Information processing apparatus, information processing method, and program

Abstract

To provide an information processing apparatus which reduces temporal cost in a case of performing system design.SOLUTION: An information processing apparatus 100 comprises: a design unit 121 that generates design path information representing a design process of system configuration information designed by converting an abstract element to a concrete element using an embodying rule, for system configuration information representing a system configuration composed of a combination of elements; a conversion unit 122 that generates embedded design path information in which information of dominant conception of an element included in the system configuration information is given for each system configuration information included in the design path information; a reward setting unit 123 that sets reward for the system configuration information depending on whether or not the element included in the system configuration information is the concrete element, for each system configuration information included in the embedded design path information; and a learning data generation unit 124 that generates each system configuration information piece included in the embedded design path information and the reward set to the system configuration information, as learning data.SELECTED DRAWING: Figure 25

Description

[Technical field]

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] When designing an ICT (Information and Communication Technology) system, the first step is to define the requirements, where the designer creates system requirements, which are information that summarizes the customer's requirements. At this stage, the system requirements generally contain abstract information, and in most cases do not represent a deployable system configuration as is. Therefore, the designer gradually concretizes the abstract information contained in the system requirements, eventually designing a system configuration in which all information is concrete and deployable.

[0003] This series of actions requires specialized knowledge about the elements contained in the system configuration and the relationships between the elements, so the more advanced the system becomes, the greater the design effort and human costs required.

[0004] As a method for solving the above problems, automatic system design technology has been proposed. Automatic system design technology is a technology that automatically derives a system configuration consisting of only concrete information based on system requirements that include abstract information.

[0005] As a related technology, Patent Document 1 discloses a system configuration derivation device that can gradually concretize the abstract parts contained in the requirements based on the system requirements, and derive a deployable and concrete ICT system configuration.

[0006] According to the system configuration derivation device of Patent Document 1, a method of calculating a score that represents the degree of appropriateness of a concretization rule, which is a rule for rewriting in more detail a part of a configuration requirement that represents a requirement related to an ICT system, is learned.

[0007] A device that has learned in this way is able to quickly and automatically design a specific system configuration by selecting appropriate instantiation rules when abstract system requirements are input. [Prior art documents] [Patent documents]

[0008] [Patent Document 1] Patent No. 6989014 Summary of the Invention [Problem to be solved by the invention]

[0009] However, in the technology described in the above-mentioned Patent Document 1, the accuracy of the evaluation by the device for new elements (unlearned elements) that do not exist in the past learning process is not guaranteed. Therefore, when a system is designed using unlearned elements, the device cannot utilize the learning experience regarding elements that have been learned in the past to evaluate the quality of the unlearned elements, and a highly accurate system design cannot be performed.

[0010] Therefore, the technology described in Patent Document 1 has a problem in that when designing a system using a new element, the device needs to be re-learned, which is time-consuming and costly.

[0011] Therefore, one of the objectives of the present disclosure is to solve the above-mentioned problem of the time-consuming cost involved in system design. [Means for solving the problem]

[0012] An information processing device according to an embodiment of the present disclosure includes: a design unit that generates design path information representing a design process of the system configuration information, which represents a system configuration consisting of a combination of elements, by converting abstract elements into concrete elements using preset instantiation rules; a conversion unit that generates embedded design path information by adding information on an element corresponding to a superordinate concept of an element included in the system configuration information to each of the system configuration information included in the design path information; a reward setting unit that sets a reward for each of the system configuration information included in the embedded design path information depending on whether an element included in the system configuration information is a specific element; a learning data generation unit that generates each of the system configuration information included in the embedded design path information and the reward set for the system configuration information as learning data to be machine-learned to generate a model that converts the system configuration information based on the instantiation rule; Equipped with The structure is as follows. In addition, an information processing method according to an embodiment of the present disclosure includes: generating design path information representing a design process of the system configuration information, which is designed by converting abstract elements into concrete elements using preset instantiation rules, for system configuration information representing a system configuration consisting of a combination of elements; generating embedded design path information for each of the system configuration information included in the design path information, the embedded design path information being provided with information on an element corresponding to a superordinate concept of the element included in the system configuration information; For each of the system configuration information included in the embedded design path information, a reward for the system configuration information is set according to whether an element included in the system configuration information is a specific element; Each of the system configuration information included in the embedded design path information and the reward set for the system configuration information are generated as learning data to be machine-learned to generate a model for converting the system configuration information based on the instantiation rule. The structure is as follows. In addition, a program according to an embodiment of the present disclosure includes: generating design path information representing a design process of the system configuration information, which is designed by converting abstract elements into concrete elements using preset instantiation rules, for system configuration information representing a system configuration consisting of a combination of elements; generating embedded design path information for each of the system configuration information included in the design path information, the embedded design path information being provided with information on an element corresponding to a superordinate concept of the element included in the system configuration information; For each of the system configuration information included in the embedded design path information, a reward for the system configuration information is set according to whether an element included in the system configuration information is a specific element; Each of the system configuration information included in the embedded design path information and the reward set for the system configuration information are generated as learning data to be machine-learned to generate a model for converting the system configuration information based on the instantiation rule. Have a computer carry out the process, The structure is as follows. Effect of the Invention

[0013] By being configured as described above, the present disclosure can reduce time costs when designing a system. [Brief description of the drawings]

[0014] [Figure 1] FIG. 1 is a diagram for explaining automatic design of a system. [Diagram 2] FIG. 1 is a diagram for explaining automatic design of a system. [Diagram 3] FIG. 1 is a diagram for explaining automatic design of a system. [Figure 4] FIG. 1 is a diagram for explaining automatic design of a system. [Diagram 5] FIG. 1 is a diagram for explaining automatic design of a system. [Figure 6] 1 is a block diagram showing a configuration of an information processing system according to the present disclosure. [Figure 7] 4 is a flowchart showing a processing operation of the information processing system according to the present disclosure. [Figure 8] 4 is a flowchart showing a processing operation of the information processing system according to the present disclosure. [Figure 9] 4 is a flowchart showing a processing operation of the information processing system according to the present disclosure. [Figure 10] FIG. 1 is a diagram showing a process performed by an information processing system according to the present disclosure. [Figure 11] FIG. 1 is a diagram showing a process performed by an information processing system according to the present disclosure. [Figure 12] FIG. 1 is a diagram showing a process performed by an information processing system according to the present disclosure. [Figure 13] 4 is a flowchart showing a processing operation of the information processing system according to the present disclosure. [Figure 14] FIG. 1 is a diagram showing a process performed by an information processing system according to the present disclosure. [Figure 15] 4 is a flowchart showing a processing operation of the information processing system according to the present disclosure. [Figure 16] FIG. 1 is a diagram showing a process performed by an information processing system according to the present disclosure. [Figure 17] 4 is a flowchart showing a processing operation of the information processing system according to the present disclosure. [Figure 18] FIG. 1 is a diagram showing a process performed by an information processing system according to the present disclosure. [Figure 19] FIG. 1 is a diagram showing a process performed by an information processing system according to the present disclosure. [Figure 20] 4 is a flowchart showing a processing operation of the information processing system according to the present disclosure. [Figure 21] 4 is a flowchart showing a processing operation of the information processing system according to the present disclosure. [Figure 22] 4 is a flowchart showing a processing operation of the information processing system according to the present disclosure. [Diagram 23] 4 is a flowchart showing a processing operation of the information processing system according to the present disclosure. [Figure 24] FIG. 2 is a block diagram showing a hardware configuration of an information processing device according to the present disclosure. [Diagram 25] 1 is a block diagram showing a configuration of an information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] <First embodiment> A first embodiment of the present disclosure will be described with reference to the drawings. Note that the drawings may be relevant to any embodiment.

[0016] [overview] First, an overview of automatic design of an ICT system in this embodiment will be described. First, as a premise, the requirements and configuration of an ICT system can be expressed in a graph. A graph represents elements (components and relationships between the components) included in the configuration of an ICT system using nodes or edges. A node is an element that represents, for example, a device or an application. An edge is an element that represents a connection relationship between two nodes.

[0017] As an example of an ICT system, the design of a face recognition system will be described. When designing a face recognition system, the designer first creates the system requirements for the face recognition system.

[0018] Fig. 1 is a diagram for explaining the automatic design of a face recognition system. Graph G1 in Fig. 1 is a graph representing the configuration of system requirements R1 of a face recognition system. Graph G1 in Fig. 1 is represented using nodes N1, N2, N3, and N4, and edges E1, E2, and E3.

[0019] Node N1 represents a camera function (solid circle) which is a concrete element, node N2 represents a face recognition function (solid circle) which is a concrete element, node N3 represents a server computer function (solid circle) which is a concrete element, and node N4 represents a server computer function (dashed circle) which is an abstract element. Edge E1 represents an HTTP communication function (dashed arrow) which is an abstract element, and edges E2 and E3 represent join (affiliation) functions (solid arrows) which are concrete elements. The parts of graph G1 (system requirements) in FIG. 1 will be described later.

[0020] Fig. 2 is a diagram for explaining the data structure of part information, which is the information on the elements described above. In the part information P1 shown in Fig. 2, for each piece of part identification information that identifies a node and an edge, function information (also called type) of the node or edge is associated with information (concrete (1) / abstract (0)) indicating whether this node or edge is a concrete part (element) or an abstract part (element).

[0021] Fig. 3 is a diagram for explaining the data structure of a system requirement. System requirement R1 in Fig. 3 is a system requirement corresponding to graph G1 shown in Fig. 1. System requirement R1 includes component identification information for identifying all nodes included in the requirement. System requirement R1 is information including component identification information for identifying all edges included in the requirement, component identification information for identifying nodes at the start points of the edges, and component identification information for identifying nodes at the end points of the edges.

[0022] In the above-mentioned Figures 1 to 3, the graphs, part information, and system requirements are explained using the graph G1, part information P1, and system requirements R1, but the graphs, part information, and system requirements are not limited to the graph G1, part information P1, and system requirements R1 shown in Figures 1 to 3.

[0023] Next, the conversion from an abstract part of a graph to a concrete part in automated system design will be explained. In the example of FIG. 1, graph G1 corresponding to system requirement R1 is concretized based on the concretization rules described below, and graphs G2, G3, and G4 shown in FIG. 1 are derived. Note that graphs G2, G3, and G4 are system configuration plans. A system configuration plan refers to one that includes abstract components and is not a system requirement. Similarly, system configuration plan G2 is concretized using the concretization rules, and concrete system configuration G5 that does not include abstract elements is derived.

[0024] 1, the system configuration plan derived by concretizing the graph G1 corresponding to the system requirement R1 may exist in other than the graphs G2, G3, and G4 in FIG.

[0025] Next, the reification rules will be described. The reification rules are rules for converting abstract parts included in the system requirements or the system configuration plan into concrete parts. The reification rules are information including detection information corresponding to the abstract parts of the graph and conversion information corresponding to the concrete parts of the graph.

[0026] The detection information and the conversion information are each a graph composed of nodes, edges, or both, and one piece of detection information is associated with one piece of conversion information.

[0027] When all or a part of a graph corresponding to a system requirement or a system configuration plan matches with detection information held by a certain concretization rule, the concretization rule is applied and the matching part is replaced with conversion information, thereby making it possible to concretize the graph. An example of a concretization rule will be described later with reference to Fig. 4. Also, an example of a data structure of a concretization rule will be described later with reference to Fig. 5.

[0028] Although not shown in the example of Fig. 3, there are also system configuration plans R2, R3, and R4 corresponding to graphs G2, G3, and G4. Like system requirement R1, system configuration plans R2, R3, and R4 contain information including component identification information of all nodes included in each configuration plan, component identification information of all edges, component identification information of start nodes of edges, and component identification information of end nodes of edges.

[0029] Fig. 4 is a diagram for explaining the instantiation rules, in which graphs G31, G32, G33, ... are shown which are graphs representing a plurality of instantiation rules.

[0030] Graph G31 is a graph representing the concatenation rule Rule1 used to convert graph G1 shown in FIG. 1 into graph G2 shown in FIG. 1 (by deleting edge E1 and adding edge E4). Graph GD31 included in graph G31 is a graph representing detection information, and graph GC31 included in graph G31 is a graph representing conversion information. Since graph GD31 matches graph G1 shown in FIG. 1, concatenation rule Rule1 can be applied. Then, by applying concatenation rule Rule1, the configuration of graph G1 is replaced with the configuration of graph GC31, resulting in graph G2.

[0031] 1 into the graph G3 shown in FIG. 1 (converting the node N4 into the node N5). Graph G33 is a graph representing the concatenation rule Rule3 used to convert the graph G1 shown in FIG. 1 into the graph G4 shown in FIG. 1 (converting the node N4 into the node N6). Like the graph G31, the graph GD32 included in the graph G32 is a graph representing detection information, and the graph GC32 is a graph representing conversion information. The graph GD32 matches a part of the graph G1 shown in FIG. 1, so the concatenation rule Rule2 can be applied. Then, by applying the concatenation rule Rule2, a part of the graph G1 (i.e., the node N4) is replaced with the graph GC32 (i.e., the node N5), and the graph G1 is converted into the graph G3. Similarly to graph G31, graph G33 includes graph GD33, which is a graph representing detection information, and graph GC33, which is a graph representing conversion information. Since graph GD33 matches a part of graph G1 shown in Fig. 1, concatenation rule Rule3 can be applied. By applying concatenation rule Rule3, a part of graph G1 (i.e., node N4) is replaced with graph GC33 (i.e., node N6), and graph G1 is converted into graph G4.

[0032] Fig. 5 is a diagram for explaining the data structure of the concatenation rule. Concise rule Rule1 shown in Fig. 5 is a concatenation rule corresponding to graph G31. Concise rule Rule1 has detection information 51 used to detect an abstract part, and conversion information 52 for converting the abstract part detected using the detection information 51 into a concrete part. Although not shown, concatenation rules Rule2, Rule3, ... as shown in Fig. 5 corresponding to graphs G32, G33, ... also exist for graphs G32, G33, ....

[0033] When deriving graphs G2, G3, and G4 from graph G1 shown in Figure 1, first, the system requirement R1 is compared with multiple pieces of detection information (corresponding to the abstract parts of the concretization rules) to detect detection information that matches the abstract parts contained in the system requirement R1.

[0034] Next, the abstract parts detected from the system requirement R1 are converted into conversion information (concrete parts of the concretization rules) using the detection information corresponding to the detected abstract parts. In the conversion to the graph G2, since the detection information 51 of the system requirement R1 and the concretization rules Rule1 match, they are replaced with the conversion information 52 of the concretization rules Rule1.

[0035] As a result, edge E1 is deleted from system requirement R1, edge E4 is added, and system configuration plan R2 corresponding to graph G2 (not shown) is generated. System configuration plans R3 and R4 corresponding to graphs G3 and G4, respectively, are also generated.

[0036] Next, for each of the multiple system configuration plans generated, the abstract parts of the system configuration plan are converted into concrete parts using the concretization rules. Furthermore, when a system configuration plan that is an abstract system configuration is generated, the above-mentioned concretization process is repeated. Then, when no more system configuration plans are generated and only the concrete system configuration without any abstract parts remains, the concretization process is stopped (automated design is terminated).

[0037] Here, when concretizing the system requirements and the system configuration plan, multiple concretization rules are used, so the derived system configuration plan and system specific configuration change depending on the concretization rule selected and the order in which the concretization rules are selected. In other words, different system configuration plans and system specific configurations are derived depending on the type of concretization rule selected.

[0038] In addition, if the number of instantiation rules to be applied is large, the number of system configuration proposals and system instantiations to be generated will be enormous. Furthermore, among the multiple different system instantiations, there may be a system instantiation that does not satisfy the system requirements. Therefore, if the number of instantiation rules to be applied is large, it becomes difficult to efficiently derive a system instantiation.

[0039] Furthermore, in order to efficiently derive a system instantiation, it is important to properly judge the merits of the instantiation rules to be applied.

[0040] Therefore, the learning model is used to select the concretization rule to be applied. That is, the system configuration plan generated by executing the concretization process is evaluated using the learning model acquired by machine learning, and the system configuration plan with the highest evaluation value is selected from the system configuration plans. In this way, by repeating the concretization process using the learning model, the system concrete configuration can be efficiently derived.

[0041] As described above, in this embodiment, a learning device that generates a learning model for automatically designing a system as described above is provided. Hereinafter, the system automatic design learning device in this embodiment will be described with reference to the drawings. In addition, in the drawings described below, elements having the same functions or corresponding functions are given the same reference numerals, and repeated description thereof may be omitted.

[0042] [composition] The configuration of an information processing system having the system automatic design learning device 10 in the embodiment 1 will be described with reference to Fig. 6. Fig. 6 is a diagram showing an example of the information processing system.

[0043] 6, the information processing system includes a system automatic design learning device 10, a storage device 20, an input device 30, and an output device 40. The system automatic design learning device 10, the storage device 20, the input device 30, and the output device 40 are communicatively connected via a network.

[0044] The system automatic design learning device 10 is, for example, an information processing device such as a CPU (Central Processing Unit), a programmable device such as an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), or a circuit equipped with one or more of these, a server computer, a personal computer, or a mobile terminal.

[0045] The storage device 20 is a database, a server computer, a circuit having a memory, etc. The storage device 20 stores various information described later. In the example of Fig. 6, one storage device 20 is provided outside the system automatic design learning device 10, but multiple storage devices 20 may be provided inside or outside the system automatic design learning device 10.

[0046] The input device 30 is, for example, a keyboard, a mouse, a touch panel, etc. The input device 30 is used when operating the system automatic design learning device 10 and the output device 40. The output device 40 is, for example, a display device such as a display.

[0047] The communication network is a general communication network constructed using communication lines such as the Internet, a LAN (Local Area Network), a dedicated line, a telephone line, an in-house network, a mobile communication network, Bluetooth (registered trademark), and Wi-Fi (Wireless Fidelity).

[0048] The system automatic design learning device 10 is a device that learns a learning model for designing an ICT system. As shown in FIG. 6, the system automatic design learning device 10 has a design unit 11, a conversion unit 12, a reward setting unit 13, a learning data generation unit 14, and a learning unit 15. The functions of the design unit 11, the conversion unit 12, the reward setting unit 13, the learning data generation unit 14, and the learning unit 15 can be realized by a calculation device such as a CPU equipped in an information processing device constituting the system automatic design learning device 10 executing a program for realizing each function stored in a storage device. Each configuration will be described below, but first an overview of each configuration will be described, and then detailed explanations will be given later when explaining the operation.

[0049] The design unit 11 performs a concretization process on system requirements, which are information representing the configuration of a system including abstract parts (elements), to convert the abstract parts into concrete parts, generates a system specific configuration, which is information representing the configuration of a system that does not include abstract parts, and generates design path information representing the process from the system requirements to the generation of the system specific configuration (the system requirements, the system configuration proposal in the process of deriving the system specific configuration from the system requirements, and information including the system specific configuration).

[0050] The conversion unit 12 adds inheritance relationship information of parts (elements) to the design path information, and generates an inheritance relationship-embedded design path. Specifically, the conversion unit 12 converts type information representing the type of a part possessed by a system requirement, a system configuration plan, or a specific system configuration included in the design path information, into an inheritance relationship-embedded type to which type information of a parent type in the inheritance relationship is added, based on type definition information for adding inheritance relationship information to the type, thereby generating an inheritance relationship-embedded system requirement, an inheritance relationship-embedded system configuration plan, and an inheritance relationship-embedded system specific configuration, and generating inheritance relationship-embedded design path information.

[0051] The reward setting unit 13 sets rewards for each of the inheritance-related embedded system requirements, the inheritance-related embedded system configuration plan, and the inheritance-related embedded system specific configuration included in the inheritance-related embedded design path information. The reward setting unit 13 also sets rewards for learning a system design method based on functional requirements.

[0052] The learning data generation unit 14 generates learning data in which a reward is associated with each of the inheritance relationship embedded system requirements, the inheritance relationship embedded system configuration proposals, and the inheritance relationship embedded system specific configurations included in the inheritance relationship embedded design path information.

[0053] The learning unit 15 learns a method for designing a system based on functional requirements, based on the learning data.

[0054] [Operation] Next, the operation of the system automatic design learning device 10 in the first embodiment will be described. In the following description, appropriate reference will be made to the drawings. In the first embodiment, the system automatic design learning method is implemented by operating the system automatic design learning device 10. Therefore, the description of the system automatic design learning method in the first embodiment is equivalent to the description of the operation of the system automatic design learning device below.

[0055] 7 is a diagram for explaining an example of the overall operation of the system automatic design learning apparatus 10 in the embodiment 1. First, the system automatic design learning apparatus 10 acquires system requirements to be learned from the storage device 20 (step S1).

[0056] Next, the system automatic design learning device 10 executes reinforcement learning for a preset period using the system requirements to be learned (step S2). This generates a learning model of the functional requirements. For example, when a neural network is used for reinforcement learning, the learning model of the functional requirements refers to the neural network.

[0057] The preset learning period is determined, for example, by an experiment, a simulation, or the like. The learning period may be the number of learning times instead of the learning period. For example, when a neural network is used, the number of learning times is the number of times the weight of the neural network is updated. However, the learning period and the number of learning times are not limited to these.

[0058] Here, details of the operation of the functional requirement learning, which is the process of step S2 described above, will be described later with reference to Fig. 8. In the functional requirement learning, a design method related to the functional requirements of an ICT system is learned.

[0059] First, the design unit 11 generates design path information by using the system requirements (step S11). Specifically, the design unit 11 generates the design path information as shown in the flowchart of FIG.

[0060] First, the design unit 11 sets the system requirements as the current configuration (step S21). Next, the design unit 11 registers the current configuration as the root node of the search tree (step S22). Specifically, the design unit 11 stores system requirement identification information for identifying the current configuration (system requirements) as the root node in the search tree information. The data structure of the search tree information will be described later with reference to FIG. 11.

[0061] Here, Fig. 10 is a diagram for explaining an example of a search tree. The search tree can be expressed as a graph (search tree T1) as shown in Fig. 10. The root node mentioned in the description of step S22 above corresponds to the system requirement R1 in Fig. 10.

[0062] Fig. 11 is a diagram for explaining an example of the data structure of search tree information. The data structure shown in Fig. 11 corresponds to the search tree in Fig. 10. In the example of Fig. 11, system requirement identification information "R1" associated with system requirement R1 stored in storage device 20 is stored in the "parent node" of search tree information T10, and further, "1" is stored as information indicating that system requirement R1 is the "root node".

[0063] Next, if none of the instantiation rules can be applied to the current configuration, or if the current configuration is a system instantiation configuration (step S23: Yes), the design unit 11 proceeds to the process of step S29.

[0064] Furthermore, if there is an instantiation rule that can be applied to the current configuration (step S23: No), the design unit 11 repeats the processes from step S24 to step S28.

[0065] Next, the design unit 11 instantiates one of the components included in the current configuration by executing an instantiation process (step S24). Next, the design unit 11 sets the configuration obtained by instantiating the above-mentioned component in step S23 as the next configuration (step S25).

[0066] Next, if the next configuration (specific configuration (system configuration proposal)) is not stored in the search tree information (step S26: No), the design unit 11 proceeds to processing in step S27. If the next configuration (specific configuration (system configuration proposal)) is stored in the search tree information (step S26: Yes), the design unit 11 proceeds to processing in step S28.

[0067] Next, the design unit 11 associates the current configuration with the next configuration and the concretized parts (concrete parts of the concretization rules) as directed edges, and stores them in the search tree information (step S27), with the node representing the current configuration as the parent node, the next configuration (concretized configuration) as the child node, and the edges representing the concretized parts (concrete parts of the concretization rules) as directed edges.

[0068] For example, if the current configuration is system requirement R1 and system configuration proposal R2 is generated from system requirement R1, as shown in Figure 11, system configuration proposal identification information "R1" corresponding to system requirement R1 in search tree information T10, system configuration proposal identification information "R2" corresponding to system configuration proposal R2 generated by the concretization process, and concretization identification information "Rule1" corresponding to the concretization rule used in the concretization process are stored in association with each other.

[0069] Furthermore, if the current configuration is system configuration proposal R2 and a specific configuration R5 is generated from system configuration proposal R2, as shown in FIG. 11, the system configuration proposal identification information "R2" of the search tree information T10, the system specific configuration identification information "R5" associated with the specific configuration generated by the concretization process, and the concretization rule identification information "Rule4" associated with the concretization rule used in the concretization process are stored in association with each other.

[0070] Next, the design unit 11 sets the next configuration as the current configuration (step S28).

[0071] Next, the design unit 11 generates a series of paths (design path information storing the configurations in chronological order) from the system requirements to the generation of the current specific system configuration based on the system configuration (system requirements, system configuration proposal, specific system configuration) obtained in the processing from step S21 to step S28 (step S29). Note that the design unit 11 also generates a series of paths in the case where the specific system configuration is not generated from the system requirements, that is, a series of paths from the system requirements to the generation of the system configuration proposal.

[0072] Fig. 12 is a diagram for explaining an example of the data structure of design path information. In the design path information DP1 shown in Fig. 12, the system requirement "R1", the system configuration plan "R2", and the system specific configuration "R5" shown in Fig. 10 and Fig. 12 are recorded in this order. In other words, the design path information DP1 indicates that there is a series of design processes starting from the system requirement "R1", passing through the system configuration plan "R2", and leading to the system specific configuration "R5" as one of the system design processes.

[0073] The information contained in the design path information (the information corresponding to "R1", "R2", and "R5" in the example of FIG. 12) is simply a code associated with the system requirement, or the configuration plan, or the specific configuration. In other words, since the design path information is merely a string of codes, it does not store information (information on nodes and edges) related to the elements that make up the system requirement, the configuration plan, or the specific configuration.

[0074] As described below, the design path information is first replaced with inheritance relationship embedded design path information that indicates an inheritance relationship embedded configuration in which inheritance relationship information is embedded in each associated configuration (configuration such as R1, R2, R5), and is then used to generate learning data.

[0075] After generating the design path information as described above (step S11 in FIG. 8), the conversion unit 12 converts each system configuration of the design path (information including the above-mentioned system requirements or system configuration proposal or specific system configuration) (system configuration information) into an inheritance relationship-embedded system configuration to which inheritance relationship information is added, and generates an inheritance relationship-embedded design path (embedded design path information) (step S12 in FIG. 8). Specifically, the conversion unit 12 generates an inheritance relationship-embedded design path as shown in the flowchart in FIG. 13. Note that the process of generating an inheritance relationship-embedded design path by the conversion unit 12, which will be described below, is performed for each path, which is a series of design processes.

[0076] First, the conversion unit 12 sets the first configuration of the design path information as a configuration to which inheritance relationship information is to be added (step S31). Next, the conversion unit 12 selects one component from among the components included in the configuration to which inheritance relationship information is to be added (step S32).

[0077] Next, the conversion unit 12 converts the selected component into an inheritance-relation embedded component (step S33). Details of step S33 will be described later with reference to FIG.

[0078] Next, if there are no selectable parts, in other words, if there are no parts that have not been selected (step S34: Yes), the conversion unit 12 proceeds to the process of step S35. If there are selectable parts (step S34: No), the conversion unit 12 proceeds to the process of step S32, and repeats the processes from step S32 to step S33 until there are no unselected parts.

[0079] Next, if inheritance relationship information has not been added to all system configurations included in the design path information (if inheritance relationship information has not been added to the last configuration in the design path information) (step G15: No), the conversion unit 12 sets the next configuration included in the design path information as a target for inheritance relationship information addition (step S36). After executing step S36, the conversion unit 12 proceeds to the process of step S32.

[0080] Furthermore, in step S35, when inheritance relationship information has been assigned to all system configurations included in the design path information (when inheritance relationship information has been assigned up to the last configuration of the design path information) (step S35: Yes), the conversion unit 12 proceeds to the process of step S37. That is, the conversion unit 12 stores in chronological order the inheritance relationship-embedded system requirements, inheritance relationship-embedded system configuration plans, and inheritance relationship-embedded system specific configurations generated by the inheritance relationship information assignment processes of steps S31 to S36, and generates inheritance relationship-embedded design path information from these inheritance relationship-embedded system configurations.

[0081] Here, Fig. 14 is a diagram for explaining an example of the data structure of the inheritance relationship embedded design path information. The inheritance relationship embedded design path information GDP1 shown in Fig. 14 represents a configuration in which inheritance relationship information is embedded in each component of the configuration associated with the design path information DP1 shown in Fig. 12. That is, the inheritance relationship embedded system requirement "GR1", the inheritance relationship embedded system configuration plan "GR2", and the inheritance relationship embedded system specific configuration "GR5" shown in Fig. 14 indicate the system requirement "R1", the system configuration plan "R2", and the system specific configuration "R5" to which inheritance relationship information has been added.

[0082] In the same way that the information in the design path information is merely a code associated with the system requirements, the system configuration plan, and the specific system configuration, the information in the inheritance-relationship-embedded design path information is merely a code associated with the inheritance-relationship-embedded system requirements, the inheritance-relationship-embedded system configuration plan, and the inheritance-relationship-embedded system specific configuration. In addition, the inheritance-relationship-embedded design path information is information used to generate learning data, as described later.

[0083] Here, the process of step S33 in FIG. 13 described above, that is, the operation of the process of converting a component included in the configuration in the design path information into an inheritance relationship embedded component, will be described with reference to the flowchart in FIG.

[0084] First, the conversion unit 12 acquires the type of the part selected in step S32 shown in Fig. 13, and sets it as the type of the target part (step S41). Specifically, the conversion unit 12 acquires the type of the selected part by referring to the part information. For example, the conversion unit 12 may acquire function information corresponding to the selected part by referring to the part information. Also, the conversion unit 12 may store type information indicating a type in association with part identification information contained in the part information, and acquire type information corresponding to the selected part. The method of acquiring the type of the selected part may be a method other than the above.

[0085] Next, the conversion unit 12 searches for a parent type in the inheritance relationship of the target type using type definition information (step S42). The type definition information is information in which type information representing a type is associated with inheritance parent type information for adding type information of a parent type in the inheritance relationship to the type information. The type definition information is stored in the storage device 20 or the like.

[0086] Here, the type information is, for example, information that indicates the function of a part, the product name, etc. The inheritance parent type information is, for example, information that expresses the function of a part or the product name as a higher-level concept and expresses it in an abstract manner. A specific description will be given with reference to FIG. 16.

[0087] FIG. 16 is a diagram for explaining the data structure of type definition information. This diagram shows type definition information used in the design of the face authentication system shown in FIG. 1. In the example of type definition information F1 shown in FIG. 16, type names of "camera", "face authentication software", "server computer", "server computer A", "server computer B", "connect", "HTTP communication", and "join" are stored as "type (functional information)" representing a type. Also, in FIG. 16, type information of a type that is a parent of "type" is stored as "inheritance parent type" representing an inheritance parent type.

[0088] In the example of Figure 16, for the type "camera," there is no type defined as the parent of camera, so "-" is stored as the "inheritance parent type," indicating that there is no type. Since "Server computer A" belongs to the category "Server computer," "Server computer" is stored as the "inheritance parent type."

[0089] In the example of Fig. 16, the type used in the description of the face recognition system in Fig. 1 is shown as an example of a stored type, but the type stored in the type definition information is not limited to the type described in Fig. 16. Types other than the type described in Fig. 16 can be defined, and inheritance parent types corresponding to each type can be defined. In addition, although only "type" and "inheritance parent type" are defined in the type definition information shown in Fig. 16, other information may be stored. For example, information such as whether the type is abstract or not, and attribute values ​​related to the performance of a part associated with the type may be associated with the type.

[0090] Next, the conversion unit 12 refers to the type definition information, and if there is a parent type in the inheritance relationship of the target type, that is, a type that is a higher concept type (step S43: Yes), it adds the parent type information to the type information of the target type (step S44), and proceeds to the processing of step S45. Note that the method of adding the parent type information to the target type will be described later with reference to FIG.

[0091] Furthermore, the conversion unit 12 refers to the type definition information, and if there is no type that is a parent of the target type in the inheritance relationship (step S43: No), the conversion unit 12 proceeds to the process of step S45.

[0092] Then, the conversion unit 12 changes the type of the selected part to an inheritance relationship embedded type, that is, changes the type of part information (such as function information) to an inheritance relationship embedded type (step S45).

[0093] Next, the process of adding inheritance parent type information to a type in step S44 in FIG. 15 described above will be described with reference to the flowchart in FIG.

[0094] First, the conversion unit 12 sets the array corresponding to the type of the selected component in the type array information as the array to be converted (step S51). Here, FIG. 18 shows an example of the data structure of type array information. F2 in FIG. 18 is an example of the data structure of type array information corresponding to the type definition information F1 shown in FIG. 16. The type array information is information that associates the type stored in the type definition information with an array having elements of "0" and "1". Such a data structure is generally called a one-hot vector. The size of each array in the type array information is equal to the number of types stored in the type definition information. In addition, each element of the array corresponds to a type stored in the type definition information in the order of definition.

[0095] For example, in the case of the type "camera" defined first in the type definition information, the array corresponding to "camera" in the type array information F2 (array "camera") stores "1" in the first element and the remaining elements are "0." For types other than "camera," arrays are stored in which "1" is stored in the position corresponding to the type and "0" is stored in the other positions.

[0096] Next, the conversion unit 12 obtains an array corresponding to the array to be converted from the inheritance relationship embedded array information, and sets it as an array for conversion (step S52). Then, the conversion unit 12 replaces the array to be converted with the array for conversion (step S53).

[0097] An example of the data structure of the inheritance relationship embedded type array information F3 is shown in Fig. 19. The inheritance relationship embedded type array information F3 is information that adds inheritance relationship information to all the arrays included in the type array information F2 in Fig. 18 and compiles those arrays.

[0098] For example, in the case of the array "Server Computer A" of the inheritance relationship embedded type array information F3, referring to the type definition information F1 in FIG. 16, the inheritance parent type is "Server Computer". Since the type "Server Computer" is defined third in the type definition information, the third element (the element at the position corresponding to the server computer) of the array "Server Computer A" is converted to "1". At this time, "1" is also stored in the fourth element of the array "Server Computer A". This is because, according to the type definition information F1 in FIG. 16, the server computer A is defined fourth. In other words, the element at the position corresponding to "Server Computer A" itself (fourth position) and the element at the position corresponding to the parent type "Server Computer" (third position) are "1".

[0099] Similarly, for all other types, a "1" is stored in the element corresponding to the type itself, and if a parent type is defined, a "1" is stored in the element corresponding to the parent type.

[0100] In the example of Fig. 19, an array is shown to which information on the type of the parent in the inheritance relationship is added, but the information to be added does not have to be limited to information on the parent's type. In other words, for example, information on the type of the parent of the parent may be added.

[0101] After generating the inheritance relationship embedded design path information as described above (step S12 in FIG. 8), rewards are set for each inheritance relationship embedded system configuration (the above-mentioned inheritance relationship embedded system requirement or inheritance relationship embedded system configuration proposal or inheritance relationship embedded system specific configuration) of the inheritance relationship embedded design path information (step S13 in FIG. 8). Specifically, the reward setting unit 13 sets rewards as shown in the flowchart in FIG. 20. The reward setting process by the reward setting unit 13 described below is performed for each path, which is a series of design processes.

[0102] Here, in the system design described in this disclosure, it is important to apply appropriate instantiation rules to the configuration plan and efficiently arrive at the concrete system configuration. Therefore, a process is performed in which the probability that each configuration plan can arrive at the concrete configuration is given as a reward using inheritance relationship embedded design path information.

[0103] First, the reward setting unit 13 determines an initial value of the reward for the update candidate (step S61). Specifically, when the last configuration of the inheritance-related embedded design path is an inheritance-related embedded system specific configuration, the reward setting unit 13 sets the reward information representing the reward of the inheritance-related embedded system specific configuration to "1" as the initial value of the reward for the update candidate, and when the last configuration is not an inheritance-related embedded system specific configuration, the reward setting unit 13 sets the reward information representing the reward corresponding to the last configuration to "0".

[0104] Here, the above-mentioned update candidate reward is a value used when updating the reward value obtained for each system configuration (inheritance relationship embedded system configuration) in the inheritance relationship embedded design path information in step S62 described later.

[0105] In the example of Figure 14, since the last configuration of the inheritance relationship embedded design path information GDP1 is the inheritance relationship embedded system specific configuration GR5, in the processing of step S61, the reward information "1" is associated with "GR5" which represents the inheritance relationship embedded system specific configuration of the inheritance relationship embedded design path information GDP1.

[0106] Next, the remuneration setting unit 13 updates the remuneration information of each system configuration (inheritance relationship embedded system configuration) included in the inheritance relationship embedded design path information (step S62). Specifically, the remuneration setting unit 13 performs a process of updating the remuneration information as shown in the flowchart of FIG.

[0107] First, the reward setting unit 13 sets the last configuration of the inheritance relationship embedded design path information (the inheritance relationship embedded system configuration) as the configuration to be updated (step S71). Next, the reward setting unit 13 compares the reward associated with the configuration to be updated with the reward of the update candidate, selects the larger reward, and stores the selected reward in association with the configuration to be updated (step S72). Next, the reward setting unit 13 sets the reward selected in step S72 (the larger reward in the comparison) as the reward of the update candidate (step S73).

[0108] Next, if the reward setting unit 13 has not performed the reward update process for all configurations in the inheritance relationship embedded design path information (if the reward update process has not been performed up to the first configuration in the inheritance relationship embedded design path information) (step S74: No), it sets the configuration immediately before the current configuration to be updated in the inheritance relationship embedded design path information as the configuration to be updated (step S75), and proceeds to processing of step S72.

[0109] In addition, when the reward setting unit 13 has performed the reward update process for all configurations of the inheritance relationship embedded design path information (when the reward update process has been performed up to the first configuration of the inheritance relationship embedded design path information) (step S74: Yes), it terminates the processing of step S62 shown in Figure 20.

[0110] Specifically, in step S62, the reward for the update candidate is determined by comparing the reward associated with the configuration to be updated with the evaluation of the update candidate, and if the former reward does not exist (is not associated) before the comparison, it is considered to be "0". After the comparison, the larger one is updated as the reward associated with the configuration to be updated and the reward for the update candidate. Then, the configuration to be updated is updated, and this process is repeated.

[0111] For example, since no reward is associated with any configuration at first, in the example of Fig. 14, "GR5" becomes the first configuration to be updated in step R71, and since "GR5" has no reward associated with it yet, its value is considered to be "0." In this case, since the reward for the update candidate was initialized to "1" in step R61, "0" is compared with "1," and since "1" is greater, a reward of "1" is associated with "GR5."

[0112] Next, the configuration to be updated is set to "GR2" and the same processing as described above is repeated. After that, the configuration to be updated is set to "GR1" and the same processing as described above is repeated.

[0113] As another example, starting from the first configuration to be updated (a configuration that is not a concrete system configuration with an embedded inheritance relationship), if it is not a concrete configuration, the reward of the update candidate is initialized to "0", and if the next configuration has an associated reward of "1", "0" and "1" are compared, and since "1" is greater, the reward value of the update candidate is updated to "1".

[0114] Specifically, in the process of step S62, data (reward) is generated for learning the evaluation values ​​of the configurations "GR2" and "GR1" in the design process based on the evaluation value of the configuration "GR5" at the end of the design from the process performed in step S71. At this time, if larger data (reward) has been obtained in the past, it is given priority, so the larger reward is compared with the reward stored in association with the configuration, and the larger one is kept.

[0115] In the above, the larger one is left and propagated upwards (GR1 from the perspective of GR2) because it is known that it is possible to transition from GR1 to GR2. What we want to learn is the expected reward to be obtained if we continue to choose the best option, and since it is known that it is possible to transition from GR1 to GR2 by applying the appropriate concretization rule, if the reward associated with GR2 is larger, the reward of GR5 should be propagated to GR1 in priority.

[0116] Note that a transition from "GR1" to "GR2" is not necessarily made, but there is a possibility. For example, in the example in Figure 10, there is also a possibility of transitioning to "GR3" or "GR4". However, the automatic design function can choose which transition to make, so the larger reward is propagated upwards.

[0117] After setting the reward as described above (step S13 in FIG. 8), the learning data generation unit 14 generates learning data by associating the inheritance relationship-embedded design system configuration with the reward for the inheritance relationship-embedded design path information, and stores the generated learning data in the storage device 20 (step S14 in FIG. 8). Specifically, the learning data generation unit 14 generates the learning data as shown in the flowchart in FIG.

[0118] First, the learning data generating unit 14 sets the first configuration of the inheritance relationship embedded design path information as the inheritance relationship embedded configuration to be converted into learning data (step S81). Next, the learning data generating unit 14 sets the first configuration of the inheritance relationship embedded design path information as the configuration to be referred to as a reward (step S82).

[0119] Next, the learning data generation unit 14 generates learning data by pairing the inheritance relationship embedded configuration, which is the subject of generating the learning data, with the reward corresponding to the configuration (the reward set in step S72 of FIG. 21), and stores the generated learning data in the storage device 20 (step S83).

[0120] Next, if the learning data generation unit 14 has not generated learning data for all configurations included in the inheritance relationship-embedded design path information (if learning data has not been generated for the last configuration of the inheritance relationship-embedded design path information) (step S84: No), the learning data generation unit 14 proceeds to the process of step S85. If the learning data generation unit 14 has generated learning data for all configurations included in the inheritance relationship-embedded design path information (if learning data has been generated for the last configuration of the inheritance relationship-embedded design path information) (step S84: Yes), the learning data generation unit 14 ends the process of generating learning data.

[0121] Next, the learning data generating unit 14 sets the next configuration of the inheritance-relation-embedded design path information as a configuration to be converted into learning data (step S85).

[0122] Next, the learning data generating unit 14 sets the next configuration of the inheritance relationship embedded design path information as the configuration to be referred to as a reward (step S86).

[0123] After the learning data is generated as described above (step S14 in FIG. 8), the learning unit 15 performs learning based on the learning data (step S15 in FIG. 8). Specifically, the learning unit 15 performs learning of the learning model as shown in the flowchart in FIG.

[0124] Here, the learning model to be learned is a GNN (Graph Neural Network) that takes graph information in which each node and edge in the graph and the graph itself have attribute values ​​as input, and outputs graph information in a similar format. Note that the attribute values ​​of each node, edge, or the graph itself in the graph include at least the above-mentioned inheritance relationship embedded type array information as a part of them.

[0125] First, the learning unit 15 selects one piece of learning data D1 from the learning data generated as described above (step S91). Next, the learning unit 15 inputs graph information representing the inheritance relationship embedded configuration included in the learning data D1 to a first learning model, and obtains a result (graph information OG1) output from the learning model (step S92).

[0126] Next, the learning unit 15 pairs the attribute value At1 of the graph itself in the graph information OG1 with the reward included in the data D1 to generate a pair VP1 (step S93).

[0127] Next, if all the learning data has been selected (step S94: Yes), the learning unit 15 proceeds to the process of step S95. If all the learning data has not been selected (step S94: No), the learning unit 15 proceeds to the process of step S91 and repeats the process up to step S93.

[0128] Next, the learning unit 15 generates a set VP1 for all data included in the learning data, and sets the collected set as VPS1 (step S95).

[0129] Then, the learning unit 15 uses each pair included in the VPS1 to learn a first learning model (step S96). Specifically, the learning unit 15 uses each pair included in the VPS1 to train a learning model so as to minimize a loss function, which is a mean square error between the attribute value and the fixed reward.

[0130] As described above, during a preset learning period, the processes from step S11 to step S15 shown in FIG. 8 are repeated (step S16 in FIG. 8) to perform reinforcement learning (step S2 in FIG. 7).

[0131] Then, the system automatic design learning device 10 executes an instantiation process (design) for the system requirements using the learning model of the current functional requirements generated by the above-mentioned reinforcement learning (step S3 in FIG. 7).

[0132] The instantiation process (design) is a process that instantiates the abstract parts (components) included in the system requirements. By repeating the instantiation process, it is possible to derive a system concrete configuration that finally includes only the concrete parts. An example of the instantiation process is shown in Figure 1.

[0133] Next, if it is determined based on the result of step S3 that the learning of the functional requirements is sufficient (step S4: Yes), the system automatic design learning device 10 ends the reinforcement learning in step S2. If it is determined that the learning of the functional requirements is not sufficient (step S4: No), the system automatic design learning device 10 performs the processes of steps S2 and S3 again. The processes of steps S2 and S3 are repeated until it is determined in step S4 that the learning of the functional requirements is sufficient.

[0134] The determination in step S4 is, for example, that the number of steps of the search is sufficient if it is equal to or less than a preset threshold value A. Alternatively, the determination in step S4 may be that the number of steps of the search is sufficient if it is equal to or less than a preset threshold value B for a specified number of consecutive times in step S3 previously performed. However, the determination in step S4 is not limited to the above-mentioned method.

[0135] The number of steps in the search described above depends on the design method in step S3. The number of steps in the search is the number of times that the instantiation rules are applied to the system requirements or the system configuration plan until the system configuration is derived from the system requirements. The number of steps in the search can also be said to be the number of system configuration plans that are actually arrived at during the design.

[0136] As described above, according to this embodiment, it is possible to reduce the time cost of re-learning that is required when an element is added in automatic system design.

[0137] In addition, by generating learning data from data in which information on the type of a component is given with information on the parent type in an inheritance relationship, and learning using the learning data, it becomes possible to utilize the learning experience of types in an inheritance relationship with the type in question for type evaluation. Therefore, it is possible to improve the evaluation accuracy of a configuration that includes a component having a type (an unlearned type) that does not exist in past learning data. As a result, when adding a new element (a component or a relationship between components) used in a system design, it is no longer necessary to relearn the system design using the element, and the time cost required for relearning can be reduced.

[0138] <Second embodiment> Next, a second embodiment of the present disclosure will be described with reference to the drawings. In this embodiment, an outline of the configuration of the system automatic design learning device described in the above embodiment is shown. Note that Figs. 24 and 25 are diagrams for explaining the configuration, and these drawings may be related to any of the embodiments.

[0139] First, the hardware configuration of the information processing device 100 will be described with reference to Fig. 24. The information processing device 100 is configured as a general information processing device, and is equipped with the following hardware configuration, as an example. ·CPU(Central Processing Unit)101(Arithmetic unit) ROM (Read Only Memory) 102 (storage device) RAM (Random Access Memory) 103 (storage device) · Programs 104 loaded into RAM 103 A storage device 105 for storing a program group 104 A drive device 106 that reads and writes data from a storage medium 110 external to the information processing device A communication interface 107 for connecting to a communication network 111 outside the information processing device Input / output interface 108 for inputting and outputting data Bus 109 connecting each component

[0140] 24 shows an example of the hardware configuration of the information processing device which is the information processing device 100, and the hardware configuration of the information processing device is not limited to the above-mentioned case. For example, the information processing device may be configured with a part of the above-mentioned configuration, such as not having the drive device 106. Moreover, the information processing device may use a GPU (Graphic Processing Unit), a DSP (Digital Signal Processor), an MPU (Micro Processing Unit), an FPU (Floating point number Processing Unit), a PPU (Physics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, a microcontroller, or a combination thereof, instead of the above-mentioned CPU.

[0141] The information processing device 100 can be equipped with the design unit 121, the conversion unit 122, the reward setting unit 123, and the learning data generation unit 124 shown in FIG. 25 by the CPU 101 acquiring the program group 104 and executing it. The program group 104 is stored in the storage device 105 or the ROM 102 in advance, for example, and the CPU 101 loads the program group 104 into the RAM 103 and executes it as necessary. The program group 104 may be supplied to the CPU 101 via the communication network 111, or may be stored in the storage medium 110 in advance, and the drive device 106 may read out the program and supply it to the CPU 101. However, the design unit 121, the conversion unit 122, the reward setting unit 123, and the learning data generation unit 124 described above may be constructed with dedicated electronic circuits for realizing such means.

[0142] The design unit 121 generates design path information representing the design process of system configuration information, which represents a system configuration consisting of a combination of elements, by converting abstract elements into concrete elements using preset concretization rules.

[0143] The conversion section 122 generates embedded design path information by adding, to each piece of system configuration information included in the design path information, information on an element corresponding to a superordinate concept of an element included in the system configuration information.

[0144] The remuneration setting unit 123 sets a remuneration for each piece of system configuration information included in the embedded design path information depending on whether an element included in the system configuration information is a specific element or not.

[0145] The learning data generation unit 124 generates each of the system configuration information included in the embedded design path information and the reward set for the system configuration information as learning data to be machine-learned to generate a model that converts the system configuration information based on the concretization rules.

[0146] By being configured as described above, the present disclosure can reduce time costs when designing a system.

[0147] At least one or more of the functions of the above-mentioned design unit 121, conversion unit 122, reward setting unit 123, and learning data generation unit 124 may be executed by an information processing device installed and connected anywhere on a network, that is, they may be executed by so-called cloud computing.

[0148] The above-mentioned program can be stored and provided to a computer using various types of non-transitory computer readable media. The non-transitory computer readable medium includes various types of tangible storage media. Examples of the non-transitory computer readable medium include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROM (Read Only Memory), CD-R, CD-R / W, and semiconductor memory (e.g., mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (Random Access Memory)). The program may be provided to a computer by various types of transitory computer readable media. Examples of the transitory computer readable medium include electric signals, optical signals, and electromagnetic waves. The transitory computer readable medium can provide the program to a computer via a wired communication path such as an electric wire and an optical fiber, or via a wireless communication path.

[0149] Although the present disclosure has been described above with reference to the above-mentioned embodiments, the present disclosure is not limited to the above-mentioned embodiments. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each of the above-mentioned embodiments can be appropriately combined with other embodiments.

[0150] <Additional Notes> A part or all of the above-described embodiments may be described as follows: Below, an overview of the configurations of an information processing device, an information processing method, and a program according to the present disclosure will be described. However, the present disclosure is not limited to the following configurations. (Appendix 1) a design unit that generates design path information representing a design process of the system configuration information, which represents a system configuration consisting of a combination of elements, by converting abstract elements into concrete elements using preset instantiation rules; a conversion unit that generates embedded design path information by adding information on an element corresponding to a superordinate concept of an element included in the system configuration information to each of the system configuration information included in the design path information; a reward setting unit that sets a reward for each of the system configuration information included in the embedded design path information depending on whether an element included in the system configuration information is a specific element; a learning data generation unit that generates each of the system configuration information included in the embedded design path information and the reward set for the system configuration information as learning data to be machine-learned to generate a model that converts the system configuration information based on the instantiation rule; An information processing device comprising: (Appendix 2) 2. The information processing device according to claim 1, the conversion unit generates, for each of the system configuration information included in the design path information, the embedded design path information including information on an element included in the system configuration information and an element corresponding to a superordinate concept of the element, based on inheritance relationship information indicating an element corresponding to a superordinate concept of the element. Information processing device. (Appendix 3) The information processing device according to claim 2, the conversion unit expresses the presence or absence of an element in each of the system configuration information included in the design path information as an array, and generates the embedded design path information by adding information of an element corresponding to a superordinate concept of the element to the array of the element included in the system configuration information. Information processing device. (Appendix 4) 2. The information processing device according to claim 1, the conversion unit generates the embedded design path information for each path representing a series of design processes of the system configuration information based on the design path information; The reward setting unit sets the reward for each of the system configuration information included in the embedded design path information for each of the paths. Information processing device. (Appendix 5) The information processing device according to claim 4, the reward setting unit sets the reward for the system configuration information in a predetermined process included in the embedded design path information in the same path, and sets the reward for other system configuration information based on the reward; Information processing device. (Appendix 6) The information processing device according to claim 5, the reward setting unit sets the reward for the system configuration information in a final process included in the embedded design path information in the same path, and sets the reward for other system configuration information based on the reward. Information processing device. (Appendix 7) The information processing device according to claim 5, The reward setting unit sets the largest reward set for the system configuration information in a predetermined design process included in the embedded design path information in the same path as the reward for the other system configuration information. Information processing device. (Appendix 8) 2. The information processing device according to claim 1, A learning unit that generates the model that converts each of the system configuration information included in the embedded design path information based on the instantiation rule by using the loss based on the reward. Information processing device. (Appendix 9) generating design path information representing a design process of the system configuration information, which is designed by converting abstract elements into concrete elements using preset instantiation rules, for system configuration information representing a system configuration consisting of a combination of elements; generating embedded design path information for each of the system configuration information included in the design path information, the embedded design path information being provided with information on an element corresponding to a superordinate concept of the element included in the system configuration information; For each of the system configuration information included in the embedded design path information, a reward for the system configuration information is set according to whether an element included in the system configuration information is a specific element; Each of the system configuration information included in the embedded design path information and the reward set for the system configuration information are generated as learning data to be machine-learned to generate a model for converting the system configuration information based on the instantiation rule. Information processing methods. (Appendix 10) generating design path information representing a design process of the system configuration information, which is designed by converting abstract elements into concrete elements using preset instantiation rules, for system configuration information representing a system configuration consisting of a combination of elements; generating embedded design path information for each of the system configuration information included in the design path information, the embedded design path information being provided with information on an element corresponding to a superordinate concept of the element included in the system configuration information; For each of the system configuration information included in the embedded design path information, a reward for the system configuration information is set according to whether an element included in the system configuration information is a specific element; Each of the system configuration information included in the embedded design path information and the reward set for the system configuration information are generated as learning data to be machine-learned to generate a model for converting the system configuration information based on the instantiation rule. A program that causes a computer to execute a process. [Explanation of symbols]

[0151] 10. System Automated Design Learning Device 11 Design Department 12 Conversion section 13. Remuneration Setting Department 14. Learning Data Generation Unit 15 Learning Department 20 Storage device 30 Input Devices 40 Output Device 100 Information processing device 101 CPU 102 ROM 103 RAM 104 Programs 105 Storage device 106 Drive device 107 Communication Interface 108 Input / Output Interface 109 Bus 110 Storage medium 111 Communication Network 121 Design Department 122 Conversion unit 123 Remuneration Setting Department 124 Learning Data Generation Unit

Claims

1. a design unit that generates design path information representing a design process of system configuration information, the system configuration information being designed by converting abstract elements into concrete elements using preset instantiation rules, for system configuration information representing a system configuration consisting of a combination of elements; a conversion unit that generates embedded design path information by adding information on an element corresponding to a superordinate concept of an element included in the system configuration information to each of the system configuration information included in the design path information; a reward setting unit that sets a reward for each of the system configuration information included in the embedded design path information depending on whether an element included in the system configuration information is a specific element; a learning data generation unit that generates each of the system configuration information included in the embedded design path information and the reward set for the system configuration information as learning data to be machine-learned to generate a model that converts the system configuration information based on the instantiation rule; An information processing device comprising:

2. 2. The information processing device according to claim 1, the conversion unit generates, for each of the system configuration information included in the design path information, the embedded design path information including information on an element included in the system configuration information and an element corresponding to a superordinate concept of the element, based on inheritance relationship information indicating an element corresponding to a superordinate concept of the element. Information processing device.

3. 3. The information processing device according to claim 2, the conversion unit expresses the presence or absence of an element in each of the system configuration information included in the design path information as an array, and generates the embedded design path information by adding information of an element corresponding to a superordinate concept of the element to the array of the element included in the system configuration information. Information processing device.

4. 2. The information processing device according to claim 1, the conversion unit generates the embedded design path information for each path representing a series of design processes of the system configuration information based on the design path information; The reward setting unit sets the reward for each of the system configuration information included in the embedded design path information for each of the paths. Information processing device.

5. 5. The information processing device according to claim 4, the reward setting unit sets the reward for the system configuration information in a predetermined process included in the embedded design path information in the same path, and sets the reward for other system configuration information based on the reward; Information processing device.

6. 6. The information processing device according to claim 5, the reward setting unit sets the reward for the system configuration information in a final process included in the embedded design path information in the same path, and sets the reward for other system configuration information based on the reward. Information processing device.

7. 6. The information processing device according to claim 5, The reward setting unit sets the largest reward set for the system configuration information in a predetermined design process included in the embedded design path information in the same path as the reward for the other system configuration information. Information processing device.

8. 2. The information processing device according to claim 1, A learning unit that generates the model that converts each of the system configuration information included in the embedded design path information based on the instantiation rule by using the loss based on the reward. Information processing device.

9. generating design path information representing a design process of the system configuration information, which is designed by converting abstract elements into concrete elements using preset instantiation rules, for system configuration information representing a system configuration consisting of a combination of elements; generating embedded design path information for each of the system configuration information included in the design path information, the embedded design path information being provided with information on an element corresponding to a superordinate concept of the element included in the system configuration information; For each of the system configuration information included in the embedded design path information, a reward for the system configuration information is set according to whether an element included in the system configuration information is a specific element; Each of the system configuration information included in the embedded design path information and the reward set for the system configuration information are generated as learning data to be machine-learned to generate a model for converting the system configuration information based on the instantiation rule. Information processing methods.

10. generating design path information representing a design process of the system configuration information, which is designed by converting abstract elements into concrete elements using preset instantiation rules, for system configuration information representing a system configuration consisting of a combination of elements; generating embedded design path information for each of the system configuration information included in the design path information, the embedded design path information being provided with information on an element corresponding to a superordinate concept of the element included in the system configuration information; For each of the system configuration information included in the embedded design path information, a reward for the system configuration information is set according to whether an element included in the system configuration information is a specific element; Each of the system configuration information included in the embedded design path information and the reward set for the system configuration information are generated as learning data to be machine-learned to generate a model for converting the system configuration information based on the instantiation rule. A program that causes a computer to execute a process.

Images