Mainboard abnormality identification method, device, equipment and storage medium

Abstract

The present invention relates to the field of computer technology, and provides a method, device, equipment and storage medium for identifying motherboard anomalies, including obtaining detection information on the motherboard, the detection information including multiple data points; substituting the multiple data points into an algorithm model, the algorithm model dividing the detection information into normal component data and abnormal component data according to the parameter information of the multiple data points; encrypting the normal component data; parsing the fault level of the corresponding abnormal component data according to a preset light signal coding rule, outputting a corresponding light signal, and inputting the corresponding light signal into a fault indicator light; parsing the parameters of the corresponding abnormal component data according to a preset data string signal coding rule, outputting a data string signal, and sending it to a digital display screen. Through the above method, the problem that the degree of damage of the abnormal component on the motherboard cannot be confirmed in the first time, and the data read from the motherboard is too much, and the detection efficiency is low when displayed on the digital display screen is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for identifying anomalies in a mainboard. Background Art

[0002] The motherboard is the core component of the computer. It connects various components of the computer, such as the CPU, memory, hard disk, sound card, network card, etc., and is responsible for coordinating and controlling the work of these components. The performance and stability of the motherboard directly affect the operating efficiency and reliability of the computer. Therefore, fault detection and identification of the motherboard is an important step in maintaining and repairing the computer.

[0003] Among the relevant technical means, the problem is determined by observing the fault indicator light or digital display on the motherboard according to the displayed code. Secondly, check whether the power supply is normal and check whether the memory, CPU, graphics card and other hardware are firmly installed, whether there is dust or oxidation, and whether they are compatible with the motherboard. If there is a problem with any hardware, the motherboard may not work properly, and the hardware needs to be cleaned or replaced to realize the function detection of the motherboard module.

[0004] With regard to the above technical solution, although the positional relationship of the abnormal component on the main board can be roughly confirmed by the fault indicator light, and the code displayed on the digital display screen can be used to analyze which component has failed, thereby realizing the detection of the functions on the main board module, there is a problem that it is impossible to confirm the extent of damage to the abnormal component on the main board in the first time, and too much data is read from the main board. When displayed on the digital display screen, it is necessary to manually identify the normal component data and the abnormal component data on the digital display screen, which leads to the problem of low detection efficiency. Summary of the invention

[0005] In order to improve the problem that the degree of damage of abnormal components on the mainboard cannot be confirmed immediately, and too much data is read from the mainboard, and when displayed on the digital display screen, it is necessary to manually identify the normal component data and the abnormal component data on the digital display screen, which leads to low detection efficiency, the present application provides a mainboard abnormality identification method, device, equipment and storage medium.

[0006] The present invention provides a method for identifying mainboard abnormalities, comprising: obtaining detection information on the mainboard; wherein the detection information includes multiple data points; substituting the multiple data points into an algorithm model, wherein the algorithm model divides the detection information into normal component data and abnormal component data according to parameter information of the multiple data points; encrypting the normal component data so that the normal component data cannot be read by a preset fault indicator light and a digital display screen; parsing the fault level of the corresponding abnormal component data according to a preset light signal coding rule, outputting a corresponding light signal, and inputting the corresponding light signal into the fault indicator light; parsing the parameters of the corresponding abnormal component data according to a preset data string signal coding rule, outputting a corresponding data string signal, and sending the corresponding data string signal to the digital display screen.

[0007] As a preferred embodiment, the step of obtaining the detection information on the main board includes: obtaining the detection information on the main board through a fault detection unit preset on the main board, the fault detection unit detecting each component on the main board through circuit signals or software programs, and obtaining the detection information based on the detection results of each component on the main board.

[0008] As a preferred solution, the algorithm model divides the detection information into normal component data and abnormal component data according to the parameter information of the multiple data points, including: performing anomaly detection on the multiple data points using a preset anomaly detection algorithm, wherein the anomaly detection algorithm calculates anomaly scores of the multiple data points according to the parameter information of the multiple data points, wherein the anomaly scores reflect the degree of abnormality of the data points; judging the anomaly scores according to a preset anomaly threshold, classifying the data points whose anomaly scores are greater than or equal to the anomaly threshold as abnormal component data, and classifying the data points whose anomaly scores are less than the anomaly threshold as normal component data.

[0009] As a preferred solution, the step of encrypting the normal component data includes: encrypting the normal component data using a preset encryption algorithm so that the normal component data cannot be recognized by the fault indicator light and the digital display screen; wherein the key of the encryption algorithm is stored in the fault detection unit.

[0010] As a preferred scheme, the steps of parsing the fault level of the corresponding abnormal component data according to a preset light signal coding rule, outputting a corresponding light signal, and inputting the corresponding light signal into the fault indicator light include: mapping the fault level of the abnormal component data into a corresponding light signal according to a mapping rule between the fault level and the light signal in the preset light signal coding rule; wherein the light signal includes a red light signal, a yellow light signal and a green light signal; inputting the light signal corresponding to the fault level of the abnormal component data into the fault indicator light; wherein a plurality of the fault indicator lights are preset on the main board, each of the fault indicator lights corresponds to a component of the main board, the fault level includes a serious fault, a general fault and a minor fault, the red light signal indicates the serious fault, the yellow light signal indicates the general fault, and the green light signal indicates the minor fault.

[0011] As a preferred solution, the step of parsing the parameters of the corresponding abnormal component data according to the preset data string signal encoding rule, outputting the corresponding data string signal, and sending the corresponding data string signal to the digital display screen includes: obtaining the preset encoding rule stored in the database, and extracting the encoding parameters in the encoding rule; inputting the fault type of the abnormal component data into a preset analysis table to obtain the initial component name corresponding to the fault type; wherein the analysis table includes a mapping relationship between the fault type and the abnormal component name causing the fault type; calculating the component name and the component name that is the same as the initial component name as the target component name; forming a vector of the component numbers corresponding to the target component names, inputting it into the correction detection model, and detecting and obtaining the corresponding correction value; wherein the correction value includes the encoding parameter that needs to be corrected in the encoding rule and its corresponding correction value; correcting the corresponding encoding parameter in the encoding rule based on the correction value to obtain the correction encoding rule; encoding the parameters of the abnormal component data into the corresponding data string signal based on the correction encoding rule, and sending the corresponding data string signal to the digital display screen.

[0012] As a preferred solution, the fault indicator light is an LED light; and the digital display screen is a liquid crystal display screen.

[0013] The present application also provides a mainboard abnormality identification device, including: a detection module, used to obtain detection information on the mainboard; wherein the detection information includes multiple data points; a calculation module, used to substitute the multiple data points into an algorithm model, and the algorithm model divides the detection information into normal component data and abnormal component data according to the distance between the multiple data points; an encryption module, used to encrypt the normal component data so that the normal component data cannot be read by a preset fault indicator light and a digital display screen; a light analysis module, used to analyze the fault level of the corresponding abnormal component data according to a preset light signal coding rule, output a corresponding light signal, and input the corresponding light signal to the fault indicator light; a display analysis module, used to analyze the parameters of the corresponding abnormal component data according to a preset data string signal coding rule, output a corresponding data string signal, and send the corresponding data string signal to the digital display screen.

[0014] The present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the mainboard abnormality identification method described in any one of the above items is implemented.

[0015] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes any of the above-described methods for identifying a mainboard abnormality.

[0016] Compared with the prior art, the present application has the following beneficial effects: fast detection efficiency and abnormal damage analysis. By encrypting the normal component data, the normal component data cannot be read by the preset fault indicator light and digital display screen, so that the fault indicator light of the normal component does not light up, thereby reducing the difficulty of identifying the abnormal component on the mainboard, and the relevant information of the normal component is not displayed on the digital display screen, thereby reducing the problem of needing to identify the normal component data and the abnormal component data on the digital display screen, and increasing the efficiency of mainboard abnormal identification; at the same time, according to the preset light signal coding rule, the fault level of the corresponding abnormal component data is parsed, the corresponding light signal is output, and the corresponding light signal is input to the fault indicator light, so as to realize the intuitive display of the damage degree of the abnormal component on the mainboard; finally, according to the preset data string signal coding rule, the parameters of the corresponding abnormal component data are parsed, the corresponding data string signal is output, and the corresponding data string signal is sent to the digital display screen, so as to improve the problem that the damage degree of the abnormal component on the mainboard cannot be confirmed in the first time, and the data of the mainboard read is too much, and when it is displayed on the digital display screen, it is necessary to manually identify the normal component data and the abnormal component data on the digital display screen, thereby causing the problem of low detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] The structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantive technical significance. Any structural modification, change in proportion or adjustment of size, without affecting the effects and purposes that can be achieved by the present invention, should still fall within the scope of the technical contents disclosed by the present invention.

[0019] Figure 1 It is a flow chart of a method for identifying a mainboard abnormality provided by an embodiment of the present invention;

[0020] Figure 2 is a schematic block diagram of the structure of a mainboard abnormality identification device provided by an embodiment of the present invention;

[0021] Figure 3 It is a schematic block diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0022] Description of reference numerals:

[0023] 10. Mainboard abnormality identification device; 11. Detection module; 12. Calculation module; 13. Encryption module; 14. Light analysis module; 15. Display analysis module; 20. Electronic device; 21. Memory; 22. Processor. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0026] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0027] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one of the associated listed items, and includes these combinations.

[0028] The technical solution of the present invention is further described below with reference to the accompanying drawings and through specific implementation methods.

[0029] Example 1

[0030] like Figure 1 As shown, the mainboard abnormality identification method provided in the embodiment of the present application includes steps S100 to S500.

[0031] Step S100: Acquire detection information on the mainboard; wherein the detection information includes a plurality of data points.

[0032] In this step, the detection information on the mainboard is obtained through the fault detection unit preset on the mainboard, which includes sensors (such as temperature sensors, voltage sensors, etc.), analog / digital converters (ADCs), microcontrollers (MCUs), and integrated circuits (ICs); the fault detection unit detects each component on the mainboard through circuit signals or software programs, and obtains detection information based on the detection results of each component on the mainboard. Among them, the detection information includes multiple data points, each data point represents the detection result of a component, including parameters such as component number, component name, component voltage, component temperature, component power, etc.

[0033] For example, Table 1 below:

[0034] Table 1

[0035]

[0036] The data point {0, CPU, 3.5 V, 75 ° C, 50 W} indicates that the voltage of CPU number 0 is 3.5 V, the temperature is 75 ° C, and the power is 50 W;

[0037] The data point {1, GPU, 3.3 V, 80 ° C, 60 W} indicates that the voltage of GPU number 1 is 3.3 V, the temperature is 80 ° C, and the power is 60 W;

[0038] The data point {2, RAM, 3.6 V, 40 ° C, 20 W} indicates that the voltage of RAM number 2 is 3.6 V, the temperature is 40 ° C, and the power is 20 W;

[0039] The data point {3, SSD, 3.4V, 50°C, 10W} indicates that the voltage of SSD numbered 3 is 3.4V, the temperature is 50°C, and the power is 10W.

[0040] Step S200: Substitute multiple data points into the algorithm model, and the algorithm model divides the detection information into normal component data and abnormal component data according to the parameter information of the multiple data points.

[0041] In this step, multiple data points are substituted into the algorithm model, and the algorithm model judges the status of each component on the motherboard based on the parameter information of the multiple data points, and divides the detection information into normal component data and abnormal component data. The algorithm model can be a model based on machine learning or deep learning, or a model based on rules or thresholds.

[0042] Step S300: encrypting the normal component data so that the normal component data cannot be read by the preset fault indicator light and digital display screen.

[0043] In this step, the normal component data is encrypted so that the normal component data cannot be read by the preset fault indicator light and the digital display screen, so that the normal component data is not displayed on the digital display screen. At this time, the digital display screen only displays the information of the abnormal component data, improving the problem of needing to identify the abnormal component data from the data on the digital display screen, thereby increasing the efficiency of mainboard abnormality identification. Among them, the encryption module can use any encryption algorithm, such as a symmetric encryption algorithm, an asymmetric encryption algorithm or a hash algorithm.

[0044] Step S400: parse the fault level of the corresponding abnormal component data according to the preset light signal coding rule, output the corresponding light signal, and input the corresponding light signal to the fault indicator light.

[0045] In this step, the fault level of the corresponding abnormal component data is parsed according to the preset light signal coding rule, the corresponding light signal is output, and the corresponding light signal is input to the fault indicator light. The fault indicator light can be a LED light of multiple colors, which is used to display the fault level of each component on the mainboard. Among them, the light signal coding rule can be any coding rule, such as binary coding, hexadecimal coding or ASCII coding.

[0046] Step S500: parse the parameters of the corresponding abnormal component data according to the preset data string signal encoding rules, output the corresponding data string signal, and send the corresponding data string signal to the digital display screen.

[0047] In this step, the parameters of the corresponding abnormal component data are parsed according to the preset data string signal encoding rule, the corresponding data string signal is output, and the corresponding data string signal is sent to the digital display screen. The digital display screen can be a digital display for displaying the abnormal parameters of each component on the mainboard. Among them, the data string signal encoding rule can be any encoding rule, such as decimal encoding, hexadecimal encoding or ASCII encoding.

[0048] By detecting, analyzing, encrypting and decoding each component on the mainboard, the abnormal components on the mainboard can be quickly, accurately and safely identified; by encrypting the normal component data, the normal component data cannot be read by the preset fault indicator light and digital display screen, so that the fault indicator light of the normal component does not light up, thereby reducing the difficulty of identifying the abnormal component on the mainboard, and the relevant information of the normal component is not displayed on the digital display screen, thereby reducing the problem of needing to identify the normal component data and the abnormal component data on the digital display screen, and increasing the efficiency of mainboard abnormality identification; at the same time, the efficiency and safety of mainboard abnormality identification are improved; and the fault of the corresponding abnormal component data is coded according to the preset light signal coding rules. The level is analyzed, and a corresponding light signal is output, which is input into the fault indicator light, thereby realizing an intuitive display of the fault level of the abnormal component on the mainboard; finally, the parameters of the corresponding abnormal component data are analyzed according to the preset data string signal encoding rule, and the corresponding data string signal is output, and the corresponding data string signal is sent to the digital display screen, thereby realizing a detailed and clear display of the abnormal parameters of the abnormal component on the mainboard, thereby improving the problem that the degree of damage of the abnormal component on the mainboard cannot be confirmed in the first time, and the data read from the mainboard is too much. When displayed on the digital display screen, it is necessary to manually identify the normal component data and the abnormal component data on the digital display screen, which leads to low detection efficiency.

[0049] Example 2

[0050] In step S100, detection information on the mainboard is obtained through a fault detection unit preset on the mainboard. The fault detection unit detects various components on the mainboard through circuit signals or software programs, and obtains detection information based on the detection results of various components on the mainboard.

[0051] Among them, the fault detection unit includes multiple sensors and a controller. The sensors are respectively connected to various components on the mainboard and are used to detect parameters such as voltage, temperature, power, etc. of the components. The controller is used to receive the detection signals of the sensors and process the detection signals according to a preset algorithm to obtain detection information.

[0052] In step S200, anomaly detection is performed on the multiple data points using a preset anomaly detection algorithm. The anomaly detection algorithm calculates anomaly scores of the multiple data points based on parameter information of the multiple data points, and the anomaly scores reflect the degree of anomaly of the data points. The anomaly scores are judged according to a preset anomaly threshold, and data points whose anomaly scores are greater than or equal to the anomaly threshold are classified as abnormal component data, and data points whose anomaly scores are less than the anomaly threshold are classified as normal component data.

[0053] Among them, the anomaly detection algorithm is an anomaly detection algorithm based on machine learning, which uses a pre-trained model to extract and classify the parameter information of the multiple data points to obtain the anomaly scores of the multiple data points. The model can be any machine learning model, such as a support vector machine, a decision tree, a neural network, etc.; in this implementation, a neural network-based anomaly detection model is used to convert the data points in Table 1 into numerical form, that is, the data point {0, CPU, 3.5V, 75°C, 50W} is converted to [0, 3.5, 75, 50], and so on, all data points are converted; the data after the data point conversion is input into the neural network to obtain the data of the output layer, as shown in the following formula:

[0054]

[0055] in, = is the transformed data, y is the data of the output layer, and is the weight matrix, and is the bias vector, is the sigmoid function;

[0056] Assumptions For a 10×5 matrix: ;

[0057] For a 1×10 matrix: ;

[0058] is a 10×1 vector: ;

[0059] is a scalar: ;

[0060] For the sigmoid function: ;

[0061] Substitute the converted data into After calculation, we get Table 2.

[0062] Table 2

[0063]

[0064] The anomaly score in Table 2 is compared with the preset anomaly threshold. If the anomaly score is greater than or equal to the anomaly threshold, the data point is considered to be an abnormal component data, otherwise the data point is considered to be a normal component data.

[0065] Assuming that the preset anomaly thresholds of CPU, GPU, RAM, and SSD are all 4.5, the data points in Table 2 are divided into normal component data and abnormal component data. The anomaly scores of the data points {0, CPU, 3.5, 75, 50} and {1, GPU, 3.3, 80, 60} are both greater than or equal to the anomaly threshold of 4.5, so they are judged as abnormal component data; the anomaly scores of the data points {2, RAM, 3.6, 40, 20} and {3, SSD, 3.4, 50, 10} are both less than the anomaly threshold of 4.5, so they are judged as normal component data.

[0066] It should be noted that the preset abnormal threshold of each component is different. The specific abnormal threshold setting is based on the rated voltage and rated power set for the specific component model, as well as the component operating temperature range.

[0067] In step S300, the normal component data is encrypted using a preset encryption algorithm so that the normal component data cannot be recognized by the fault indicator light and the digital display screen; wherein the encryption algorithm key is stored in the fault detection unit.

[0068] Among them, the encryption algorithm is the AES algorithm, which is a symmetric encryption algorithm, that is, the same key is used for encryption and decryption. The key of the encryption algorithm is stored in the fault detection unit and can only be accessed by authorized users, so as to achieve the effect of not directly displaying the normal component information on the digital display screen. In this way, the number of parameters on the digital display screen can be reduced, which is convenient for quickly observing the data parameters of abnormal components, thereby increasing the efficiency of mainboard abnormality identification; at the same time, it can also protect the security of normal component data and avoid the risk of data leakage.

[0069] In step S400, according to the mapping rule between the fault level and the light signal in the preset light signal coding rule, the fault level of the abnormal component data is mapped to the corresponding light signal; wherein the light signal includes a red light signal, a yellow light signal and a green light signal; the light signal corresponding to the fault level of the abnormal component data is input into the fault indicator light; wherein, multiple fault indicator lights are preset on the main board, the number of fault indicator lights is consistent with the number of components on the main board, and each fault indicator light corresponds to a component of the main board; the fault level includes a serious fault, a general fault and a minor fault; a red light signal indicates a serious fault, a yellow light signal indicates a general fault, and a green light signal indicates a minor fault.

[0070] The light signal coding rule is formulated according to the fault level of the abnormal component data, and the fault level is determined according to the abnormal score. For example, an abnormal score of 4.5 to 6 is a minor fault, an abnormal score of 6 to 9 is a general fault, and an abnormal score of 9 or more is a serious fault. The fault indicator light is an LED light, and multiple fault indicator lights are preset on the motherboard. Each fault indicator light corresponds to a component of the motherboard. For example, LED light 1 corresponds to CPU, LED light 2 corresponds to GPU, LED light 3 corresponds to RAM, LED light 4 corresponds to SSD, etc. The corresponding fault level is displayed by the color of the light signal.

[0071] In step S500, it is necessary to first obtain the preset coding rules stored in the database and extract the coding parameters in the coding rules; input the fault type of the abnormal component data into the preset analysis table to obtain the initial component name corresponding to the fault type; wherein the analysis table includes a mapping relationship between the fault type and the abnormal component name causing the fault type, and calculate the component name and the component name that is the same as the initial component name as the target component name.

[0072] In this step, the fault type in the abnormal component data is input into the analysis table preset in the fault detection unit, and the initial component name corresponding to the faulty component is obtained through mapping through the analysis table. At this time, the initial component name obtained cannot be determined to be the abnormal component name that causes the fault type, and further calculation is required. The abnormal component name that causes the fault type and the initial component name are substituted into the calculation, and the component name that has the same abnormal component name as the initial component name is used as the target component name. For example: assuming that the fault type is CPU overheating, the analysis table shows that the abnormal component names that cause CPU overheating are CPU, fan, radiator, etc., and the initial component name is CPU. The CPU is compared with the fan and radiator, and it is found that the CPU has the same name as the initial component, so the CPU is the target component name.

[0073] The component numbers corresponding to the target component names are formed into a vector and input into the correction detection model to detect and obtain the corresponding correction values; wherein the correction values ​​include the coding parameters that need to be corrected in the coding rules and their corresponding correction values.

[0074] In this step, a vector consisting of the target component name and the component number corresponding to the target component name is input into the correction detection model to obtain the corresponding correction value. For example, if the target component name is CPU and the corresponding component number is 0, [0, CPU] is input into the correction detection model to obtain a correction value of [0.1, 0.2], indicating that the first and second encoding parameters in the encoding rule need to be corrected, and the correction values ​​are 0.1 and 0.2 respectively.

[0075] Based on the correction value, the corresponding coding parameter in the coding rule is corrected to obtain the corrected coding rule; based on the corrected coding rule, the parameter of the abnormal component data is encoded into a corresponding data string signal, and the corresponding data string signal is sent to the digital display screen.

[0076] In this step, the corresponding coding parameters in the coding rule are corrected by the correction value to obtain the corrected coding rule, and then the parameters of the abnormal component data are encoded into corresponding data string signals by the corrected coding rule, and the corresponding data string signals are sent to the digital display screen, wherein the digital display screen is a liquid crystal display screen, and the liquid crystal display screen decodes the data string signal to obtain and display the abnormal component data parameters. For example, assuming that the coding rule is to convert the component number, component name, component voltage, component temperature, and component power into hexadecimal numbers respectively and separate them with commas, such as the data point {0,CPU,3.5,75,50} is encoded as [0,43, 50,55,3.5,4B,32], and according to the correction value [0.1,0.2], the first and second encoding parameters in the encoding rule are corrected, that is, 0.1 and 0.2 are added to the part number and part name respectively to obtain the corrected encoding rule. For example, the data point of CPU is {0,CPU,3.5,75,50}, which is encoded as [0.1,43.2,50,55,3.5,4B,32]. Finally, the data string signal of [0.1,43.2,50,55,3.5,4B,32] is sent to the digital display screen, and the digital display screen displays [0.1,CPU,3.5,75,50] after decoding.

[0077] Example 3

[0078] like Figure 2 As shown, the present invention further provides a motherboard abnormality identification device 10, comprising the following components: a detection module 11, a calculation module 12, an encryption module 13, a light analysis module 14 and a display analysis module 15.

[0079] The detection module 11 is used to obtain detection information on the mainboard; wherein the detection information includes a plurality of data points.

[0080] The calculation module 12 is used to substitute the multiple data points into the algorithm model, and the algorithm model divides the detection information into normal component data and abnormal component data according to the distance between the multiple data points.

[0081] The encryption module 13 is used to encrypt the normal component data so that the normal component data cannot be read by the preset fault indicator light and digital display screen.

[0082] The light analysis module 14 is used to analyze the fault level of the corresponding abnormal component data according to the preset light signal coding rules, output the corresponding light signal, and input the corresponding light signal to the fault indicator light.

[0083] The display analysis module 15 is used to analyze the parameters of the corresponding abnormal component data according to the preset data string signal coding rules, output the corresponding data string signal, and send the corresponding data string signal to the digital display screen.

[0084] In this embodiment, the mainboard abnormality identification device 10 can be connected to the mainboard to achieve the acquisition, analysis, processing, encryption, display and transmission of the detection information on the mainboard.

[0085] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned mainboard abnormality identification method embodiment, and will not be repeated here.

[0086] Example 4

[0087] like Figure 3 As shown, the present invention also provides an electronic device 20, including a memory 21 and a processor 22, the memory 21 stores a computer program that can be run on the processor 22, and the processor 22 implements the above-mentioned mainboard abnormality identification method when executing the computer program.

[0088] In this step, the electronic device 20 can be any device having a memory 21 and a processor 22, such as a personal computer, a laptop computer, a tablet computer, a smart phone, etc.

[0089] Example 5

[0090] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the processor executes the above-mentioned mainboard abnormality identification method.

[0091] In this step, the computer-readable storage medium may be any medium that can store a computer program, such as a CD, a disk, a USB flash drive, a memory card, etc.

[0092] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying a mainboard abnormality, characterized in that: include: Acquiring detection information on the mainboard through a fault detection unit preset on the mainboard, wherein the fault detection unit detects various components on the mainboard through circuit signals or software programs, and obtains the detection information according to the detection results of various components on the mainboard; wherein the detection information includes a plurality of data points; Performing anomaly detection on the multiple data points using a preset anomaly detection algorithm, wherein the anomaly detection algorithm calculates anomaly scores of the multiple data points according to parameter information of the multiple data points, wherein the anomaly scores reflect the degree of anomaly of the data points; judging the anomaly scores according to a preset anomaly threshold, classifying the data points whose anomaly scores are greater than or equal to the anomaly threshold as abnormal component data, and classifying the data points whose anomaly scores are less than the anomaly threshold as normal component data; Encrypting the normal component data using a preset encryption algorithm so that the normal component data cannot be recognized by the fault indicator light and the digital display screen; According to the mapping rule between the fault level and the light signal in the preset light signal coding rule, the fault level of the abnormal component data is mapped to the corresponding light signal; wherein the light signal includes a red light signal, a yellow light signal and a green light signal; the light signal corresponding to the fault level of the abnormal component data is input into the fault indicator light; wherein a plurality of the fault indicator lights are preset on the main board, each of the fault indicator lights corresponds to a component of the main board, the fault level includes a serious fault, a general fault and a minor fault, the red light signal indicates the serious fault, the yellow light signal indicates the general fault, and the green light signal indicates the minor fault; Obtain a preset coding rule stored in a database, and extract coding parameters in the coding rule; input the fault type of the abnormal component data into a preset analysis table to obtain an initial component name corresponding to the fault type; wherein the analysis table includes a mapping relationship between the fault type and the abnormal component name causing the fault type; calculate the component name that is the same as the abnormal component name and the initial component name as the target component name; if the fault type is CPU overheating, the initial component name is CPU, and the abnormal component names causing the CPU overheating are shown in the analysis table as CPU, fan, and radiator, the initial component name is mapped to the CPU, fan, and heat sink; and the radiator, and found that the CPU has the same name as the initial component, so the target component name is CPU; the component number corresponding to the target component name is composed of a vector, which is input into the correction detection model to detect the corresponding correction value; wherein, the correction value includes the coding parameter that needs to be corrected in the coding rule and its corresponding correction value; based on the correction value, the corresponding coding parameter in the coding rule is corrected to obtain the correction coding rule; based on the correction coding rule, the parameter encoding of the abnormal component data is parsed into a corresponding data string signal, and the data string signal is sent to the digital display screen; wherein, the fault indicator light is an LED lamp; and the digital display screen is a liquid crystal display screen.

2. A motherboard abnormality identification device, characterized in that: include: a detection module, configured to obtain detection information on the mainboard through a fault detection unit preset on the mainboard, wherein the fault detection unit detects each component on the mainboard through a circuit signal or a software program, and obtains the detection information according to the detection results of each component on the mainboard; wherein the detection information includes a plurality of data points; A calculation module, configured to perform anomaly detection on the plurality of data points using a preset anomaly detection algorithm, wherein the anomaly detection algorithm calculates anomaly scores of the plurality of data points according to parameter information of the plurality of data points, wherein the anomaly scores reflect the degree of anomaly of the data points; the anomaly scores are judged according to a preset anomaly threshold, and data points whose anomaly scores are greater than or equal to the anomaly threshold are classified as abnormal component data, and data points whose anomaly scores are less than the anomaly threshold are classified as normal component data; An encryption module, used to encrypt the normal component data using a preset encryption algorithm so that the normal component data cannot be recognized by the fault indicator light and the digital display screen; A light parsing module, for mapping the fault level of the abnormal component data to a corresponding light signal according to a mapping rule between the fault level and the light signal in a preset light signal coding rule; wherein the light signal includes a red light signal, a yellow light signal and a green light signal; inputting the light signal corresponding to the fault level of the abnormal component data into a fault indicator light; wherein a plurality of the fault indicator lights are preset on the main board, each of the fault indicator lights corresponds to a component of the main board, the fault level includes a serious fault, a general fault and a minor fault, the red light signal indicates the serious fault, the yellow light signal indicates the general fault, and the green light signal indicates the minor fault; A display parsing module is used to obtain a preset coding rule stored in a database and extract coding parameters in the coding rule; input the fault type of the abnormal component data into a preset analysis table to obtain the initial component name corresponding to the fault type; wherein the analysis table includes a mapping relationship between the fault type and the abnormal component name causing the fault type; calculate the component name that is the same as the abnormal component name and the initial component name as the target component name; if the fault type is CPU overheating, the initial component name is CPU, and the abnormal component names causing the CPU overheating shown in the analysis table are CPU, fan, and radiator, the initial component name is compared with the CPU , fan and radiator, and find that the CPU is the same as the initial component name, and obtain the target component name as CPU; the component number corresponding to the target component name is composed of a vector, which is input into the correction detection model to detect the corresponding correction value; wherein, the correction value includes the coding parameter that needs to be corrected in the coding rule and its corresponding correction value; based on the correction value, the corresponding coding parameter in the coding rule is corrected to obtain the correction coding rule; based on the correction coding rule, the parameter encoding of the abnormal component data is parsed into a corresponding data string signal, and the data string signal is sent to the digital display screen; wherein, the fault indicator light is an LED lamp; and the digital display screen is a liquid crystal display screen.

3. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor implements the mainboard abnormality identification method according to claim 1 when executing the computer program.

4. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the processor is enabled to execute the mainboard abnormality identification method as claimed in claim 1.

Images