further configured to prompt the second information when the health of the target electronic device is lower than a first threshold; The communication module is further configured to prompt the third information when the health of the target electronic device is lower than a second threshold, the first threshold is greater than the second threshold, and the second information is different from the third information.

16. The device according to any one of claims 13 to 15, characterized in that: The processing module is also used to determine the failure rate of each hardware component in the multiple electronic devices based on the failure statistics of the multiple electronic devices; sort the multiple hardware components from high to low according to the failure rate of each hardware component in the multiple electronic devices, and determine the hardware component type whose failure rate ranking is greater than a preset ranking and belongs to the target electronic device as the health assessment object.

17. The device according to any one of claims 13 to 16, characterized in that: The processing module is also used to determine the fault prediction result of the health assessment object using a first prediction algorithm based on the evaluation parameters of the health assessment object within a historical preset time period; and determine the health of the target electronic device based on the evaluation parameters of at least one health assessment object within a historical preset time period and at least one fault prediction result of the health assessment object.

18. An electronic equipment health assessment system, characterized in that: include: a processor coupled to the memory; The processor is used to execute the computer program stored in the memory so that the electronic device health assessment system executes the method as described in any one of claims 1-12.

19. A computer-readable storage medium, characterized in that: The computer-readable storage medium comprises a computer program or instructions, and when the computer program or instructions are executed on a vehicle control device, the vehicle control device is caused to execute the method according to any one of claims 1 to 12.

Images