Computer intelligent fault diagnosis and early warning system based on artificial intelligence
Through an intelligent computer fault diagnosis and early warning system based on artificial intelligence, the computer hardware and software operation status is monitored and evaluated, the safety score trend chart is generated, and the fault warning is provided, which solves the problem of inadequate early warning in the existing technology and ensures the stability of the computer's operation. Sex and safety.
Patent Information
- Application Number
- CN202410943851.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-15
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing technology cannot warning computer disk failure in distributed storage systems in advance, resulting in failure to replace the disk in time when the failure occurs, affecting the system use.
Design an intelligent computer fault diagnosis and early warning system based on artificial intelligence, obtain hardware and software running status parameters through the acquisition module, configure the module to set the operation cycle, store the module to store parameters, evaluate the module to calculate the safety score, and visualize the module to generate a trend chart. The diagnostic module diagnoses faults and provides early warnings and fault prompts.
It realizes comprehensive monitoring and fault warning of the computer's operating status, ensures that safety hazards are known in a timely manner, supports foresight maintenance, and improves the stability and reliability of computer operation.
Smart Images

Figure CN118939458A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and in particular to a computer intelligent fault diagnosis and early warning system based on artificial intelligence. Background Art
[0002] Computer intelligent fault diagnosis and early warning refers to the process of using artificial intelligence, machine learning and other technologies to detect, diagnose and predict faults in computer systems or related equipment.
[0003] The invention patent with application number 202210873414.X discloses a CEPH distributed computer fault diagnosis method, which is characterized in that the method includes the following steps: obtaining the IOPS load characteristic indicators of the disks under each object storage, the transient upstream and downstream traffic corresponding to each object storage, and the buffer queue depth; wherein the IOPS load characteristic indicators include: IOPS total performance extreme value, IOPS total performance variance, and IOPS total performance minimum value envelope value; for any object storage, respectively calculate the frequency fluctuation degree of each of the IOPS load characteristic indicators within a fixed time period as the first fluctuation degree, the second fluctuation degree, and the third fluctuation degree; respectively calculate the amplitude fluctuation degree of each of the IOPS load characteristic indicators as the fourth fluctuation degree , fifth fluctuation degree and sixth fluctuation degree; calculate the fluctuation degree of the buffer queue depth within a fixed time period as the seventh fluctuation degree; calculate the fluctuation degree of the transient upstream and downstream traffic within a fixed time period as the eighth fluctuation degree; construct a feature matrix from the first, second, third, fourth, fifth, sixth, seventh and eighth fluctuation degrees; cluster the feature matrices corresponding to each of the object storages to obtain a plurality of cluster clusters; convert the feature matrix into a determinant, and use the absolute value of the determinant as a load fault hidden danger index; input the load fault hidden danger index into a hidden danger index development trend model corresponding to the cluster cluster to which the feature matrix belongs, and output a predicted load fault hidden danger index; and perform a fault judgment on the computer's disk based on the predicted load fault hidden danger index.
[0004] The application aims to solve the problem that "at present, the common method for diagnosing computer faults in distributed storage systems is to determine whether the disk is abnormal based on the real-time read and write rates of the disk in the distributed storage system. Directly judging whether the disk is abnormal based on the real-time read and write rates will affect the use of the computer when the disk is abnormal, and early warning is not achieved, and the disk cannot be replaced in time before the fault occurs."
[0005] However, due to the characteristics of computers integrating multiple hardware and software, the failure problems during use are complex, unpredictable and random.
[0006] To this end, we proposed a computer intelligent fault diagnosis and early warning system based on artificial intelligence. Summary of the invention
[0007] In view of the above-mentioned shortcomings of the prior art, the present invention provides a computer intelligent fault diagnosis and early warning system based on artificial intelligence, which solves the technical problems raised in the above-mentioned background technology.
[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:
[0009] A computer intelligent fault diagnosis and early warning system based on artificial intelligence, comprising:
[0010] An acquisition module is used to acquire computer hardware operation status parameters and software operation process parameters; a configuration module is used to configure the operation cycle of the acquisition module; a storage module is used to receive the computer hardware operation status parameters and software operation process parameters acquired by the acquisition module, and store the computer hardware operation status parameters and software operation process parameters; an evaluation module is used to traverse the computer hardware operation status parameters and software operation process parameters stored in the storage module, and evaluate the computer security score through the computer hardware operation status parameters and software operation process parameters; a visualization module is used to continuously receive the computer security score evaluated by the evaluation module, and generate a trend chart representing the continuous change of the computer security score based on the continuously received computer security score; a diagnosis module is used to read the trend chart representing the continuous change of the computer security score generated in the visualization module, and diagnose whether the computer has a fault problem through the trend of the trend chart;
[0011] The acquisition module is interactively connected to the sensor module and the monitoring unit at the lower level through a wireless network, the acquisition module is interactively connected to the configuration module through a wireless network, the configuration module is interactively connected to the recording unit through a wireless network, the configuration module is interactively connected to the sensor module and the monitoring unit through a wireless network, the configuration module is interactively connected to the storage module, the evaluation module, the visualization module and the diagnosis module through a wireless network, and the storage module is interactively connected to the acquisition module through a wireless network.
[0012] Furthermore, the acquisition module is provided with submodules at the lower level, including:
[0013] A sensor module is used to sense the operating status parameters of computer hardware;
[0014] A monitoring unit, used to monitor the parameters of the computer software running process;
[0015] Among them, the sensor module is integrated with a temperature sensor, a speed sensor and a voltage and current sensor. The computer hardware operation status parameters include: hardware temperature, hardware speed, hardware operation voltage and current. The monitoring unit operation monitors the computer software operation process parameters including: operation occupied memory, startup response time, and control command response time.
[0016] Furthermore, the configuration module is configured to run in the operation cycle of the acquisition module and is synchronously applied to the operation of the sensor module and the monitoring unit;
[0017] The configuration module is internally provided with submodules, including:
[0018] The recording unit is used to set the initial operation cycle of the acquisition module and record the computer usage time;
[0019] Among them, the initial operation period of the acquisition module set in the recording unit is configured in the computer by the configuration module when the system is first run, and the initial operation period of the acquisition module is not less than seven days.
[0020] Furthermore, the recording unit operates in real time within the collection module operation cycle to record the computer usage time. Based on the recorded computer usage time data, the configuration module sets a new operation cycle for the collection module. After the current collection module operation cycle ends, the newly set operation cycle is iterated over the previous operation cycle for further operation of the collection module.
[0021] The new operation cycle set by the configuration module for the acquisition module is subject to:
[0022]
[0023] Where: d is the new operation cycle; d0 is the initial operation cycle; ti is the computer usage time on the i-th day in the initial operation cycle; ε is the correction;
[0024] Among them, the new operation cycle d is converted into hours and rounded up by truncation. Table pair The average of the correction 1≥ε>0, and obey d IS The larger the value, the smaller the correction value. On the contrary, the larger the correction value, the setting logic, d IS Indicates the time corresponding to the intersection of the computer usage time and the time threshold of each day in the initial operation cycle.
[0025] Furthermore, during the operation cycle, when the computer is not turned on, the operations run by the acquisition module corresponding to the operation cycle are accumulated and executed in the next operation cycle. When the computer is turned on, and the number of operations run by the acquisition module in the same operation cycle is not less than two, the operations run by the acquisition module are evenly distributed in the time span from when the computer is turned on to when the computer is turned off.
[0026] Furthermore, the storage module performs a storage phase for the computer hardware operation status parameters and the software operation process parameters, and distinguishes and stores the computer hardware operation status parameters and the software operation process parameters based on their actual source cycles;
[0027] The evaluation module runs once each time the storage module stores new computer hardware operating status parameters and software operating process parameters. Each time the evaluation module runs, the storage module is synchronously controlled to delete the earliest computer hardware operating status parameters and software operating process parameters stored therein that are equal to the number of newly stored parameters.
[0028] Furthermore, the computer security score evaluation logic in the evaluation module is expressed as:
[0029]
[0030] Where: k is the reference value of computer hardware security score; u is the set of operation cycles; s v is the computer hardware speed in the vth operation cycle; cv is the computer hardware temperature in the vth operation cycle; is the voltage-to-current ratio of the computer hardware in the vth operation cycle; ω1, ω2, ω3, ... are weights; K is the reference value of the computer safety score; m is the set of computer hardware; k j is the security score reference value of the jth group of computer hardware; j is the correlation factor; P is the computer security score; is the average startup response time of computer software; g v The memory occupied by the computer software in the vth operation cycle; v is the average response time of the computer software control command in the vth operation cycle;
[0031] in, Table pair The average of the weights ω1, ω2, ω3, ... follows: ω1, ω2, ω 3 , ... is 1, the weight product object computer hardware operation status parameter corresponding to the computer hardware is more important to the computer operation, the corresponding weight value is larger, conversely, the weight value is smaller;
[0032] Correlation factor 1>λ j > 0, associated factor product object k j The more important the computer hardware is to the operation of the computer, the larger the correlation factor value is. Conversely, the smaller the correlation factor value is, the higher the computer security score P is, which means the computer is safer. Conversely, it means that the computer has faults or the probability of faults occurring is greater.
[0033] Furthermore, the trend graph representing the continuous change of the computer security score generated in the visualization module is a line graph, the horizontal axis of the trend graph represents time, and the vertical axis represents the computer security score P obtained by running the evaluation module in the corresponding period.
[0034] Furthermore, the logic of the diagnosis module running to diagnose whether the computer has a fault problem is:
[0035] In the trend graph showing the continuous change of the computer security score, the latest three consecutive groups of line segments show a downward trend, and an early warning prompt is issued. The content of the early warning prompt is "the computer has an operation security risk". The early warning prompt content is displayed on the computer screen in text format every time the computer is turned on;
[0036] In the trend graph showing the continuous change of the computer security score, the latest five consecutive groups of line segments show a downward trend, issuing a fault prompt. The fault prompt content is "The computer is at risk of operating failure." The fault prompt content is displayed on the computer screen in text format every time the computer is turned on.
[0037] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects:
[0038] The present invention provides a computer intelligent fault diagnosis and early warning system based on artificial intelligence. During operation, the system monitors the hardware operation status parameters and software operation process parameters of the computer in the operation state through sensing devices, comprehensively monitors the computer operation status security, further analyzes the computer security score based on the monitored computer parameters, and finally issues fault early warning and fault diagnosis to computer users according to the dynamic changes of the computer security score, thereby ensuring that the potential safety hazards in the computer operation process can be known to the computer users in time, so as to facilitate the predictive maintenance and care of the computer. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] 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 prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0040] Figure 1 It is a structural diagram of a computer intelligent fault diagnosis and early warning system based on artificial intelligence. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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.
[0042] The present invention will be further described below in conjunction with the embodiments.
[0043] Embodiment 1:
[0044] The present embodiment is a computer intelligent fault diagnosis and early warning system based on artificial intelligence, such as Figure 1 As shown, including:
[0045] The acquisition module is used to collect computer hardware operation status parameters and software operation process parameters;
[0046] The acquisition module is equipped with submodules, including:
[0047] A sensor module is used to sense the operating status parameters of computer hardware;
[0048] A monitoring unit, used to monitor the parameters of the computer software running process;
[0049] Among them, the sensor module is integrated with temperature sensor, speed sensor and voltage and current sensor. The computer hardware operation status parameters include: hardware temperature, hardware speed, hardware operation voltage and current. The monitoring unit operation monitoring computer software operation process parameters include: operation occupied memory, startup response time, control command response time;
[0050] Configuration module, used to configure the operation cycle of the acquisition module;
[0051] The configuration module runs in the operation cycle of the acquisition module and is synchronously applied to the operation of the sensor module and the monitoring unit;
[0052] The configuration module has submodules inside, including:
[0053] The recording unit is used to set the initial operation cycle of the acquisition module and record the computer usage time;
[0054] The initial operation period of the acquisition module set in the recording unit is configured on the computer by the configuration module when the system is first operated, and the initial operation period of the acquisition module is not less than seven days;
[0055] The recording unit runs in real time within the operation cycle of the acquisition module to record the computer usage time. Based on the recorded computer usage time data, the configuration module sets a new operation cycle for the acquisition module. After the current operation cycle of the acquisition module ends, the newly set operation cycle is iterated over the previous operation cycle for further operation of the acquisition module.
[0056] The configuration module sets a new operating cycle for the acquisition module to follow:
[0057]
[0058] Where: d is the new operation cycle; d0 is the initial operation cycle; ti is the computer usage time on the i-th day in the initial operation cycle; ε is the correction;
[0059] Among them, the new operation cycle d is converted into hours and rounded up by truncation. Table pair The average of the correction 1≥ε>0, and obey d IS The larger the value, the smaller the correction value. On the contrary, the larger the correction value, the setting logic, d IS Indicates the time corresponding to the intersection of the computer usage time and the time threshold every day in the initial operation cycle;
[0060] A storage module is used to receive the computer hardware operation status parameters and software operation process parameters collected by the collection module, and store the computer hardware operation status parameters and software operation process parameters;
[0061] An evaluation module, used to traverse the computer hardware operation status parameters and software operation process parameters stored in the storage module, and evaluate the computer security score through the computer hardware operation status parameters and software operation process parameters;
[0062] The computer security score evaluation logic in the evaluation module is expressed as:
[0063]
[0064] Where: k is the reference value of computer hardware security score; u is the set of operation cycles; s v is the computer hardware speed in the vth operation cycle; cv is the computer hardware temperature in the vth operation cycle; is the voltage-to-current ratio of the computer hardware in the vth operation cycle; ω1, ω2, ω 3 , ... are weights; K is the reference value of computer security score; m is the set of computer hardware; k j is the security score reference value of the jth group of computer hardware; j is the correlation factor; P is the computer security score; is the average startup response time of computer software; gv The memory occupied by the computer software in the vth operation cycle; v is the average response time of the computer software control command in the vth operation cycle;
[0065] in, Table pair The average weight ω 1 The values of ω1, ω2, ω3, ... are subject to the following: the sum of ω1, ω2, ω3, ... is 1. The more important the computer hardware corresponding to the operating status parameter of the weight product object is to the computer operation, the greater the corresponding weight value is, and vice versa, the smaller the weight value is;
[0066] Correlation factor 1>λ j > 0, associated factor product object k j The more important the source computer hardware is to the operation of the computer, the greater the value of the correlation factor. Conversely, the smaller the value of the correlation factor, the higher the computer security score P, indicating that the computer is safer. Conversely, it means that the computer has faults or the probability of faults occurring is greater;
[0067] A visualization module, used for continuously receiving the computer security scores evaluated by the evaluation module, and generating a trend graph representing the continuous change of the computer security scores based on the continuously received computer security scores;
[0068] The diagnosis module is used to read the trend chart representing the continuous change of the computer security score generated by the visualization module, and diagnose whether the computer has a fault problem through the trend chart trend;
[0069] The acquisition module is interactively connected to the sensor module and the monitoring unit through a wireless network, the acquisition module is interactively connected to the configuration module through a wireless network, the configuration module is interactively connected to the recording unit through a wireless network, the configuration module is interactively connected to the sensor module and the monitoring unit through a wireless network, the configuration module is interactively connected to the storage module, the evaluation module, the visualization module and the diagnosis module through a wireless network, and the storage module is interactively connected to the acquisition module through a wireless network.
[0070] In this embodiment, the acquisition module operates to collect computer hardware operation status parameters and software operation process parameters, the sensor module synchronously senses the computer hardware operation status parameters, the monitoring unit monitors the computer software operation process parameters in real time, the configuration module further configures the operation cycle of the acquisition module, the recording unit synchronously sets the initial operation cycle of the acquisition module, records the computer usage time, the storage module operates in real time to receive the computer hardware operation status parameters and software operation process parameters collected by the acquisition module, and stores the computer hardware operation status parameters and software operation process parameters, the evaluation module post-operates to traverse the computer hardware operation status parameters and software operation process parameters stored in the storage module, and evaluates the computer security score through the computer hardware operation status parameters and software operation process parameters, and then the visualization module continuously receives the computer security score evaluated by the evaluation module, and based on the continuously received computer security score, generates a trend graph representing the continuous change of the computer security score, and finally reads the trend graph representing the continuous change of the computer security score generated in the visualization module through the diagnosis module, and diagnoses whether the computer has a fault problem through the trend of the trend graph;
[0071] Through the operation of the system in the above embodiment, a comprehensive operation fault diagnosis and early warning system based on the combination of hardware and software levels is provided for the computer, which provides stable operation guarantee for the computer operation and ensures that the potential safety hazards during the operation of the computer can be known to the computer user in a timely manner, so as to facilitate the predictive maintenance and care of the computer.
[0072] Embodiment 2:
[0073] In terms of specific implementation, based on Example 1, this example refers to Figure 1 The computer intelligent fault diagnosis and early warning system based on artificial intelligence in Example 1 is further described in detail:
[0074] During the operation cycle, when the computer is not turned on, the operations run by the acquisition module corresponding to the operation cycle are accumulated and executed in the next operation cycle. When the computer is turned on, and the number of operations run by the acquisition module in the same operation cycle is not less than two, the operations run by the acquisition module are evenly distributed in the time span from when the computer is turned on to when the computer is turned off.
[0075] Through the above settings, it is further limited that the operation cycle of the acquisition module actually adapts to the application logic of the computer after the operation cycle is configured.
[0076] like Figure 1 As shown, the storage module performs a storage phase for the computer hardware operation status parameters and the software operation process parameters, and distinguishes and stores the computer hardware operation status parameters and the software operation process parameters based on the actual source cycle of the computer hardware operation status parameters and the software operation process parameters;
[0077] The evaluation module runs once each time the storage module stores new computer hardware operating status parameters and software operating process parameters. Each time the evaluation module runs, the storage module is synchronously controlled to delete the earliest computer hardware operating status parameters and software operating process parameters stored therein that are equal to the number of newly stored parameters.
[0078] Through the above settings, the source of parameters used in the computer security score evaluation logic is further limited.
[0079] like Figure 1 As shown, the trend graph representing the continuous change of the computer security score generated in the visualization module is a line graph, the horizontal axis of the trend graph represents time, and the vertical axis represents the computer security score P obtained by running the evaluation module in the corresponding period.
[0080] Through the above settings, the form of the trend graph representing the continuous change of the computer security score is further limited.
[0081] Embodiment 3:
[0082] In terms of specific implementation, based on Example 1, this example refers to Figure 1 The computer intelligent fault diagnosis and early warning system based on artificial intelligence in Example 1 is further described in detail:
[0083] The logic of the diagnostic module to diagnose whether the computer has a fault problem is as follows:
[0084] In the trend graph showing the continuous change of the computer security score, the latest three consecutive groups of line segments show a downward trend, and an early warning prompt is issued. The content of the early warning prompt is "the computer has an operation security risk". The early warning prompt content is displayed on the computer screen in text format every time the computer is turned on;
[0085] In the trend graph showing the continuous change of the computer security score, the latest five consecutive groups of line segments show a downward trend, issuing a fault prompt. The fault prompt content is "The computer is at risk of operating failure." The fault prompt content is displayed on the computer screen in text format every time the computer is turned on.
[0086] In this embodiment, through the above settings, the operation logic of the diagnosis module is further limited, ensuring that the system has the basic conditions for interaction between the computer and the computer user.
[0087] In summary, during the operation of the system in the above embodiment, the system monitors the hardware operating status parameters and software operating process parameters of the computer through the sensing device, and comprehensively monitors the computer operating status security. Further, based on the monitored computer parameters, a comprehensive analysis is performed to obtain the computer security score. Finally, according to the dynamic changes of the computer security score, fault warnings and fault diagnosis are issued to computer users to ensure that the safety hazards in the computer operation process can be known to the computer users in a timely manner, so as to facilitate the predictive maintenance and care of the computer.
[0088] 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 may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A computer intelligent fault diagnosis and early warning system based on artificial intelligence, characterized in that: include: The acquisition module is used to collect computer hardware operation status parameters and software operation process parameters; Configuration module, used to configure the operation cycle of the acquisition module; A storage module is used to receive the computer hardware operation status parameters and software operation process parameters collected by the collection module, and store the computer hardware operation status parameters and software operation process parameters; An evaluation module, used to traverse the computer hardware operation status parameters and software operation process parameters stored in the storage module, and evaluate the computer security score through the computer hardware operation status parameters and software operation process parameters; A visualization module, used to continuously receive the computer security scores evaluated by the evaluation module, and generate a trend chart representing the continuous change of the computer security scores based on the continuously received computer security scores; The diagnosis module is used to read the trend chart generated by the visualization module, which represents the continuous change of the computer security score, and diagnose whether the computer has a fault problem through the trend chart.
2. According to claim 1, a computer intelligent fault diagnosis and early warning system based on artificial intelligence is characterized in that: The acquisition module is provided with submodules at the lower level, including: A sensor module is used to sense the operating status parameters of computer hardware; A monitoring unit, used to monitor the parameters of the computer software running process; Among them, the sensor module is integrated with a temperature sensor, a speed sensor and a voltage and current sensor. The computer hardware operation status parameters include: hardware temperature, hardware speed, hardware operation voltage and current. The monitoring unit operation monitors the computer software operation process parameters including: operation occupied memory, startup response time, and control command response time.
3. The computer intelligent fault diagnosis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The configuration module is configured to run in the operation cycle of the acquisition module and is synchronously applied to the operation of the sensor module and the monitoring unit; The configuration module is internally provided with submodules, including: The recording unit is used to set the initial operation cycle of the acquisition module and record the computer usage time; Among them, the initial operation period of the acquisition module set in the recording unit is configured in the computer by the configuration module when the system is first run, and the initial operation period of the acquisition module is not less than seven days.
4. The computer intelligent fault diagnosis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The recording unit runs in real time within the collection module operation cycle to record the computer usage time. Based on the recorded computer usage time data, the configuration module sets a new operation cycle for the collection module. After the current collection module operation cycle ends, the newly set operation cycle is iterated over the previous operation cycle for further operation of the collection module. The new operation cycle set by the configuration module for the acquisition module is subject to: Where: d is the new operation cycle; d0 is the initial operation cycle; ti is the computer usage time on the i-th day in the initial operation cycle; ε is the correction; Among them, the new operation cycle d is converted into hours and rounded up by truncation. Table pair The average of the correction 1≥ε>0, and obey d IS The larger the value, the smaller the correction value. On the contrary, the larger the correction value, the setting logic, d IS Indicates the time corresponding to the intersection of the computer usage time and the time threshold every day in the initial operation cycle.
5. The computer intelligent fault diagnosis and early warning system based on artificial intelligence according to claim 1 is characterized in that: During the operation cycle, when the computer is not turned on, the operations of the acquisition module corresponding to the operation cycle are accumulated and executed in the next operation cycle. When the computer is turned on, and the number of operations run by the acquisition module in the same operation cycle is not less than two, the operations run by the acquisition module are evenly distributed in the time span from when the computer is turned on to when the computer is turned off.
6. A computer intelligent fault diagnosis and early warning system based on artificial intelligence according to claim 1 or 5, characterized in that: The storage module performs a storage phase for the computer hardware operation status parameters and the software operation process parameters, and distinguishes and stores the computer hardware operation status parameters and the software operation process parameters based on their actual source cycles; The evaluation module runs once each time the storage module stores new computer hardware operating status parameters and software operating process parameters. Each time the evaluation module runs, the storage module is synchronously controlled to delete the earliest computer hardware operating status parameters and software operating process parameters stored therein that are equal to the number of newly stored parameters.
7. The computer intelligent fault diagnosis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The computer security score evaluation logic in the evaluation module is expressed as: Where: k is the reference value of computer hardware security score; u is the set of operation cycles; s v is the computer hardware speed in the vth operation cycle; cv is the computer hardware temperature in the vth operation cycle; is the voltage-to-current ratio of the computer hardware in the vth operation cycle; ω1, ω2, ω3, ... are weights; K is the reference value of the computer safety score; m is the set of computer hardware; k j is the security score reference value of the jth group of computer hardware; j is the correlation factor; P is the computer security score; is the average startup response time of computer software; g v The memory occupied by the computer software in the vth operation cycle; v is the average response time of the computer software control command in the vth operation cycle; in, Table pair The average of the weights ω1, ω2, ω3, ... is: the sum of ω1, ω2, ω3, ... is 1, and the weight product object computer hardware operation status parameter corresponds to the computer hardware. The more important it is to the computer operation, the greater the corresponding weight value is, and vice versa, the smaller the weight value is; Correlation factor 1>λ j > 0, associated factor product object k j The more important the computer hardware is to the operation of the computer, the larger the correlation factor value is. Conversely, the smaller the correlation factor value is, the higher the computer security score P is, which means the computer is safer. Conversely, it means that the computer has faults or the probability of faults occurring is greater.
8. The computer intelligent fault diagnosis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The trend graph representing the continuous change of the computer security score generated in the visualization module is a line graph, the horizontal axis of the trend graph represents time, and the vertical axis represents the computer security score P obtained by running the evaluation module in the corresponding period.
9. The computer intelligent fault diagnosis and early warning system based on artificial intelligence according to claim 1 is characterized in that: The logic of the diagnostic module running to diagnose whether the computer has a fault problem is: In the trend graph showing the continuous change of the computer security score, the latest three consecutive groups of line segments show a downward trend, and an early warning prompt is issued. The content of the early warning prompt is "the computer has an operation security risk". The early warning prompt content is displayed on the computer screen in text format every time the computer is turned on; In the trend graph showing the continuous change of the computer security score, the latest five consecutive groups of line segments show a downward trend, issuing a fault prompt. The fault prompt content is "the computer is at risk of operating failure". The fault prompt content is displayed on the computer screen in text format every time the computer is turned on.
Citation Information
Cited By
Computer intelligent fault diagnosis and early warning system based on artificial intelligence
CN120179513A
Computer intelligent fault diagnosis and early warning system based on artificial intelligence
CN120179513B
