A Modeling Method for Combat System Architecture Based on Hypernetwork Model

Abstract

The present invention belongs to the technical field of combat systems and discloses a method for modeling a combat system architecture based on a hypernetwork model, including preprocessing the task nodes for constructing the hypernetwork model to obtain the corresponding relationship between the task nodes and the system nodes; constructing a task network according to the corresponding relationship between the task nodes and the system nodes; generalizing and representing the task nodes and the system nodes of the architecture pattern according to the design scheme of the architecture pattern to construct a hybrid structure of the hypernetwork; using the hypernetwork to construct a system network with the generalized and represented task nodes and system nodes; and combining the task network and the system network to construct a combat system architecture model. The present invention can construct a combat system architecture model with multiple architecture scheme selections, which is convenient for decision-makers to make the best choice; this method is of polynomial time, and its return value is significantly better than other benchmark algorithms, and it is optimal under the assumption of the independence of the combat system architecture scheme space.

Description

Technical Field

[0001] The present invention belongs to the technical field of combat systems, and in particular, discloses a combat system architecture modeling method based on a hypernetwork model. Background Art

[0002] With the development of the informatization and intelligence of weapon systems, the interconnections between weapons have become increasingly diverse. In particular, the widespread use of unmanned systems has brought about significant changes in the combat modes of modern warfare. Studying war from the perspective of joint operations is a challenging issue. A system is an integration of a finite number of component systems, which are independent and operable, and are interconnected for a certain period of time to achieve a higher goal. A combat system is a manifestation of a system in the field of war. However, due to the high complexity of combat systems, how to study combat systems is an urgent problem that current researchers need to solve. Fortunately, system architecture provides an effective way to address this problem. System architecture reflects the configuration of components in a system and the interactions between components and the external environment. System architecture focuses on physical entities, information structures, and system functions, and is the core framework of a system. System architecture runs through the entire process of design, requirements demonstration, prototype development, application testing, and field trials. Therefore, by studying combat systems through system architecture and defining a reasonable formal combat system architecture, the optimal configuration of the core elements of combat systems can be achieved. Aiming at the problem of uncertain potential capabilities of combat system architectures, an architecture model, an architecture solution space exploration problem model, and a solution algorithm are constructed. The following problems need to be solved in architecture modeling and selection: First, the potential capabilities of architectures are uncertain. In previous studies, the capabilities of combat systems were determined after the architecture was established. In fact, the uncertainty of architecture potential capabilities is reflected in two aspects: on the one hand, task uncertainty and resource combination diversity; on the other hand, the influence of secondary factors, because only the main factors affecting system capabilities are often considered when designing architectures. Second, if the decision maker chooses to continue developing the architecture, there are multiple strategies to obtain the potential capabilities of the architecture. Therefore, the decision maker should evaluate the expected return values of these strategies to make the best choice. Third, when selecting several optimal architectures from multiple architecture solution spaces, previous studies often only selected one architecture solution, lacking research on the selection of multiple architecture solutions. Therefore, a novel architecture model and a combat system architecture solution space exploration problem need to be constructed to solve the above problems.

[0003] Through the above analysis, the problems and deficiencies of the existing technology are summarized as follows:

[0004] (1) Due to the high complexity of combat systems, how to study combat systems is an urgent problem that current researchers need to solve;

[0005] (2) Since only the main factors affecting the system's capabilities are often considered in the design of the architecture, the potential capabilities of the architecture have uncertainties and are affected by secondary factors;

[0006] (3) Regarding how to select several optimal architectures from multiple architecture solution spaces, previous studies often only select one architecture solution, lacking research on the selection of multiple architecture solutions. Summary of the Invention

[0007] In view of the problems existing in the prior art, the present invention provides a method for modeling the combat system architecture based on a hypernetwork model.

[0008] The present invention is implemented as follows. A method for modeling the combat system architecture based on a hypernetwork model includes:

[0009] Step 1, preprocess the task nodes for constructing the hypernetwork model to obtain the corresponding relationship between the task nodes and the system nodes;

[0010] Step 2, construct a task network according to the corresponding relationship between the task nodes and the system nodes;

[0011] Step 3, based on the design scheme of the architecture pattern, generalize and represent the task nodes and system nodes of the architecture pattern, and construct the hybrid structure of the hypernetwork;

[0012] Step 4, use the hypernetwork to construct a system network with the generalized and represented task nodes and system nodes;

[0013] Step 5, combine the task network and the system network to construct a combat system architecture model.

[0014] Furthermore, in Step 1, the specific steps of preprocessing the task nodes for constructing the hypernetwork model include:

[0015] According to the hypernetwork modeling, unify the expression of the multi-attributes of the task nodes in the network, and normalize the performance metrics;

[0016] Obtain the differential features of different task nodes, and use the differential features as classification features to perform classification using a support vector machine;

[0017] Identify and correspond the classified task nodes of different classes with the comprehensive attributes of the system nodes in sequence.

[0018] Furthermore, the unified expression is to represent the i-th task node in the network as:

[0019] N(i) = <ID_Num, Layer, Attr, Cap>;

[0020] Among them, ID_Num is the sequence identifier of the node in the entire combat system network; Layer is the level within the base network where the node is located; Attr is the representation of the functions possessed by the node, which is represented by a vector; when a certain node has this function, the corresponding position in the vector is 1, otherwise the value is 0; Cap is the performance representation of the node, which is also represented by a vector.

[0021] Furthermore, in step one, obtaining the correspondence between the task nodes and the system nodes includes:

[0022] According to the hypernetwork model, set the number of system nodes connected by each task node selection, and set the limit value of the maximum number of task nodes that a system node can connect to.

[0023] Calculate the selection probability of the task nodes, and adjust the proportion of the rule factor and the random factor in the modeling rule.

[0024] Connect the system nodes with a larger selection probability under different factors to the task nodes.

[0025] Furthermore, in step two, the correspondence between the task nodes and the system nodes is denoted as GTS = <V TA , V SY , E TS >, where E TS represents the edge set between node V TA and node V SY .

[0026] Furthermore, the task network is denoted as G TA = <V TA , E TA >, where V TA represents the set of task nodes, and E TA represents the edge set between the nodes; the task network all has a starting task node, an ending task node, and intermediate nodes.

[0027] Furthermore, the system network represents the functional relationship between system nodes, and the system network is denoted as G SY = <V SY , E SY >, where V SY represents the set of system nodes, and E SY represents the edge set between system nodes.

[0028] Combining all the above technical solutions, the advantages and positive effects of the present invention are:

[0029] By preprocessing the task nodes for constructing the hypernetwork model, the present invention can unify the expression of multiple attributes of task nodes in the network, sort and output according to the relevance degree with the task nodes according to the probability algorithm, effectively improving the efficiency of combat system architecture modeling. Through this modeling method, a combat system architecture model with multiple architecture scheme selections can be constructed, facilitating decision-makers to make the best choice; this method is a polynomial time method, and its return value is significantly better than other benchmark algorithms, and it is optimal under the assumption of the independence of the combat system architecture scheme space. Brief Description of the Drawings

[0030] Figure 1 It is a flowchart of the combat system architecture modeling method based on the hypernetwork model provided by the embodiment of the present invention.

[0031] Figure 2 It is a flowchart of the method for preprocessing the task nodes for constructing the hypernetwork model provided by the embodiment of the present invention.

[0032] Figure 3 It is a flowchart of the method for obtaining the correspondence relationship between task nodes and system nodes provided by the embodiment of the present invention. Detailed Embodiments

[0033] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0034] Aiming at the problems existing in the prior art, the present invention provides a combat system architecture modeling method based on the hypernetwork model, which will be described in detail below with reference to the drawings.

[0035] As Figure 1 shown, the combat system architecture modeling method based on the hypernetwork model provided by the embodiment of the present invention includes:

[0036] S101, preprocess the task nodes for constructing the hypernetwork model to obtain the correspondence relationship between the task nodes and the system nodes;

[0037] S102, construct a task network according to the correspondence relationship between the task nodes and the system nodes;

[0038] S103, according to the design scheme of the architecture mode, generalize and represent the task nodes and system nodes of the architecture mode, and construct the hybrid structure of the hypernetwork;

[0039] S104, use the hypernetwork to construct a system network with the generalized and represented task nodes and system nodes;

[0040] S105. Construct an operational system architecture model by combining the mission network and the system network.

[0041] In step S101 of the example of the present invention, the specific steps for preprocessing the mission nodes for constructing the hypernetwork model include:

[0042] S201. Unify the expression of the multi-attributes of the mission nodes in the network according to hypernetwork modeling, and normalize the performance metrics.

[0043] S202. Obtain the differential features of different mission nodes, and use the differential features as classification features to perform classification using a support vector machine.

[0044] S203. Correspondingly identify the classified mission nodes of different classes with the comprehensive attributes of the system nodes in sequence.

[0045] In the example of the present invention, the unified expression is to represent the i-th mission node in the network as:

[0046] N(i) = <ID_Num, Layer, Attr, Cap>;

[0047] Among them, ID_Num is the sequence identifier of the node in the entire operational system network; Layer is the level within the base network where the node is located; Attr is the representation of the functions possessed by the node, which is represented by a vector; when a certain node has this function, the corresponding position in the vector is 1, otherwise the value is 0; Cap is the performance representation of the node, which is also represented by a vector.

[0048] In step S101 of the example of the present invention, the obtaining of the correspondence relationship between the mission nodes and the system nodes includes:

[0049] S301. Set the number of system nodes connected to each mission node selection according to the hypernetwork model, and set the limit value of the maximum number of mission nodes connected to the system nodes.

[0050] S302. Calculate the selection probability of the mission nodes, and adjust the proportion of the rule factor and the random factor in the modeling rules.

[0051] S303. Connect the system nodes with a relatively large selection probability under different factors to the mission nodes.

[0052] In step S102 of the example of the present invention, the correspondence relationship between the mission nodes and the system nodes is denoted as GTS = <V TA , V SY , E TS >, where E TS represents the edge set between node V TA and node V SY .

[0053] The task network in the embodiment of the present invention is denoted as G TA = <V TA , E TA >>, where V TA represents the set of task nodes, and E TA represents the set of edges between the nodes; the task network all has a start task node, an end task node, and intermediate nodes.

[0054] The system network in the embodiment of the present invention represents the functional relationship between system nodes, and the system network is denoted as G SY = <V SY , E SY >>, where V SY represents the set of system nodes, and E SY represents the set of edges between system nodes.

[0055] As mentioned above, it is only a relatively preferable specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for modeling the combat system architecture based on the hypernetwork model, characterized in that The method for modeling the combat system architecture based on the hypernetwork model includes: Step 1: Preprocess the task nodes for constructing the hypernetwork model to obtain the corresponding relationship between the task nodes and the system nodes; Step 2: Construct a task network according to the corresponding relationship between the task nodes and the system nodes; Step 3: Based on the design scheme of the architecture pattern, generalize and represent the task nodes and system nodes of the architecture pattern, and construct the hybrid structure of the hypernetwork; Step 4: Use the hypernetwork to construct a system network with the generalized and represented task nodes and system nodes; Step 5: Combine the task network and the system network to construct a combat system architecture model; In Step 1, the specific steps for preprocessing the task nodes for constructing the hypernetwork model include: Unify the expression of the multi-attributes of the task nodes in the network according to the hypernetwork modeling, and normalize the performance metrics; Obtain the differential features of different task nodes, and use the support vector machine to classify the differential features as classification features; Sequentially identify and correspond the classified task nodes of different classes with the comprehensive attributes of the system nodes; The unified expression is to represent the i-th task node in the network as: N(i) = <ID_Num, Layer, Attr, Cap>; where ID_Num is the sequence identifier of the node in the entire combat system network; Layer is the level of the node in the base network; Attr is the representation of the functions possessed by the node, which is represented by a vector; when a certain node has this function, the corresponding position of the vector is 1, otherwise the value is 0; Cap is the performance representation of the node, which is also represented by a vector; In Step 1, the obtaining of the corresponding relationship between the task nodes and the system nodes includes: Set the number of system nodes connected to each task node selection according to the hypernetwork model, and set the limit value of the maximum number of task nodes that a system node can connect; Calculate the selection probability of the task nodes, and adjust the proportion of the rule factor and the random factor in the modeling rule; Connect the system nodes with a larger selection probability under different factors to the task nodes; In step 2, the correspondence between the task nodes and the system nodes is denoted as GTS = <V TA , V SY , E TS >, where E TS represents the set of edges between nodes V TA and node V SY .

2. The method for modeling the combat system architecture based on the hypernetwork model according to claim 1, wherein, The task network is denoted as G TA = <V TA , E TA >>, where V TA represents the set of task nodes, and E TA represents the set of edges between nodes; the task network all has a start task node, an end task node, and intermediate nodes.

3. The method for modeling the combat system architecture based on the hypernetwork model according to claim 1, wherein, The system network represents the functional relationships between system nodes, and the system network is denoted as G SY = <V SY , E SY >, where V SY represents the set of system nodes, and E SY represents the set of edges between system nodes.

4. A computer program product stored on a computer-readable medium, including a computer-readable program, which provides a user input interface to apply the method for modeling the combat system architecture based on the hypernetwork model as described in any one of claims 1 to 3 when executed on an electronic device.

5. A computer-readable storage medium stores instructions, which cause a computer to apply the method for modeling the combat system architecture based on the hypernetwork model as described in any one of claims 1 to 3 when the instructions run on the computer.

6. An information data processing terminal, characterized in that, The information data processing terminal is used to implement the method for modeling the combat system architecture based on the hypernetwork model as described in any one of claims 1 to 3.

Images