Method and system for unified management and control and rapid arrangement of network stealth security policy

By adopting a two-step search method in the power network and using the combination of words and context vectors, the problem of low search efficiency of existing power network stealth security strategies is solved, and more accurate and efficient strategic positioning is achieved, satisfying the power network Complexity and attack diversity requirements.

CN119011265APending Publication Date: 2024-11-22ELECTRIC POWER RES INST STATE GRID SHANXI ELECTRIC POWER +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411152854.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The existing power network stealth security policy search query methods are inefficient, unable to accurately and quickly locate appropriate response strategies, and unable to fully consider various factors, resulting in inaccurate query results or missing important information.

Method used

Using a two-step search method, first searching through word vectors. If it is invalid, searching with context vectors is combined to obtain search data from the network stealth security policy library, overcoming the technical defects of imperfect category keywords and improving grid data search efficiency.

Benefits of technology

Through the two-layer search method, the unified control and orchestration efficiency of network stealth security policies is improved, the accuracy and completeness of query results are ensured, and the needs of expanding the scale of power network and changing attack methods are met.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119011265A_ABST
    Figure CN119011265A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a method and system for unified management and control and rapid arrangement of network stealth security policies, and belongs to the technical field of network security defense. The method comprises the following steps: acquiring a keyword field of a network stealth security policy; generating word vectors according to the word information of the keyword fields; generating a corresponding first keyword matching result according to the word vector; determining whether the first keyword matching result conforms to the search intention of the keyword field or not; under the condition that it is determined that the first keyword matching result conforms to the search intention of the keyword field, obtaining search data from a network stealth security policy library according to the first keyword matching result; under the condition that it is determined that the first keyword matching result does not conform to the search intention of the keyword field, a context vector used for searching is generated according to the context information; and generating a corresponding second keyword matching result according to the context vector. According to the method and the system, the unified management and control capability and arrangement efficiency of the network stealth security policy can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of network security defense technology, and in particular to a method and system for unified management and rapid arrangement of network stealth security strategies. Background Art

[0002] With the rapid development of information technology, power grids have become an important cornerstone of modern society. However, with the widespread application of network technology, power grids are also facing increasingly severe threats of network attacks. In order to ensure the safe and stable operation of power grids, power grid managers need to preset a variety of response strategies to deal with various possible network attacks.

[0003] However, the existing search and query methods for stealth security strategies in power networks have obvious efficiency problems. Traditional query methods often rely on manual experience or simple keyword matching. These keyword networks are not accurate enough to directly reflect the characteristics of the target strategy, resulting in the inability to accurately and quickly locate the appropriate response strategy. In the context of the ever-expanding scale of power networks and the continuous innovation of attack methods, this inefficient query method can no longer meet actual needs.

[0004] In addition, the complexity of the stealth security strategy of the power network also increases the difficulty of query. Different network attack behaviors may have different characteristics and impacts, so targeted response strategies need to be formulated. However, existing query methods often fail to fully consider various factors, resulting in inaccurate query results or missing important information. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method and system for unified management and rapid orchestration of network stealth security policies, which can improve the unified management and control capabilities and orchestration efficiency of network stealth security policies.

[0006] In order to achieve the above-mentioned purpose, an embodiment of the present invention provides a method for unified management and rapid arrangement of network stealth security policies, including:

[0007] Get the keyword field of the input network stealth security policy;

[0008] Generate a word vector for searching according to the word information of the keyword field;

[0009] Generate a corresponding first keyword matching result according to the word vector;

[0010] Determining whether the first keyword matching result meets the search intent of the keyword field;

[0011] In the case where it is determined that the first keyword matching result meets the search intention of the keyword field, obtaining search data from the network stealth security policy library according to the first keyword matching result;

[0012] In the case where it is determined that the first keyword matching result does not meet the search intention of the keyword field, generating a context vector for searching according to the context information of the keyword field;

[0013] A corresponding second keyword matching result is generated according to the context vector.

[0014] Optionally, generating a word vector for searching according to the word information of the keyword field includes:

[0015] Expanding the word information using a preset synonym library to obtain a corresponding word information set;

[0016] A preset corpus is used to generate a corresponding word vector matrix according to the word information set.

[0017] Optionally, generating a corresponding first keyword matching result according to the word vector includes:

[0018] Calculating the distance between the word vector matrix and the keyword vector matrix of each data index keyword set respectively;

[0019] In order of distance from small to large, the data indexes corresponding to the first S keyword vector matrices are selected as the first keyword matching results.

[0020] Optionally, determining whether the first keyword matching result meets the search intention of the keyword field includes:

[0021] Displaying the first keyword matching result to the user in a pop-up window;

[0022] When the user clicks on any data index in the first keyword matching result, determining that the first keyword matching result meets the search intention of the keyword field;

[0023] When the user clicks the Not Matched button, it is determined that the first keyword matching result does not match the search intention of the keyword field.

[0024] Optionally, acquiring search data from a network stealth security policy library according to the first keyword matching result includes:

[0025] Determine a topological matrix of the first keyword matching result;

[0026] Determine whether the number of topological matrices is greater than or equal to a preset threshold;

[0027] When it is determined that the number of the topological matrices is less than the preset threshold, respectively calculating the distance between the word vector matrix corresponding to the word vector and each topological matrix;

[0028] In order of distance from small to large, select the first S topological class matrices as new first keyword matching results, and return to the step of determining the topological class matrix of the first keyword matching result;

[0029] When it is determined that the number of the topology-like matrices is less than the preset threshold, the content corresponding to the topology-like matrices is used as the search data.

[0030] Optionally, the method comprises:

[0031] Calculate the preselected value S according to formula (1):

[0032]

[0033] Where S is the preselected value of the current generation, γ is the converged perturbation value, and γ>1, S i-1 is the preselected value of the previous generation, and n is the number of iterations.

[0034] Optionally, generating a corresponding second keyword matching result according to the context vector includes:

[0035] Calculating the distance between the vector matrix corresponding to the context vector and the keyword vector matrix of each data index keyword set respectively;

[0036] In order of distance from small to large, the data indexes corresponding to the first S keyword vector matrices are selected as the second keyword matching results.

[0037] Optionally, the method comprises:

[0038] The search data is obtained from the network stealth security policy library according to the second keyword matching result.

[0039] Optionally, acquiring search data from a network stealth security policy library according to the second keyword matching result includes:

[0040] Determine a topological matrix of the second keyword matching result;

[0041] Determine whether the number of topological matrices is greater than or equal to a preset threshold;

[0042] When it is determined that the number of the topological matrices is less than the preset threshold, respectively calculating the distance between the word vector matrix corresponding to the word vector and each topological matrix;

[0043] In order of distance from small to large, select the first S topological class matrices as new second keyword matching results, and return to the step of determining the topological class matrix of the second keyword matching result;

[0044] When it is determined that the number of the topology-like matrices is less than the preset threshold, the content corresponding to the topology-like matrices is used as the search data.

[0045] On the other hand, the present invention also provides a system for unified management and rapid orchestration of network stealth security policies, the system comprising a processor, and the processor is configured to execute any of the methods described above.

[0046] Through the above technical solution, the embodiment of the present invention provides a method and system for unified control and rapid arrangement of network stealth security policies. The method and system, while taking into account the unified control objectives of network stealth security policies and improving the arrangement efficiency, generates a two-step search method, first searches by the first-layer word vector, and then searches in combination with the context vector when the word vector search is invalid. Compared with the prior art, the method and system provided by the present invention overcomes the technical defect of imperfect category keywords by using a two-layer search method, thereby improving the search efficiency of power grid data.

[0047] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0049] Figure 1 is a flow chart of a method for unified management and rapid orchestration of network stealth security policies according to an embodiment of the present invention;

[0050] Figure 2 is a flowchart of a method for obtaining search data according to one embodiment of the present invention;

[0051] Figure 3 is a flowchart of a method for obtaining search data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0053] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0054] like Figure 1 The figure is a flow chart of a method for unified management and rapid arrangement of network stealth security policies according to the present invention. Figure 1 In the method, the method may include the following steps:

[0055] In step S10, a keyword field of the input network stealth security policy is obtained;

[0056] In step S11, a word vector for searching is generated according to word information of the keyword field;

[0057] In step S12, a corresponding first keyword matching result is generated according to the word vector;

[0058] In step S13, determining whether the first keyword matching result meets the search intention of the keyword field;

[0059] In step S14, when it is determined that the first keyword matching result meets the search intention of the keyword field, the search data is obtained from the network stealth security policy library according to the first keyword matching result;

[0060] In step S15, when it is determined that the first keyword matching result does not meet the search intention of the keyword field, a context vector for searching is generated according to the context information of the keyword field;

[0061] In step S16, a corresponding second keyword matching result is generated according to the context vector.

[0062] In this Figure 1 In the method shown, step S10 can be used to obtain an input keyword field. The keyword field can be obtained by a user inputting text information in a search bar.

[0063] Step S11 can be used to generate a word vector for searching based on the word information of the keyword field. Considering the usage habits of network stealth security policy words, idiomatic expressions may be input in actual input, such as "port xx is not open", etc. Therefore, when generating word vectors in step S11, they can be expanded by synonyms. Specifically, step S11 can be to first expand the word information using a preset synonym library to obtain a corresponding word information set, and then use a preset corpus to generate a corresponding word vector matrix based on the word information set.

[0064] Step S12 can be used to generate the corresponding first keyword matching result according to the word vector. Specifically, step S12 can be to first calculate the distance between the word vector matrix and the keyword vector matrix of each data index keyword set, and then select the data index corresponding to the first S keyword vector matrices as the first keyword matching result in order of distance from small to large. The distance can be, for example, the Euclidean distance.

[0065] Step S13 can be used to determine whether the first keyword matching result meets the search intent of the keyword field. Specifically, step S13 can be to display the first keyword matching result to the user in a pop-up window. When the user clicks on any data index of the first keyword matching result, it is determined that the first keyword matching result meets the search intent of the keyword field. On the contrary, when the user clicks on the "Not Meet" button, it can be determined that the first keyword matching result does not meet the search intent of the keyword field.

[0066] When it is determined that the first keyword matching result meets the search intention of the keyword field, step S14 can be executed, that is, obtaining search data from the network stealth security policy library according to the first keyword matching result. The specific method for obtaining the search data can be various forms known to those skilled in the art. In an example of the present invention, step S14 may include: Figure 2 In the steps shown in Figure 2 In the step S14, the step S14 may further include the following steps:

[0067] In step S20, a topological class matrix of the first keyword matching result is determined;

[0068] In step S21, it is determined whether the number of topological matrices is greater than or equal to a preset threshold;

[0069] In step S22, when it is determined that the number of topological class matrices is less than a preset threshold, the distance between the word vector matrix corresponding to the word vector and each topological class matrix is ​​calculated respectively;

[0070] In step S23, the first S topological class matrices are selected as the new first keyword matching result in order of distance from small to large, and the step of determining the topological class matrix of the first keyword matching result is returned, that is, the step of returning to execute step S20. Among them, the preselected value S can be obtained in a variety of forms known to those skilled in the art, such as directly obtaining it based on human experience. In one example of the present invention, considering that the preselected value S needs to be determined based on the number of topological class matrices currently determined, when the number is large, the preselected value S can also be large, and as the number of iterations gradually increases, the number of topological class matrices gradually decreases, then the preselected value S should also gradually decrease. Therefore, in one example of the present invention, the preselected value S can be determined according to the following formula (1),

[0071]

[0072] Where S is the preselected value of the current generation, γ is the convergence perturbation value, and γ>1, S i-1 is the preselected value of the previous generation, and n is the number of iterations.

[0073] In step S24, when it is determined that the number of topology-like matrices is less than a preset threshold, the content corresponding to the topology-like matrices is used as search data.

[0074] In the case where it is determined that the first keyword matching result does not meet the search intention of the keyword field, step S15 can be executed at this time, that is, generating a context vector for searching based on the context information of the keyword field. Context information is the semantic information representing the association between the first one or more words and the last one or more words in the keyword field. Compared with a single word, it has more associated semantics. Therefore, in this embodiment, when the word vector cannot be matched, further matching through context information can maximize the efficiency of the search. The specific method of step S16 to generate the corresponding second keyword matching result based on the context vector can be similar to the aforementioned step S12. Specifically, step S16 can be to first calculate the distance between the vector matrix corresponding to the context vector and the keyword vector matrix of each data index keyword set, and then select the data index corresponding to the first S keyword vector matrices as the second keyword matching result in order of distance from small to large, and finally obtain the search data from the network stealth security policy library based on the second keyword matching result.

[0075] The specific method for obtaining search data from the network stealth security policy library according to the second keyword matching result in step S16 may be similar to the aforementioned step S14. Specifically, step S16 may include: Figure 3 In the steps shown in Figure 3 In the step S16, the step S16 may further include:

[0076] In step S30, a topological class matrix of the second keyword matching result is determined;

[0077] In step S31, it is determined whether the number of topological matrices is greater than or equal to a preset threshold;

[0078] In step S32, when it is determined that the number of topology class matrices is less than a preset threshold, the distance between the vector matrix corresponding to the context vector and each topology class matrix is ​​calculated respectively;

[0079] In step S33, the first S topological class matrices are selected as the new second keyword matching result in the order of distance from small to large, and the step of determining the topological class matrix of the second keyword matching result is returned to, that is, step S30 is returned to. Similarly, the preselected value S can also be determined by formula (1).

[0080] In step S34, when it is determined that the number of topology-like matrices is less than a preset threshold, the content corresponding to the topology-like matrices is used as search data.

[0081] On the other hand, the present invention also provides a system for unified management and rapid arrangement of network stealth security policies, the system comprising a processor, the processor being configured to execute any of the above methods. The method may include: Figures 1 to 3 In the steps shown in Figure 1 In the method, the method may include the following steps:

[0082] In step S10, a keyword field of the input network stealth security policy is obtained;

[0083] In step S11, a word vector for searching is generated according to word information of the keyword field;

[0084] In step S12, a corresponding first keyword matching result is generated according to the word vector;

[0085] In step S13, determining whether the first keyword matching result meets the search intention of the keyword field;

[0086] In step S14, when it is determined that the first keyword matching result meets the search intention of the keyword field, the search data is obtained from the network stealth security policy library according to the first keyword matching result;

[0087] In step S15, when it is determined that the first keyword matching result does not meet the search intention of the keyword field, a context vector for searching is generated according to the context information of the keyword field;

[0088] In step S16, a corresponding second keyword matching result is generated according to the context vector.

[0089] In this Figure 1 In the method shown, step S10 can be used to obtain an input keyword field. The keyword field can be obtained by a user inputting text information in a search bar.

[0090] Step S11 can be used to generate a word vector for searching based on the word information of the keyword field. Considering the usage habits of network stealth security policy words, idiomatic expressions may be input in actual input, such as "port xx is not open", etc. Therefore, when generating word vectors in step S11, they can be expanded by synonyms. Specifically, step S11 can be to first expand the word information using a preset synonym library to obtain a corresponding word information set, and then use a preset corpus to generate a corresponding word vector matrix based on the word information set.

[0091] Step S12 can be used to generate the corresponding first keyword matching result according to the word vector. Specifically, step S12 can be to first calculate the distance between the word vector matrix and the keyword vector matrix of each data index keyword set, and then select the data index corresponding to the first S keyword vector matrices as the first keyword matching result in order of distance from small to large. The distance can be, for example, the Euclidean distance.

[0092] Step S13 can be used to determine whether the first keyword matching result meets the search intent of the keyword field. Specifically, step S13 can be to display the first keyword matching result to the user in a pop-up window. When the user clicks on any data index of the first keyword matching result, it is determined that the first keyword matching result meets the search intent of the keyword field. On the contrary, when the user clicks on the "Not Meet" button, it can be determined that the first keyword matching result does not meet the search intent of the keyword field.

[0093] When it is determined that the first keyword matching result meets the search intention of the keyword field, step S14 can be executed, that is, obtaining search data from the network stealth security policy library according to the first keyword matching result. The specific method for obtaining the search data can be various forms known to those skilled in the art. In an example of the present invention, step S14 may include: Figure 2 In the steps shown in Figure 2 In the step S14, the step S14 may further include the following steps:

[0094] In step S20, a topological class matrix of the first keyword matching result is determined;

[0095] In step S21, it is determined whether the number of topological matrices is greater than or equal to a preset threshold;

[0096] In step S22, when it is determined that the number of topological class matrices is less than a preset threshold, the distance between the word vector matrix corresponding to the word vector and each topological class matrix is ​​calculated respectively;

[0097] In step S23, the first S topological class matrices are selected as the new first keyword matching result in order of distance from small to large, and the step of determining the topological class matrix of the first keyword matching result is returned, that is, the step of returning to execute step S20. Among them, the preselected value S can be obtained in a variety of forms known to those skilled in the art, such as directly obtaining it based on human experience. In one example of the present invention, considering that the preselected value S needs to be determined based on the number of topological class matrices currently determined, when the number is large, the preselected value S can also be large, and as the number of iterations gradually increases, the number of topological class matrices gradually decreases, then the preselected value S should also gradually decrease. Therefore, in one example of the present invention, the preselected value S can be determined according to the following formula (1),

[0098]

[0099] Where S is the preselected value of the current generation, γ is the convergence perturbation value, and γ>1, S i-1 is the preselected value of the previous generation, and n is the number of iterations.

[0100] In step S24, when it is determined that the number of topology-like matrices is less than a preset threshold, the content corresponding to the topology-like matrices is used as search data.

[0101] In the case where it is determined that the first keyword matching result does not meet the search intention of the keyword field, step S15 can be executed at this time, that is, generating a context vector for searching based on the context information of the keyword field. Context information is the semantic information representing the association between the first one or more words and the last one or more words in the keyword field. Compared with a single word, it has more associated semantics. Therefore, in this embodiment, when the word vector cannot be matched, further matching through context information can maximize the efficiency of the search. The specific method of step S16 to generate the corresponding second keyword matching result based on the context vector can be similar to the aforementioned step S12. Specifically, step S16 can be to first calculate the distance between the vector matrix corresponding to the context vector and the keyword vector matrix of each data index keyword set, and then select the data index corresponding to the first S keyword vector matrices as the second keyword matching result in order of distance from small to large, and finally obtain the search data from the network stealth security policy library based on the second keyword matching result.

[0102] The specific method for obtaining search data from the network stealth security policy library according to the second keyword matching result in step S16 may be similar to the aforementioned step S14. Specifically, step S16 may include: Figure 3 In the steps shown in Figure 3 In the step S16, the step S16 may further include:

[0103] In step S30, a topological class matrix of the second keyword matching result is determined;

[0104] In step S31, it is determined whether the number of topological matrices is greater than or equal to a preset threshold;

[0105] In step S32, when it is determined that the number of topology class matrices is less than a preset threshold, the distance between the vector matrix corresponding to the context vector and each topology class matrix is ​​calculated respectively;

[0106] In step S33, the first S topological class matrices are selected as the new second keyword matching result in the order of distance from small to large, and the step of determining the topological class matrix of the second keyword matching result is returned to, that is, step S30 is returned to. Similarly, the preselected value S can also be determined by formula (1).

[0107] In step S34, when it is determined that the number of topology-like matrices is less than a preset threshold, the content corresponding to the topology-like matrices is used as search data.

[0108] Through the above technical solution, the embodiment of the present invention provides a method and system for unified control and rapid arrangement of network stealth security policies. The method and system, while taking into account the unified control objectives of network stealth security policies and improving the arrangement efficiency, generates a two-step search method, first searches by the first-layer word vector, and then searches in combination with the context vector when the word vector search is invalid. Compared with the prior art, the method and system provided by the present invention overcomes the technical defect of imperfect category keywords by using a two-layer search method, thereby improving the search efficiency of power grid data.

[0109] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0110] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0114] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0115] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0116] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0117] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for unified control and rapid orchestration of network stealth security policies, It is characterized in that The method comprises: Get the keyword field of the input network stealth security policy; Generate a word vector for searching according to the word information of the keyword field; Generate a corresponding first keyword matching result according to the word vector; Determining whether the first keyword matching result meets the search intent of the keyword field; In the case where it is determined that the first keyword matching result meets the search intention of the keyword field, obtaining search data from the network stealth security policy library according to the first keyword matching result; In the case where it is determined that the first keyword matching result does not meet the search intention of the keyword field, generating a context vector for searching according to the context information of the keyword field; A corresponding second keyword matching result is generated according to the context vector.

2. The method according to claim 1, It is characterized in that Generating a word vector for searching according to the word information of the keyword field includes: Expanding the word information using a preset synonym library to obtain a corresponding word information set; A preset corpus is used to generate a corresponding word vector matrix according to the word information set.

3. The method according to claim 2, It is characterized in that Generating a corresponding first keyword matching result according to the word vector includes: Calculating the distance between the word vector matrix and the keyword vector matrix of each data index keyword set respectively; In order of distance from small to large, the data indexes corresponding to the first S keyword vector matrices are selected as the first keyword matching results.

4. The method according to claim 1, It is characterized in that Determining whether the first keyword matching result meets the search intention of the keyword field includes: Displaying the first keyword matching result to the user in a pop-up window; When the user clicks on any data index in the first keyword matching result, determining that the first keyword matching result meets the search intention of the keyword field; When the user clicks the Not Matched button, it is determined that the first keyword matching result does not match the search intention of the keyword field.

5. The method according to claim 1, It is characterized in that Acquiring search data from a network stealth security policy library according to the first keyword matching result includes: Determine a topological matrix of the first keyword matching result; Determine whether the number of topological matrices is greater than or equal to a preset threshold; When it is determined that the number of the topological matrices is less than the preset threshold, respectively calculating the distance between the word vector matrix corresponding to the word vector and each topological matrix; In order of distance from small to large, select the first S topological class matrices as new first keyword matching results, and return to the step of determining the topological class matrix of the first keyword matching result; When it is determined that the number of the topology-like matrices is less than the preset threshold, the content corresponding to the topology-like matrices is used as the search data.

6. The method according to claim 5, It is characterized in that The method comprises: Calculate the preselected value S according to formula (1): Where S is the preselected value of the current generation, γ is the converged perturbation value, and γ>1, S i -1 is the preselected value of the previous generation, and n is the number of iterations.

7. The method according to claim 2, It is characterized in that Generating a corresponding second keyword matching result according to the context vector includes: Calculating the distance between the vector matrix corresponding to the context vector and the keyword vector matrix of each data index keyword set respectively; In order of distance from small to large, the data indexes corresponding to the first S keyword vector matrices are selected as the second keyword matching results.

8. The method according to claim 1, It is characterized in that The method comprises: The search data is obtained from the network stealth security policy library according to the second keyword matching result.

9. The method according to claim 8, It is characterized in that Acquiring search data from a network stealth security policy library according to the second keyword matching result includes: Determine a topological matrix of the second keyword matching result; Determine whether the number of topological matrices is greater than or equal to a preset threshold; When it is determined that the number of the topological matrices is less than the preset threshold, respectively calculating the distance between the word vector matrix corresponding to the word vector and each topological matrix; In order of distance from small to large, select the first S topological class matrices as new second keyword matching results, and return to the step of determining the topological class matrix of the second keyword matching result; When it is determined that the number of the topology-like matrices is less than the preset threshold, the content corresponding to the topology-like matrices is used as the search data.

10. A system for unified control and rapid orchestration of network stealth security strategies, It is characterized in that The system comprises a processor configured to execute the method according to any one of claims 1 to 9.

Citation Information

Cited By

  • A method for building a knowledge base of asset state data fused with threat intelligence

    CN122783335A