An information security system capability requirement satisfaction degree evaluation method

Abstract

The application discloses an information guarantee system capacity demand satisfaction degree evaluation method, which comprises the following steps: capacity index set construction: setting a capacity index set, which comprises a first comprehensive index, a second capacity index and a third performance index; capacity index weight determination: based on the capacity index set and Saaty scale, the importance of each index is compared, the importance scale between indexes is determined, a pairwise comparison judgment matrix is constructed and is converted into an attribute judgment matrix to calculate the relative attribute weight, and then based on the hierarchical relationship of the capacity index set, the absolute weight of each index is synthesized; demand satisfaction degree evaluation: the quantitative sample values of all indexes are constructed into a matrix, and each index is converted into a cloud model; based on the cloud model and the qualitative concept Euclidean distance between indexes, the positive and negative distances of the system capacity are calculated, so that the information guarantee system capacity demand satisfaction degree is calculated. The application can intuitively and scientifically calculate the information guarantee system capacity demand satisfaction degree.

Description

Technical Field

[0001] This invention relates to the intersection of uncertainty artificial intelligence and performance evaluation, and in particular to a method for evaluating the satisfaction of capability requirements of an intelligence assurance system. Background Technology

[0002] With the continuous development of information warfare, information data is characterized by multiple sources, diverse types, and massive volumes, posing significant challenges to intelligence support. This has led to major changes in the structure and model of the support system. Real-time monitoring of whether the support system meets current mission requirements is therefore crucial. It allows for strengthening and addressing weaknesses within the support system, thereby continuously improving intelligence support capabilities. The degree to which the support system meets current mission requirements can be termed "requirement fulfillment." Quantifying requirement fulfillment through effectiveness assessment methods can intuitively reveal the current capability status of the system.

[0003] Currently, there are few research methods for assessing the satisfaction of capability requirements. In China, this field is still in its early stages. Most studies assess the satisfaction of capability requirements under deterministic assessment data. These studies are mainly divided into two approaches: constructing an indicator system, defining quantitative formulas for indicator satisfaction, and implementing an assessment algorithm; and constructing a demand satisfaction calculation model based on the working principle and task of the assessment object itself. However, the evaluation process often encounters problems such as the randomness and fuzziness of the assessment data, which leads to inaccurate assessment results.

[0004] To address this issue, some scholars have undertaken the following approaches: constructing a reliability rule base to transform uncertain data into a reliability structure, and introducing evidence-based reasoning methods to solve for capability requirement satisfaction; employing fuzzy comprehensive evaluation to assess capability requirement satisfaction; addressing data uncertainty based on QFD and rough sets; and introducing cloud model theory to determine the level of requirement satisfaction using cloud centroid distance. However, these methods all have different shortcomings, resulting in assessments that are not scientific or objective enough to meet the assessment requirements. Therefore, how to scientifically, reasonably, and objectively assess whether the intelligence support system's capabilities meet the requirements is a crucial and urgent problem that needs to be solved. Summary of the Invention

[0005] To address the aforementioned problems, this invention proposes a method for assessing the satisfaction of capability requirements of an intelligence support system. This method can intuitively and scientifically calculate the satisfaction of capability requirements of the support system. The technical solution adopted by this invention is as follows: A method for assessing the satisfaction of intelligence assurance system capability requirements includes the following steps: S1. Construction of Capability Indicator Set: Set up a capability indicator set, which includes a first-level comprehensive indicator, a second-level capability indicator, and a third-level performance indicator. Each first-level comprehensive indicator corresponds to multiple second-level capability indicators, and each second-level capability indicator corresponds to multiple third-level performance indicators. S2. Determining the weights of capability indicators: Based on the set of capability indicators and the Saaty scale, the importance of each secondary capability indicator and tertiary performance indicator is compared to determine the importance scale between indicators. A pairwise comparison judgment matrix is ​​constructed and converted into an attribute judgment matrix. The relative attribute weights are calculated based on the attribute judgment matrix. Then, the absolute weights of each indicator are synthesized based on the hierarchical relationship of the set of capability indicators. S3. Demand Satisfaction Assessment: Based on the set of capability indicators, construct a matrix from the quantitative sample values ​​of all indicators, and perform cloud model transformation on each indicator. The cloud model includes a weighted performance decision cloud matrix of the evaluation object, a weighted positive ideal cloud, and a weighted negative ideal cloud. Based on the cloud model, calculate the positive and negative distances of the system capability through the qualitative concept of Euclidean distance between indicators, combined with the characteristics of expectation, entropy, and hyperentropy in the cloud model. Finally, use the positive and negative distances of the system capability to calculate the demand satisfaction of the intelligence support system capability.

[0006] Furthermore, the pairwise comparison judgment matrix between the secondary capability indicators is as follows:

[0007] in, For the first i , j The importance scale between the secondary capability indicators n The number of secondary capability indicators; The pairwise comparison judgment matrix between the three-level performance indicators is as follows:

[0008] in, For the first q The first secondary capability indicator corresponds to the first i , j The importance scale between the three-level performance indicators m q For the first q The number of tertiary performance indicators corresponding to each secondary capability indicator.

[0009] Furthermore, the elements of the attribute judgment matrix The conversion formula is:

[0010] in, for N The pairwise comparison judgment matrix between the indicators is the first one. i Line 1 j The column values, where k is the scale value; The pairwise comparison matrix is ​​transformed into the attribute judgment matrix using the above conversion formula: .

[0011] Furthermore, the formula for calculating the relative attribute weights based on the attribute judgment matrix is ​​as follows:

[0012] in, For the first i The relative attribute weights of each secondary capability indicator. For the first i The relative attribute weights of the tertiary performance indicators corresponding to the secondary capability indicators are represented by the following vector form: .

[0013] Furthermore, based on the hierarchical relationship of the aforementioned capability indicator set, the absolute weights of each indicator are synthesized as follows:

[0014] in, For the first The relative weights of each secondary capability indicator.

[0015] Furthermore, based on the aforementioned set of capability indicators, the matrix constructed from the quantified sample values ​​of all indicators is as follows:

[0016] in, For the first The first indicator Each normalized quantized sample value has a value range of 0-1. For the sample size, For the number of indicators; Quantization sample value matrix Expectations of various indicators ,variance ,entropy hyperentropy They are respectively:

[0017]

[0018]

[0019] .

[0020] Furthermore, the weighted performance decision cloud matrix, weighted positive ideal cloud, and weighted negative ideal cloud constructed based on each indicator are as follows:

[0021]

[0022]

[0023] in, For the first M The weight of each indicator.

[0024] Furthermore, based on Euclidean distance reflecting the weighted positive ideal cloud and weighted negative ideal cloud The absolute difference, the formula for calculating the positive distance of system capability is:

[0025] in, The vector's 1-norm, i.e., Euclidean distance. Weighted positive difference matrix The M Column vector, For the first M The weighted positive difference matrix is ​​calculated by considering the positive distances of the indicators:

[0026] The expected difference between the evaluation sample and the positive demand sample in the above formula Entropy difference and hyperentropy difference They are respectively: .

[0027] Furthermore, the formula for calculating the negative distance of the system capability is as follows:

[0028] in, Weighted negative difference matrix The M Column vector, For the first M The weighted negative difference matrix is ​​calculated by taking the negative distances of each performance metric:

[0029] The expected difference between the evaluation sample and the negative demand sample in the above formula Entropy difference and hyperentropy difference They are respectively: .

[0030] Furthermore, using the positive and negative distances of system capabilities, the formula for calculating the satisfaction degree of intelligence support system capability requirements is as follows:

[0031] Among them, satisfaction p The higher the value, the better the requirement is met. p When = 1, it indicates that the system capability fully meets the requirements; when p =0 indicates that the requirements are not met at all; Similarly, the formula for calculating the satisfaction level of each performance requirement is as follows: .

[0032] The beneficial effects of this invention are as follows: (1) The present invention introduces an attribute hierarchy model, which can give full play to the advantages of expert knowledge and is simpler and faster to calculate than the traditional AHP method.

[0033] (2) This invention solves the problem of data uncertainty in demand satisfaction assessment by using cloud model, making the originally vague assessment more accurate.

[0034] (3) Compared with the existing process of standardizing the demand and capability assessment data for accurate numerical satisfaction assessment, the present invention uses the Approximation Ideal Solution Ranking (TOPSIS) method to calculate the positive and negative distances directly using the weighted assessment object performance decision cloud matrix and positive and negative ideal clouds without prior standardization, which saves computing resources to a certain extent. Attached Figure Description

[0035] Figure 1 This is a schematic diagram of the intelligence assurance system capability index set according to an embodiment of the present invention. Detailed Implementation

[0036] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments are now described. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention; that is, the described embodiments are only a part of the embodiments of the invention, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0037] This embodiment provides a method for assessing the satisfaction of intelligence assurance system capability requirements, including the following steps: S1. Construction of Capability Indicator Set: Set up a capability indicator set, which includes a first-level comprehensive indicator, a second-level capability indicator, and a third-level performance indicator. Each first-level comprehensive indicator corresponds to multiple second-level capability indicators, and each second-level capability indicator corresponds to multiple third-level performance indicators. S2. Determining the weights of capability indicators: Based on the set of capability indicators and the Saaty scale, the importance of each secondary capability indicator and tertiary performance indicator is compared to determine the importance scale between indicators. A pairwise comparison judgment matrix is ​​constructed and converted into an attribute judgment matrix. The relative attribute weights are calculated based on the attribute judgment matrix. Then, the absolute weights of each indicator are synthesized based on the hierarchical relationship of the set of capability indicators. S3. Demand Satisfaction Assessment: Based on the set of capability indicators, construct a matrix from the quantitative sample values ​​of all indicators, and perform cloud model transformation on each indicator. The cloud model includes a weighted performance decision cloud matrix of the evaluation object, a weighted positive ideal cloud, and a weighted negative ideal cloud. Based on the cloud model, calculate the positive and negative distances of the system capability through the qualitative concept of Euclidean distance between indicators, combined with the characteristics of expectation, entropy, and hyperentropy in the cloud model. Finally, use the positive and negative distances of the system capability to calculate the demand satisfaction of the intelligence support system capability.

[0038] Preferably, in step S1, when constructing the capability indicator set, a hierarchical indicator system architecture is used to construct a comprehensive capability evaluation indicator set for the intelligence support system, comprising one comprehensive support capability, four sub-capabilities, and 16 performance indicators, based on four aspects: planning and organization capability, data discovery capability, intelligent analysis capability, and data application capability. In step S2, when determining the capability indicator weights, the relative and absolute weights of each indicator are quickly derived using the Attribute Hierarchy Model (AHM) and expert scoring data. In step S3, when assessing the satisfaction of requirements, the numerical characteristics of qualitative concepts are transformed based on the cloud model, and the positive and negative distances are defined using improved Euclidean distance. The Top-Ordered Solution Approximation (TOPSIS) method is then used to calculate the system capability requirement satisfaction and the satisfaction of each performance requirement.

[0039] More preferably, the specific steps of the intelligence assurance system capability requirement satisfaction assessment method in this embodiment are as follows.

[0040] Step S1: Constructing a set of capability indicators.

[0041] Based on the daily operational tasks of the intelligence support system, and to emphasize its capabilities in intelligence, planning, service, and reconnaissance, the comprehensive capabilities of the intelligence support system are divided into four sub-capabilities: planning and organization capability, data discovery capability, intelligent analysis capability, and data application capability. Sixteen performance indicators are further defined, including the timeliness of node planning and organization, the coverage of the scope of action, and the timeliness of intelligent analysis. The specific correspondence between each performance indicator and the capability indicators is as follows: Figure 1 As shown.

[0042] Step S2: Determine the weights of capability indicators.

[0043] Step S201: Combine expert scores to construct pairwise comparison judgment matrices.

[0044] Based on the set of capability indicators constructed in step S1, the importance of each secondary and tertiary indicator is compared according to the Saaty scale to determine the importance scale between indicators, and a pairwise comparison judgment matrix is ​​constructed. The Saaty scale table is as follows: Table 1. Satty Scale

[0045] The pairwise comparison judgment matrix between secondary indicators is as follows: , The number of secondary indicators, i.e. The pairwise comparison judgment matrix of the three-level indicators under the planning and organization capability is as follows: The pairwise comparison judgment matrix of the three-level indicators under data discovery capability is as follows: The pairwise comparison judgment matrix of the three-level indicators under intelligent analysis capability is as follows: The pairwise comparison judgment matrix of the three-level indicators under data application capability is as follows: ,in , , and These represent the number of tertiary performance indicators corresponding to each secondary capability.

[0046] Step S202: Construct an attribute judgment matrix based on pairwise comparison judgment matrices.

[0047] Assumption for The pairwise comparison judgment matrix between the indicators is the first one. Line 1 Column values, attribute determination matrix elements The conversion formula is as follows:

[0048] The pairwise comparison matrix is ​​transformed into an attribute judgment matrix using the above conversion formula, specifically in the following form:

[0049] Step S203: Calculate the relative attribute weights based on the attribute judgment matrix.

[0050] Based on the attribute judgment matrix derived from the transformation formula, the method for calculating the relative weights among the three-level indicators under each sub-capability is as follows:

[0051] The first line is the Weight of each secondary indicator The calculation formula is for the first line, and the remaining lines are the calculation formulas for the weights of the three-level indicators under each sub-capability.

[0052] Its vector representation is:

[0053] Step S204: Synthesize the absolute weights of performance indicators based on the hierarchical relationship of the indicator set:

[0054] in, For the first The relative weights of each secondary indicator.

[0055] Step S3: Demand satisfaction assessment.

[0056] Step S301: Construct a quantized sample value matrix.

[0057] Based on the set of capability indicators for the intelligence support system, a matrix is ​​constructed using the quantitative sample values ​​of all performance indicators. Then the matrix can be represented as

[0058] in, For the first The first indicator Each normalized quantized sample value has a value range of 0-1. For the sample size, This represents the number of performance metrics, with a value of 16.

[0059] Step S302: Perform cloud model conversion on each indicator.

[0060] Using the quantized sample value matrix It can perform cloud model conversion on various evaluation indicators, transforming precise data into qualitative concepts with numerical characteristics based on cloud model theory, as follows: (1) Calculate the expected value of each indicator based on the normalized sample values ​​of each indicator.

[0061]

[0062] (2) Calculate the variance of each indicator using the expected value and normalized sample value of each indicator.

[0063]

[0064] (3) Calculate the entropy of each indicator using the expected value and normalized sample value of each indicator.

[0065]

[0066] (4) By analyzing the variance of each indicator Entropy Together, calculate the hyperentropy of each indicator.

[0067]

[0068] For the set of evaluation objects and indicators, construct a weighted performance decision cloud matrix for the evaluation objects. Weighted positive ideal cloud and weighted negative ideal cloud The specific form is as follows: (5) Weighted evaluation object performance decision cloud matrix

[0069] Based on the sample data of the system capability assessment indicators, the expected value, entropy, and hyperentropy of the cloud model for each indicator are calculated using an inverse cloud generator. A weighted evaluation object performance decision cloud matrix is ​​constructed by introducing the weights of each indicator. The specific form is as follows:

[0070] in, For the first The weights of each performance metric.

[0071] (6) Weighted positive ideal cloud

[0072] Based on sample data of system capability requirement indicators, the expected value, entropy, and hyperentropy of the requirement cloud model for each indicator are calculated using an inverse cloud generator. By introducing the weights of various indicators, a weighted positive ideal cloud is constructed. The specific form is as follows:

[0073] (7) Weighted Negative Ideal Cloud

[0074] The weighted negative ideal cloud corresponds to the lower bound of demand. Therefore, the expectation, entropy, and hyperentropy of the cloud model for each indicator's lower bound are set to 0, 0.005, and 0.005, respectively. The weighted negative ideal cloud is then represented as follows:

[0075] Step S303: Calculate the positive and negative distances of the system capabilities based on the cloud model.

[0076] based on , and By using the qualitative concept of Euclidean distance between indicators, and combining the characteristics of expectation, entropy, and hyperentropy in the cloud model, the positive and negative distances of system capabilities are calculated. The specific calculation formula is as follows: (1) Positive distance of system capability

[0077] Using Euclidean distance to reflect and The absolute difference in the indicator cloud model is expressed by the following formula:

[0078] in, The vector's 1-norm, i.e., Euclidean distance. Weighted positive difference matrix The Column vector, For the first The positive distance of each performance metric is then used to calculate the weighted positive difference matrix. The specific form is as follows:

[0079] Since expectation describes the mean of sample data, and entropy and hyperentropy describe the fuzziness and randomness of sample data, in demand satisfaction assessment, when the expected value of the assessment sample is higher than that of the positive demand sample, or when the entropy and hyperentropy of the assessment sample are lower than those of the positive demand sample, the mean, fuzziness, and randomness are respectively considered to meet the demand; that is, the difference between the assessment sample and the positive demand sample is zero. Based on the above principle, the expected difference between the assessment sample and the positive demand sample is defined. Entropy difference and hyperentropy difference Specifically:

[0080] (2) Negative distance of system capability

[0081] Similar to the positive distance of system capability, the formula for calculating the negative distance of system capability is as follows:

[0082] in, Weighted negative difference matrix The Column vector, For the first The negative distance of each performance metric is then used to calculate the weighted negative difference matrix. The specific form is as follows:

[0083] The expected difference between the evaluation sample and the negative demand sample in the above formula Entropy difference and hyperentropy difference Specifically:

[0084] Step S304: Calculate the degree to which the system's capability requirements and performance requirements are met.

[0085] System requirements satisfaction The calculation method is as follows:

[0086] A higher value indicates a greater degree of satisfaction with the requirements. A value of 1 indicates that the system's capability fully meets the requirements; conversely, a lower value indicates a lower degree of satisfaction. The smaller the value, the less the need is met; when the need is not met at all, the satisfaction level is... The value is 0.

[0087] Similarly, the degree to which the requirements of each performance indicator are met. The calculation formula is as follows: .

[0088] It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

Claims

1. A method for assessing the satisfaction of capability requirements of an intelligence support system, characterized in that, Includes the following steps: S1. Construction of Capability Indicator Set: Set up a capability indicator set, which includes a first-level comprehensive indicator, a second-level capability indicator, and a third-level performance indicator. Each first-level comprehensive indicator corresponds to multiple second-level capability indicators, and each second-level capability indicator corresponds to multiple third-level performance indicators. S2. Determining the weights of capability indicators: Based on the set of capability indicators and the Saaty scale, the importance of each secondary capability indicator and tertiary performance indicator is compared to determine the importance scale between indicators. A pairwise comparison judgment matrix is ​​constructed and converted into an attribute judgment matrix. The relative attribute weights are calculated based on the attribute judgment matrix. Then, the absolute weights of each indicator are synthesized based on the hierarchical relationship of the set of capability indicators. S3. Demand Satisfaction Assessment: Based on the set of capability indicators, construct a matrix from the quantified sample values ​​of all indicators, and perform cloud model transformation on each indicator. The cloud model includes a weighted performance decision cloud matrix of the evaluation object, a weighted positive ideal cloud, and a weighted negative ideal cloud. Based on the cloud model, calculate the positive and negative distances of the system capability through the qualitative concept of Euclidean distance between indicators, combined with the characteristics of expectation, entropy, and hyperentropy in the cloud model. Finally, use the positive and negative distances of the system capability to calculate the demand satisfaction of the intelligence support system capability. The matrix constructed from the quantified sample values ​​of all indicators based on the aforementioned set of capability indicators is as follows: in, For the first The first indicator Each normalized quantized sample value has a value range of 0-1. For the sample size, For the number of indicators; Quantization sample value matrix Expectations of various indicators ,variance ,entropy hyperentropy They are respectively: The weighted performance decision cloud matrix, weighted positive ideal cloud, and weighted negative ideal cloud constructed based on each indicator are as follows: in, For the first M The weight of each indicator; Based on Euclidean distance to reflect weighted positive ideal cloud and weighted negative ideal cloud The absolute difference, the formula for calculating the positive distance of system capability is: in, The vector's 1-norm, i.e., Euclidean distance. Weighted positive difference matrix The M Column vector, For the first M The weighted positive difference matrix is ​​calculated by considering the positive distances of the indicators: The expected difference between the evaluation sample and the positive demand sample in the above formula Entropy difference and hyperentropy difference They are respectively: The formula for calculating the negative distance of the system capability is as follows: in, Weighted negative difference matrix The M Column vector, For the first M The weighted negative difference matrix is ​​calculated by taking the negative distances of each performance metric: The expected difference between the evaluation sample and the negative demand sample in the above formula Entropy difference and hyperentropy difference They are respectively: 。 2. The method for assessing the satisfaction of intelligence support system capability requirements according to claim 1, characterized in that, The pairwise comparison judgment matrix between the secondary capability indicators is as follows: in, For the first i , j The importance scale between the secondary capability indicators n The number of secondary capability indicators; The pairwise comparison judgment matrix between the three-level performance indicators is as follows: in, For the first q The first secondary capability indicator corresponds to the first i , j The importance scale between the three-level performance indicators m q For the first q The number of tertiary performance indicators corresponding to each secondary capability indicator.

3. The method for assessing the satisfaction of intelligence support system capability requirements according to claim 2, characterized in that, Elements of the attribute judgment matrix The conversion formula is: in, for N The pairwise comparison judgment matrix between the indicators is the first one. i Line 1 j The column values, where k is the scale value; The pairwise comparison matrix is ​​transformed into the attribute judgment matrix using the above conversion formula: 。 4. The method for assessing the satisfaction of intelligence support system capability requirements according to claim 3, characterized in that, The formula for calculating the relative attribute weights based on the attribute judgment matrix is ​​as follows: in, For the first i The relative attribute weights of each secondary capability indicator. For the first i The relative attribute weights of the tertiary performance indicators corresponding to the secondary capability indicators are represented by the following vector form: 。 5. The method for assessing the satisfaction of intelligence support system capability requirements according to claim 4, characterized in that, The absolute weights of each indicator are synthesized based on the hierarchical relationship of the aforementioned set of capability indicators: in, For the first The relative weights of each secondary capability indicator.

6. The method for assessing the satisfaction of intelligence support system capability requirements according to claim 1, characterized in that, The formula for calculating the satisfaction degree of intelligence support system capability requirements using the positive and negative distances of system capabilities is as follows: Among them, satisfaction p The higher the value, the better the requirement is met. p When = 1, it indicates that the system capability fully meets the requirements; when p =0 indicates that the requirements are not met at all; Similarly, the formula for calculating the satisfaction level of each performance requirement is as follows: 。

Images