A computer hardware fault early warning method and system based on multi-dimensional data

Abstract

The application relates to the technical field of computer hardware, and provides a computer hardware fault early warning method and system based on multidimensional data. The method comprises the following steps: classifying and integrating multidimensional running state data information according to running data attribute information to obtain standard multidimensional running state data information; evaluating the standard multidimensional running state data information to obtain hardware running effect information; when the hardware running effect information is lower than a preset hardware effect threshold value, obtaining hardware fault state data information; inputting the hardware fault state data information into a fault maintenance measure analysis model to obtain a hardware maintenance measure scheme; generating a computer hardware fault early warning report according to the hardware fault state data information and the hardware maintenance measure scheme, and performing running fault early warning on target computer hardware based on the computer hardware fault early warning report. The method can realize timely hardware fault early warning, thereby guaranteeing the technical effect of stable computer operation.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of computer hardware, in particular to a computer hardware fault early warning method and system based on multidimensional data. BACKGROUND

[0002] Hardware refers to various physical devices composed of electronic, mechanical and optoelectronic elements, etc. in a computer system, which form an organic whole according to the requirements of the system structure to provide a material basis for the operation of computer software. The functions of hardware are to input and store programs and data, and to execute programs to process data into a form that can be utilized, mainly including CPU, memory, motherboard, hard disk drive, optical disk drive, various expansion cards, connection lines, power supply, etc. Therefore, it has important practical significance to make timely early warning before the computer hardware fails, to ensure the stable operation of the computer and reduce losses.

[0003] However, the existing technology has low manual fault diagnosis efficiency and cannot make timely early warning of hardware failure, which leads to the technical problem of affecting the stable operation of the computer. SUMMARY

[0004] Therefore, it is necessary to provide a computer hardware fault early warning method and system based on multidimensional data, which can realize timely hardware failure early warning and ensure the stable operation of the computer.

[0005] A computer hardware fault early warning method based on multidimensional data, the method comprising: monitoring a target computer hardware in real time through a sensor group to obtain multidimensional running state data information; marking the multidimensional running state data information with attributes to obtain running data attribute information; classifying and integrating the multidimensional running state data information according to the running data attribute information to obtain standard multidimensional running state data information; evaluating the running effect of the standard multidimensional running state data information to obtain hardware running effect information; when the hardware running effect information is lower than a preset hardware effect threshold, marking unqualified dimensional data to obtain hardware fault state data information; inputting the hardware fault state data information into a fault maintenance measure analysis model to obtain a hardware maintenance measure scheme; generating a computer hardware fault early warning report according to the hardware fault state data information and the hardware maintenance measure scheme, and making running fault early warning of the target computer hardware based on the computer hardware fault early warning report.

[0006] A computer hardware failure early warning system based on multi-dimensional data, the system comprising: a data real-time monitoring module for real-time monitoring of target computer hardware by a sensor group, obtaining multi-dimensional running state data information; a data attribute marking module for marking the attributes of the multi-dimensional running state data information, obtaining running data attribute information; a data classification and integration module for classifying and integrating the multi-dimensional running state data information according to the running data attribute information, obtaining standard multi-dimensional running state data information; a running effect evaluation module for evaluating the running effect of the standard multi-dimensional running state data information, obtaining hardware running effect information; a data marking module for marking unqualified dimensional data when the hardware running effect information is lower than a preset hardware effect threshold, obtaining hardware failure state data information; a fault maintenance measure analysis module for inputting the hardware failure state data information into a fault maintenance measure analysis model, obtaining a hardware maintenance measure scheme; a running failure early warning module for generating a computer hardware failure early warning report according to the hardware failure state data information and the hardware maintenance measure scheme, and performing running failure early warning on the target computer hardware based on the computer hardware failure early warning report.

[0007] A computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0008] Real-time monitoring of target computer hardware by a sensor group, obtaining multi-dimensional running state data information;

[0009] Marking the attributes of the multi-dimensional running state data information, obtaining running data attribute information;

[0010] Classifying and integrating the multi-dimensional running state data information according to the running data attribute information, obtaining standard multi-dimensional running state data information;

[0011] Evaluating the running effect of the standard multi-dimensional running state data information, obtaining hardware running effect information;

[0012] When the hardware running effect information is lower than a preset hardware effect threshold, marking unqualified dimensional data, obtaining hardware failure state data information;

[0013] Inputting the hardware failure state data information into a fault maintenance measure analysis model, obtaining a hardware maintenance measure scheme;

[0014] Generating a computer hardware failure early warning report according to the hardware failure state data information and the hardware maintenance measure scheme, and performing running failure early warning on the target computer hardware based on the computer hardware failure early warning report.

[0015] A computer readable storage medium, having stored thereon a computer program, the computer program being executed by a processor to implement the following steps:

[0016] Real-time monitoring of target computer hardware by a sensor group obtains multi-dimensional running state data information;

[0017] Attribute labeling of the multi-dimensional running state data information obtains running data attribute information;

[0018] Classification and integration of the multi-dimensional running state data information according to the running data attribute information obtains standard multi-dimensional running state data information;

[0019] Running effect evaluation of the standard multi-dimensional running state data information obtains hardware running effect information;

[0020] When the hardware running effect information is lower than a preset hardware effect threshold, labeling of unqualified dimension data obtains hardware fault state data information;

[0021] Inputting the hardware fault state data information into a fault maintenance measure analysis model obtains a hardware maintenance measure scheme;

[0022] Generating a computer hardware fault warning report according to the hardware fault state data information and the hardware maintenance measure scheme, and performing running fault warning on the target computer hardware based on the computer hardware fault warning report.

[0023] The above computer hardware fault warning method and system based on multi-dimensional data solve the technical problem of low efficiency of manual fault diagnosis in the prior art, cannot timely warn of hardware faults, and affects stable operation of the computer, achieve the technical effects of collecting computer hardware running data in multiple dimensions in real time, comprehensively analyzing hardware running effect, improving hardware fault diagnosis efficiency and diagnosis accuracy, realizing timeliness of hardware fault warning, and further ensuring stable operation of the computer.

[0024] The above description is only a summary of the technical solutions of the present application, in order to more clearly understand the technical means of the present application, the specific embodiments of the present application can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 is a flowchart of a computer hardware fault warning method based on multi-dimensional data in one embodiment;

[0026] Figure 2A flowchart for obtaining multi-dimensional running state data information in a computer hardware fault early warning method based on multi-dimensional data in an embodiment;

[0027] Figure 3 A structural block diagram of a computer hardware fault early warning system based on multi-dimensional data in an embodiment;

[0028] Figure 4 An internal structure diagram of a computer device in an embodiment;

[0029] Legend: data real-time monitoring module 11, data attribute marking module 12, data classification integration module 13, running effect evaluation module 14, data marking module 15, fault maintenance measure analysis module 16, and running fault early warning module 17. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0031] As shown in Figure 1 , the present application provides a computer hardware fault early warning method based on multi-dimensional data, which comprises:

[0032] Step S100: Real-time monitoring of target computer hardware by a sensor group to obtain multi-dimensional running state data information;

[0033] In an embodiment, as shown in Figure 2 , the multi-dimensional running state data information is obtained, and the step S100 of the present application further comprises:

[0034] Step S110: The sensor group comprises a temperature and humidity sensor, a vibration sensor, and a voltage and current sensor;

[0035] Step S120: Obtaining running environment temperature and humidity information and running voltage and current information of the target computer hardware by the temperature and humidity sensor and the voltage and current sensor, respectively;

[0036] Step S130: Obtaining sound vibration waveform information of the target computer hardware based on the vibration sensor;

[0037] Step S140: Performing waveform signal analysis on the sound vibration waveform information to obtain sound vibration feature information;

[0038] Step S150: Obtaining the multi-dimensional running state data information based on the running environment temperature and humidity information, the running voltage and current information, and the sound vibration feature information.

[0039] Specifically, hardware refers to a variety of physical devices composed of electronic, mechanical and optoelectronic elements in a computer system, which form an organic whole as required by the system structure to provide a material basis for computer software running. The function of hardware is to input and store programs and data, and to execute programs to process data into a form that can be utilized, mainly including CPU, memory, motherboard, hard drive, optical drive, various expansion cards, connection lines, power supply, etc. Therefore, timely early warning before computer hardware failure has important practical significance for stable operation of computers and reduction of losses.

[0040] To realize intelligent fault warning of computer hardware, the target computer hardware is first monitored in real time by a sensor group, which mainly includes temperature and humidity sensors, vibration sensors, voltage and current sensors, etc. The sensor group can be installed at each operating part of the computer hardware for real-time monitoring of operating data. The temperature and humidity information and operating voltage and current information of the target computer hardware are obtained by the temperature and humidity sensors and the voltage and current sensors, respectively. For example, the load current and voltage of the system board card, CPU, display, hard disk, host and other circuits are monitored and collected to prevent hardware circuit short circuit or excessive operating temperature.

[0041] The vibration sensor is then used to obtain the sound vibration waveform information of the target computer hardware, i.e. to listen to whether the working sound of the hardware devices such as power fan, hard / soft disk motor or seek mechanism, display transformer is normal. Abnormal sound often accompanies short circuit failure of the system, and listening can timely find hardware failure hidden danger. Waveform signal analysis is performed on the sound vibration waveform information, including extraction and analysis of parameters such as period, amplitude, frequency, sound intensity, etc. to obtain sound vibration characteristic information, which is used to indicate whether the hardware operating sound is normal. Based on the operating environment temperature and humidity information, the operating voltage and current information and the sound vibration characteristic information, multi-dimensional operating state data information is determined, which is used to fully and multi-dimensionally reflect the operating state of the computer hardware. Through multi-dimensional real-time collection of computer hardware operating data by the sensor group, the data collection comprehensiveness is improved, and the accuracy of hardware operating effect analysis is further improved.

[0042] Step S200: Attribute labeling is performed on the multi-dimensional operating state data information to obtain operating data attribute information;

[0043] Step S300: The multi-dimensional operating state data information is classified and integrated according to the operating data attribute information to obtain standard multi-dimensional operating state data information;

[0044] Specifically, the multi-dimensional running state data information is marked with attributes, that is, the state collection data is classified according to attribute categories to obtain running data attribute information, and the running data attribute information includes temperature and humidity running data attributes, vibration running data attributes, and voltage and current running data attributes. Then, the multi-dimensional running state data information is classified and integrated according to the running data attribute information to obtain standard multi-dimensional running state data information after attribute classification processing, so as to improve the data processing efficiency.

[0045] Step S400: performing running effect evaluation on the standard multi-dimensional running state data information to obtain hardware running effect information;

[0046] In one embodiment, the hardware running effect information is obtained, and the step S400 of the application further includes:

[0047] Step S410: performing running effect evaluation on the standard multi-dimensional running state data information to obtain a hardware running score matrix;

[0048] In one embodiment, the hardware running score matrix is obtained, and the step S410 of the application further includes:

[0049] Step S411: constructing a hardware running evaluation model, and the hardware running evaluation model includes a temperature and humidity running evaluation model, a vibration running evaluation model, and a voltage and current running evaluation model;

[0050] Step S412: inputting the standard multi-dimensional running state data information into the temperature and humidity running evaluation model, the vibration running evaluation model, and the voltage and current running evaluation model respectively, and sequentially outputting temperature and humidity running evaluation information, vibration running evaluation information, and voltage and current running information;

[0051] Step S413: obtaining the hardware running score matrix based on the temperature and humidity running evaluation information, the vibration running evaluation information, and the voltage and current running information.

[0052] In one embodiment, the vibration running evaluation information is obtained, and the step S412 of the application further includes:

[0053] Step S4121: the vibration running evaluation model includes an input layer, a waveform analysis layer, a vibration score layer, and an output layer;

[0054] Step S4122: inputting the standard multi-dimensional running state data information into the waveform matching layer through the input layer to perform waveform matching and obtain fault waveform matching information;

[0055] Step S4123: obtaining vibration running evaluation information based on evaluation of the fault waveform matching information in the vibration score layer;

[0056] Step S4124: model outputting the vibration operation evaluation information based on the output layer.

[0057] Specifically, the hardware operation effect evaluation is performed on the standard multi-dimensional operation state data information. First, the hardware operation state data is scored. Specifically, a hardware operation evaluation model is constructed. The hardware operation evaluation model is a three-dimensional neural network model, which can be obtained by training historical data and includes a temperature and humidity operation evaluation model, a vibration operation evaluation model, and a voltage and current operation evaluation model. The standard multi-dimensional operation state data information is input into the temperature and humidity operation evaluation model, the vibration operation evaluation model, and the voltage and current operation evaluation model, i.e., the multi-dimensional operation state data information is input into the corresponding attribute model for analysis and evaluation. The temperature and humidity operation evaluation information, the vibration operation evaluation information, and the voltage and current operation information are sequentially output to indicate whether the hardware temperature and humidity operation environment, the hardware vibration operation, and the hardware voltage and current operation conform to the safety standards and the operation fault degree.

[0058] In this embodiment, the functional layer of the vibration operation evaluation model includes an input layer, a waveform analysis layer, a vibration scoring layer, and an output layer. The standard multi-dimensional operation state data information is input into the waveform matching layer through the input layer for waveform matching. The waveform matching layer stores a hardware abnormal operation waveform database obtained by big data, and further obtains fault waveform matching information. The vibration scoring layer is used to evaluate the fault waveform matching information according to the fault waveform type and the severity level, to obtain vibration operation evaluation information. The greater the fault degree, the lower the operation evaluation. If there is no abnormal operation waveform matching, the hardware is in a safe operation state. The scoring information is a standard score, which can be set by the user, for example, 90 points for safe operation. The output layer is used to model output the vibration operation evaluation information. Based on the temperature and humidity operation evaluation information, the vibration operation evaluation information, and the voltage and current operation information, a hardware operation scoring matrix composed of each scoring information is obtained to improve the scoring rationality and the scoring efficiency.

[0059] Step S420: constructing a hardware operation effect mesh graph according to the operation data attribute information.

[0060] Step S430: projecting the element values in the hardware operation scoring matrix into the hardware operation effect mesh graph to obtain a hardware effect scoring mesh graph.

[0061] Step S440: obtaining the hardware operation effect information based on the hardware effect scoring mesh graph.

[0062] In one embodiment, the step S440 of the present application further includes:

[0063] Step S441: obtaining computer hardware evaluation attribute information;

[0064] Step S442: performing principal component analysis on the computer hardware evaluation attribute information to obtain dimension-reduced hardware evaluation attribute information;

[0065] Step S443: performing factor analysis on the dimension-reduced hardware evaluation attribute information to obtain an evaluation effect key degree coefficient;

[0066] Step S444: correcting the hardware running effect information based on the evaluation effect key degree coefficient.

[0067] Specifically, according to the running data attribute information, i.e., the temperature and humidity running data attribute, the vibration running data attribute, and the voltage and current running data attribute, a hardware running effect network diagram is constructed by taking these as network diagram indexes, each index corresponding to a network line segment group of the network diagram, for visualizing the hardware running effect score. The element values in the hardware running score matrix are projected into the hardware running effect network diagram according to the network diagram index attribute, and an evaluation score-mapped hardware effect score network diagram is obtained. The area enclosed by the hardware effect score network diagram is taken as the hardware running effect information, and the greater the hardware running effect information, the greater the area enclosed by the network diagram evaluation score, and the better the hardware running effect.

[0068] To improve the accuracy of hardware running effect evaluation, computer hardware evaluation attribute information is obtained, which is a plurality of variables related to hardware running effect proposed for comprehensive analysis of hardware running effect, such as board circuit, display running temperature, etc., each of which reflects the hardware running effect to varying degrees. Principal component analysis is performed on the computer hardware evaluation attribute information, i.e., dimension reduction processing of evaluation attributes, to explicitly display important attribute features in the data, thereby obtaining attribute information with strong relevance to hardware running effect, i.e., dimension-reduced hardware evaluation attribute information.

[0069] Factor analysis is further performed on the dimension-reduced hardware evaluation attribute information, i.e., extracting common features in each attribute information, thereby grouping attribute information of the same nature into one attribute information, and the weight of attribute information with more common factors is larger, and the weight of attribute information with fewer common factors is smaller, thereby obtaining an evaluation effect key degree coefficient, i.e., the weight distribution result of running data attribute information. Based on the evaluation effect key degree coefficient, the hardware running effect score is weighted calculated, and the hardware running effect information is corrected according to the calculation result. By using principal component analysis to reduce the dimension of computer hardware evaluation attribute information, the system calculation complexity is reduced, and the weight distribution of running data attribute information is further performed, thereby improving the accuracy and reliability of the hardware running effect information.

[0070] Step S500: When the hardware running effect information is lower than the preset hardware effect threshold, mark the unqualified dimension data to obtain hardware failure state data information;

[0071] Step S600: Input the hardware failure state data information into a failure maintenance measure analysis model to obtain a hardware maintenance measure scheme;

[0072] Specifically, the preset hardware effect threshold is a standard score threshold for safe running of computer hardware. When the hardware running effect information is lower than the preset hardware effect threshold, it indicates that the hardware running effect score is lower than the safe running standard, and the hardware running has failed. Therefore, the unqualified dimension data is marked to obtain hardware failure state data information that does not meet the safe standard. The hardware failure state data information is input into the failure maintenance measure analysis model for analysis. The failure maintenance measure analysis model can be obtained by training historical data and is used to analyze and match hardware failure maintenance schemes. For example, when a board card is damaged, the damaged parts are replaced to eliminate the failure.

[0073] Step S700: Generate a computer hardware failure warning report according to the hardware failure state data information and the hardware maintenance measure scheme, and perform running failure warning on the target computer hardware based on the computer hardware failure warning report.

[0074] Specifically, a computer hardware failure warning report is generated according to the hardware failure state data information and the hardware maintenance measure scheme, and running failure warning is performed on the target computer hardware based on the computer hardware failure warning report, which is displayed to the maintenance personnel. This achieves the technical effects of improving hardware failure diagnosis efficiency and accuracy, and realizing timeliness of hardware failure warning.

[0075] In one embodiment, the step of the application further includes:

[0076] Step S810: Obtain the service life information of the target computer hardware;

[0077] Step S820: Perform aging degree analysis on the service life information to obtain a running aging influence factor;

[0078] Step S830: Perform loss analysis on the hardware use quality based on the running aging influence factor to obtain a running effect influence coefficient;

[0079] Step S840: Adjust and correct the hardware running effect information according to the running effect influence coefficient.

[0080] Specifically, to improve the accuracy of hardware operation effect evaluation, the service life information of the target computer hardware is obtained. The service life information is analyzed for aging degree, the longer the service life, the higher the hardware aging degree, and the corresponding operation aging influence factor is obtained, the higher the aging influence factor, the longer the service life. Hardware aging will affect the quality of hardware use, based on the operation aging influence factor, the loss of hardware use quality is analyzed, the operation effect influence coefficient is obtained, the operation aging influence factor and the operation effect influence coefficient are positively correlated, the greater the aging influence, the greater the loss of hardware operation effect caused by the quality of use. According to the operation effect influence coefficient, the hardware operation effect information is adjusted and corrected, the quality loss caused by hardware aging is analyzed to improve the analysis accuracy and practicality of hardware operation effect information, and then the timeliness of hardware fault warning is realized.

[0081] In one embodiment, as shown in Figure 3 A computer hardware fault warning system based on multi-dimensional data is provided, comprising: a data real-time monitoring module 11, a data attribute marking module 12, a data classification integration module 13, an operation effect evaluation module 14, a data marking module 15, a fault maintenance measure analysis module 16, and an operation fault warning module 17, wherein:

[0082] The data real-time monitoring module 11 is used for real-time monitoring of the target computer hardware by a sensor group to obtain multi-dimensional operation state data information;

[0083] The data attribute marking module 12 is used for attribute marking of the multi-dimensional operation state data information to obtain operation data attribute information;

[0084] The data classification integration module 13 is used for classifying and integrating the multi-dimensional operation state data information according to the operation data attribute information to obtain standard multi-dimensional operation state data information;

[0085] The operation effect evaluation module 14 is used for operation effect evaluation of the standard multi-dimensional operation state data information to obtain hardware operation effect information;

[0086] The data marking module 15 is used for marking unqualified dimension data when the hardware operation effect information is lower than a preset hardware effect threshold to obtain hardware fault state data information;

[0087] The fault maintenance measure analysis module 16 is used for inputting the hardware fault state data information into a fault maintenance measure analysis model to obtain a hardware maintenance measure scheme;

[0088] The operation fault early warning module 17 is configured to generate a computer hardware fault early warning report according to the hardware fault state data information and the hardware maintenance measure scheme, and perform operation fault early warning on the target computer hardware based on the computer hardware fault early warning report.

[0089] In one embodiment, the data real-time monitoring module further comprises:

[0090] The sensor group constitutes a unit for the sensor group comprising a temperature and humidity sensor, a vibration sensor, and a voltage and current sensor.

[0091] The hardware operation information obtaining unit is configured to obtain operation environment temperature and humidity information and operation voltage and current information of the target computer hardware through the temperature and humidity sensor and the voltage and current sensor, respectively.

[0092] The sound vibration waveform information obtaining unit is configured to obtain sound vibration waveform information of the target computer hardware based on the vibration sensor.

[0093] The waveform signal analysis unit is configured to perform waveform signal analysis on the sound vibration waveform information to obtain sound vibration feature information.

[0094] The multi-dimensional operation state data obtaining unit is configured to obtain the multi-dimensional operation state data information based on the operation environment temperature and humidity information, the operation voltage and current information, and the sound vibration feature information.

[0095] In one embodiment, the operation effect evaluation module further comprises:

[0096] The scoring matrix obtaining unit is configured to perform operation effect evaluation on the standard multi-dimensional operation state data information to obtain a hardware operation scoring matrix.

[0097] The operation effect net chart constructing unit is configured to construct a hardware operation effect net chart according to the operation data attribute information.

[0098] The hardware effect scoring net chart obtaining unit is configured to project element values in the hardware operation scoring matrix into the hardware operation effect net chart to obtain a hardware effect scoring net chart.

[0099] The hardware operation effect information obtaining unit is configured to obtain the hardware operation effect information based on the hardware effect scoring net chart.

[0100] In one embodiment, the scoring matrix obtaining unit further comprises:

[0101] The hardware operation evaluation model constitutes a unit for constructing a hardware operation evaluation model, which includes a temperature and humidity operation evaluation model, a vibration operation evaluation model, and a voltage and current operation evaluation model.

[0102] The model evaluation output unit inputs the standard multi-dimensional operation state data information into the temperature and humidity operation evaluation model, the vibration operation evaluation model, and the voltage and current operation evaluation model, and sequentially outputs the temperature and humidity operation evaluation information, the vibration operation evaluation information, and the voltage and current operation information.

[0103] The hardware operation score matrix obtaining unit obtains the hardware operation score matrix based on the temperature and humidity operation evaluation information, the vibration operation evaluation information, and the voltage and current operation information.

[0104] In one embodiment, the model evaluation output unit further includes:

[0105] The vibration operation evaluation model constitutes a unit for the vibration operation evaluation model to include an input layer, a waveform analysis layer, a vibration score layer, and an output layer.

[0106] The waveform matching unit inputs the standard multi-dimensional operation state data information through the input layer into the waveform matching layer for waveform matching to obtain fault waveform matching information.

[0107] The vibration evaluation unit evaluates the fault waveform matching information based on the vibration score layer to obtain vibration operation evaluation information.

[0108] The model output unit outputs the vibration operation evaluation information based on the output layer.

[0109] In one embodiment, the system further includes:

[0110] The evaluation attribute obtaining unit obtains computer hardware evaluation attribute information.

[0111] The main feature analysis unit performs main feature analysis on the computer hardware evaluation attribute information to obtain reduced-dimension hardware evaluation attribute information.

[0112] The factor analysis unit performs factor analysis on the hardware reduced-dimension evaluation attribute information to obtain an evaluation effect key degree coefficient.

[0113] The operation effect information correction unit corrects the hardware operation effect information based on the evaluation effect key degree coefficient.

[0114] In one embodiment, the system further includes:

[0115] a use life information obtaining unit, configured to obtain use life information of the target computer hardware;

[0116] an aging degree analysis unit, configured to perform aging degree analysis on the use life information to obtain a running aging impact factor;

[0117] a quality loss analysis unit, configured to perform loss analysis on hardware use quality based on the running aging impact factor to obtain a running effect impact coefficient;

[0118] a running effect adjustment correction unit, configured to adjust and correct the hardware running effect information according to the running effect impact coefficient.

[0119] For a specific embodiment of the computer hardware fault early warning system based on multi-dimensional data, refer to the embodiment of the computer hardware fault early warning method based on multi-dimensional data described above, which will not be repeated here. Each module in the computer hardware fault early warning device based on multi-dimensional data described above can be realized by software, hardware and their combination, in whole or in part. Each module described above can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operation corresponding to each module.

[0120] In one embodiment, a computer device, which can be a server, is provided, and an internal structure diagram of the computer device can be as shown in Figure 4 The computer device includes a processor, a memory and a network interface connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store news data and time decay factors and other data. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a computer hardware fault early warning method based on multi-dimensional data.

[0121] Those skilled in the art can understand that Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0122] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program: obtaining multi-dimensional running state data information of a target computer hardware by real-time monitoring of the target computer hardware through a sensor group; obtaining running data attribute information by attribute marking of the multi-dimensional running state data information; obtaining standard multi-dimensional running state data information by classified integration of the multi-dimensional running state data information according to the running data attribute information; obtaining hardware running effect information by running effect evaluation of the standard multi-dimensional running state data information; obtaining hardware fault state data information by marking unqualified dimension data when the hardware running effect information is lower than a preset hardware effect threshold; obtaining a hardware maintenance measure scheme by inputting the hardware fault state data information into a fault maintenance measure analysis model; generating a computer hardware fault early warning report according to the hardware fault state data information and the hardware maintenance measure scheme, and performing running fault early warning on the target computer hardware based on the computer hardware fault early warning report.

[0123] In one embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program is executed by a processor to implement the following steps: obtaining multi-dimensional running state data information of a target computer hardware by real-time monitoring of the target computer hardware through a sensor group; obtaining running data attribute information by attribute marking of the multi-dimensional running state data information; obtaining standard multi-dimensional running state data information by classified integration of the multi-dimensional running state data information according to the running data attribute information; obtaining hardware running effect information by running effect evaluation of the standard multi-dimensional running state data information; obtaining hardware fault state data information by marking unqualified dimension data when the hardware running effect information is lower than a preset hardware effect threshold; obtaining a hardware maintenance measure scheme by inputting the hardware fault state data information into a fault maintenance measure analysis model; generating a computer hardware fault early warning report according to the hardware fault state data information and the hardware maintenance measure scheme, and performing running fault early warning on the target computer hardware based on the computer hardware fault early warning report. Each technical feature of the above embodiments can be combined arbitrarily, and to make the description concise, each technical feature in the above embodiments is not described in all possible combinations, however, as long as the combination of these technical features does not exist contradictory, it should be considered as the scope of the present disclosure.

[0124] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific and detailed manner, but should not be construed as limiting the scope of the patent. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A computer hardware failure early warning method based on multidimensional data, characterized in that: The method comprises: Real-time monitoring of target computer hardware is performed through a sensor group to obtain multi-dimensional operating status data information; Performing attribute marking on the multi-dimensional operation status data information to obtain operation data attribute information; Classifying and integrating the multidimensional operation status data information according to the operation data attribute information to obtain standard multidimensional operation status data information; Performing an operation effect evaluation on the standard multi-dimensional operation status data information to obtain hardware operation effect information; When the hardware operation effect information is lower than the preset hardware effect threshold, the unqualified dimension data is marked to obtain hardware failure status data information; Inputting the hardware fault status data information into a fault maintenance measure analysis model to obtain a hardware maintenance measure plan; Generate a computer hardware failure warning report based on the hardware failure status data information and the hardware maintenance measure plan, and perform an operation failure warning on the target computer hardware based on the computer hardware failure warning report; The obtaining of hardware operation effect information includes: Evaluate the operation effect of the standard multi-dimensional operation status data information to obtain a hardware operation score matrix; Constructing a hardware operation effect network diagram based on the operation data attribute information; Projecting the element values ​​in the hardware operation score matrix onto the hardware operation effect network graph to obtain a hardware effect score network graph; Based on the hardware effect scoring network diagram, obtaining the hardware operation effect information; The obtaining of the hardware operation score matrix includes: Constructing a hardware operation evaluation model, wherein the hardware operation evaluation model includes a temperature and humidity operation evaluation model, a vibration operation evaluation model, and a voltage and current operation evaluation model; Input the standard multi-dimensional operation status data information into the temperature and humidity operation evaluation model, the vibration operation evaluation model, and the voltage and current operation evaluation model respectively, and output the temperature and humidity operation evaluation information, the vibration operation evaluation information, and the voltage and current operation information in sequence; Obtaining the hardware operation scoring matrix based on the temperature and humidity operation evaluation information, the vibration operation evaluation information, and the voltage and current operation information; Obtain computer hardware evaluation attribute information; Performing main feature analysis on the computer hardware evaluation attribute information to obtain dimension-reduced hardware evaluation attribute information; Performing factor analysis on the dimension-reduced hardware evaluation attribute information to obtain an evaluation effect criticality coefficient; Based on the evaluation effect criticality coefficient, modifying the hardware operation effect information; Obtaining service life information of the target computer hardware; Performing an aging analysis on the service life information to obtain an operational aging impact factor; Performing a loss analysis on the hardware usage quality based on the operation aging impact factor to obtain an operation effect impact coefficient; Adjust and correct the hardware operation effect information according to the operation effect impact coefficient; The obtaining of multi-dimensional operation status data information includes: The sensor group includes a temperature and humidity sensor, a vibration sensor, and a voltage and current sensor; Obtaining the operating environment temperature and humidity information and operating voltage and current information of the target computer hardware respectively through the temperature and humidity sensor and the voltage and current sensor; Acquiring sound vibration waveform information of the target computer hardware based on the vibration sensor; Performing waveform signal analysis on the sound vibration waveform information to obtain sound vibration characteristic information; Obtaining the multi-dimensional operating status data information based on the operating environment temperature and humidity information, the operating voltage and current information, and the sound and vibration characteristic information; Obtaining the vibration operation evaluation information includes: The vibration operation evaluation model includes an input layer, a waveform analysis layer, a vibration scoring layer, and an output layer; Inputting the standard multi-dimensional operating status data information into the waveform analysis layer through the input layer to perform waveform matching to obtain fault waveform matching information; Evaluate the fault waveform matching information based on the vibration scoring layer to obtain vibration operation evaluation information; The vibration operation evaluation information is modeled and outputted based on the output layer.

2. A computer hardware failure early warning system based on multidimensional data, characterized in that: The system is used to perform the method according to claim 1, and the system includes: The data real-time monitoring module is used to monitor the target computer hardware in real time through the sensor group to obtain multi-dimensional operating status data information; A data attribute marking module is used to perform attribute marking on the multi-dimensional operation status data information to obtain operation data attribute information; a data classification and integration module, configured to classify and integrate the multi-dimensional operation status data information according to the operation data attribute information to obtain standard multi-dimensional operation status data information; An operation effect evaluation module is used to evaluate the operation effect of the standard multi-dimensional operation status data information to obtain hardware operation effect information; A data marking module is used to mark unqualified dimension data when the hardware operation effect information is lower than a preset hardware effect threshold, and obtain hardware failure status data information; A fault maintenance measure analysis module is used to input the hardware fault status data information into a fault maintenance measure analysis model to obtain a hardware maintenance measure plan; The operation fault warning module is used to generate a computer hardware fault warning report according to the hardware fault status data information and the hardware maintenance measure plan, and to perform an operation fault warning on the target computer hardware based on the computer hardware fault warning report.

3. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to claim 1 are implemented.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

Images