Network engineering construction progress intelligent management method and system based on machine learning

Abstract

The invention discloses a network engineering construction progress intelligent management method and system based on machine learning, relates to the field of construction progress management, and optimizes and manages the construction progress of network engineering from two aspects of data security of the network engineering and time-limited completion of the network engineering. According to the technical scheme of the invention, the safety parameter data of the plurality of network devices needing to be installed in the current network engineering construction are collected, and then the safety parameter data are optimized, so that the possibility of data leakage after the current network engineering is constructed is small, and the data safety is ensured. In cooperation with the final debugging time consumption mapping model, security parameter data of network equipment in the current network project is adjusted, and a proper number of people can be allocated for adjustment according to a security type needing to be adjusted, so that the overall time consumption is controlled before the end of the construction period of the current network project. Therefore, normal completion of the current network engineering can be ensured.

Description

Technical Field

[0001] The present invention belongs to the field of construction progress management, and in particular, relates to a method and system for intelligent management of network engineering construction progress based on machine learning. Background Art

[0002] In a network project, it is necessary to install a variety of network devices. The joint work of these network devices constitutes the entire network project. When different network devices are installed or put into use, relevant parameters need to be set. These parameters have a great impact on the security of the entire network project. If the parameters of each network device cannot be set accurately and reasonably, it may lead to network data leakage during the construction of the network project, causing losses to the company. Secondly, when it is necessary to adjust the parameters of the network device, it is often necessary to allocate manpower for manual adjustment. Different network devices have different adjustment methods. If a reasonable number of debugging personnel cannot be allocated according to the need to adjust the parameters of various network devices, it may cause delays in the construction period and failure to complete on time. Summary of the invention

[0003] In response to the problems in the related technology, the present invention proposes a method and system for intelligent management of network engineering construction progress based on machine learning to overcome the above-mentioned technical problems existing in the existing related technology.

[0004] To solve the above technical problems, the present invention is achieved through the following technical solutions:

[0005] The present invention is a method for intelligent management of network engineering construction progress based on machine learning, comprising the following steps:

[0006] S1. Collect security parameter data of multiple network devices that need to be installed during the current network engineering construction to obtain a current security parameter data matrix; collect multiple sets of historical network equipment security parameter data and the number of data leaks after the corresponding network engineering is completed to obtain a historical security parameter data set matrix and a historical data leakage number data set; collect multiple sets of historically allocated numbers of debugging personnel for updating and installing network equipment security parameters, the types of security parameters of debugged network equipment, and the corresponding time-consuming data to obtain a historical security parameter debugging personnel number set, a historical debugging security parameter type set matrix, and a historical debugging time-consuming data set;

[0007] S2, using the historical security parameter data set matrix, the historical data leakage number data set, the historical security parameter debugging personnel number set, the historical debugging security parameter type set matrix, and the historical debugging time-consuming data set to respectively construct the final data leakage number mapping model and the final debugging time-consuming mapping model;

[0008] S3, optimizing the current security parameter data matrix in conjunction with the final data leakage times mapping model to obtain the current final security parameter data matrix;

[0009] S4. Optimize and adjust the number of preset security parameter debugging personnel according to the current final security parameter data matrix and the corresponding time-consuming data and in conjunction with the final debugging time-consuming mapping model to obtain the current final number of debugging personnel;

[0010] In this scheme, firstly, by collecting the security parameter data of multiple network devices that need to be installed during the current network engineering construction, a data basis is provided for the subsequent determination of whether the security parameters in the current network engineering are set reasonably; by using multiple sets of historical network equipment security parameter data and the number of data leakages after the corresponding network engineering is completed, data support is provided for the subsequent construction of a mapping model between network equipment security parameter data and the number of data leakages; by collecting multiple sets of historically allocated numbers of debugging personnel for updating and installing network equipment security parameters, the types of security parameters of the debugged network equipment, and the corresponding time-consuming data, data support is provided for the subsequent construction of a mapping model between the number of debugging personnel, the types of security parameters of the debugged network equipment, and the time-consuming data; By constructing a final data leakage frequency mapping model, a mapping module is provided for the subsequent mapping and classification of the security parameter data of the network equipment in the current network project; by optimizing the current security parameter data matrix, the security parameters of the optimized network equipment are set to the current network project, which can ensure that the possibility of data leakage after the current network project is completed is small, thereby ensuring data security; by constructing a final debugging time-consuming mapping model, when it is necessary to adjust the security parameter data of the network equipment in the current network project, the appropriate number of people can be allocated according to the security type that needs to be adjusted, so that the overall time consumption is controlled before the end of the current network project, thereby ensuring that the current network project can be completed normally.

[0011] Preferably, the S1 comprises the following steps:

[0012] S11, setting the parameter types for setting network security in various network device types, and obtaining the network device security parameter type matrix a; as follows,

[0013]

[0014] Among them, a ij Indicates the jth type of security parameters for the i-th network device type, a i ′ represents the total number of security parameter types set for the i-th network device type, Indicates the total number of set network device types;

[0015] Set multiple network devices that need to be installed in the current network engineering construction, and get the current network device set represents the i-th network device that needs to be installed in the current network engineering construction, and b1 represents the total number of network devices that need to be installed in the current network engineering construction; when the installation setting is completed, the security parameter data of each network device in the current network device set is collected according to the network device security parameter type matrix a to obtain the current security parameter data matrix b1′; as follows,

[0016]

[0017] Among them, b1′ ij Indicates the security parameter data of the jth type of the i-th network device in the current network device set. Indicates the total amount of security parameter data collected for the i-th network device in the current network device set;

[0018] S12, collect multiple sets of historical network equipment security parameter data installed during the construction process of the network project and the corresponding number of data leakage after the network project was completed without adjusting the security parameters, and obtain the historical security parameter data set matrix b2′ and the historical data leakage number data set b3′ i It represents the number of data leaks after the completion of the i-th historical network project. represents the total number of historical network projects collected; b2′ is as follows,

[0019]

[0020] Among them, b2′ ij represents the security parameter dataset of the jth network device installed during the i-th historical network engineering construction process, c i represents the total number of network devices installed during the construction of the i-th historical network project;

[0021] b2′ ijk Indicates b2′ ij The kth type of security parameter data, c i ' j Indicates b2′ ij The total number of security parameter data in;

[0022] S13, in conjunction with the network equipment security parameter type matrix a, collect multiple groups of historical network engineering construction processes, the number of debugging personnel for updating and installing network equipment security parameters, the types of security parameters of the debugged network equipment, and the corresponding time-consuming data, to obtain a historical security parameter debugging personnel number set Historical Debug Security Parameter Type Set Matrix And historical debugging time-consuming data set They respectively represent the number of debugging personnel assigned to update and install network equipment security parameters during the i-th group of historical network engineering construction and the corresponding time consumption data, Indicates the number of debugging personnel assigned to update and install network equipment security parameters during the construction process of the collected historical network projects, corresponding to the total number of network projects; as follows,

[0023]

[0024] in, Indicates the jth network device that needs to be debugged during the construction of the i-th group of historical network projects collected, d i The total number of network devices that need to be debugged during the construction of the i-th historical network project represented by;

[0025] express The i-th security parameter type, d i ' j express The total number of security parameter types;

[0026] Network device types include network cards, hubs, repeaters, bridges, switches, routers, firewalls, network storage devices, network printers, Internet phones, servers, modems, and fiber optic transceivers; the network device security parameter type matrix includes access control parameters, encryption parameters, identity authentication parameters, security protocol parameters, firewall rule parameters, log audit parameters, network isolation and segmentation parameters, intrusion detection and defense parameters, physical security parameters, and system and application security parameters; time-consuming data refers to the time consumed to adjust the originally unreasonable security parameters of all network devices to reasonable security parameters.

[0027] Preferably, S2 comprises the following steps:

[0028] S21, based on the historical security parameter data set matrix b2′ and the historical data leakage times data set Construct the final data leakage frequency mapping model;

[0029] S22, debugging the personnel quantity set according to the historical safety parameters Historical Debug Security Parameter Type Set Matrix And historical debugging time-consuming data set Build the final debugging time-consuming mapping model;

[0030] The final data leakage frequency mapping model can map the security parameter data of network equipment to the number of data leakages after the network project is completed, providing a mapping tool for the subsequent iterative update of the network equipment security parameters of the current network project, making the update process more feasible and convenient; the final debugging time mapping model can map the number of security parameter debugging personnel and the parameter types that need to be debugged to the total time data for debugging completion, providing a mapping tool for the subsequent iterative update of the personnel data assigned to security parameter debugging in the current network project, also making the update process more feasible and convenient.

[0031] Preferably, S3 comprises the following steps:

[0032] S31, input the current security parameter data matrix b1′ into the final data leakage frequency mapping model for mapping, and obtain the current data leakage frequency data matrix b1′.

[0033] S32, setting a leakage times threshold; when the current data leakage times data is greater than or equal to the leakage times threshold, adjusting each security parameter data in the current security parameter data matrix until the current data leakage times data is less than the leakage times threshold, and obtaining the current final security parameter data matrix; otherwise, there is no need to adjust the current security parameter data matrix, and the current security parameter data matrix is ​​used as the current final security parameter data matrix;

[0034] S33: Compare the current final security parameter data matrix with the current security parameter data matrix, collect the security parameter types corresponding to the adjusted security parameter data, and obtain the current security parameter type matrix to be adjusted. as follows,

[0035]

[0036] in, represents the jth type of security parameter that needs to be adjusted in the i-th network device in the current network device set, e i Indicates the total number of security parameter types that need to be adjusted in the i-th network device in the current network device set;

[0037] Preferably, S4 comprises the following steps:

[0038] S41, setting the current preset number of debugging personnel;

[0039] S42: Input the current preset number of debugging personnel and the current matrix of the safety parameter type to be adjusted into the final debugging time-consuming mapping model for mapping, and obtain the current time-consuming data.

[0040] S43, when the current time consumption data is greater than the remaining construction period of the current network engineering construction, the current preset number of debugging personnel is adjusted until the current time consumption data is less than or equal to the remaining construction period of the current network engineering construction, and the current final number of debugging personnel is obtained; otherwise, the current preset number of debugging personnel does not need to be adjusted, and the current preset number of debugging personnel is used as the current final number of debugging personnel;

[0041] By obtaining the current time consumption data, a data basis is provided for the subsequent determination of whether the number of personnel currently assigned to debug the security parameters of network equipment is reasonable; since the process of debugging the security parameters of network equipment needs to be completed within the scheduled construction period of the entire network project, this solution controls the total debugging time within the total construction period by comparing the current time consumption data with the remaining construction period, thereby ensuring that the entire network project is completed within the construction period.

[0042] Preferably, in S43, the current preset number of debugging personnel is adjusted until the current time consumption data is less than or equal to the remaining construction period of the current network engineering, and obtaining the current final number of debugging personnel includes the following steps:

[0043] S431. Establishment of the second Harris Hawk population e′ 2i represents the i-th Harris hawk in the second Harris hawk population, represents the size of the second Harris Hawk population; sets the maximum number of iterations of the second Harris Hawk population to And the current number of iterations is are recorded as the second maximum number of iterations and the second current number of iterations respectively; the search space dimension of the second Harris hawk population is 1;

[0044] S432, setting the value interval of the current preset number of debugging personnel to obtain the personnel number value interval [g1, g2]; g1 and g2 respectively represent the lower limit and upper limit of the current preset number of debugging personnel;

[0045] The initial position of each Harris hawk in the second Harris hawk population is set according to the personnel number value interval to obtain the second initial position set f2′ k represents the initial position of the kth Harris hawk in the second Harris hawk population; the calculation formula is as follows,

[0046] f2′ k =g1+rand 2k ×(g2-g1);

[0047] In the formula, rand 2k Indicates for f2′k Generate a random number between 0 and 1;

[0048] S433: Based on the current time-consuming data Setting the fitness function of the second Harris Hawk population as follows,

[0049]

[0050] S434, start iteration, before iteration, set the second current iteration number Set to 1; the fitness function of the second Harris Hawk population is used in the first iteration And cooperate with the final debugging time-consuming mapping model to calculate the fitness value of the initial position of each Harris hawk in the second initial position set to obtain a third fitness value set; the maximum fitness value in the third fitness value set and the corresponding initial position of the Harris hawk in the second Harris hawk population are respectively used as the third global optimal fitness and the third global optimal position; the initial position of each Harris hawk in the second initial position set is updated according to the third global optimal fitness and the third global optimal position; after the update is completed, the second current iteration number is Add 1 and enter the next iteration;

[0051] The fitness function of the second Harris Hawk population is used in each other iteration process And cooperate with the final debugging time-consuming mapping model to calculate the fitness value of the position of each Harris hawk in the second Harris hawk population updated in the previous round of iterations, and obtain a fourth fitness value set; the maximum fitness value in the fourth fitness value set and the corresponding position of the Harris hawk in the second Harris hawk population are respectively used as the fourth global optimal fitness and the fourth global optimal position; according to the fourth global optimal fitness and the fourth global optimal position, the position of each Harris hawk in the second Harris hawk population updated in the previous round of iterations is updated again; after the update is completed, the second current iteration number Add 1 and enter the next iteration;

[0052] S435, when When , stop the iteration and get the second global final best position; otherwise, continue to iterate until The first global final optimal position is used as the current final number of debugging personnel;

[0053] The Harris Eagle Optimization Algorithm is used to update and iterate the number of people allocated to debugging safety parameters, and the total time consumed in the entire debugging process is used as the fitness function. Therefore, as the iteration proceeds, the time consumed by the number of people allocated to debugging safety parameters obtained by the iteration becomes smaller and smaller, and finally the construction period requirements are met.

[0054] The intelligent management system for network engineering construction progress based on machine learning includes a safety parameter type setting module, a current safety parameter data collection module, a historical leakage data collection module, a historical parameter debugging data collection module, a mapping model building module, a current safety parameter optimization module and a safety parameter debugging personnel allocation management module.

[0055] The present invention has the following beneficial effects:

[0056] 1. The present invention optimizes and manages the construction progress of the network project from two aspects: data security of the network project and time-limited completion of the network project; by collecting security parameter data of multiple network devices that need to be installed in the current network project construction, and then optimizing the security parameter data, the security parameters of the optimized network devices are set to the current network project, which can ensure that the possibility of data leakage after the current network project is completed is small, thereby ensuring data security; in conjunction with the final debugging time-consuming mapping model, the security parameter data of the network devices in the current network project are adjusted, and the appropriate number of people can be allocated according to the security type that needs to be adjusted, so that the overall time consumption is controlled before the end of the current network project construction period, thereby ensuring that the current network project can be completed normally.

[0057] 2. The present invention provides a quantitative judgment standard by obtaining the current data leakage frequency data and the leakage frequency threshold, so that the judgment is more based on evidence.

[0058] 3. In the present invention, the number of people allocated to debugging safety parameters is updated and iterated by adopting the Harris Eagle optimization algorithm, and the total time consumed in the entire debugging process is used as the fitness function. Therefore, as the iteration proceeds, the time consumed corresponding to the number of people allocated to debugging safety parameters obtained by the iteration becomes smaller and smaller, and finally the requirements of the construction period are met; wherein, by comparing the current time consumption data with the remaining construction period, the total time consumption for debugging is controlled within the total construction period, thereby ensuring that the entire network project is completed within the construction period.

[0059] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0061] Figure 1 It is a flow chart of the intelligent management method of network engineering construction progress based on machine learning of the present invention. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0063] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0064] Embodiment 1

[0065] This embodiment is a network engineering construction progress intelligent management method based on machine learning, including the following steps:

[0066] S1. Collect security parameter data of multiple network devices that need to be installed during the current network engineering construction to obtain a current security parameter data matrix; collect multiple sets of historical network equipment security parameter data and the number of data leaks after the corresponding network engineering is completed to obtain a historical security parameter data set matrix and a historical data leakage number data set; collect multiple sets of historically allocated numbers of debugging personnel for updating and installing network equipment security parameters, the types of security parameters of debugged network equipment, and the corresponding time-consuming data to obtain a historical security parameter debugging personnel number set, a historical debugging security parameter type set matrix, and a historical debugging time-consuming data set;

[0067] The S1 comprises the following steps:

[0068] S11, setting the parameter types for setting network security in various network device types, and obtaining the network device security parameter type matrix a; as follows,

[0069]

[0070] Among them, aij Indicates the jth type of security parameters for the i-th network device type, a i ′ represents the total number of security parameter types set for the i-th network device type, Indicates the total number of set network device types;

[0071] Set multiple network devices that need to be installed in the current network engineering construction, and get the current network device set represents the i-th network device that needs to be installed in the current network engineering construction, and b1 represents the total number of network devices that need to be installed in the current network engineering construction; when the installation setting is completed, the security parameter data of each network device in the current network device set is collected according to the network device security parameter type matrix a to obtain the current security parameter data matrix b1′; as follows,

[0072]

[0073] Among them, b1′ ij Indicates the security parameter data of the jth type of the i-th network device in the current network device set. Indicates the total amount of security parameter data collected for the i-th network device in the current network device set;

[0074] S12, collect multiple sets of historical network equipment security parameter data installed during the construction process of the network project and the corresponding number of data leakage after the network project was completed without adjusting the security parameters, and obtain the historical security parameter data set matrix b2′ and the historical data leakage number data set b3′ i It represents the number of data leaks after the completion of the i-th historical network project. represents the total number of historical network projects collected; b2′ is as follows,

[0075]

[0076] Among them, b2′ ij represents the security parameter dataset of the jth network device installed during the i-th historical network engineering construction process, c i represents the total number of network devices installed during the construction of the i-th historical network project;

[0077] b2′ ijk Indicates b2′ ij The kth type of security parameter data, c i ' j Indicates b2′ ij The total number of security parameter data in;

[0078] S13, in conjunction with the network equipment security parameter type matrix a, collect multiple groups of historical network engineering construction processes, the number of debugging personnel for updating and installing network equipment security parameters, the types of security parameters of the debugged network equipment, and the corresponding time-consuming data, to obtain a historical security parameter debugging personnel number set Historical Debug Security Parameter Type Set Matrix And historical debugging time-consuming data set They respectively represent the number of debugging personnel assigned to update and install network equipment security parameters during the i-th group of historical network engineering construction and the corresponding time consumption data, Indicates the number of debugging personnel assigned to update and install network equipment security parameters during the construction process of the collected historical network projects, corresponding to the total number of network projects; as follows,

[0079]

[0080] in, Indicates the jth network device that needs to be debugged during the construction of the i-th group of historical network projects collected, d i The total number of network devices that need to be debugged during the construction of the i-th historical network project represented by;

[0081] express The i-th security parameter type, d i ' j express The total number of security parameter types;

[0082] S2, using the historical security parameter data set matrix, the historical data leakage number data set, the historical security parameter debugging personnel number set, the historical debugging security parameter type set matrix, and the historical debugging time-consuming data set to respectively construct the final data leakage number mapping model and the final debugging time-consuming mapping model;

[0083] The S2 comprises the following steps:

[0084] S21, based on the historical security parameter data set matrix b2′ and the historical data leakage times data set Construct the final data leakage frequency mapping model;

[0085] The S21 comprises the following steps:

[0086] S211, constructing a first initial SVM classification model and setting a first training data ratio; dividing the historical security parameter data set matrix and the historical data leakage number data set according to the first training data ratio to obtain a historical security parameter training data set matrix, a historical data leakage number training data set, a historical security parameter test data set matrix, and a historical data leakage number test data set;

[0087] S212, setting a first training error threshold; inputting the historical security parameter training data set matrix and the historical data leakage number training data set as training data and training labels respectively into a first initial SVM classification model for training; during the training process, when the training error is less than the first training error threshold, stopping the training to obtain a first trained SVM classification model; otherwise, continuing the training until the training error is less than the first training error threshold;

[0088] S213, setting a first test accuracy threshold; inputting the historical security parameter test data set matrix and the historical data leakage test data set as test data and test labels respectively into the first trained SVM classification model for testing; after the test is completed, obtaining a first test accuracy; when the first test accuracy is greater than or equal to the first test accuracy threshold, using the first trained SVM classification model as the final data leakage mapping model; otherwise, returning to S212 to continue training the first trained SVM classification model until the first test accuracy is greater than or equal to the first test accuracy threshold, and obtaining the final data leakage mapping model;

[0089] The first initial SVM classification model is trained and tested by using the historical security parameter training data set matrix, the historical data leakage number training data set, the historical security parameter test data set matrix, and the historical data leakage number test data set, respectively, so that the final data leakage number mapping model obtained has a good mapping ability from security parameter data to data leakage number;

[0090] S22, debugging the personnel quantity set according to the historical safety parameters Historical Debug Security Parameter Type Set Matrix And historical debugging time-consuming data set Build the final debugging time-consuming mapping model;

[0091] The S22 comprises the following steps:

[0092] S221, construct a second initial SVM classification model and set a second training data ratio; divide the historical safety parameter debugging personnel quantity set, the historical debugging safety parameter type set matrix, and the historical debugging time-consuming data set according to the second training data ratio, and obtain the historical safety parameter debugging personnel quantity training set, the historical debugging safety parameter type training set matrix, the historical debugging time-consuming training data set, the historical safety parameter debugging personnel quantity test set, the historical debugging safety parameter type test set matrix, and the historical debugging time-consuming test data set;

[0093] S222, setting a second training error threshold; inputting the historical safety parameter debugging personnel number training set, the historical debugging safety parameter type training set matrix as training data, and the historical debugging time-consuming training data set as training labels into the second initial SVM classification model for training; during the training process, when the training error is less than the second training error threshold, stop the training and obtain the second trained SVM classification model; otherwise, continue the training until the training error is less than the second training error threshold;

[0094] S223, set a second test accuracy threshold; input the historical safety parameter debugging personnel quantity test set, the historical debugging safety parameter type test set matrix as test data and the historical debugging time-consuming test data set as test labels into the second trained SVM classification model for testing; after the test is completed, obtain the second test accuracy; when the second test accuracy is greater than or equal to the second test accuracy threshold, use the second trained SVM classification model as the final debugging time-consuming mapping model; otherwise, return to S222 to continue training the second trained SVM classification model until the second test accuracy is greater than or equal to the second test accuracy threshold, and obtain the final debugging time-consuming mapping model;

[0095] The second initial SVM classification model is trained and tested by using the historical safety parameter debugging personnel number training set, the historical debugging safety parameter type training set matrix, the historical debugging time-consuming training data set, and the historical safety parameter debugging personnel number test set, the historical debugging safety parameter type test set matrix, and the historical debugging time-consuming test data set, so that the final debugging time-consuming mapping model obtained has a good mapping ability from the safety parameter type and the number of debugging personnel to the total debugging time.

[0096] S3, optimizing the current security parameter data matrix in conjunction with the final data leakage times mapping model to obtain the current final security parameter data matrix;

[0097] The S3 comprises the following steps:

[0098] S31, input the current security parameter data matrix b1′ into the final data leakage frequency mapping model for mapping, and obtain the current data leakage frequency data matrix b1′.

[0099] S32, setting a leakage times threshold; when the current data leakage times data is greater than or equal to the leakage times threshold, adjusting each security parameter data in the current security parameter data matrix until the current data leakage times data is less than the leakage times threshold, and obtaining the current final security parameter data matrix; otherwise, there is no need to adjust the current security parameter data matrix, and the current security parameter data matrix is ​​used as the current final security parameter data matrix;

[0100] In S32, each security parameter data in the current security parameter data matrix is ​​adjusted until the current data leakage times is less than the leakage times threshold value, and obtaining the current final security parameter data matrix includes the following steps:

[0101] S321. Establishing the first Harris Hawk population e1′ i represents the i-th Harris hawk in the first Harris hawk population, represents the size of the first Harris Hawk population; sets the maximum number of iterations of the first Harris Hawk population to And the current iteration number is are respectively recorded as the first maximum number of iterations and the first current number of iterations; the search space dimension of the first Harris Hawk population is

[0102] S322, cooperate with the network device security parameter type matrix a to obtain the value interval of the security parameter type corresponding to each security parameter data in the current security parameter data matrix b1′, and obtain the current security parameter value interval matrix f; as follows,

[0103]

[0104] in, They respectively represent the lower limit and upper limit of the security parameter type corresponding to the j-th type of security parameter data of the ith network device in the current network device set;

[0105] The initial position matrix of each Harris hawk in the first Harris hawk population is set according to the current safety parameter value interval matrix to obtain a first initial position matrix set f1′ k represents the initial position matrix of the kth Harris hawk in the first Harris hawk population; as follows,

[0106]

[0107] Among them, f1′ kij represents the position component of the initial position matrix of the k-th Harris Hawk in the first Harris Hawk population in the dimension of the j-th type of security parameter data of the ith network device in the current network device set; the calculation formula is as follows,

[0108]

[0109] In the formula, rand 1kij Indicates that for f1′ kij Generate a random number between 0 and 1;

[0110] S323, according to the current data leakage times data Set the fitness function of the first Harris Hawk population as follows,

[0111]

[0112] S324, start iteration, before iteration, set the first current iteration number Set to 1; the fitness function of the first Harris Hawk population is used in the first iteration And cooperate with the final data leakage number mapping model to calculate the fitness value of the initial position matrix of each Harris hawk in the first initial position matrix set to obtain the first fitness value set; the maximum fitness value in the first fitness value set and the corresponding initial position matrix of the Harris hawk in the first Harris hawk population are respectively used as the first global optimal fitness and the first global optimal position; according to the first global optimal fitness and the first global optimal position, the initial position matrix of each Harris hawk in the first initial position matrix set is updated; after the update is completed, the first current iteration number Add 1 and enter the next iteration;

[0113] The fitness function of the first Harris Hawk population is used in each other iteration process And cooperate with the final data leakage number mapping model to calculate the fitness value of the position matrix of each Harris hawk in the first Harris hawk population updated in the previous iteration process to obtain a second fitness value set; the maximum fitness value in the second fitness value set and the corresponding position matrix of the Harris hawk in the first Harris hawk population are used as the second global optimal fitness and the second global optimal position respectively; according to the second global optimal fitness and the second global optimal position, the position matrix of each Harris hawk in the first Harris hawk population updated in the previous iteration process is updated again; after the update is completed, the first current iteration number Add 1 and enter the next iteration;

[0114] S325, when When , stop the iteration and get the first global final optimal position; otherwise, continue to iterate until until the time; taking the first global final optimal position as the current final safety parameter data matrix;

[0115] The Harris Eagle optimization algorithm can effectively search in the entire search space and avoid falling into the local optimal solution; fewer parameters need to be adjusted, which makes the implementation and debugging of the algorithm easier. By dynamically switching between the exploration and utilization phases, it can balance between global search and local search, which helps to avoid the algorithm from converging to the local optimal solution too early, and can usually converge to a higher quality solution more quickly, improving the efficiency of solving the optimization problem; Based on the above advantages of the Harris Eagle optimization algorithm, this solution uses the Harris Eagle optimization algorithm to simultaneously update and iterate the security parameter data of the network device for multiple times, and uses the number of data leakage as the fitness function. As the iteration proceeds, the number of data leakages corresponding to the adjusted security parameter data of the network device becomes smaller and smaller, thereby making the security level of the current network project higher and higher;

[0116] S33: Compare the current final security parameter data matrix with the current security parameter data matrix, collect the security parameter types corresponding to the adjusted security parameter data, and obtain the current security parameter type matrix to be adjusted. as follows,

[0117]

[0118] in, represents the jth type of security parameter that needs to be adjusted in the i-th network device in the current network device set, e i Indicates the total number of security parameter types that need to be adjusted in the i-th network device in the current network device set;

[0119] S4. Optimize and adjust the number of preset security parameter debugging personnel according to the current final security parameter data matrix and the corresponding time-consuming data and in conjunction with the final debugging time-consuming mapping model to obtain the current final number of debugging personnel;

[0120] The S4 comprises the following steps:

[0121] S41, setting the current preset number of debugging personnel;

[0122] S42: Input the current preset number of debugging personnel and the current matrix of the safety parameter type to be adjusted into the final debugging time-consuming mapping model for mapping, and obtain the current time-consuming data.

[0123] S43, when the current time consumption data is greater than the remaining construction period of the current network engineering construction, the current preset number of debugging personnel is adjusted until the current time consumption data is less than or equal to the remaining construction period of the current network engineering construction, and the current final number of debugging personnel is obtained; otherwise, the current preset number of debugging personnel does not need to be adjusted, and the current preset number of debugging personnel is used as the current final number of debugging personnel;

[0124] In S43, the current preset number of debugging personnel is adjusted until the current time consumption data is less than or equal to the remaining construction period of the current network engineering construction, and obtaining the current final number of debugging personnel includes the following steps:

[0125] S431. Establishment of the second Harris Hawk population e′ 2i represents the i-th Harris hawk in the second Harris hawk population, represents the size of the second Harris Hawk population; sets the maximum number of iterations of the second Harris Hawk population to And the current iteration number is are recorded as the second maximum number of iterations and the second current number of iterations respectively; the search space dimension of the second Harris hawk population is 1;

[0126] S432, setting the value interval of the current preset number of debugging personnel to obtain the personnel number value interval [g1, g2]; g1 and g2 respectively represent the lower limit and upper limit of the current preset number of debugging personnel;

[0127] The initial position of each Harris hawk in the second Harris hawk population is set according to the personnel number value interval to obtain the second initial position set f2′ k represents the initial position of the kth Harris hawk in the second Harris hawk population; the calculation formula is as follows,

[0128] f2′ k =g1+rand 2k ×(g2-g1);

[0129] In the formula, rand 2k Indicates for f2′ k Generate a random number between 0 and 1;

[0130] S433: Based on the current time-consuming data Setting the fitness function of the second Harris Hawk population as follows,

[0131]

[0132] S434, start iteration, before iteration, set the second current iteration number Set to 1; the fitness function of the second Harris Hawk population is used in the first iteration And cooperate with the final debugging time-consuming mapping model to calculate the fitness value of the initial position of each Harris hawk in the second initial position set to obtain a third fitness value set; the maximum fitness value in the third fitness value set and the corresponding initial position of the Harris hawk in the second Harris hawk population are respectively used as the third global optimal fitness and the third global optimal position; the initial position of each Harris hawk in the second initial position set is updated according to the third global optimal fitness and the third global optimal position; after the update is completed, the second current iteration number is Add 1 and enter the next iteration;

[0133] The fitness function of the second Harris Hawk population is used in each other iteration process And cooperate with the final debugging time-consuming mapping model to calculate the fitness value of the position of each Harris hawk in the second Harris hawk population updated in the previous round of iterations, and obtain a fourth fitness value set; the maximum fitness value in the fourth fitness value set and the corresponding position of the Harris hawk in the second Harris hawk population are respectively used as the fourth global optimal fitness and the fourth global optimal position; according to the fourth global optimal fitness and the fourth global optimal position, the position of each Harris hawk in the second Harris hawk population updated in the previous round of iterations is updated again; after the update is completed, the second current iteration number Add 1 and enter the next iteration;

[0134] S435, when When , stop the iteration and get the second global final best position; otherwise, continue to iterate until The first global final optimal position is taken as the current final number of debugging personnel.

[0135] Embodiment 2

[0136] This embodiment discloses a network engineering construction progress intelligent management system based on machine learning, which can implement the method of the above embodiment, including a security parameter type setting module, a current security parameter data collection module, a historical leakage data collection module, a historical parameter debugging data collection module, a mapping model construction module, a current security parameter optimization module and a security parameter debugging personnel allocation management module;

[0137] The security parameter type setting module is used to set the parameter types for setting network security in various network devices in the network project, and obtain a network device security parameter type matrix;

[0138] The current security parameter data acquisition module is used to collect security parameter data of multiple network devices that need to be installed in the current network engineering construction according to the network device security parameter type matrix to obtain the current security parameter data matrix;

[0139] The historical leakage data collection module is used to collect multiple groups of historical network equipment security parameter data and the number of data leakages after the corresponding network project is completed, and obtain a historical security parameter data set matrix and a historical data leakage number data set;

[0140] The historical parameter debugging data collection module is used to collect multiple groups of historically allocated numbers of debugging personnel for updating and installing network equipment security parameters, types of security parameters of debugged network equipment, and corresponding time-consuming data, to obtain a historical security parameter debugging personnel number set, a historical debugging security parameter type set matrix, and a historical debugging time-consuming data set;

[0141] The mapping model construction module is used to use the historical security parameter data set matrix, the historical data leakage number data set, the historical security parameter debugging personnel number set, the historical debugging security parameter type set matrix, and the historical debugging time-consuming data set to respectively construct the final data leakage number mapping model and the final debugging time-consuming mapping model;

[0142] The current security parameter optimization module is used to optimize the current security parameter data matrix in conjunction with the final data leakage times mapping model to obtain the current final security parameter data matrix;

[0143] The safety parameter debugging personnel allocation management module is used to optimize and adjust the number of preset safety parameter debugging personnel according to the current final safety parameter data matrix and the current safety parameter optimization module and in cooperation with the final debugging time-consuming mapping model to obtain the current final number of debugging personnel.

[0144] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0145] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A network engineering construction progress intelligent management method based on machine learning, characterized in that: The following steps are involved: S1. Collect security parameter data of multiple network devices that need to be installed during the current network engineering construction to obtain a current security parameter data matrix; collect multiple sets of historical network equipment security parameter data and the number of data leaks after the corresponding network engineering is completed to obtain a historical security parameter data set matrix and a historical data leakage number data set; collect multiple sets of historically allocated numbers of debugging personnel for updating and installing network equipment security parameters, the types of security parameters of debugged network equipment, and the corresponding time-consuming data to obtain a historical security parameter debugging personnel number set, a historical debugging security parameter type set matrix, and a historical debugging time-consuming data set; S2, using the historical security parameter data set matrix, the historical data leakage number data set, the historical security parameter debugging personnel number set, the historical debugging security parameter type set matrix, and the historical debugging time-consuming data set to respectively construct the final data leakage number mapping model and the final debugging time-consuming mapping model; S3, optimizing the current security parameter data matrix in conjunction with the final data leakage times mapping model to obtain the current final security parameter data matrix; S4. According to the current final safety parameter data matrix and the corresponding time-consuming data and in conjunction with the final debugging time-consuming mapping model, the number of preset safety parameter debugging personnel is optimized and adjusted to obtain the current final number of debugging personnel.

2. The method for intelligent management of network engineering construction progress based on machine learning according to claim 1 is characterized in that: The S1 comprises the following steps: S11, setting parameter types for setting network security in multiple network device types to obtain a network device security parameter type matrix; setting multiple network devices that need to be installed in the current network engineering construction to obtain a current network device set; when the installation and setting are completed, collecting security parameter data of each network device in the current network device set according to the network device security parameter type matrix to obtain a current security parameter data matrix; S12, collecting multiple sets of historical network equipment security parameter data installed during the construction process of the network project and the number of data leakages after the network project was completed without adjusting the security parameters, to obtain a historical security parameter data set matrix and a historical data leakage number data set; S13. In conjunction with the network equipment security parameter type matrix, collect multiple groups of historical network engineering construction processes allocated for updating and installing network equipment security parameter debugging personnel numbers, debugged network equipment security parameter types, and corresponding time-consuming data to obtain a historical security parameter debugging personnel number set, a historical debugging security parameter type set matrix, and a historical debugging time-consuming data set.

3. The method for intelligent management of network engineering construction progress based on machine learning according to claim 2 is characterized in that: The S2 comprises the following steps: S21, constructing a final data leakage frequency mapping model according to the historical security parameter data set matrix and the historical data leakage frequency data set; S22. Construct a final debugging time-consuming mapping model according to the historical safety parameter debugging personnel quantity set, the historical debugging safety parameter type set matrix, and the historical debugging time-consuming data set.

4. The method for intelligent management of network engineering construction progress based on machine learning according to claim 3 is characterized in that: The final data leakage times mapping model described in S21 adopts a support vector machine model.

5. The method for intelligent management of network engineering construction progress based on machine learning according to claim 3 is characterized in that: The final debugging time-consuming mapping model described in S22 adopts a support vector machine model.

6. The method for intelligent management of network engineering construction progress based on machine learning according to claim 5 is characterized in that: The S3 comprises the following steps: S31, inputting the current security parameter data matrix into the final data leakage frequency mapping model for mapping, to obtain current data leakage frequency data; S32, setting a leakage times threshold; when the current data leakage times data is greater than or equal to the leakage times threshold, adjusting each security parameter data in the current security parameter data matrix until the current data leakage times data is less than the leakage times threshold, and obtaining the current final security parameter data matrix; otherwise, there is no need to adjust the current security parameter data matrix, and the current security parameter data matrix is ​​used as the current final security parameter data matrix; S33: Compare the current final security parameter data matrix with the current security parameter data matrix, collect the security parameter types corresponding to the adjusted security parameter data, and obtain the current security parameter type matrix to be adjusted.

7. The method for intelligent management of network engineering construction progress based on machine learning according to claim 6 is characterized in that: In S32, the Harris Eagle optimization algorithm is used to adjust each safety parameter data in the current safety parameter data matrix.

8. The method for intelligent management of network engineering construction progress based on machine learning according to claim 7 is characterized in that: The S4 comprises the following steps: S41, setting the current preset number of debugging personnel; S42, inputting the currently preset number of debugging personnel and the current matrix of the safety parameter type to be adjusted into the final debugging time-consuming mapping model for mapping, and obtaining the current time-consuming data; S43. When the current time consumption data is greater than the remaining construction period of the current network engineering project, the current preset number of debugging personnel is adjusted until the current time consumption data is less than or equal to the remaining construction period of the current network engineering project, and the current final number of debugging personnel is obtained; otherwise, there is no need to adjust the current preset number of debugging personnel, and the current preset number of debugging personnel is used as the current final number of debugging personnel.

9. The method for intelligent management of network engineering construction progress based on machine learning according to claim 8 is characterized in that: In S43, the current preset number of debugging personnel is adjusted until the current time consumption data is less than or equal to the remaining construction period of the current network engineering construction, and obtaining the current final number of debugging personnel includes the following steps: S431, constructing a second Harris Hawk population; setting the maximum number of iterations of the second Harris Hawk population to e-3 and the current number of iterations to e-4, which are recorded as the second maximum number of iterations and the second current number of iterations respectively; the search space dimension of the second Harris Hawk population is 1; S432, setting a value interval of the current preset number of debugging personnel to obtain a value interval of the number of personnel; setting an initial position of each Harris hawk in the second Harris hawk population according to the value interval of the number of personnel to obtain a second initial position set; S433, setting the fitness function of the second Harris hawk population according to the current time-consuming data; S434, start iteration, and set the second current iteration number to 1 before iteration; in the first round of iteration, use the fitness function of the second Harris hawk population and cooperate with the final debugging time-consuming mapping model to calculate the fitness value of the initial position of each Harris hawk in the second initial position set to obtain a third fitness value set; use the maximum fitness value in the third fitness value set and the corresponding initial position of the Harris hawk in the second Harris hawk population as the third global optimal fitness and the third global optimal position respectively; update the initial position of each Harris hawk in the second initial position set according to the third global optimal fitness and the third global optimal position; after the update is completed, add 1 to the second current iteration number and enter the next round of iteration; In each other round of iteration, the fitness function of the second Harris hawk population is used in conjunction with the final debugging time-consuming mapping model to calculate the fitness value of the position of each Harris hawk in the second Harris hawk population updated in the previous round of iteration, and a fourth fitness value set is obtained; the maximum fitness value in the fourth fitness value set and the corresponding position of the Harris hawk in the second Harris hawk population are respectively used as the fourth global optimal fitness and the fourth global optimal position; the position of each Harris hawk in the second Harris hawk population updated in the previous round of iteration is updated again according to the fourth global optimal fitness and the fourth global optimal position; after the update is completed, the second current iteration number is increased by 1 and the next round of iteration is entered; S435. When e~4≥e~3, stop iteration and obtain the second global final optimal position; otherwise, continue iteration until e~4≥e~3; and use the first global final optimal position as the current final number of debugging personnel.

10. A system for implementing the intelligent management method for network engineering construction progress based on machine learning as described in any one of claims 1 to 9.

Images