Comprehensive transformation method based on autonomy of information system

Abstract

The invention discloses a comprehensive transformation method based on autonomy of an information system, and relates to the technical field of comprehensive transformation of the information system. The method comprises the following steps: integrating a replacement program into an information system for testing, and extracting running data of the replacement program in a running log of the information system; processing the operation data to obtain an operation data standard value and an operation data weight, and constructing a compatibility risk prediction model; calculating a compatibility risk coefficient between the replacement program and the information system through the compatibility risk prediction model, and judging whether the replacement program is compatible with the information system or not according to the compatibility risk coefficient; if the judgment result is that the replacement program is compatible with the information system, fixing the replacement program in the information system for use; if the judgment result is that the replacement program is incompatible with the information system, key testing is conducted on the replacement program. According to the method, by quantitatively evaluating the compatibility risk coefficient, the cost loss caused by program deployment failure is reduced, and the information system integration efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of comprehensive transformation of information systems, and in particular to a comprehensive transformation method based on the autonomy of information systems. Background Art

[0002] When integrating domestic technology into existing information systems, compatibility issues often occur, which may lead to system performance degradation, data loss, or even system crashes. In order to ensure the smooth integration of domestic technology and guarantee the stable operation of information systems, compatibility testing has become an indispensable link. Summary of the invention

[0003] The purpose of the present invention is to provide a comprehensive transformation method based on information system autonomy to solve the problems raised in the prior art.

[0004] To achieve the above object, the present invention provides the following technical solution: a comprehensive transformation method based on information system autonomy, the method comprising:

[0005] S1. Select a running program as a replacement program, integrate the replacement program into the information system for testing, obtain the operation log of the information system, and extract the operation data of the replacement program in the operation log;

[0006] S2. Process the operation data to obtain the standard value of the operation data and the weight of the operation data, and use the standard value of the operation data and the weight of the operation data to build a compatibility risk prediction model;

[0007] S3. Calculate the compatibility risk coefficient between the replacement program and the information system through the compatibility risk prediction model, and determine whether the replacement program is compatible with the information system according to the compatibility risk coefficient;

[0008] S4. If the judgment result of step S3 is that the replacement program is compatible with the information system, the replacement program is fixed in the information system for use; if the judgment result of step S3 is that the replacement program is incompatible with the information system, the replacement program is intensively tested.

[0009] According to the above technical solution, in step S1, it also includes:

[0010] Step S101: select a running program as a replacement program, the replacement program meets the functional requirements of the information system, and integrate the replacement program into the information system;

[0011] Step S102: After the replacement program is integrated into the information system, the information system will continue to run, and the operation log of the information system is obtained;

[0012] Step S103: extracting the operation data of the replacement program in the operation log, wherein the operation data includes the number of failures, the amount of data loss, and the number of security events.

[0013] 8. According to the above technical solution, the standard values ​​of the operating data include the standard values ​​of the number of failures, the standard values ​​of the amount of data loss and the standard values ​​of the number of security events;

[0014] Extracting operation data from the operation log of the information system, obtaining the operation time of the replacement program on the information system, dividing the operation time into n consecutive time periods t, and counting the operation data within the n time periods;

[0015] The process of calculating the standard value of the number of failures is as follows:

[0016] Obtain the number of failures of the replacement program in each time period, and form a failure number set A = {F1, F2, F3, ... F n}, where F1, F2, F3, ... F n The number of failures of the replacement program in the first time period, the number of failures of the replacement program in the second time period, the number of failures of the replacement program in the third time period, ... the number of failures of the replacement program in the nth time period are represented in sequence, and the average number of failures of the replacement program in the n time periods is calculated and marked as the number of failures F;

[0017] The maximum value F in the failure number set n Marked as the maximum number of failures F max ; Set the minimum value F in the failure number set n Marked as the maximum number of failures F min ;

[0018] The normalized processing formula for the number of failures is:

[0019]

[0020] Among them, F * is the standard value of the number of failures, F is the number of failures, and F max is the maximum number of failures, F min is the minimum number of failures;

[0021] The process of calculating the standard value of data loss is as follows:

[0022] Obtain the amount of data lost by the replacement program in each time period to form a data loss amount set B = {D1, D2, D3, ... D n}, where D1, D2, D3, ... D nThe data lost by the replacement program in the first time period, the data lost by the replacement program in the second time period, the data lost by the replacement program in the third time period, and so on, are represented in sequence. The average value of the data lost by the replacement program in the n time periods is calculated and marked as the data loss amount D.

[0023] The maximum value D in the data loss amount set n Marked as the maximum data loss amount D max ; The minimum value D in the data loss amount set n Marked as the maximum data loss amount D min ;

[0024] The normalization formula for the data loss amount is:

[0025]

[0026] Among them, D * is the standard value of data loss, D is the amount of data loss, D max is the maximum value of data loss, D min is the minimum value of data loss;

[0027] The process of calculating the standard value of the number of security events is as follows:

[0028] Obtain the number of security events that occurred in the replacement program in each time period, and form a security event number set C = {S1, S2, S3, ... S n}, where S1, S2, S3, ... S n The number of security incidents that occurred in the replacement program in the first time period, the number of security incidents that occurred in the replacement program in the second time period, the number of security incidents that occurred in the replacement program in the third time period, ... the number of security incidents that occurred in the replacement program in the nth time period are represented in sequence. The average number of security incidents that occurred in the replacement program in the n time periods is calculated and marked as the data loss amount S;

[0029] The maximum value S in the security event count set n The maximum number of security events marked as S max ; Set the minimum value S in the security event count set n The maximum number of security events marked as S min ;

[0030] The normalization formula for the number of security events is:

[0031]

[0032] Among them, S *is the standard value of the number of security events, S is the number of security events, S max is the maximum number of security events, S min The minimum number of security events.

[0033] In the above technical solution, the operating data is calculated by a normalization formula to obtain the operating data standard value, and the original operating data is adjusted by the maximum and minimum values ​​of the data, thereby eliminating the influence of different dimensions.

[0034] 9. According to the above technical solution, the operation data weight includes the weight of the number of failures, the weight of the amount of data loss and the weight of the number of security events;

[0035] The process of training the random forest model with standard values ​​of running data is as follows:

[0036] Obtaining the standard value of the running data to form a data set, dividing it into a training set and a test set, selecting random forest parameters, initializing a random forest model using the selected random forest parameters, training the random forest model using the training set, and testing the accuracy of the random forest model using the test set;

[0037] After the random forest model training is completed, the random forest model outputs the important values ​​of the number of failures, the important values ​​of the amount of data loss, and the important values ​​of the number of security events;

[0038] The process of calculating the failure number weight is as follows:

[0039] Extract the important value of the number of failures output by the random forest model and mark it as the important value of the number of failures P F The random forest model outputs the important value of data loss as the important value of fault loss P D The random forest model outputs the important value of the number of security events as the important value of the number of security events P S ;

[0040] The calculation formula of the failure number weight is:

[0041]

[0042] Among them, Q F is the failure number weight, P F is the important value of the number of failures, P D is the important value of the data loss, P S is the important value of the number of security events;

[0043] The calculation formula of the data loss weight is:

[0044]

[0045] Among them, Q D is the weight of data loss, P F is the important value of the number of failures, P D is the important value of the data loss, P S is the important value of the number of security events;

[0046] The calculation formula for the weight of the number of security events is:

[0047]

[0048] Among them, Q S is the weight of the number of security events, P F is the important value of the number of failures, P D is the important value of the data loss, P S is the important value of the number of security events.

[0049] In the above technical solution, the random forest model is trained by the standard value of the operating data to quantify the relative importance of the number of failures, the amount of data loss and the number of security incidents in the compatibility between the replacement program and the information system.

[0050] 10. According to the above technical solution, the construction process of the compatibility risk prediction model is as follows:

[0051] Obtaining the standard value of the number of failures, the standard value of the amount of data loss, the standard value of the number of security events, and the weight of the number of failures, the weight of the amount of data loss, and the weight of the number of security events;

[0052] The failure number weighted item is calculated according to the failure number standard value and the failure number weight, and the calculation formula is:

[0053] W F =F * *Q F ;

[0054] Among them, W F is the weighted term of the number of failures, F* is the standard value of the number of failures, Q F is the weight of the number of failures;

[0055] The data loss weighted item is calculated according to the data loss standard value and the data loss weight, and the calculation formula is:

[0056] W D =D * *Q D ;

[0057] Among them, W Dis the weighted term of the data loss amount, D* is the standard value of the data loss amount, Q D is the weight of the data loss amount;

[0058] The weighted item of the number of security events is calculated according to the standard value of the number of security events and the weight of the number of security events, and the calculation formula is:

[0059] W S =S * *Q S ;

[0060] Among them, W S is the weighted item of the number of security events, S* is the standard value of the security event occurrence rate, Q S is the weight of the safety incident incidence rate;

[0061] The compatibility risk prediction model is:

[0062] N=W F +W D +W S ;

[0063] Wherein, N is the compatibility risk coefficient, W F is the weighted term of the number of failures, W D is the weighted term for the data loss amount, W S A weighted item for the number of security events.

[0064] In the above technical solution, the compatibility risk coefficient is obtained by weighted summing up the standard values ​​of the operating data, so as to quantify the compatibility risk level and more intuitively reflect the compatibility of the replacement program and the information system.

[0065] According to the above technical solution, in step S3, it specifically includes:

[0066] The compatibility risk threshold is set to N*, and the compatibility risk coefficient N is calculated according to the compatibility risk prediction model. If N>N*, it is determined that the replacement program is incompatible with the information system; if N<N*, it is determined that the replacement program is compatible with the information system.

[0067] According to the above technical solution, in step S4, the specific process of focusing on testing the replacement program is as follows:

[0068] Step S401: Obtain the failure number weighted item W F , the data loss weighted term W D and the weighted term W of the number of security events S , and the failure number weighted term W F , the data loss weighted term W Dand the weighted term W of the number of security events S Sort by size, and perform key tests on the replacement program according to the sorting results. The key tests include fault simulation test, data transmission stability test, and security vulnerability scanning test.

[0069] Step S402: If the failure number weighted item W F If the data loss weighted item W is ranked first, the fault simulation test is performed, and various faults are introduced when the replacement program is running using an automated tool to evaluate the system's fault recovery capability, fault tolerance and stability. D If the first one is ranked, the data transmission stability test is performed, and the packet loss rate is tested using an automated tool when the replacement program is running to ensure the integrity and security of the data during transmission, storage and processing; if the weighted item W of the number of security events is S If it ranks first, the security vulnerability scanning test is performed, using an automatic vulnerability scanning tool to check whether there are known security vulnerabilities when the replacement program is running, so as to evaluate the system's security protection capabilities and ability to cope with potential security threats;

[0070] Step S403: If the key test passes, it is determined that the replacement program is compatible with the information system; if the key test fails, it is determined that the replacement program is incompatible with the information system.

[0071] Compared with the prior art, the beneficial effects of the present invention are as follows: by introducing a quantitative evaluation method for compatibility risk coefficients, the present invention achieves accurate prediction and timely discovery of potential compatibility issues during system integration, thereby fundamentally reducing cost losses caused by system integration failures and greatly improving the efficiency and quality of information system integration. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0073] Figure 1 The present invention is a flow chart of a comprehensive transformation method based on information system autonomy. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0075] See also Figure 1 The present invention provides a comprehensive transformation method based on information system autonomy, the method comprising: selecting a certain running program as a replacement program, the replacement program meets the functional requirements of the information system, and integrating the replacement program into the information system; after the replacement program is integrated into the information system, the information system will continue to run, and at the same time obtain the operation log of the information system; extracting the operation data of the replacement program in the operation log, the operation data including the number of failures, the amount of data loss, and the number of security events.

[0076] Process the operation data to obtain the standard value and weight of the operation data, and use the standard value and weight of the operation data to build a compatibility risk prediction model;

[0077] The standard values ​​of operation data include standard values ​​of the number of failures, standard values ​​of data loss, and standard values ​​of the number of safety events;

[0078] Extracting operation data from the operation log of the information system, obtaining the operation time of the replacement program on the information system, dividing the operation time into n consecutive time periods t, and counting the operation data in the n time periods;

[0079] The process of calculating the standard value of the number of failures is as follows:

[0080] Obtain the number of failures of the replacement program in each time period, and form a failure number set A = {F1, F2, F3, ... F n}, where F1, F2, F3, ... F n The number of failures of the replacement program in the first time period, the number of failures of the replacement program in the second time period, the number of failures of the replacement program in the third time period, ... the number of failures of the replacement program in the nth time period are represented in sequence, and the average number of failures of the replacement program in the n time periods is calculated and marked as the number of failures F;

[0081] The maximum value F in the failure number set n Marked as the maximum number of failures F max ; Set the minimum value F in the failure number set n Marked as the maximum number of failures F min ;

[0082] The normalized processing formula for the number of failures is:

[0083]

[0084] Among them, F * is the standard value of the number of failures, F is the number of failures, and F max is the maximum number of failures, F minis the minimum number of failures;

[0085] For example, extract the operation data within 120 seconds from the operation log of the information system, divide the 120 seconds operation time into 6 consecutive time periods at a time interval of 20 seconds, and count the operation data within the 6 time periods;

[0086] The number of times the replacement program fails in the running data in the six time periods is extracted, which are 0, 2, 1, 1, 0, and 2 respectively. The number of failures F of the replacement program in the six time periods is calculated as:

[0087]

[0088] The maximum number of failures in the replacement program within the 6 time periods is marked as the maximum number of failures F max The minimum number of failures in the replacement program within 2 and 6 time periods is marked as the minimum number of failures F. min is 0;

[0089] The standard value of the number of failures is:

[0090]

[0091] The process of calculating the standard value of data loss is as follows:

[0092] Obtain the amount of data lost by the replacement program in each time period to form a data loss amount set B = {D1, D2, D3, ... D n}, where D1, D2, D3, ... D n The data lost by the replacement program in the first time period, the data lost by the replacement program in the second time period, the data lost by the replacement program in the third time period, and so on, are represented in sequence. The average value of the data lost by the replacement program in the n time periods is calculated and marked as the data loss amount D.

[0093] The maximum value D in the data loss amount set n Marked as the maximum data loss amount D max ; The minimum value D in the data loss amount set n Marked as the maximum data loss amount D min ;

[0094] The normalization formula for the data loss amount is:

[0095]

[0096] Among them, D * is the standard value of data loss, D is the amount of data loss, D maxis the maximum value of data loss, D min is the minimum value of data loss;

[0097] The process of calculating the standard value of the number of security events is as follows:

[0098] Obtain the number of security events that occurred in the replacement program in each time period, and form a security event number set C = {S1, S2, S3, ... S n}, where S1, S2, S3, ... S n The number of security incidents that occurred in the replacement program in the first time period, the number of security incidents that occurred in the replacement program in the second time period, the number of security incidents that occurred in the replacement program in the third time period, ... the number of security incidents that occurred in the replacement program in the nth time period are represented in sequence. The average number of security incidents that occurred in the replacement program in the n time periods is calculated and marked as the data loss amount S;

[0099] The maximum value S in the security event count set n The maximum number of security events marked as S max ; Set the minimum value S in the security event count set n The maximum number of security events marked as S min ;

[0100] The normalization formula for the number of security events is:

[0101]

[0102] Among them, S * is the standard value of the number of security events, S is the number of security events, S max is the maximum number of security events, S min The minimum number of security events.

[0103] The operation data weights include the failure number weights, data loss amount weights and security event number weights;

[0104] The process of training the random forest model with standard values ​​of running data is as follows:

[0105] Obtaining the standard value of the running data to form a data set, dividing it into a training set and a test set, selecting random forest parameters, initializing a random forest model using the selected random forest parameters, training the random forest model using the training set, and testing the accuracy of the random forest model using the test set;

[0106] After the random forest model training is completed, the random forest model outputs the important values ​​of the number of failures, the important values ​​of the amount of data loss, and the important values ​​of the number of security events;

[0107] For example, the standard value of the operating data is obtained to form a data set I = {F * , D * , S *}, where F * , D * , S * The standard values ​​of the number of failures, the standard values ​​of the amount of data loss, and the standard values ​​of the number of security events are represented in turn. 70% of the data set is used as the training set, and 30% of the data set is used as the test set.

[0108] Select the random forest parameters as follows:

[0109] n_estimators = 100;

[0110] max_depth=None;

[0111] min_samples_split = 5;

[0112] random_state = 42;

[0113] The random forest model is initialized using the selected random forest parameters, trained using the training set, and tested using the test set; the importance value of the number of failures output by the random forest model is 0.5, the importance value of the amount of data loss is 0.3, and the importance value of the number of security events is 0.2;

[0114] The process of calculating the failure number weight is as follows:

[0115] Extract the important value of the number of failures output by the random forest model and mark it as the important value of the number of failures P F The random forest model outputs the important value of data loss as the important value of fault loss P D The random forest model outputs the important value of the number of security events as the important value of the number of security events P S ;

[0116] The calculation formula of the failure number weight is:

[0117]

[0118] Among them, Q F is the failure number weight, P F is the important value of the number of failures, P D is the important value of the data loss, P S is the important value of the number of security events;

[0119] Then the failure number weight Q F for

[0120]

[0121] The calculation formula of the data loss weight is:

[0122]

[0123] Among them, Q D is the weight of data loss, P F is the important value of the number of failures, P D is the important value of the data loss, P S is the important value of the number of security events;

[0124] The calculation formula for the weight of the number of security events is:

[0125]

[0126] Among them, Q S is the weight of the number of security events, P F is the important value of the number of failures, P D is the important value of the data loss, P S is the important value of the number of security events.

[0127] The construction process of the compatibility risk prediction model is as follows:

[0128] Obtaining the standard value of the number of failures, the standard value of the amount of data loss, the standard value of the number of security events, and the weight of the number of failures, the weight of the amount of data loss, and the weight of the number of security events;

[0129] The failure number weighted item is calculated according to the failure number standard value and the failure number weight, and the calculation formula is:

[0130] W F =F * *Q F ;

[0131] Among them, W F is the weighted term of the number of failures, F* is the standard value of the number of failures, Q F is the weight of the number of failures;

[0132] For example, obtain the standard value of the number of failures F* as 0.5 and the weight of the number of failures Q F is 0.5, then the failure number weighting term W F for:

[0133] W F =F * *Q F =0.5*0.5=0.25;

[0134] The data loss weighted item is calculated according to the data loss standard value and the data loss weight, and the calculation formula is:

[0135] W D =D * *Q D ;

[0136] Among them, W D is the weighted term of the data loss amount, D* is the standard value of the data loss amount, Q D is the weight of the data loss amount;

[0137] The weighted item of the number of security events is calculated according to the standard value of the number of security events and the weight of the number of security events, and the calculation formula is:

[0138] W S =S * *Q S ;

[0139] Among them, W S is the weighted item of the number of security events, S* is the standard value of the security event occurrence rate, Q S is the weight of the safety incident incidence rate;

[0140] The compatibility risk prediction model is:

[0141] N=W F +W D +W S ;

[0142] Wherein, N is the compatibility risk coefficient, W F is the weighted term of the number of failures, W D is the weighted term for the data loss amount, W S A weighted item for the number of security events;

[0143] For example, get the failure count weighted item W F is 0.25, the data loss weighting term W D is 0.16, the weighted term of the number of security events W S is 0.08, then the compatibility risk coefficient N is:

[0144] N=W F +W D +W S =0.25+016+0.08=0.49.

[0145] The compatibility risk threshold is set to N*, and the compatibility risk coefficient N is calculated according to the compatibility risk prediction model. If N>N*, the replacement program is judged to be incompatible with the information system; if N<N*, the replacement program is judged to be compatible with the information system.

[0146] If the above judgment result is that the replacement program is compatible with the information system, the replacement program is fixed in the information system for use; if the above judgment result is that the replacement program is not compatible with the information system, the replacement program is tested intensively;

[0147] The specific process of focusing on testing the replacement program is as follows:

[0148] Get the failure number weighted item W F , the data loss weighted term W D and the weighted term W of the number of security events S , and the failure number weighted term W F , the data loss weighted term W D and the weighted term W of the number of security events S Sort from largest to smallest, and focus on testing the replacement program based on the sorting results;

[0149] If the failure number weighted term W F If the data loss amount W is greater than 100%, the fault simulation test in the key test is carried out, and various faults are introduced when the replacement program is running using an automated tool to evaluate the system's fault recovery capability, fault tolerance and stability. D If the weighted item ranks first, the data transmission stability test in the key test is carried out, and the packet loss rate is tested using an automated tool when the replacement program is running to ensure the integrity and security of the data during transmission, storage and processing; if the weighted item W of the number of security events ranks first, the data transmission stability test in the key test is carried out, and the packet loss rate is tested using an automated tool when the replacement program is running to ensure the integrity and security of the data during transmission, storage and processing; S If it ranks first, the security vulnerability scanning test in the key test is carried out, using an automatic vulnerability scanning tool to check whether there are known security vulnerabilities when the replacement program is running, so as to evaluate the system's security protection capabilities and ability to cope with potential security threats;

[0150] For example, get the failure count weighted item W F is 0.25, the weighted term of data loss W D =0.16 and the weighted term W of the number of security events S = 0.08, W F , W D , W S Sort from large to small, the sorting result is W F >W D >W S , then the replacement program is subjected to the fault simulation test in the key test;

[0151] If the key test passes, it is determined that the replacement program is compatible with the information system; if the key test fails, it is determined that the replacement program is incompatible with the information system.

[0152] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A comprehensive transformation method based on information system autonomy, characterized by: The method comprises the following steps: S1. Select a running program as a replacement program, integrate the replacement program into the information system for testing, obtain the operation log of the information system, and extract the operation data of the replacement program in the operation log; S2. Process the operation data to obtain the standard value of the operation data and the weight of the operation data, and use the standard value of the operation data and the weight of the operation data to build a compatibility risk prediction model; S3. Calculate the compatibility risk coefficient between the replacement program and the information system through the compatibility risk prediction model, and determine whether the replacement program is compatible with the information system according to the compatibility risk coefficient; S4. If the judgment result of step S3 is that the replacement program is compatible with the information system, the replacement program is fixed in the information system for use; if the judgment result of step S3 is that the replacement program is incompatible with the information system, the replacement program is intensively tested.

2. The comprehensive transformation method based on information system autonomy according to claim 1 is characterized by: In step S1, it also includes: Step S101: select a running program as a replacement program, the replacement program meets the functional requirements of the information system, and integrate the replacement program into the information system; Step S102: After the replacement program is integrated into the information system, the information system will continue to run, and the operation log of the information system is obtained; Step S103: extracting the operation data of the replacement program in the operation log, wherein the operation data includes the number of failures, the amount of data loss, and the number of security events.

3. The comprehensive transformation method based on information system autonomy according to claim 1 is characterized by: The standard values ​​of operation data include standard values ​​of the number of failures, standard values ​​of data loss, and standard values ​​of the number of safety events; Extracting operation data from the operation log of the information system, obtaining the operation time of the replacement program on the information system, dividing the operation time into n consecutive time periods t, and counting the operation data within the n time periods; The process of calculating the standard value of the number of failures is as follows: Obtain the number of failures of the replacement program in each time period, and form a failure number set A = {F1, F2, F3, ... F n }, where F1, F2, F3, ... F n The number of failures of the replacement program in the first time period, the number of failures of the replacement program in the second time period, the number of failures of the replacement program in the third time period, ... the number of failures of the replacement program in the nth time period are represented in sequence, and the average number of failures of the replacement program in the n time periods is calculated and marked as the number of failures F; The maximum value F in the failure number set n Marked as the maximum number of failures F max ; Set the minimum value F in the failure number set n Marked as the maximum number of failures F min ; The normalized processing formula for the number of failures is: Among them, F * is the standard value of the number of failures, F is the number of failures, and F max is the maximum number of failures, F min is the minimum number of failures; The process of calculating the standard value of data loss is as follows: Obtain the amount of data lost by the replacement program in each time period to form a data loss amount set B = {D1, D2, D3, ... D n }, where D1, D2, D3, ... D n The data lost by the replacement program in the first time period, the data lost by the replacement program in the second time period, the data lost by the replacement program in the third time period, and so on, are represented in sequence. The average value of the data lost by the replacement program in the n time periods is calculated and marked as the data loss amount D. The maximum value D in the data loss amount set n Marked as the maximum data loss amount D max ; The minimum value D in the data loss amount set n Marked as the maximum data loss amount D min ; The normalization formula for the data loss amount is: Among them, D * is the standard value of data loss, D is the amount of data loss, D max is the maximum value of data loss, D min is the minimum value of data loss; The process of calculating the standard value of the number of security events is as follows: Obtain the number of security events that occurred in the replacement program in each time period, and form a security event number set C = {S1, S2, S3, ... S n }, where S1, S2, S3, ... S n The number of security incidents that occurred in the replacement program in the first time period, the number of security incidents that occurred in the replacement program in the second time period, the number of security incidents that occurred in the replacement program in the third time period, ... the number of security incidents that occurred in the replacement program in the nth time period are represented in sequence. The average number of security incidents that occurred in the replacement program in the n time periods is calculated and marked as the data loss amount S; The maximum value S in the security event count set n The maximum number of security events marked as S max ; Set the minimum value S in the security event count set n The maximum number of security events marked as S min ; The normalization formula for the number of security events is: Among them, S * is the standard value of the number of security events, S is the number of security events, S max is the maximum number of security events, S min The minimum number of security events.

4. The comprehensive transformation method based on information system autonomy according to claim 1 is characterized by: The operation data weights include the failure number weights, data loss amount weights and security event number weights; The process of training the random forest model with standard values ​​of running data is as follows: Obtaining the standard value of the running data to form a data set, dividing it into a training set and a test set, selecting random forest parameters, initializing a random forest model using the selected random forest parameters, training the random forest model using the training set, and testing the accuracy of the random forest model using the test set; After the random forest model training is completed, the random forest model outputs the important values ​​of the number of failures, the important values ​​of the amount of data loss, and the important values ​​of the number of security events; The process of calculating the failure number weight is as follows: Extract the important value of the number of failures output by the random forest model and mark it as the important value of the number of failures P F The random forest model outputs the important value of data loss as the important value of fault loss P D The random forest model outputs the important value of the number of security events as the important value of the number of security events P S ; The calculation formula of the failure number weight is: Among them, Q F is the failure number weight, P F is the important value of the number of failures, P D is the important value of the data loss, P S is the important value of the number of security events; The calculation formula of the data loss weight is: Among them, Q D is the weight of data loss, P F is the important value of the number of failures, P D is the important value of the data loss, P S is the important value of the number of security events; The calculation formula for the weight of the number of security events is: Among them, QS is the weight of the number of security events, PF is the importance value of the number of failures, PD is the importance value of the amount of data loss, P S is the important value of the number of security events.

5. The comprehensive transformation method based on information system autonomy according to claim 4 is characterized by: The construction process of the compatibility risk prediction model is as follows: Obtaining the standard value of the number of failures, the standard value of the amount of data loss, the standard value of the number of security events, and the weight of the number of failures, the weight of the amount of data loss, and the weight of the number of security events; The failure number weighted item is calculated according to the failure number standard value and the failure number weight, and the calculation formula is: W=F** F Wherein, WF is the weighted term of the number of failures, F* is the standard value of the number of failures, and QF is the weight of the number of failures; The data loss weighted item is calculated according to the data loss standard value and the data loss weight, and the calculation formula is: WD=D**QD Among them, W D is the weighted item of the data loss amount, D* is the standard value of the data loss amount, and QD is the weight of the data loss amount; The weighted item of the number of security events is calculated according to the standard value of the number of security events and the weight of the number of security events, and the calculation formula is: WS=S**QS Among them, W S is the weighted item of the number of security events, S* is the standard value of the security event occurrence rate, and QS is the weight of the security event occurrence rate; The compatibility risk prediction model is: N=WF+WD+WS Wherein, N is the compatibility risk coefficient, W F is the weighted term of the number of failures, W D is the weighted term for the data loss amount, W S A weighted item for the number of security events.

6. The comprehensive transformation method based on information system autonomy according to claim 5 is characterized by: In step S3, it specifically includes: The compatibility risk threshold is set to N*, and the compatibility risk coefficient N is calculated according to the compatibility risk prediction model. If N>N*, it is determined that the replacement program is incompatible with the information system; if N<N*, it is determined that the replacement program is compatible with the information system.

7. The comprehensive transformation method based on information system autonomy according to claim 5 is characterized by: In step S4, the specific process of focusing on testing the replacement program is as follows: Step S401, obtaining the weighted item of the number of failures, the weighted item of the amount of data loss, and the weighted item of the number of security events, and sorting the weighted item of the number of failures, the weighted item of the amount of data loss, and the weighted item of the number of security events from large to small, and performing key tests on the replacement program according to the sorting results, wherein the key tests include a fault simulation test, a data transmission stability test, and a security vulnerability scanning test; Step S402: If the weighted item of the number of failures ranks first, the failure simulation test is performed; If the weighted item of the amount of data loss ranks first, then the data transmission stability test is performed; If the weighted item of the number of security events ranks first, the security vulnerability scanning test is performed; Step S403: If the key test passes, it is determined that the replacement program is compatible with the information system; If the key test fails, it is determined that the replacement program is incompatible with the information system.

Images