Information system operation and maintenance service system

Abstract

The invention discloses an information system operation and maintenance service system, which comprises a data acquisition module, a data processing module and an operation and maintenance module, relates to the technical field of information systems, and solves the technical problem that an information system maintenance system in the prior art is not high in stability and reliability in the operation process. The method comprises the steps of calculating a state evaluation coefficient of an information system based on operation data; inputting the state evaluation coefficient of the latest period into a state coefficient prediction model to obtain a state evaluation coefficient prediction value; determining a risk level of the information system based on the state evaluation coefficient prediction value; and taking corresponding maintenance measures for the information system based on the risk level. According to the method, the state evaluation coefficient of the information system is calculated by substituting the average response duration, the response timeout times and the virus identification times into the formula, so that the state evaluation coefficient can accurately reflect the actual operation condition of the information system, and the stability and the reliability of the information system in the operation process are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of information systems, and in particular is an information system operation and maintenance service system. Background Art

[0002] With the continuous advancement of information technology, information systems have become an indispensable part of modern enterprise and organizational operations. However, the stability and reliability issues of information systems have become increasingly prominent, bringing huge challenges to operation and maintenance. Traditional manual operation and maintenance methods are not only inefficient, but also difficult to ensure the continuous and stable operation of the system. Therefore, developing a stable and reliable maintenance information system is of great significance to improving the efficiency of information system operation and maintenance and ensuring business continuity.

[0003] The existing technology continuously monitors the performance data changes of the information system during operation, and checks the information system when an abnormality is identified in the performance data; however, the solution of the existing technology requires that maintenance and processing can only be performed when an abnormality has occurred in the information system, and it is difficult to predict the operation risk of the information system in advance, so that the maintenance of the information system is not timely enough, resulting in low stability and reliability of the information system during operation.

[0004] The present invention proposes an information system operation and maintenance service system to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an information system operation and maintenance service system, which is used to solve the technical problem that the solutions in the prior art require maintenance processing to be performed only when an abnormality has occurred in the information system, making it difficult to predict the operation risks of the information system in advance, resulting in insufficient maintenance of the information system, thereby causing the stability and reliability of the information system to be low during operation.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides an information system operation and maintenance service system, comprising: a data processing module, and a data acquisition module and an operation and maintenance module connected thereto;

[0007] The data collection module is used to collect the operation information of the information system in several consecutive cycles; pre-process the operation information to obtain operation data; wherein the operation data includes the system response time and the virus identification time;

[0008] The data processing module is used to calculate the state evaluation coefficient of the information system based on the operation data; input the state evaluation coefficient of the latest period into the state coefficient prediction model to obtain the predicted value of the state evaluation coefficient; wherein the state coefficient prediction model is constructed based on the artificial intelligence model;

[0009] The operation and maintenance module is used to determine the risk level of the information system based on the predicted value of the status assessment coefficient; and take corresponding maintenance measures for the information system based on the risk level; wherein the risk level includes low risk, medium risk and high risk.

[0010] Preferably, the information system operation and maintenance service system further includes a display module, and the display module is used to display the operation data of the information system in real time.

[0011] Preferably, the preprocessing of the operation information includes:

[0012] A1: Extract the operation information of several consecutive cycles;

[0013] A2: Eliminate abnormal data in the operation information;

[0014] A3: Fill in the missing data in the operation information;

[0015] A4: Mark the pre-processed operation information as operation data.

[0016] Preferably, the calculating of the status assessment coefficient of the information system based on the operation data includes:

[0017] B1: Extract the system response time and virus identification time from the operation data of several consecutive cycles;

[0018] B2: Calculate the average response time based on the system response time of several consecutive cycles, count the number of times the system response time is longer than the preset response threshold and mark it as the number of response timeouts;

[0019] B3: Through the formula ZPX = a × ln (1 + PSC) + b × e XCS +c×BSY calculates the state assessment coefficient ZPX; where PSC is the average response time, XCS is the number of response timeouts, and BSY is the time taken for virus identification; a, b, and c are all proportional coefficients greater than 0; e is a natural constant, and ln() is a logarithmic function with the natural constant as the base.

[0020] The present invention obtains the system response time and the virus identification time, and calculates the average response time and the number of response timeouts according to the system response time, and substitutes the average response time, the number of response timeouts and the virus identification time into a formula to calculate the state assessment coefficient of the information system without dimensioning, so that the calculated state assessment coefficient can accurately reflect the actual operation of the information system, facilitates the subsequent determination of the risk level of the information system according to the state assessment coefficient, and maintains the information system according to the risk level, which is beneficial to improving the stability and reliability of the information system during operation.

[0021] Preferably, the method for obtaining the proportional coefficient a includes:

[0022] Obtain the number of requests for each request data type in the information system in several consecutive cycles; calculate the proportional coefficient a by the formula a=0.04×CSL+0.06×XGL; wherein the request data type includes query type and modification type; CSL is the number of requests for the query type, and XGL is the number of requests for the modification type.

[0023] Preferably, the method for obtaining the proportional coefficient c includes:

[0024] Obtain the number of virus infections of the information system in a number of consecutive cycles; obtain the infection number function f(x) through linear fitting based on the number of virus infections in a number of consecutive cycles;

[0025] By formula Calculate the proportionality coefficient c, where t represents time and M represents the duration corresponding to a number of consecutive cycles.

[0026] Preferably, the number of virus infections based on several consecutive cycles is linearly fitted, including:

[0027] The number of virus infections in several consecutive cycles was extracted, with time as the independent variable and the number of virus infections as the dependent variable, and the infection number function was obtained through linear fitting.

[0028] Preferably, the state coefficient prediction model is constructed based on an artificial intelligence model, including:

[0029] Extract state assessment coefficients of several consecutive periods and integrate them into several groups of training data and test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model according to the test results; finally obtain a state coefficient prediction model whose input is the state assessment coefficients of the most recent several consecutive periods and whose output is the state assessment coefficient of the prediction period; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0030] The present invention extracts state assessment coefficients of several consecutive periods for training an artificial intelligence model, and marks the trained artificial intelligence model as a state coefficient prediction model. By inputting the state assessment coefficients of several consecutive periods into the state coefficient prediction model, the state assessment coefficient of the prediction period is obtained, so that the operation and maintenance system can analyze the operation status of the information system in advance and take corresponding maintenance measures, which is beneficial to improving the stability and reliability of the information system operation.

[0031] Preferably, the step of determining the risk level of the information system based on the predicted value of the status assessment coefficient includes:

[0032] P1: Extract the predicted value of the status assessment coefficient of the information system;

[0033] P2: Set the status evaluation range threshold [ZPY1, ZPY2], and 0 <ZPY1<ZPY2;

[0034] P3: Determine whether the predicted value of the state assessment coefficient is within the state assessment range threshold [ZPY1, ZPY2]; if yes, mark the risk level as medium risk; if no, jump to P4;

[0035] P4: Determine whether the predicted value of the state assessment coefficient is greater than the maximum value ZPY2 of the state assessment range threshold; if yes, mark the risk level as high risk; if no, mark the risk level as low risk.

[0036] Preferably, taking corresponding maintenance measures on the information system based on the risk level includes:

[0037] Extract the risk level of the information system; determine whether the risk level is low risk; if yes, continue to monitor the information system; if not, adaptively adjust the monitoring frequency of the operation and maintenance module.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. The present invention aims to optimize the status assessment of the information system, and further calculates the average response time and the number of response timeouts by accurately obtaining the system response time and the virus identification time; these data are dedimensionalized and then input into a specific formula to calculate the status assessment coefficient of the information system; so that the status assessment coefficient can accurately reflect the actual operating status of the system, provide a scientific basis for the subsequent risk level classification, and thus carry out targeted system maintenance; this method not only improves the accuracy of risk assessment, but also promotes the improvement of the stability and reliability of the information system during operation, ensures timely and effective performance monitoring and the implementation of security protection measures, and helps to build a more robust information environment.

[0040] 2. The present invention extracts state assessment coefficients of several consecutive periods for training artificial intelligence models, and marks the trained artificial intelligence models as state coefficient prediction models. By inputting state assessment coefficients of several consecutive periods into the state coefficient prediction model, the state assessment coefficients of the prediction period are obtained, so that the operation and maintenance system can analyze the operation status of the information system in advance and take corresponding maintenance measures, which is beneficial to improving the stability and reliability of the information system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] 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 work.

[0042] Figure 1 It is an overall flow chart of the information system operation and maintenance system of the present invention;

[0043] Figure 2 It is a schematic diagram of the principle of the information system operation and maintenance system of the present invention. DETAILED DESCRIPTION

[0044] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0045] See also Figure 1-Figure 2 , the first aspect of the present invention provides an information system operation and maintenance service system, including: a data processing module, and a data acquisition module and an operation and maintenance module connected thereto;

[0046] Data collection module: used to collect the operation information of the information system in several continuous cycles; pre-process the operation information to obtain operation data; wherein the operation data includes the system response time and the virus identification time;

[0047] Data processing module: used to calculate the status assessment coefficient of the information system based on the operating data; input the status assessment coefficient of the latest period into the status coefficient prediction model to obtain the status assessment coefficient prediction value; wherein the status coefficient prediction model is constructed based on the artificial intelligence model;

[0048] Operation and maintenance module: used to determine the risk level of the information system based on the predicted value of the status assessment coefficient; take corresponding maintenance measures for the information system based on the risk level; among which, the risk level includes low risk, medium risk and high risk.

[0049] In this embodiment, an information system operation and maintenance service system further includes a display module, and the display module is used to display the operation data of the information system in real time.

[0050] In this embodiment, the operation information is preprocessed, including:

[0051] A1: Extract the operation information of several consecutive cycles;

[0052] A2: Eliminate abnormal data in the operation information;

[0053] A3: Fill in the missing data in the operation information;

[0054] A4: Mark the pre-processed operation information as operation data.

[0055] Exemplarily, abnormal data in the operation information include data that are obviously unreasonable, such as the system response time and virus identification time, for example: the system response time is a negative number, the system response time is greater than 1 minute, the virus identification time is a negative number, the virus identification time is greater than 1 hour, etc.; for missing data in the operation information, the corresponding missing data is filled by calculating the average value of the system response time or the virus identification time.

[0056] In this embodiment, the state evaluation coefficient of the information system is calculated based on the operation data, including:

[0057] B1: Extract the system response time and virus identification time from the operation data of several consecutive cycles;

[0058] B2: Calculate the average response time based on the system response time of several consecutive cycles, count the number of times the system response time is longer than the preset response threshold and mark it as the number of response timeouts;

[0059] B3: Through the formula ZPX = a × ln (1 + PSC) + b × e XCS +c×BSY calculates the state assessment coefficient ZPX; where PSC is the average response time, XCS is the number of response timeouts, and BSY is the time taken for virus identification; a, b, and c are all proportional coefficients greater than 0; e is a natural constant, and ln() is a logarithmic function with the natural constant as the base.

[0060] The present invention obtains the system response time and the virus identification time, and calculates the average response time and the number of response timeouts according to the system response time, and substitutes the average response time, the number of response timeouts and the virus identification time into a formula to calculate the state assessment coefficient of the information system without dimensioning, so that the calculated state assessment coefficient can accurately reflect the actual operation of the information system, facilitates the subsequent determination of the risk level of the information system according to the state assessment coefficient, and maintains the information system according to the risk level, which is beneficial to improving the stability and reliability of the information system during operation.

[0061] Exemplarily, the proportional coefficients a=22.04, b=0.8, c=1.79 are set; the average response time PSC=60ms, the number of response timeouts XCS=5, and the virus identification time BSY=33min are set; and the information system status assessment coefficient ZPX=268.40 is calculated by the formula.

[0062] In this embodiment, the method for obtaining the proportional coefficient a includes:

[0063] Obtain the number of requests for each request data type in the information system in several consecutive cycles; calculate the proportional coefficient a by the formula a=0.04×CSL+0.06×XGL; wherein the request data type includes query type and modification type; CSL is the number of requests for the query type, and XGL is the number of requests for the modification type.

[0064] Exemplarily, the number of query type requests CSL=347 and the number of modification type requests XGL=136 are set; the proportional coefficient a=22.04 is calculated by the formula.

[0065] In this embodiment, the method for obtaining the proportionality coefficient c includes:

[0066] Obtain the number of virus infections of the information system in a number of consecutive cycles; obtain the infection number function f(x) through linear fitting based on the number of virus infections in a number of consecutive cycles;

[0067] By formula Calculate the proportionality coefficient c, where t represents time and M represents the duration corresponding to a number of consecutive cycles.

[0068] For example, the duration M corresponding to several consecutive periods is set to 36 hours, and the cumulative number of virus infections in the information system in several consecutive periods is The proportionality coefficient c≈1.79 is calculated by the formula.

[0069] In this embodiment, the number of virus infections based on several consecutive cycles is linearly fitted, including:

[0070] The number of virus infections in several consecutive cycles was extracted, with time as the independent variable and the number of virus infections as the dependent variable, and the infection number function was obtained through linear fitting.

[0071] In this embodiment, the state coefficient prediction model is constructed based on an artificial intelligence model, including:

[0072] Extract state assessment coefficients of several consecutive periods and integrate them into several groups of original data, use 80% of the original data as training data and 20% as test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model according to the test results; finally obtain a state coefficient prediction model whose input is the state assessment coefficients of the most recent several consecutive periods and whose output is the state assessment coefficient of the prediction period; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0073] The present invention extracts state assessment coefficients of several consecutive periods for training an artificial intelligence model, and marks the trained artificial intelligence model as a state coefficient prediction model. By inputting the state assessment coefficients of several consecutive periods into the state coefficient prediction model, the state assessment coefficient of the prediction period is obtained, so that the operation and maintenance system can analyze the operation status of the information system in advance and take corresponding maintenance measures, which is beneficial to improving the stability and reliability of the information system operation.

[0074] In this embodiment, determining the risk level of the information system based on the predicted value of the state assessment coefficient includes:

[0075] P1: Extract the predicted value of the status assessment coefficient of the information system;

[0076] P2: Set the status evaluation range threshold [ZPY1, ZPY2], and 0 <ZPY1<ZPY2;

[0077] P3: Determine whether the predicted value of the state assessment coefficient is within the state assessment range threshold [ZPY1, ZPY2]; if yes, mark the risk level as medium risk; if no, jump to P4;

[0078] P4: Determine whether the predicted value of the state assessment coefficient is greater than the maximum value ZPY2 of the state assessment range threshold; if yes, mark the risk level as high risk; if no, mark the risk level as low risk.

[0079] Exemplarily, the information system's state assessment coefficient prediction value ZPX predicted is set to 274, and the state assessment range threshold [ZPY1, ZPY2] to [250, 280]. Since the state assessment coefficient prediction value ZPX predicted is within the state assessment range threshold [250, 280], the risk level is marked as medium risk.

[0080] In this embodiment, corresponding maintenance measures are taken for the information system based on the risk level, including:

[0081] Extract the risk level of the information system; determine whether the risk level is low risk; if yes, continue to monitor the information system; if not, adaptively adjust the monitoring frequency of the operation and maintenance module.

[0082] Exemplarily, the risk level of the information system is set to medium risk; because the risk level is not low risk, the monitoring frequency of the operation and maintenance module is adaptively adjusted.

[0083] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0084] Working principle of the present invention:

[0085] The present invention collects the operation information of the information system in several continuous cycles; pre-processes the operation information to obtain operation data; calculates the state assessment coefficient of the information system based on the operation data; inputs the state assessment coefficient of the most recent cycle into a state coefficient prediction model to obtain a state assessment coefficient prediction value; determines the risk level of the information system based on the state assessment coefficient prediction value; and takes corresponding maintenance measures for the information system based on the risk level.

[0086] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An information system operation and maintenance service system, comprising: The data processing module, and the data acquisition module and operation and maintenance module connected thereto are characterized in that: The data collection module is used to collect the operation information of the information system in several consecutive cycles; pre-process the operation information to obtain operation data; wherein the operation data includes the system response time and the virus identification time; The data processing module is used to calculate the state evaluation coefficient of the information system based on the operation data; input the state evaluation coefficient of the latest period into the state coefficient prediction model to obtain the predicted value of the state evaluation coefficient; wherein the state coefficient prediction model is constructed based on the artificial intelligence model; The operation and maintenance module is used to determine the risk level of the information system based on the predicted value of the status assessment coefficient; and take corresponding maintenance measures for the information system based on the risk level; wherein the risk level includes low risk, medium risk and high risk.

2. The information system operation and maintenance service system according to claim 1, characterized in that: It also includes a display module, which is used to display the operating data of the information system in real time.

3. The information system operation and maintenance service system according to claim 1, characterized in that: The preprocessing of the operation information includes: A1: Extract the operation information of several consecutive cycles; A2: Eliminate abnormal data in the operation information; A3: Fill in the missing data in the operation information; A4: Mark the pre-processed operation information as operation data.

4. The information system operation and maintenance service system according to claim 1, characterized in that: The step of calculating the status assessment coefficient of the information system based on the operation data includes: B1: Extract the system response time, virus identification time and virus identification accuracy from the operation data of several consecutive cycles; B2: Calculate the average response time based on the system response time of several consecutive cycles, count the number of times the system response time is longer than the preset response threshold and mark it as the number of response timeouts; B3: Through the formula ZPX = a × ln (1 + PSC) + b × e XCS +c×BSY calculates the state assessment coefficient ZPX; where PSC is the average response time, XCS is the number of response timeouts, and BSY is the time taken for virus identification; a, b, and c are all proportional coefficients greater than 0; e is a natural constant, and ln() is a logarithmic function with the natural constant as the base.

5. The information system operation and maintenance service system according to claim 4, characterized in that: The method for obtaining the proportional coefficient a includes: Obtain the number of requests for each request data type in the information system in several consecutive cycles; calculate the proportional coefficient a by the formula a=0.04×CSL+0.06×XGL; wherein the request data type includes query type and modification type; CSL is the number of requests for the query type, and XGL is the number of requests for the modification type.

6. The information system operation and maintenance service system according to claim 4, characterized in that: The method for obtaining the proportional coefficient c includes: Obtain the number of virus infections of the information system in a number of consecutive cycles; obtain the infection number function f(x) through linear fitting based on the number of virus infections in a number of consecutive cycles; By formula Calculate the proportionality coefficient c, where t represents time and M represents the duration corresponding to a number of consecutive cycles.

7. An information system operation and maintenance service system according to claim 6, characterized in that: The number of virus infections based on several consecutive cycles is linearly fitted, including: The number of virus infections in several consecutive cycles was extracted, with time as the independent variable and the number of virus infections as the dependent variable, and the infection number function was obtained through linear fitting.

8. The information system operation and maintenance service system according to claim 1, characterized in that: The state coefficient prediction model is constructed based on an artificial intelligence model, including: Extract state assessment coefficients of several consecutive periods and integrate them into several groups of training data and test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model according to the test results; finally obtain a state coefficient prediction model whose input is the state assessment coefficients of the most recent several consecutive periods and whose output is the state assessment coefficient of the prediction period; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

9. The information system operation and maintenance service system according to claim 1, characterized in that: The step of determining the risk level of the information system based on the predicted value of the status assessment coefficient includes: P1: Extract the predicted value of the status assessment coefficient of the information system; P2: Set the status evaluation range threshold [ZPY1, ZPY2], and 0 <ZPY1<ZPY2; P3: Determine whether the predicted value of the state assessment coefficient is within the state assessment range threshold [ZPY1, ZPY2]; if yes, mark the risk level as medium risk; if no, jump to P4; P4: Determine whether the predicted value of the state assessment coefficient is greater than the maximum value ZPY2 of the state assessment range threshold; if yes, mark the risk level as high risk; if no, mark the risk level as low risk.

10. The information system operation and maintenance service system according to claim 1, characterized in that: The corresponding maintenance measures for the information system based on the risk level include: Extract the risk level of the information system; determine whether the risk level is low risk; if yes, continue to monitor the information system; if not, adaptively adjust the monitoring frequency of the operation and maintenance module.

Images