Improved method and system for evaluating pattern recognition networkTechnical Field
The present application relates to the field of network multimedia, and more particularly, to an improved method and system for pattern recognition network evaluation.
Background
The existing network security assessment is modeled by adopting a clustering analysis method, however, parameters in a real scene are not in a fixed corresponding relation with a network environment, so that the actual application value of the existing assessment method is low. If only the correspondence between the scene parameters and the network environment is improved, the correspondence is still affected by the number of samples, so that the evaluation accuracy is affected, and a great amount of calculation is brought to repeated evaluation.
Accordingly, there is an urgent need for a method and system for targeted and improved pattern recognition network evaluation.
Disclosure of Invention
The invention aims to provide an improved method and system for evaluating a pattern recognition network, which are characterized in that a network security parameter set is established, historical data are combined to form a training sample set, two samples are sequentially extracted to construct sample pairs, a branch convolutional neural network is utilized to reject sample pairs which do not belong to the same category, a second training sample set is obtained again, the pattern recognition method is called to train the second sample set, the optimal solution is solved to obtain the required vector width, and finally an evaluation model is established, so that the influence of the number of samples is reduced.
In a first aspect, the present application provides a method of improved pattern recognition network evaluation, the method comprising:
collecting network environment parameters, gathering the network environment parameters in terms, and establishing a network security parameter set;
Assigning a value to the network security parameter set according to the value of the network environment parameter;
Requesting a server for historical values of the network security parameter set, and listing the historical values and the collected current values into a vector by terms, wherein each term forms a training sample set;
Sequentially extracting two samples from the training sample set, constructing a sample pair, respectively inputting the two samples of the sample pair into a branch convolutional neural network, calculating a similar probability value between the sample pair, judging whether the samples belong to the same category according to the size of the similar probability value, if so, re-storing the weights of the samples into the training sample set, otherwise, removing the sample pair by the training sample set;
Obtaining a second training sample set through the branch convolutional neural network;
Invoking a pattern recognition unit to train the second training sample set, extracting a single item of historical value in the second training sample set, multiplying the historical value by alpha, and meeting a first condition that the sum of a multiplication result and a preset constant a is equal to 0, wherein alpha is a convex set coefficient, and the reciprocal of an absolute value of alpha is defined as a vector width;
the values of the preset constants a and b depend on the type of the current network, the server stores a mapping relation between the network type and the preset constants in advance, and the a and b are a pair of constants;
Invoking an operation unit to calculate a bias guide for the second condition, wherein the bias guide is operated based on the alpha and the beta respectively to obtain an optimal solution of the vector width;
Taking the optimal solution of the vector width as an input parameter of a decision function of a network security evaluation model, and establishing an evaluation model;
And inputting the collected network environment parameters into the evaluation model, and judging whether the network environment is safe or not.
With reference to the first aspect, in a first possible implementation manner of the first aspect, the clustering of the items includes a clustering operation, complexing and analyzing local area networks of a same type or adjacent positions, and collecting data according to a specified item.
With reference to the first aspect, in a second possible implementation manner of the first aspect, when the network environment is judged to be unsafe, the current network environment parameter reporting server is recorded.
With reference to the first aspect, in a third possible implementation manner of the first aspect, the operation unit adopts a neural network model.
In a second aspect, the present application provides a system for improved pattern recognition network evaluation, the system comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to perform the method according to any one of the four possible aspects of the first aspect according to instructions in the program code.
In a third aspect, the present application provides a computer readable storage medium for storing program code for performing the method of any one of the four possibilities of the first aspect.
Advantageous effects
The invention provides an improved method and system for evaluating a pattern recognition network, which are characterized in that a training sample set is formed by establishing a network security parameter set and combining historical data items, then sample pairs are sequentially constructed, sample pairs which do not belong to the same category are removed, a second training sample set is obtained again, the second sample set is trained by calling the pattern recognition method, the optimal solution is solved to obtain the required vector width, and an evaluation model is established, so that the dynamic correspondence of scene parameters and the network environment can be realized, the influence of the number of samples can be reduced, and the efficiency of network security evaluation is further improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making clear and defining the scope of the present invention.
FIG. 1 is a flow chart of a method for improved pattern recognition network evaluation provided by the present application, comprising:
collecting network environment parameters, gathering the network environment parameters in terms, and establishing a network security parameter set;
Assigning a value to the network security parameter set according to the value of the network environment parameter;
Requesting a server for historical values of the network security parameter set, and listing the historical values and the collected current values into a vector by terms, wherein each term forms a training sample set;
Sequentially extracting two samples from the training sample set, constructing a sample pair, respectively inputting the two samples of the sample pair into a branch convolutional neural network, calculating a similar probability value between the sample pair, judging whether the samples belong to the same category according to the size of the similar probability value, if so, re-storing the weights of the samples into the training sample set, otherwise, removing the sample pair by the training sample set;
Obtaining a second training sample set through the branch convolutional neural network;
Invoking a pattern recognition unit to train the second training sample set, extracting a single item of historical value in the second training sample set, multiplying the historical value by alpha, and meeting a first condition that the sum of a multiplication result and a preset constant a is equal to 0, wherein alpha is a convex set coefficient, and the reciprocal of an absolute value of alpha is defined as a vector width;
the values of the preset constants a and b depend on the type of the current network, the server stores a mapping relation between the network type and the preset constants in advance, and the a and b are a pair of constants;
Invoking an operation unit to calculate a bias guide for the second condition, wherein the bias guide is operated based on the alpha and the beta respectively to obtain an optimal solution of the vector width;
Taking the optimal solution of the vector width as an input parameter of a decision function of a network security evaluation model, and establishing an evaluation model;
And inputting the collected network environment parameters into the evaluation model, and judging whether the network environment is safe or not.
In some preferred embodiments, the aggregation of the items includes a clustering operation that complexes and analyzes local area networks of the same type or adjacent locations, and the aggregation of the items further includes collecting data according to specified items.
In some preferred embodiments, when the network environment is judged to be unsafe, the current network environment parameter reporting server is recorded.
In some preferred embodiments, the arithmetic unit employs a neural network model.
The present application provides an improved pattern recognition network evaluation system comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
The processor is configured to perform the method according to any of the embodiments of the first aspect according to instructions in the program code.
The present application provides a computer readable storage medium for storing program code for performing the method of any one of the embodiments of the first aspect.
In a specific implementation, the present invention also provides a computer storage medium, where the computer storage medium may store a program, where the program may include some or all of the steps in the various embodiments of the present invention when executed. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a Random Access Memory (RAM).
It will be apparent to those skilled in the art that the techniques of embodiments of the present invention may be implemented in software plus a necessary general purpose hardware platform. Based on such understanding, the technical solutions in the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the embodiments or some parts of the embodiments of the present invention.
The same or similar parts between the various embodiments of the present description are referred to each other. In particular, for the embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference should be made to the description of the method embodiments for the matters.
The embodiments of the present invention described above do not limit the scope of the present invention.