Internet operation and maintenance method based on artificial intelligence algorithm optimization

Abstract

The invention discloses an internet operation and maintenance method based on artificial intelligence algorithm optimization, which relates to the technical field of internet, and comprises the following steps of: mining an implicit relationship between an internet operation fault and a performance index parameter; performing correlation analysis on the two operation faults to generate at least one fault routine combination; forming a judgment standard for the conventional combination of the suspected faults; at least one suspected fault routine combination is obtained, and a judgment standard that the performance index parameters conform to the suspected fault routine combination is met; obtaining a target fault conventional combination; and processing the operation fault in the target fault routine combination. A target fault routine combination is obtained and the operation faults in the target fault routine combination are processed by mining the implicit relation between the internet operation faults and the performance index parameters, so that targeted maintenance parameters can be set, and meanwhile, the maintenance sequence is set according to the severity of the maintenance parameters, so that the maintenance efficiency is improved. And the operation and maintenance requirements can be well met.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to an Internet operation and maintenance method based on artificial intelligence algorithm optimization. Background Art

[0002] At present, the development of the Internet is characterized by high integration, intelligence and ecology, and has been widely used in many fields such as manufacturing, energy, transportation, and medical care. Internet operators are personnel who carry out network interconnection, data collection and processing, identity resolution applications, platform application optimization, and system security maintenance for Internet systems, ensuring the efficient and safe operation of Internet systems. Among them, the more important thing in Internet operation and maintenance is to identify and handle various operating failures.

[0003] However, there are many types of Internet failures and the mix of operational failures is unknown. At the same time, the severity of each failure is different, which poses great challenges to identification and repair. During maintenance, it is difficult to sort maintenance according to severity, which cannot meet the requirements of operation and maintenance. Summary of the invention

[0004] In order to solve the above technical problems, an Internet operation and maintenance method based on artificial intelligence algorithm optimization is provided. This technical solution solves the problems raised in the above background technology.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is: An Internet operation and maintenance method based on artificial intelligence algorithm optimization, comprising: Using an intelligent terminal, real-time data of at least one performance indicator parameter of the Internet is collected in real time; Determine the data transmission method, configure the data transmission protocol, establish the data transmission channel, and perform automatic data collection and transmission; Obtain at least one operation fault in the Internet, and mine the implicit connection between the Internet operation fault and the performance indicator parameter; Based on the implicit connection, a correlation analysis is performed on the two operating faults, and based on the correlation of the two operating faults, at least one fault regular combination is generated; Form judgment criteria for conventional combinations of suspected faults; Obtaining at least one suspected fault conventional combination, which satisfies the judgment criteria that the performance indicator parameters meet the suspected fault conventional combination; Screening at least one suspected fault regular combination to obtain a target fault regular combination; Based on big data, operational faults in the regular combination of target faults are processed.

[0006] Preferably, the determining of the data transmission mode, configuring the data transmission protocol, establishing the data transmission channel, and performing automatic data collection and transmission specifically include: Wireless ZigBee technology is used for transmission between the Internet and smart terminals; The data collection software reads various data from the Internet in real time and converts them into a format for transmission; Configure the data trigger mechanism as a timed trigger. When the trigger conditions are met, the data acquisition software automatically collects data and sends it to the smart terminal.

[0007] Preferably, mining the implicit connection between Internet operation failures and performance indicator parameters specifically includes: When an operation fault occurs, the performance indicator parameter that changes by more than a preset range will be used as the target performance indicator parameter, and the performance indicator parameter that changes by no more than a preset range will be used as the non-target performance indicator parameter. The preset range is the normal fluctuation range of the performance indicator parameter; There is an implicit connection between the target performance indicator parameters and the operation failure, but there is no implicit connection between the non-target performance indicator parameters and the operation failure; The time range of the operation fault is divided into equal intervals to obtain at least one time point, the time point is paired with the value of the non-target performance indicator parameter at the time point and fitted to obtain a preliminary function, and the average of all preliminary functions is taken to obtain a non-target function; Pairing and fitting the time points with the values ​​of the target performance indicator parameters at the time points to obtain the target function; The result of comparing the objective function with the non-objective function is integrated within the time range of the operation fault, and the implicit coefficient of the objective performance index parameter and the operation fault is obtained; The implicit coefficients of non-target performance index parameters and operational failures are set to 0; The non-target performance index parameters are combined with the target performance index parameters to obtain the implicit coefficients of the performance index parameters and the operation failure.

[0008] Preferably, the correlation analysis of two operation failures based on implicit connection specifically includes: The two operation failures are recorded as a first operation failure and a second operation failure respectively; Subtract the implicit coefficient of the first operation fault and performance index parameter from the implicit coefficient of the second operation fault and performance index parameter and take the absolute value to obtain the actual gap; The actual gaps of all performance indicator parameters are accumulated to obtain the overall gap; Accumulating the implicit coefficients of the first operation fault and all performance index parameters and the implicit coefficients of the second operation fault and all performance index parameters to obtain an implicit sum; The overall gap is divided by the implicit sum, then subtracted from 1 and the absolute value is taken to obtain the correlation coefficient.

[0009] Preferably, generating at least one conventional combination of faults based on the correlation between the two operating faults specifically includes: All possible combinations of all operating faults are taken as fault combinations to be verified; Select any operation fault in the fault combination to be verified as a characteristic operation fault; Based on big data, obtain the probability of occurrence of characteristic operation failures; Pairing the characteristic operation fault with the remaining operation faults in the fault combination to be verified to obtain at least one characteristic operation fault group; Divide the correlation between two operation faults in the characteristic operation fault group by the occurrence probability of the characteristic operation fault to obtain the independence probability; Multiply the occurrence probability by the independent probability of all characteristic operation fault groups to obtain the probability to be identified; The maximum value of the probability of occurrence of operating failures with a frequency lower than 1 in a year is used as the identification threshold; The fault combination to be verified whose probability of being identified exceeds the identification threshold is regarded as the normal fault combination.

[0010] Preferably, forming a judgment standard for a conventional combination of suspected faults includes the following steps: Based on big data, the maximum value of the performance indicator parameter when there is an operation fault is obtained as the maximum eigenvalue, and the minimum value of the performance indicator parameter when there is an operation fault is obtained as the minimum eigenvalue; The maximum value of the maximum characteristic values ​​of the performance index parameters of all operating faults in the conventional fault combination is taken as the upper threshold value of the performance index parameter; The minimum value of the minimum characteristic values ​​of the performance index parameters of all operating faults in the conventional fault combination is taken as the lower threshold value of the performance index parameter; The lower threshold value and the upper threshold value of the performance indicator parameter form the evaluation range of the performance indicator parameter; The judgment criteria for the suspected fault conventional combination are: when the real-time data of the performance indicator parameters all belong to the evaluation range of the performance indicator parameters in the fault conventional combination, the fault conventional combination is regarded as the suspected fault conventional combination.

[0011] Preferably, screening at least one suspected fault conventional combination to obtain a target fault conventional combination comprises the following steps: Obtaining a fault degree range of the operation fault, dividing the fault degree range at equal intervals, and obtaining at least one identification point; Randomly matching at least one identification point to an operational fault in a conventional combination of suspected faults, each matching method forming a suspected allocation scheme; Under the condition of the suspected allocation scheme, the conditional value of the performance indicator parameter is calculated, and the conditional value of the performance indicator parameter is equal to the result of multiplying and accumulating the performance indicator parameter and the implicit coefficient of the operating fault and the identification point of the operating fault in the conventional combination of the suspected fault; Arrange the performance indicator parameters in ascending order according to their conditional values ​​to obtain a conditional sequence; Arrange the performance indicator parameters from small to large according to the real-time data of the performance indicator parameters to obtain a real-time sequence; If there is a condition sequence that is consistent with the real-time sequence, the suspected fault regular combination corresponding to the condition sequence is used as the target fault regular combination; The failure degree of the operating failure in the suspected allocation scheme for generating the regular combination of target failures is used as the real-time approximate failure degree of the operating failure.

[0012] Preferably, the processing of the operation failure in the conventional combination of target failures based on big data includes the following steps: Identify the urgency of the operation fault, and multiply the urgency of the operation fault by the real-time approximate fault severity of the operation fault to obtain the severity of the operation fault; According to the severity of the operating faults, the operating faults in the conventional combination of target faults are sorted from large to small to obtain an operating fault sequence; Based on big data, obtain the parameters of the benchmark processing scheme when the severity of the operation fault is a preset value, and the preset value is any value within the value range of the severity of the operation fault; The severity of the operating fault is divided by the preset value to obtain the target multiple; The processing parameters are set according to the target multiples of the benchmark processing scheme parameters for the operating faults in the target fault conventional combination.

[0013] Preferably, the step of identifying the urgency of the operating failure comprises the following steps: When the fault degree of the operation fault is 0, obtaining first sample data of the performance indicator parameter; When the fault degree of the operation fault is a preset value, obtaining second sample data of the performance indicator parameter; Based on the analytic hierarchy process, the weights of performance indicator parameters for Internet operation are obtained; Accumulate the first sample data and the second sample data of all performance indicator parameters to obtain a comprehensive evaluation value; According to the weight of the performance indicator parameter, the absolute value of the difference between the first sample data and the second sample data of the performance indicator parameter is accumulated to obtain a key coefficient; The critical coefficient is divided by the comprehensive evaluation value to obtain the urgency of the operating failure.

[0014] Compared with the prior art, the present invention has the following beneficial effects: By mining the implicit connection between Internet operation failures and performance indicator parameters, performing correlation analysis on two operation failures, generating at least one general combination of failures, obtaining a target general combination of failures and processing the operation failures in the target general combination of failures, the general combination of failures can be generated, and then preliminary screening of the failure combinations can be performed in combination with pre-set standards. At the same time, through further screening, the target general combination of failures can be obtained, and the degree of the operation failures in the target general combination of failures can be determined, so that targeted maintenance parameters can be set. At the same time, the maintenance sequence can be set according to its severity, so that the operation and maintenance needs can be better met. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flowchart of an Internet operation and maintenance method based on artificial intelligence algorithm optimization according to the present invention; Figure 2 A schematic diagram of the process of determining the data transmission mode, configuring the data transmission protocol, establishing the data transmission channel, and performing automatic data collection and transmission of the present invention; Figure 3 A schematic diagram of a process for mining the implicit relationship between Internet operation failures and performance indicator parameters of the present invention; Figure 4 It is a flow chart of performing correlation analysis on two operation faults based on implicit connection of the present invention; Figure 5 A flow chart of generating at least one conventional combination of faults based on the correlation between two operating faults according to the present invention; Figure 6 A schematic diagram of a flow chart of forming a judgment standard for a conventional combination of suspected faults according to the present invention; Figure 7 A schematic diagram of a flow chart of the present invention for screening at least one suspected fault conventional combination to obtain a target fault conventional combination; Figure 8 It is a flow chart of processing the operation failure in the conventional combination of target failures based on big data in the present invention; Fig. 9 It is a flowchart of identifying the urgency of an operation failure according to the present invention. DETAILED DESCRIPTION

[0016] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0017] Reference Figure 1As shown, an Internet operation and maintenance method based on artificial intelligence algorithm optimization includes: Using an intelligent terminal, real-time data of at least one performance indicator parameter of the Internet is collected in real time; Determine the data transmission method, configure the data transmission protocol, establish the data transmission channel, and perform automatic data collection and transmission; Obtain at least one operation fault in the Internet, and mine the implicit connection between the Internet operation fault and the performance indicator parameter; Based on the implicit connection, a correlation analysis is performed on the two operating faults, and based on the correlation of the two operating faults, at least one fault regular combination is generated; Form judgment criteria for conventional combinations of suspected faults; Obtaining at least one suspected fault conventional combination, which satisfies the judgment criteria that the performance indicator parameters meet the suspected fault conventional combination; Screening at least one suspected fault regular combination to obtain a target fault regular combination; Based on big data, operational faults in the regular combination of target faults are processed.

[0018] In this scheme, the main focus is on identifying situations where multiple faults occur in parallel. The main basis is that different operating faults have different effects on performance index parameters. Therefore, based on this, the existing operating faults can be determined by comparing with the real-time data of the performance index parameters. Therefore, it is necessary to analyze the relationship between the performance index parameters and the operating faults, and use the relationship obtained from the analysis to set up the corresponding algorithm to obtain the existing operating faults and their degree.

[0019] Reference Figure 2 As shown, determining the data transmission mode, configuring the data transmission protocol, establishing the data transmission channel, and performing automatic data collection and transmission specifically include: Wireless ZigBee technology is used for transmission between the Internet and smart terminals; The data collection software reads various data from the Internet in real time and converts them into a format for transmission; Configure the data trigger mechanism as a timed trigger. When the trigger conditions are met, the data acquisition software automatically collects data and sends it to the smart terminal.

[0020] Reference Figure 3 As shown in Figure 1, mining the implicit relationship between Internet operation failures and performance indicator parameters specifically includes: When an operation fault occurs, the performance indicator parameter that changes by more than a preset range will be used as the target performance indicator parameter, and the performance indicator parameter that changes by no more than a preset range will be used as the non-target performance indicator parameter. The preset range is the normal fluctuation range of the performance indicator parameter; There is an implicit connection between the target performance indicator parameters and the operation failure, but there is no implicit connection between the non-target performance indicator parameters and the operation failure; The time range of the operation fault is divided into equal intervals to obtain at least one time point, the time point is paired with the value of the non-target performance indicator parameter at the time point and fitted to obtain a preliminary function, and the average of all preliminary functions is taken to obtain a non-target function; Pairing and fitting the time points with the values ​​of the target performance indicator parameters at the time points to obtain the target function; The result of comparing the objective function with the non-objective function is integrated within the time range of the operation fault, and the implicit coefficient of the objective performance index parameter and the operation fault is obtained; The implicit coefficients of non-target performance index parameters and operational failures are set to 0; The non-target performance index parameters are combined with the target performance index parameters to obtain the implicit coefficients of the performance index parameters and the operation failure.

[0021] Implicit connections are mainly characterized by implicit coefficients, and the implicit coefficients are obtained by comparing the objective function with the non-objective function. The non-objective performance indicator parameters are mainly used as the comparison object to characterize the relationship between different objective performance indicator parameters. Here, since the non-objective performance indicator parameters are approximate and are almost unaffected by operating failures, their data are basically consistent. Therefore, selecting any non-objective performance indicator parameter for reference will result in basically consistent results.

[0022] Reference Figure 4 As shown in the figure, based on the implicit connection, the correlation analysis of the two operating failures specifically includes: The two operation failures are recorded as a first operation failure and a second operation failure respectively; Subtract the implicit coefficient of the first operation fault and performance index parameter from the implicit coefficient of the second operation fault and performance index parameter and take the absolute value to obtain the actual gap; The actual gaps of all performance indicator parameters are accumulated to obtain the overall gap; Accumulating the implicit coefficients of the first operation fault and all performance index parameters and the implicit coefficients of the second operation fault and all performance index parameters to obtain an implicit sum; The overall gap is divided by the implicit sum, then subtracted from 1 and the absolute value is taken to obtain the correlation coefficient.

[0023] The analysis of correlation analysis is used to obtain the correlation coefficient, which is mainly characterized by the summary analysis of the difference between the first operation fault and the second operation fault and the implicit coefficient of each performance indicator parameter. The principle is that when the correlation between the first operation fault and the second operation fault is higher, the difference between the implicit coefficients relative to the same performance indicator parameter is smaller, and thus the correlation is higher. Therefore, the correlation coefficient is obtained according to this principle.

[0024] Reference Figure 5 As shown, based on the correlation between two operating faults, generating at least one fault regular combination specifically includes: All possible combinations of all operating faults are taken as fault combinations to be verified; Select any operation fault in the fault combination to be verified as a characteristic operation fault; Based on big data, obtain the probability of occurrence of characteristic operation failures; Pairing the characteristic operation fault with the remaining operation faults in the fault combination to be verified to obtain at least one characteristic operation fault group; Divide the correlation between two operation faults in the characteristic operation fault group by the occurrence probability of the characteristic operation fault to obtain the independence probability; Multiply the occurrence probability by the independent probability of all characteristic operation fault groups to obtain the probability to be identified; The maximum value of the probability of occurrence of operating failures with a frequency lower than 1 in a year is used as the identification threshold; The fault combination to be verified whose probability of being identified exceeds the identification threshold is regarded as the normal fault combination.

[0025] Although the combinations of faults are infinite, in actual situations, there are only a limited number of fault combinations worth considering. This is because many fault combinations have too low a probability of occurrence, such as once a year. Therefore, there is no need to consider them as routine Internet operation and maintenance. Therefore, corresponding classification standards are set to determine the regular combinations of faults.

[0026] Reference Figure 6 As shown, forming a judgment standard for a conventional combination of suspected faults includes the following steps: Based on big data, the maximum value of the performance indicator parameter when there is an operation fault is obtained as the maximum eigenvalue, and the minimum value of the performance indicator parameter when there is an operation fault is obtained as the minimum eigenvalue; The maximum value of the maximum characteristic values ​​of the performance index parameters of all operating faults in the conventional fault combination is taken as the upper threshold value of the performance index parameter; The minimum value of the minimum characteristic values ​​of the performance index parameters of all operating faults in the conventional fault combination is taken as the lower threshold value of the performance index parameter; The lower threshold value and the upper threshold value of the performance indicator parameter form the evaluation range of the performance indicator parameter; The judgment criteria for the suspected fault conventional combination are: when the real-time data of the performance indicator parameters all belong to the evaluation range of the performance indicator parameters in the fault conventional combination, the fault conventional combination is regarded as the suspected fault conventional combination.

[0027] When the real-time data of the performance indicator parameters is determined, the common fault combinations can be preliminarily screened based on this data, thereby reducing the amount of data analysis for subsequent detailed analysis, because the operating faults in the common fault combinations will have maximum and minimum values ​​that affect the performance indicator parameters. Therefore, their overall situation is summarized to form an evaluation range of the performance indicator parameters corresponding to the common fault combinations. Here, the maximum value of the impact of each operating fault on the performance indicator parameters is not superimposed, because the acquisition environment is when there is an operating fault, and this is the actual environment, which must include various other operating faults that occur in parallel. Therefore, there is no need to superimpose, only the maximum value needs to be taken. For the minimum value, the corresponding minimum value can be taken. Then, the suspected common fault combinations can be preliminarily screened according to the formed standards.

[0028] Reference Figure 7 As shown, screening at least one suspected fault conventional combination to obtain a target fault conventional combination includes the following steps: Obtaining a fault degree range of the operation fault, dividing the fault degree range at equal intervals, and obtaining at least one identification point; Randomly matching at least one identification point to an operational fault in a conventional combination of suspected faults, each matching method forming a suspected allocation scheme; Under the condition of the suspected allocation scheme, the conditional value of the performance indicator parameter is calculated, and the conditional value of the performance indicator parameter is equal to the result of multiplying and accumulating the performance indicator parameter and the implicit coefficient of the operating fault and the identification point of the operating fault in the conventional combination of the suspected fault; Arrange the performance indicator parameters in ascending order according to their conditional values ​​to obtain a conditional sequence; Arrange the performance indicator parameters from small to large according to the real-time data of the performance indicator parameters to obtain a real-time sequence; If there is a condition sequence that is consistent with the real-time sequence, the suspected fault regular combination corresponding to the condition sequence is used as the target fault regular combination; The failure degree of the operating failure in the suspected allocation scheme for generating the regular combination of target failures is used as the real-time approximate failure degree of the operating failure.

[0029] Here, since the degree of the operation failure in the Internet is unknown, a suspected allocation scheme is formed for the suspected failure conventional combination, and multiple suspected allocation schemes form all possible combinations of the degree of the operation failure in the suspected failure conventional combination, because when the distance between the identification points is small enough, any value of the degree of the operation failure in the suspected failure conventional combination can be approximated by a suspected allocation scheme; After that, it is necessary to screen the suspected allocation schemes and the suspected fault conventional combinations. Since the implicit connection between the operating fault and the performance indicator parameters has been determined before, the value of each performance indicator parameter can be calculated and accumulated according to the fault degree of the operating fault and the implicit connection to obtain a conditional sequence. The sorting relationship of the performance indicator parameters calculated by the suspected allocation schemes and the suspected fault conventional combinations corresponding to the actual situation at this time must be consistent with the sorting relationship of at least one performance indicator parameter sorted by real-time data. Therefore, the required target fault conventional combination can be selected.

[0030] Reference Figure 8 As shown, based on big data, processing the operation faults in the conventional combination of target faults includes the following steps: Identify the urgency of the operation fault, and multiply the urgency of the operation fault by the real-time approximate fault severity of the operation fault to obtain the severity of the operation fault; According to the severity of the operating faults, the operating faults in the conventional combination of target faults are sorted from large to small to obtain an operating fault sequence; Based on big data, obtain the parameters of the benchmark processing scheme when the severity of the operation fault is a preset value, and the preset value is any value within the value range of the severity of the operation fault; The severity of the operating fault is divided by the preset value to obtain the target multiple; The processing parameters are set according to the target multiples of the benchmark processing scheme parameters for the operating faults in the target fault conventional combination.

[0031] When processing, it is necessary to allocate the processing order according to the severity of the operating failure, but the severity of the operating failure is not only related to the urgency of the operating failure, but also to the fault degree of the operating failure. The urgency of the operating failure is an assessment of the attributes of the operating failure, not an assessment of the severity of the failure. Taking two situations as examples, one is a very urgent failure, but the degree of its failure is very low, and the other is a non-urgent failure, but the degree of its failure is very serious. Therefore, it is necessary to set the corresponding algorithm to sort them, otherwise it is difficult to make an accurate judgment.

[0032] Reference Fig. 9 As shown, identifying the urgency of an operational failure includes the following steps: When the fault degree of the operation fault is 0, obtaining first sample data of the performance indicator parameter; When the fault degree of the operation fault is a preset value, obtaining second sample data of the performance indicator parameter; Based on the analytic hierarchy process, the weights of performance indicator parameters for Internet operation are obtained; Accumulate the first sample data and the second sample data of all performance indicator parameters to obtain a comprehensive evaluation value; According to the weight of the performance indicator parameter, the absolute value of the difference between the first sample data and the second sample data of the performance indicator parameter is accumulated to obtain a key coefficient; The critical coefficient is divided by the comprehensive evaluation value to obtain the urgency of the operating failure.

[0033] Furthermore, the present solution also proposes a storage medium on which a computer-readable program is stored, and when the computer-readable program is called, the above-mentioned Internet operation and maintenance method based on artificial intelligence algorithm optimization is executed.

[0034] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0035] In summary, the advantages of the present invention are: by mining the implicit connection between Internet operation failures and performance indicator parameters, performing correlation analysis on two operation failures, generating at least one fault routine combination, obtaining a target fault routine combination and processing the operation failure in the target fault routine combination, the fault routine combination can be generated, and then the fault combination can be initially screened in combination with pre-set standards. At the same time, through further screening, the target fault routine combination can be obtained, and the degree of the operation failure in the target fault routine combination can be determined, so that targeted maintenance parameters can be set. At the same time, the maintenance sequence can be set according to its severity, so that the operation and maintenance needs can be better met.

[0036] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An Internet operation and maintenance method based on artificial intelligence algorithm optimization, characterized in that: include: Using an intelligent terminal, real-time data of at least one performance indicator parameter of the Internet is collected in real time; Determine the data transmission method, configure the data transmission protocol, establish the data transmission channel, and perform automatic data collection and transmission; Obtain at least one operation fault in the Internet, and mine the implicit connection between the Internet operation fault and the performance indicator parameter; Based on the implicit connection, a correlation analysis is performed on the two operating faults, and based on the correlation of the two operating faults, at least one fault regular combination is generated; Form judgment criteria for conventional combinations of suspected faults; Obtaining at least one suspected fault conventional combination, which satisfies the judgment criteria that the performance indicator parameters meet the suspected fault conventional combination; Screening at least one suspected fault regular combination to obtain a target fault regular combination; Based on big data, operational faults in the regular combination of target faults are processed.

2. The Internet operation and maintenance method based on artificial intelligence algorithm optimization according to claim 1 is characterized in that: Determining the data transmission mode, configuring the data transmission protocol, establishing the data transmission channel, and performing automatic data collection and transmission specifically include: Wireless ZigBee technology is used for transmission between the Internet and smart terminals; The data collection software reads various data from the Internet in real time and converts them into a format for transmission; Configure the data trigger mechanism as a timed trigger. When the trigger conditions are met, the data acquisition software automatically collects data and sends it to the smart terminal.

3. The Internet operation and maintenance method based on artificial intelligence algorithm optimization according to claim 2 is characterized in that: The mining of the implicit connection between Internet operation failures and performance indicator parameters specifically includes: When an operation fault occurs, the performance indicator parameter that changes by more than a preset range will be used as the target performance indicator parameter, and the performance indicator parameter that changes by no more than a preset range will be used as the non-target performance indicator parameter. The preset range is the normal fluctuation range of the performance indicator parameter; There is an implicit connection between the target performance indicator parameters and the operation failure, but there is no implicit connection between the non-target performance indicator parameters and the operation failure; The time range of the operation fault is divided into equal intervals to obtain at least one time point, the time point is paired with the value of the non-target performance indicator parameter at the time point and fitted to obtain a preliminary function, and the average of all preliminary functions is taken to obtain a non-target function; Pairing and fitting the time points with the values ​​of the target performance indicator parameters at the time points to obtain the target function; The result of comparing the objective function with the non-objective function is integrated within the time range of the operation fault, and the implicit coefficient of the objective performance index parameter and the operation fault is obtained; The implicit coefficients of non-target performance index parameters and operational failures are set to 0; The non-target performance index parameters are combined with the target performance index parameters to obtain the implicit coefficients of the performance index parameters and the operation failure.

4. The Internet operation and maintenance method based on artificial intelligence algorithm optimization according to claim 3 is characterized in that: The correlation analysis of two operation failures based on implicit connection specifically includes: The two operation failures are recorded as a first operation failure and a second operation failure respectively; Subtract the implicit coefficient of the first operation fault and performance index parameter from the implicit coefficient of the second operation fault and performance index parameter and take the absolute value to obtain the actual gap; The actual gaps of all performance indicator parameters are accumulated to obtain the overall gap; Accumulating the implicit coefficients of the first operation fault and all performance index parameters and the implicit coefficients of the second operation fault and all performance index parameters to obtain an implicit sum; The overall gap is divided by the implicit sum, then subtracted from 1 and the absolute value is taken to obtain the correlation coefficient.

5. The Internet operation and maintenance method based on artificial intelligence algorithm optimization according to claim 4 is characterized in that: The generating at least one conventional fault combination based on the correlation between the two operating faults specifically includes: All possible combinations of all operating faults are taken as fault combinations to be verified; Select any operation fault in the fault combination to be verified as a characteristic operation fault; Based on big data, obtain the probability of occurrence of characteristic operation failures; Pairing the characteristic operation fault with the remaining operation faults in the fault combination to be verified to obtain at least one characteristic operation fault group; Divide the correlation between two operation faults in the characteristic operation fault group by the occurrence probability of the characteristic operation fault to obtain the independence probability; Multiply the occurrence probability by the independent probability of all characteristic operation fault groups to obtain the probability to be identified; The maximum value of the probability of occurrence of operating failures with a frequency lower than 1 in a year is used as the identification threshold; The fault combination to be verified whose probability of being identified exceeds the identification threshold is regarded as the normal fault combination.

6. The Internet operation and maintenance method based on artificial intelligence algorithm optimization according to claim 5 is characterized in that: The formation of a judgment standard for a conventional combination of suspected faults includes the following steps: Based on big data, the maximum value of the performance indicator parameter when there is an operation fault is obtained as the maximum eigenvalue, and the minimum value of the performance indicator parameter when there is an operation fault is obtained as the minimum eigenvalue; The maximum value of the maximum characteristic values ​​of the performance index parameters of all operating faults in the conventional fault combination is taken as the upper threshold value of the performance index parameter; The minimum value of the minimum characteristic values ​​of the performance index parameters of all operating faults in the conventional fault combination is taken as the lower threshold value of the performance index parameter; The lower threshold value and the upper threshold value of the performance indicator parameter form the evaluation range of the performance indicator parameter; The judgment criteria for the suspected fault conventional combination are: when the real-time data of the performance indicator parameters all belong to the evaluation range of the performance indicator parameters in the fault conventional combination, the fault conventional combination is regarded as the suspected fault conventional combination.

7. The Internet operation and maintenance method based on artificial intelligence algorithm optimization according to claim 6 is characterized in that: The screening of at least one suspected fault conventional combination to obtain a target fault conventional combination comprises the following steps: Obtaining a fault degree range of the operation fault, dividing the fault degree range at equal intervals, and obtaining at least one identification point; Randomly matching at least one identification point to an operational fault in a conventional combination of suspected faults, each matching method forming a suspected allocation scheme; Under the condition of the suspected allocation scheme, the conditional value of the performance indicator parameter is calculated, and the conditional value of the performance indicator parameter is equal to the result of multiplying and accumulating the performance indicator parameter and the implicit coefficient of the operating fault and the identification point of the operating fault in the conventional combination of the suspected fault; Arrange the performance indicator parameters in ascending order according to their conditional values ​​to obtain a conditional sequence; Arrange the performance indicator parameters from small to large according to the real-time data of the performance indicator parameters to obtain a real-time sequence; If there is a condition sequence that is consistent with the real-time sequence, the suspected fault regular combination corresponding to the condition sequence is used as the target fault regular combination; The failure degree of the operating failure in the suspected allocation scheme for generating the regular combination of target failures is used as the real-time approximate failure degree of the operating failure.

8. The Internet operation and maintenance method based on artificial intelligence algorithm optimization according to claim 7 is characterized in that: The processing of the operation failure in the conventional combination of target failures based on big data includes the following steps: Identify the urgency of the operation fault, and multiply the urgency of the operation fault by the real-time approximate fault severity of the operation fault to obtain the severity of the operation fault; According to the severity of the operating faults, the operating faults in the conventional combination of target faults are sorted from large to small to obtain an operating fault sequence; Based on big data, obtain the parameters of the benchmark processing scheme when the severity of the operation fault is a preset value, and the preset value is any value within the value range of the severity of the operation fault; The severity of the operating fault is divided by the preset value to obtain the target multiple; The processing parameters are set according to the target multiples of the benchmark processing scheme parameters for the operating faults in the target fault conventional combination.

9. The Internet operation and maintenance method based on artificial intelligence algorithm optimization according to claim 8 is characterized in that: The step of identifying the urgency of the operational failure comprises the following steps: When the fault degree of the operation fault is 0, obtaining first sample data of the performance indicator parameter; When the fault degree of the operation fault is a preset value, obtaining second sample data of the performance indicator parameter; Based on the analytic hierarchy process, the weights of performance indicator parameters for Internet operation are obtained; Accumulate the first sample data and the second sample data of all performance indicator parameters to obtain a comprehensive evaluation value; According to the weight of the performance indicator parameter, the absolute value of the difference between the first sample data and the second sample data of the performance indicator parameter is accumulated to obtain a key coefficient; The critical coefficient is divided by the comprehensive evaluation value to obtain the urgency of the operating failure.

Images