Information processing method, program, and information processing system

Abstract

Provided is an information processing method, which is executed by an information processing device and includes: a processing information acquisition step for acquiring information including unstructured data necessary for processing; a policy information acquisition step for acquiring policy information for processing said information; and a processing step for performing processing in accordance with the information and the policy information.

Description

Information processing method, program, and information processing system

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

[0002] Japanese Patent Application Laid-Open No. 2016-4437 discloses an information processing method that includes an information processing device, prioritizes a plurality of processing items based on processing requests, and processes information based on the determined priorities.

[0003] Generally, in the information processing methods described above, processing items are structured data that are predefined, and processing requests are specified for the structured data. In other words, the processing requests generally depend on the structured data that are predefined, and there is room for improvement in processing efficiency and flexibility when handling information that includes unstructured data.

[0004] In consideration of the above, the present disclosure aims to improve efficiency and flexibility in information processing including unstructured data.

[0005] According to one embodiment of an information processing method, the information processing method is executed by an information processing device and includes a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of performing processing based on the information and the policy information.

[0006] According to one embodiment of the program, an information processing device is caused to execute an information processing method including a processing information acquisition step for acquiring information necessary for processing, a policy information acquisition step for acquiring policy information for processing the information, and a processing step for performing processing based on the information and the policy information.

[0007] According to one embodiment of the information processing system, a processing information acquisition step is performed to acquire information necessary for processing, a policy information acquisition step is performed to acquire policy information for processing the information, and a processing step is performed based on the information and the policy information.

[0008] According to one embodiment, efficiency and flexibility in processing information including unstructured data can be improved.

[0009] FIG. 1 is a diagram showing an example of the configuration of an information processing system according to a first embodiment. FIG. 2 is a diagram showing an example of the hardware configuration of a server according to the first embodiment. FIG. 3 is a diagram showing an example of the functional configuration of a server according to the first embodiment. FIG. 4 is a diagram showing an example of the processing flow of the information processing system according to the first embodiment. FIG. 5 is a diagram showing an example of a design screen in the information processing system according to the first embodiment and a relationship with an external tool. FIG. 6 is a diagram showing an example of a design screen in the information processing system according to the first embodiment. FIG. 7 is a diagram showing an example of the functional configuration of a server according to a second embodiment. FIG. 8 is a diagram showing an example of the processing flow of the information processing system according to the second embodiment.

[0010] First Embodiment A first embodiment of an information processing system according to the present disclosure will be described below with reference to Figures 1 to 6. Note that identical or equivalent components and parts in each figure are denoted by the same reference numerals. Also, the dimensional proportions in the drawings have been exaggerated for the sake of explanation and may differ from the actual proportions.

[0011] (System Overview) First, an overview of the information processing system 10 according to this embodiment will be described. The information processing system 10 according to this embodiment is an information processing system for a user U to develop a desired system. The desired system here refers to an information processing system or control system configured by a combination including at least one information processing device, sensor, and facility equipment. The user designs the desired system by placing a component image c and a flow image f on the screen of the user terminal 14 (see FIG. 5 ). The user also adds the contents of the system component (detailed settings, source code, and policy information) to the placed component image c. The information processing system 10 automatically generates a design file for the system designed by the user and automatically builds an infrastructure capable of running the system according to the design file.

[0012] (System Configuration) Fig. 1 is a diagram showing an example of the configuration of an information processing system 10 according to this embodiment. As shown in Fig. 1, the information processing system 10 according to this embodiment includes a development support device 12 and a user terminal 14, which are communicably connected to each other via a network N. The network N is, for example, a wired LAN (Local Area Network), a wireless LAN, the Internet, a public line network, a mobile data communication network, or a combination thereof.

[0013] The user terminal 14 is an example of an information processing device that is operated by a user U to input and display various information. The user terminal 14 may be a personal computer (PC), a smartphone, a tablet terminal, a server device, a microcomputer, a wearable device, or a combination thereof.

[0014] The development support device 12 is an example of an information processing device that acquires information input from a user terminal 14, processes the information, and outputs the results. The development support device 12 may be a PC (Personal Computer), a smartphone, a tablet terminal, a server device, a microcomputer, or a combination of these. The specific configuration and operation of the development support device 12 will be described later.

[0015] 2 is a block diagram showing the hardware configuration of the development support device 12. The development support device 12 includes a processor 120, a memory 122, a storage 124, a communication I / F 126, an input / output I / F 128, and a drive device 134, which are communicatively connected to each other via a bus B.

[0016] The processor 120 controls each component of the development support device 12 and realizes the functions of the development support device 12 by loading various programs stored in the storage 124 into the memory 122 and executing them. The programs executed by the processor 120 include, but are not limited to, an operating system (OS) and a program 220 described below. The execution of these programs by the processor 120 realizes part of the state visualization method according to this embodiment. The processor 120 is, for example, a central processing unit (CPU), a micro processing unit (MPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a digital signal processor (DSP), or a combination thereof.

[0017] The memory 122 is, for example, a read-only memory (ROM), a random access memory (RAM), or a combination thereof. The ROM is, for example, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a combination thereof. The RAM is, for example, a dynamic random access memory (DRAM), a static random access memory (SRAM), a magnetoresistive random access memory (MRAM), or a combination thereof.

[0018] The storage 124 stores the OS, various programs described below, and various data. The storage 124 is, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), a storage class memory (SCM), or a combination thereof.

[0019] The communication I / F 126 is an interface for connecting the development support device 12 to external devices, including the user terminal 14 and the image capture device 16, via the network N and for controlling communication. The communication I / F 126 is, for example, an adapter compliant with Bluetooth (registered trademark), Wi-Fi (registered trademark), ZigBee (registered trademark), Ethernet (registered trademark), or optical communication (e.g., Fibre Channel), but is not limited to these.

[0020] The input / output I / F 128 is an interface for connecting an input device 132 and an output device 130 to the development support device 12. The input device 132 is, for example, a mouse, keyboard, touch panel, microphone, scanner, camera, various sensors, operation buttons, or a combination of these. The output device 130 is, for example, a display, projector, printer, speaker, vibrator, or a combination of these.

[0021] The drive device 134 reads and writes data from and to the disk media 136. The drive device 134 is, for example, a magnetic disk drive, an optical disk drive, a magneto-optical disk drive, or a combination thereof. The disk media 109 is, for example, a compact disc (CD), a digital versatile disc (DVD), a floppy disc (FD), a magneto-optical disc (MO), a Blu-ray (registered trademark) disc (BD), or a combination thereof.

[0022] In this embodiment, the program may be written to memory 122 or storage 124 during the manufacturing stage of the development support device 12, or may be provided to the development support device 12 via the network N, or may be provided to the development support device 12 via a non-transitory computer-readable recording medium such as disk media 136.

[0023] The hardware configuration of the user terminal 14 is substantially the same as that of the development support device 12 described above, and therefore a detailed description thereof will be omitted.

[0024] (Functional Configuration) Next, the functional configuration of the development support device 12 will be described. Fig. 3 is a diagram showing an example of the functional configuration of the development support device 12. When executing various programs, the development support device 12 uses the above-mentioned hardware resources to realize various functions. The development support device 12 has a communication unit 20, a storage unit 22, and a control unit 24 as the functional configuration realized by the development support device 12. Each functional configuration is realized when the processor 120 reads and executes a program 220 stored in the memory 122 or the storage 124.

[0025] The communication unit 20 is realized by the communication I / F 126. The communication unit 20 transmits and receives information to and from the user terminal 14 via the network N. The communication unit 20 receives information input from the user terminal 14. The communication unit 20 also transmits information to the user terminal 14 and receives requests from the user U from the user terminal 14.

[0026] The storage unit 22 is realized by the memory 122 and the storage 124. The storage unit 22 stores a program 220, a trained model 222, policy information 224, user information 226, component information 228, design information 230, a design file 232, and infrastructure information 234.

[0027] The trained model 222 is composed of at least one trained machine learning model. As an example, the trained model 222 is a large-scale language model trained on a large amount of text data from online articles, books, websites, and the like. When text data called a prompt is input, the trained model 222 generates and outputs text data corresponding to the prompt. The language model in the trained model 222 of this embodiment acquires information including unstructured data as necessary in response to the prompt, processes it, and generates text data as the processing result. Note that "unstructured data" here refers to data that is stored without being structured in a predefined manner. On the other hand, "structured data" refers to data that exists in a specific field in a file or record. "Structured data" also includes "semi-structured data."

[0028] The trained model 222 also performs processing in response to prompts based on policy information 224, which will be described later. The policy information 224, for example, is text data in natural language and indicates rules to be followed during processing. Specifically, the policy information 224 indicates in natural language that personal information should not be leaked or that output that violates public order and morals should not be generated. The policy information is not limited to these, and may also be based on access control, data protection, security, laws, regulations, guidelines, business plans, etc. The policy information may also be input by the user U, generated by the system, acquired from other data sources, or a combination of these. Furthermore, the policy information is not limited to natural language, and may be other text data such as unique prompts or languages ​​that only the trained model can understand, or may even be non-text data such as audio or video. In other words, the policy information 224 instructs the system on rules for processing structured data and unstructured data across the board.

[0029] The user information 226 is various information about the user U who has registered to use the information processing system 10. Specifically, the user information 226 includes user identification information for unique identification, user preference information such as interest information, user history information including past usage status, and user attribute information such as occupation and job title.

[0030] The component information 228 is information about pre-prepared system components. A system component is a component of a system. The pre-prepared system components include a UI (User Interface), an endpoint, an entity, a trigger, a data source, a storage, a pipeline, a function, an AI (Artificial Intelligence) model, a policy agent, and an action generator. Note that the pre-prepared system components may not include some of the above, or may include components other than the above.

[0031] The UI is a screen on which the output of the system is displayed. The endpoint is the address of the API (Application Programming Interface). The entity is a variable in which a value that changes over time is stored. The trigger is an event that is the starting point of processing. The data source is the location of the data. The storage is a storage device in which data is stored. The pipeline is a collection of a series of processes. The function is some kind of computational processing. The trained model is processing by a trained model including the trained model 222. The policy agent is applied to processing in the system including policy information. The action generator generates execution instructions to control external tools, sensors, data sources, etc. based on the processing results of the trained model.

[0032] The component information 228 includes a component image c, a component setting, a registered component, and a flow image f.

[0033] The component images c are images corresponding to the types of pre-prepared system components, such as a UI, an endpoint, an entity, a trigger, a data source, a storage, a pipeline, a function, a trained model, a policy agent, and an action generator.

[0034] Component settings are information indicating setting items corresponding to the type of system component prepared in advance. Component settings include, for example, the name and content of the component, but are not limited to this. For example, UI setting items include the name of the UI, the content of the UI, the entities to be displayed on the screen, and the display format of the entities. Furthermore, trained model setting items include the name of the trained model, the content of the trained model, and the input / output of the trained model. Furthermore, policy agent setting items include the name of the policy agent and policy information assigned to the policy agent. Furthermore, action generator setting items include the name of the action generator and information on the destination of the execution instruction generated by the action generator (i.e., external tools, sensors, data sources, etc.).

[0035] A registered component is a system component that has been prepared in advance. A registered component can be prepared for each type of system component that has been prepared in advance. A user can select a registered component as the content of a component.

[0036] The flow image f is an image showing the data flow between system components. The flow image f is, for example, an arrow connecting the component images c, but is not limited to this.

[0037] The design information 230 is information about a system designed by a user on a system design screen D. The design screen D is a screen on which a user designs a system. The design information 230 includes the layout of component images c placed by the user, component settings of the placed component images c, and the layout of flow images f placed by the user.

[0038] The design file 232 is a file representing the system design generated from the design information 230. The design file 232 includes information indicating the component settings of the system components corresponding to the component images c placed by the user and the data flow corresponding to the flow images f placed by the user. The design file 232 is, for example, an XML file, a YAML file, or a JSON file, but is not limited to these.

[0039] The infrastructure information 234 is information indicating the infrastructure of the system designed based on the design file 232. The infrastructure information 234 includes information indicating an API gateway, a DB (Data Base), a virtual machine, storage, and network settings.

[0040] The control unit 24 is realized by the processor 120 reading and executing the program 220 from the memory 122 (see FIG. 2 ) and working in cooperation with other hardware components. The control unit 24 includes an information acquisition unit 242, an information processing unit 244, a display control unit 246, a generation unit 248, and a construction unit 250.

[0041] The information acquisition unit 242 acquires various information required for processing in the information processing unit 244. Specifically, it acquires information including unstructured data required for processing, policy information for processing the information, and processing results. This information may be information stored in the storage unit 22, or may be information acquired from an external data source or the like. Furthermore, if policy information 224 related to the processing is stored in the storage unit 22, the information acquisition unit 242 acquires the policy information 224. Furthermore, the information acquisition unit 242 acquires information regarding functions including external tools, sensors, etc. that can execute the processing results.

[0042] The information processing unit 244 performs information processing using the trained model 222. Specifically, when a prompt instructing processing is input by the user, the information processing unit 244 outputs text data as a processing result based on various information, including policy information, acquired by the information acquisition unit 242 in accordance with the prompt. Note that, if information regarding a function capable of executing the processing result has been acquired, the information processing unit 244 uses the function to output the processing result. That is, as an example, if a spreadsheet software is connected to the information processing system 10 as an external tool, information regarding the spreadsheet function is acquired as a function capable of executing the processing result. Then, based on the information, the information processing unit 244 generates an execution instruction for the spreadsheet software to output the processing result using the spreadsheet function as necessary.

[0043] The information processing unit 244 also uses the user information 226 to execute processing in accordance with at least one of the content of the prompt and the policy information 224. That is, if the policy information 224 specifies that the processing result resulting from the prompt should vary depending on the user's attributes, the information processing unit 244 controls the processing result using the user information 226. As a specific example of this processing, when a prompt inquiring about personal information is input by a user U, the information processing unit 244 determines whether the user U is a manager based on the user information 226 of the user U. If the user U is a manager, the information processing unit 244 processes the prompt so as to output the personal information in response to the prompt, whereas if the user U is not a manager, the information processing unit 244 does not respond to the prompt and does not output the personal information. Furthermore, for a user U who inputs a prompt instructing a process that violates the policy information 224 a predetermined number of times or more, the information processing unit 244 adds information indicating that the user U is a suspicious user to the user information 226, and is also capable of issuing a warning or restricting processing to the user U identified as a suspicious user.

[0044] The display control unit 246 controls the display on the display in response to user operations. The display control unit 246, for example, displays a design screen D on the display and arranges component images c and flow images f on the design screen D in response to user operations. The display control unit 246 stores the arrangement of the component images c arranged by the user, the component settings of the arranged component images c, and the arrangement of the flow images f arranged by the user as design information 230 in the storage unit 22.

[0045] The generation unit 248 generates a design file 232 based on the design information 230 stored in the storage unit 22. This generates a system design file corresponding to the component image c and its component settings arranged on the design screen D, and the flow image f arranged on the design screen D. The generation unit 248 stores the generated design file 232 in the storage unit 22.

[0046] The construction unit 250 constructs a system infrastructure based on the design file 232 stored in the storage unit 22 so that the system represented by the design file 232 can operate. The construction of the infrastructure includes setting up an API gateway, setting up a database, setting up a virtual machine, preparing storage, and setting up a network. Note that the construction of the infrastructure may not include some of the above, or may include other than the above. The construction unit 250 stores information indicating the constructed infrastructure as infrastructure information 234 in the storage unit 22.

[0047] (Processing Executed by Information Processing System 10) Next, the operation of the information processing system 10 will be described. Fig. 4 is a flowchart showing an example of the flow of processing by the information processing system 10. The processor 120 reads out the program 220 stored in the storage 124, expands it in the memory 122, and executes it, thereby performing processing. Although not shown, when the processor 120 receives operation information to terminate the operation of the information processing system 10, or operation termination information from the user terminal 14 during the ongoing determination processing (these will be simply referred to as "termination operations"), the processor 120 terminates the processing based on the program 220 that is currently being processed.

[0048] The processor 120 refers to the component information 228 and displays the design screen D on the display of the user terminal 14 (step S100). Fig. 5 is a diagram showing an example of the design screen D. The design screen D in Fig. 5 has a selection area d1 and a design area d2.

[0049] The selection area d1 is an area where the user selects an operation target, and is located on the left side of the design screen D. In the selection area d1, a cursor, a list of system components that can be placed on the design screen D (UI, endpoint, entity, trigger, data source, storage, pipeline, function, trained model, policy agent, and action generator), and a data flow that can connect between component images c are displayed in a selectable manner. Also, a deploy button BT is located in the selection area d1. The deploy button BT is a button for deploying a system designed by the user.

[0050] The design area d2 is an area for the user to design the system and is located to the right of the selection area d1. Component images c and flow images f can be freely placed in the design area d2. Component settings, including the component name and content, can also be added to the component images c placed in the design area d2.

[0051] Next, the user designs a desired system on the design screen D (step S102). Specifically, the user selects a system component in the selection area d1 and selects a desired position in the design area d2. Upon receiving this user operation, the processor 120 (display control unit 246) places a component image c corresponding to the system component selected by the user in the selection area d1 at the position selected by the user in the design area d2. By the user repeating this operation, multiple component images c are placed in the design area d2.

[0052] The user also selects a data flow in the selection area d1 and selects two component images c placed in the design area d2. Upon receiving this user operation, the processor 120 places in the design area d2 a flow image f (arrow) pointing from the first component image c selected by the user to the second component image c, or a flow image f (arrow) pointing from the first component image c and the second component image c to each other.

[0053] Furthermore, the user selects a component image c placed in the design area d2. When the processor 120 accepts this user operation, it displays a setting screen for the selected component image c. From the setting screen, the user can add component settings including the name and content of the system component. The user may select a registered component as the content of the system component, or may directly input source code or natural language. Alternatively, the user may leave the content of the system component blank.

[0054] In the example of FIG. 5, component images c1 to c9 and flow images f1 to f11 are arranged in the design area d2.

[0055] Component images c1, c2, and c3 are component images c corresponding to endpoints and are named "connectors." The component images c corresponding to endpoints are differentiated from the other component images c by, for example, using a marker (not shown) or a different color from the other component images c. This allows the user to grasp the location of the endpoints, which are the input and output points of information, at a glance, even if the names of the component images c become small and difficult to see when the entire system design screen is scaled down on the user terminal 14, making it easier to understand the flow of information in the system. While the component images c corresponding to endpoints are expressed differently from the others in this embodiment, this is not limiting, and the expressions of the other component images c may also be different, or all of the component images c may be expressed differently.

[0056] Component image c4 is a component image c corresponding to storage and is named "Data Lake." Component image c5 is a component image c corresponding to a trained model and is named "Data Processing." Component image c6 is a component image c corresponding to a function and is named "Data Processing." Component image c7 is a component image c corresponding to a policy agent and is named "Policy Agent." Component image c8 is a component image c corresponding to a trained model and is named "LLMs." Note that component image c8 is actually a proxy for the trained model. In other words, requests are sent to the trained model via a proxy, preventing a large number of requests from directly reaching a single trained model and distributing requests among multiple trained models. This improves system performance. Furthermore, by controlling requests and responses, the proxy can filter inappropriate requests. This makes it possible to prevent unauthorized access to or attacks on the trained model itself. Furthermore, requests sent through the proxy can be preprocessed and modified to make them easier for the trained model to process. As an example, a request incorporating policy information 224 can be sent. This improves the efficiency and performance of the trained model while adhering to the policy information 224. Furthermore, when using multiple trained models, centralized data management is possible through the proxy, which maintains data consistency and facilitates troubleshooting. Furthermore, when system demand increases, adding new trained model instances through the proxy facilitates scaling. It also facilitates switching to a different trained model.

[0057] The component image c9 is a component image c corresponding to an action generator, and is named "action generator."

[0058] Flow image f1 is a flow image f that moves from component image c1 to component image c4. Flow image f2 is a flow image f that moves from component image c2 to component image c4. Flow image f3 is a flow image f that moves from component image c3 to component image c4. Flow image f4 is a flow image f that connects component image c4 and component image c5. Flow image f5 is a flow image f that connects component image c4 and component image c6. Flow image f6 is a flow image f that connects component image c4 and component image c7. Flow image f7 is a flow image f that connects component image c4 and component image c8. Flow image f8 is a flow image f that connects component image c7 and component image c8. Flow image f9 is a flow image f that connects component image c8 and component image c9. The flow image f10 is a flow image f from the component image c9 to the component image c3, and the flow image f11 is a flow image f from the component image c9 to the component image c2.

[0059] As an example, the system in Figure 5 connects multiple data sources such as external tools and sensors, acquires information including unstructured data from each, processes it using a trained model including a large-scale language model, and then executes the processed results using an external tool, etc.

[0060] The user can design the above-described system simply by arranging the component image c and the flow image f on the design screen D. Note that the user operations for arranging the component image c and the flow image f are not limited to the above example.

[0061] The processor 120 performs a process of accepting input or change of the policy information 224 (step S104). In the example of Fig. 6, by selecting the component image c7 corresponding to the policy agent, a policy information input screen PW is displayed, and the user U can input or change the policy information 224 in natural language.

[0062] When the user completes the system design, he or she selects the deploy button BT. When the deploy button BT is selected, the processor 120 stores in the storage unit 22 the design information 230, which includes the layout of the component images c that the user has placed on the design screen D, the component settings of the placed component images c, and the layout of the flow images f that the user has placed (step S106).

[0063] Next, the processor 120 generates a design file 232 based on the design information 230 stored in the storage unit 22 (step S108). That is, the processor 120 (generation unit 248) generates the design file 232 based on the arrangement of component images c arranged by the user on the design screen D, the component settings of the arranged component images c, and the arrangement of flow images f arranged by the user. The generation unit 248 stores the generated design file 232 in the storage unit 22.

[0064] Thereafter, the processor 120 (construction unit 250) constructs the infrastructure of the system based on the design file 232 stored in the storage unit 22 (step S110). The processor 120 stores infrastructure information 234 relating to the constructed infrastructure in the storage unit 22.

[0065] The processor 120 determines whether an instruction to start execution of the constructed system has been issued (step S112). If an instruction to start execution has not been issued (step S112: NO), the processor 120 ends the process. On the other hand, if an instruction to start execution has been issued (step S112: NO), the processor 120 acquires a prompt and information necessary for processing based on the prompt (step S114).

[0066] The processor 120 acquires the policy information 224 related to the processing (step S116), and then executes the processing based on the acquired information and the policy information 224 (step S118).

[0067] The processor 120 outputs the processing results (step S120) and ends the processing. This output includes displaying the results on the display of the user terminal 14, executing processing on external tools, sensors, data sources, etc. by the action generator, etc.

[0068] (Effects of the First Embodiment) The information processing system 10 according to the present embodiment executes a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of performing processing based on the information and the policy information, thereby making it possible to control the handling of information including unstructured data based on the policy information 224. This makes it possible to improve the efficiency and flexibility of information processing including unstructured data.

[0069] Furthermore, because the policy information 224 is written in natural language, processing rules can be provided to the system without the need for code or specialized language. This allows even non-technical personnel to easily build a system. Furthermore, because the policy information 224 can be widely expressed in natural language, it becomes possible to control processing more specifically. Furthermore, by writing the policy information 224 in natural language, new ideas can be tried out immediately, shortening development and testing time.

[0070] Furthermore, the policy information 224 can be entered and / or modified on a policy information input screen PW, which is displayed on a design screen that constructs a system by arranging pre-prepared component images c corresponding to the types of system components and flow images f showing the data flow between the system components. Therefore, the user U can design the desired system simply by arranging the component images c and flow images f. Furthermore, the contents of the system components can be freely added after arranging the component images c. Furthermore, since the policy information 224 can be entered and modified on the same screen as the design screen, it is easy to formulate the policy information 224 while viewing the information and processing flow. This further shortens development time and facilitates stable operation by preventing omissions and oversights of rules.

[0071] Furthermore, by placing a policy agent (component image c7) that controls the content and application destination of the policy information 224 on a design screen that constructs a system by placing component image c and flow image f, the same policy information 224 can be applied even if the trained model, external tool, etc. are replaced. In other words, without replacing the entire system due to partial changes, it is possible to change only the configuration that you want to change and redeploy the system with the previous configuration for the rest. This makes it possible to update systems efficiently and with reduced time and cost, even for systems that include configurations that change significantly due to technological evolution, etc.

[0072] Furthermore, the action generator is capable of executing an executable information acquisition step that acquires information about functions that can be executed as a result of the processing performed in the processing step, and an execution instruction generation step that generates execution instructions as needed based on the information processing results, so that the processing results can be made more practical, thereby improving productivity and efficiency.

[0073] Second Embodiment Next, an information processing system 500 according to a second embodiment of the present disclosure will be described using Figures 7 and 8. The information processing system 500 according to the second embodiment has the same basic configuration as the first embodiment, and is characterized in that it updates the policy information 224 and determines whether there is an inconsistency in the policy information 224. Note that the same components as those in the first embodiment are denoted by the same reference numerals, and their description will be omitted.

[0074] (System Overview) The information processing system 500 is, as an example, a system excluding the design system described in the first embodiment. In other words, it is a deployed system on which it is possible to update the policy information 224 and determine whether or not there is an inconsistency in the policy information 224.

[0075] (Functional Configuration) Next, the functional configuration of the development support device 50 will be described. FIG. 7 is a diagram showing an example of the functional configuration of the development support device 50. When executing various programs, the development support device 50 realizes various functions using the same hardware resources as in the first embodiment. The development support device 50 has a communication unit 20, a storage unit 60, and a control unit 70 as the functional configuration realized by the development support device 50. Each functional configuration is realized when the processor 120 reads and executes a program 600 stored in the memory 122 or the storage 124.

[0076] The storage unit 60 is realized by the memory 122 and the storage 124. The storage unit 22 stores a program 600, a trained model 222, policy information 224, and user information 226.

[0077] The control unit 70 is realized by the processor 120 reading and executing the program 600 from the memory 122 (see FIG. 2 ) and working in cooperation with other hardware components. The control unit 70 includes an information acquisition unit 242, an information processing unit 700, and a display control unit 246.

[0078] The information processing unit 700 performs information processing using the trained model 222, similar to the information processing unit 244 of the first embodiment. The information processing unit 244 also determines whether there is an inconsistency in the content of the policy information 224, and issues a notification if the determination results in an inconsistency. This inconsistency refers to a case where the content of the policy information 224 lacks consistency or is contradictory. For example, information about a user performing access control described in the policy information 224 differs in multiple sentences. The notification may be an alert displayed to the user U indicating that there is an inconsistency in the policy information 224, or it may be a notification that the inconsistency is clearly indicated by displaying the text data of the policy information 224, or it may be a notification in some other way.

[0079] The information processing unit 700 is also capable of updating the policy information 224 based on the results of processing performed based on the prompt. As a specific example, if there is policy information that is not explicitly stated in the original policy information 224 but that should be stated based on the overall trend of the policy information 224, this policy information is reflected in the policy information 224. Furthermore, if an instruction prompt for a process that is not stated in the original policy information 224 but is inappropriate to execute from a legal perspective is input, the information processing unit 700 determines that the prompt is inappropriate to execute and updates the policy information 224 to indicate that the instruction and similar processes will not be executed. In addition, the information processing unit 700 may correct typographical errors in the policy information 224, or, if it determines that the policy information 224 contains an inconsistency, update the policy information 224 to correct the inconsistency.

[0080] Furthermore, the information processing unit 700 determines whether the processing result is in accordance with the policy information 224, and outputs the processing result if it is determined to be in accordance with the policy information 224. On the other hand, if it is determined to be in accordance with the policy information 224, the processing result is not output. If the processing result is not output, the processing may be re-executed, and the processing result determined not to be output may be added to a reprocessing instruction as an undesired process. This makes the processing result more in line with the policy information. Furthermore, processing results determined not to be output may be flagged and listed, and processing or reprocessing may be performed based on this list. This makes the processing result more in line with the policy information. Furthermore, the determination of whether the processing result is in accordance with the policy information 224 is performed using a trained model other than the trained model used for processing. This provides flexibility, such as improved performance due to parallelization of processing and determination, and individual tuning. In this embodiment, processing and determination are performed using different trained models, but this is not limited to this, and they may also be performed using the same trained model.

[0081] The display control unit 246 enables the processing results output by the information processing unit 700 to be output to the user terminal 14 .

[0082] (Processing Executed by Information Processing System 500) Next, the operation of the information processing system 500 will be described. Fig. 8 is a flowchart showing an example of the flow of processing by the information processing system 500. The processor 120 reads out the program 600 stored in the storage 124, expands it in the memory 122, and executes it, thereby performing processing. Note that the same processes as those in the first embodiment are assigned the same reference numerals, and descriptions thereof will be omitted.

[0083] After the process of step S114, the processor 120 determines whether the policy information 224 is registered (step S200). If the policy information 224 is not registered (step S200: NO), the processor 120 proceeds to step S104. On the other hand, if the policy information 224 is registered (step S200: YES), the processor 120 proceeds to step S116.

[0084] After processing step S116, the processor 120 determines whether or not there is an inconsistency in the contents of the policy information 224 (step S202). If there is no inconsistency (step S202: NO), the processor 120 proceeds to step S118. On the other hand, if there is an inconsistency (step S202: YES), the processor 120 notifies the user terminal 14 of the inconsistency (step S204) and displays the policy information input screen PW (see FIG. 6) (step S206).

[0085] The processor 120 determines whether the input of the policy information 224 is complete (step S208). If the processor 120 determines that the input is not complete (step S208: NO), the processor 120 proceeds to step S206. On the other hand, if the processor 120 determines that the input is complete (step S208: YES), the processor 120 updates the policy information 224 with the input information (step S210), stores the policy information 224 in the storage unit 60 (step S212), and proceeds to step S202.

[0086] After processing step S118, the processor 120 determines whether the processing result conforms to the policy information 224 (step S214). If the processing result does not conform to the policy information 224 (step S214: NO), the processor 120 attaches an output restriction flag to the output result, does not output it, and proceeds to step S118. On the other hand, if the processing result conforms to the policy information 224 (step S214: YES), the processor 120 determines whether the policy information 224 needs to be updated based on the output result (step S218). If it is determined that the policy information 224 does not need to be updated (step S218: NO), the processor 120 proceeds to step S120. On the other hand, if it is determined that the policy information 224 needs to be updated (step S218: YES), the processor 120 updates the policy information 224 based on the processing result (step S220), stores the policy information 224 in the memory unit 60 (step S222), and proceeds to step S120.

[0087] (Effects of the Second Embodiment) The information processing system 500 according to this embodiment has the same configuration as the first embodiment, except for updating the policy information 224 and determining whether there is an inconsistency in the policy information 224, and therefore provides the same effects as the first embodiment. Furthermore, because the information processing system 500 allows the policy information 224 to be updated based on the processing results of the processing steps, it is possible to make the policy information 224 more realistic in light of the actual operational situation. This makes it possible to obtain highly accurate output results.

[0088] Furthermore, the information processing system 500 determines whether or not there is an inconsistency in the content of the policy information 224, and performs a notification step to notify the user if there is an inconsistency, thereby making the policy information 224 clearer, which can lead to improved reliability of the processing results.

[0089] (Variation 1) Note that the above-described embodiment does not include a design system for constructing a system on a design screen using the component image c and flow image f of the first embodiment, but the configuration may include the design system. Also, the first embodiment may not include the design system.

[0090] It is also possible to view the above-described information processing system from a different perspective. For example, the problem (purpose) that the information processing system according to this embodiment aims to solve can be viewed as "improving work efficiency by generating execution instructions for processing results in accordance with executable functions."

[0091] If the problem is understood as described above, an invention as a means for solving the problem could be, for example, as follows: "An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information necessary for processing; an executable information acquisition step of acquiring information about an executable function as a result of the processing performed in the processing step; and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information."

[0092] According to the above configuration, since the executable information acquisition step of acquiring information on executable functions as a result of processing performed in the processing step and the execution instruction generation step of generating an execution instruction as needed based on the processing result of the information are executable, even if the executable functions of the processing result change depending on the status of the system itself or the status of cooperation with external tools, an instruction to execute the processing result can be generated from information on the functions that can execute the processing result at that time based on the acquired executable information. This makes it possible to make the processing result more practical depending on the situation, thereby improving productivity and efficiency.

[0093] (Variant 2) Furthermore, if we look at the above-mentioned information processing system from a different perspective, the problem (purpose) that the information processing system of this embodiment aims to solve can also be seen as ``providing feedback to the user to input prompts that are in line with policy information when the user inputs prompts to instruct processing.''

[0094] If the problem is viewed as described above, an invention as a means for solving the problem could be, for example, as follows: "An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; and a processing step of, when a processing instruction and the information are input, executing the processing using a trained model that performs processing based on the instruction and the information, and, if the instruction is contrary to the policy information, correcting the instruction to conform to the policy information and presenting the correction result before executing the processing."

[0095] According to the above configuration, if a prompt as a processing instruction violates the policy information, the information processing device modifies the prompt to conform to the policy information, i.e., to follow the policy information, and then presents the modified result before performing the processing. This allows the prompt, which has a significant impact on the processing result, to conform to the policy information, thereby significantly affecting the processing result. Furthermore, by presenting the modified result by the information processing device, the user can see how the prompt they entered has been changed in comparison with the policy information, allowing them to enter appropriate prompts and formulate appropriate policy information. In other words, feedback to the user can encourage them to enter prompts that conform to the policy information, contributing to the formulation of effective policy information.

[0096] (Variant 3) Furthermore, if we look at the above-mentioned information processing system from a different perspective, the problem (purpose) that the information processing system of this embodiment aims to solve can also be seen as "enabling rapid system construction."

[0097] If the problem is viewed as described above, an invention as a means for solving the problem can be, for example, as follows: "An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; and a processing step of executing the processing using a trained model that, when inputting the information and the policy information, performs processing based on the policy information, wherein the policy information can be input and / or changed in a policy information input screen that is displayed on a design screen for building a system by arranging component images corresponding to types of pre-prepared system components and flow images that indicate data flows between the system components; and a status can be set to public, limited public, or private for each predetermined combination of the component image and the flow image including the policy information input screen, and the disclosure status of the predetermined combination to others is controlled in accordance with the status."

[0098] According to the above configuration, in a design screen for constructing a system by arranging component images and flow images, a disclosure status can be set for each predetermined combination of component images and flow images, including a policy information input screen. Therefore, by extracting and publishing combinations of open source processes or open sections of the overall system design screen, the combination of public sections can be reused or repurposed. This speeds up system construction. Furthermore, various benefits can be obtained by providing the data to others. Meanwhile, by extracting and publishing combinations of sections of the overall in-house system design screen, such as sections to be provided only to relevant parties, for limited disclosure, the system can be constructed quickly while controlling the scope of disclosure and information security. Furthermore, by extracting and publishing combinations of sections containing know-how or confidential information from the overall in-house system design screen and making them private, information security can be enhanced. In other words, these disclosure statuses can be set for each predetermined combination of component images and flow images, including a policy information input screen, on the design screen, thereby achieving both rapid system construction and information security.

[0099] <Additional Notes> This embodiment includes the following disclosure.

[0100] (Supplementary Note 1) An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; and a processing step of executing processing using a trained model that, when the information and the policy information are input, performs processing based on the policy information.

[0101] (Supplementary Note 2) The information processing method according to Supplementary Note 1, wherein the policy information is information written in a natural language.

[0102] (Supplementary Note 3) The information processing method according to Supplementary Note 1, wherein the policy information can be updated based on a processing result in the processing step.

[0103] (Supplementary Note 4) The information processing method according to Supplementary Note 1, further comprising: determining whether or not there is an inconsistency in the content of the policy information; and issuing a notification if there is an inconsistency.

[0104] (Appendix 5) The information processing method described in Appendix 1, wherein the policy information can be input and / or changed on a policy information input screen displayed on a design screen for constructing a system by arranging component images corresponding to types of pre-prepared system components and flow images showing the data flow between the system components.

[0105] (Supplementary Note 6) An information processing method according to Supplementary Note 1, further comprising a determination step of acquiring a processing result performed in the processing step, determining whether the processing result complies with the policy information, and restricting output of the processing result if it is determined that the processing result does not comply with the policy information.

[0106] (Supplementary Note 7) An information processing method according to Supplementary Note 1, comprising: an executable information acquisition step of acquiring information relating to functions that can be executed as a result of the processing performed in the processing step; and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information.

[0107] (Appendix 8) A program for causing an information processing device to execute an information processing method including: a processing information acquisition step for acquiring information necessary for processing; a policy information acquisition step for acquiring policy information for processing the information; and a processing step for performing processing based on the information and the policy information.

[0108] (Supplementary Note 9) An information processing system executed by an information processing device, which performs the following steps: a processing information acquisition step of acquiring information necessary for processing; a policy information acquisition step of acquiring policy information for processing the information; and a processing step of performing processing based on the information and the policy information.

[0109] (Supplementary Note 10) An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of executing the processing using a trained model that performs processing based on the policy information when the information and the policy information are input, wherein the policy information is updatable based on the processing results of the processing steps. (Supplementary Note 11) An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of executing the processing using a trained model that performs processing based on the policy information when the information and the policy information are input, wherein the information processing method comprises: determining whether or not there is an inconsistency in the content of the policy information, and performing a notification step of issuing a notification if there is an inconsistency. (Supplementary Note 12) An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; and a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, wherein the policy information can be input and / or changed on a policy information input screen that is displayed on a design screen that constructs a system by arranging component images corresponding to types of system components prepared in advance and flow images that show the data flow between the system components.(Supplementary Note 13) An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, a processing step of executing the processing using a trained model that performs processing based on the policy information when the information and the policy information are input, and a determination step of acquiring a processing result performed in the processing step, determining whether the processing result conforms to the policy information, and restricting output of the processing result when it is determined that the processing result does not conform to the policy information. (Supplementary Note 14) An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, an executable information acquisition step of acquiring information about functions that can be executed by the processing result performed in the processing step, and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information. (Supplementary Note 15) The information processing method according to any one of Supplementary Notes 10 to 14, wherein the policy information is information in a natural language. (Supplementary Note 16) A program for causing an information processing device to execute the information processing method, including: a processing information acquisition step of acquiring information necessary for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of performing processing based on the information and the policy information, wherein the policy information can be updated based on a processing result in the processing step.(Supplementary Note 17) A program for causing an information processing device to execute an information processing method executed by the information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of executing the processing using a trained model that performs processing based on the policy information when the information and the policy information are input, the program performing a notification step of determining whether or not there is an inconsistency in the content of the policy information, and notifying the user if there is an inconsistency. (Supplementary Note 18) A program for causing an information processing device to execute an information processing method, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of executing the processing using a trained model that performs processing based on the policy information when the information and the policy information are input, the policy information being able to be at least one of entered and changed on a policy information input screen displayed on a design screen for constructing a system by arranging component images corresponding to types of system components prepared in advance and flow images showing the data flow between the system components. (Supplementary Note 19) A program for causing an information processing device to execute an information processing method, including: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input; and a determination step of acquiring a processing result performed in the processing step, determining whether the processing result is in accordance with the policy information, and restricting output of the processing result if it is determined that the processing result is not in accordance with the policy information.(Supplementary Note 20) A program for causing an information processing device to execute an information processing method including: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, an executable information acquisition step of acquiring information about executable functions as a result of the processing performed in the processing step, and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information. (Supplementary Note 21) An information processing system executed by an information processing device, comprising: a processing information acquisition step of acquiring information required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of performing processing based on the information and the policy information, and wherein the policy information is updatable based on the processing result of the processing steps. (Supplementary Note 22) An information processing system executed by an information processing device, which performs a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, and also performs a notification step of determining whether there is any inconsistency in the content of the policy information and notifying if there is any inconsistency.(Supplementary Note 23) An information processing system executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of executing the processing using a trained model that performs processing based on the policy information when the information and the policy information are input, wherein the policy information can be input and / or changed on a policy information input screen that is displayed on a design screen for constructing a system by arranging component images corresponding to types of system components prepared in advance and flow images that indicate data flows between the system components. (Supplementary Note 24) An information processing system executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, and a determination step of acquiring a processing result performed in the processing step, determining whether the processing result conforms to the policy information, and restricting output of the processing result when it is determined that the processing result does not conform to the policy information. (Supplementary Note 25) An information processing system executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input; an executable information acquisition step of acquiring information regarding functions that can be executed as a result of the processing performed in the processing step; and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information.(Supplementary Note 26) An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; and a processing step of, when a processing instruction and the information are input, executing the processing using a trained model that performs processing based on the instruction and the information, and, if the instruction is contrary to the policy information, correcting the instruction to conform to the policy information and presenting the corrected result before executing the processing. (Supplementary Note 27) The information processing method according to Supplementary Note 26, wherein the policy information is information in natural language. (Supplementary Note 28) The information processing method according to Supplementary Note 26 or Supplementary Note 27, wherein the policy information is updatable based on the processing result in the processing step. (Supplementary Note 29) The information processing method according to any one of Supplements 26 to 28, further comprising: a notification step of determining whether or not there is a content inconsistency in the policy information, and notifying if there is an inconsistency. (Supplementary Note 30) The information processing method according to any one of Supplementary Notes 26 to 29, wherein the policy information can be input and / or changed on a policy information input screen that is displayed on a design screen for constructing a system by arranging component images corresponding to types of system components prepared in advance and flow images that indicate data flows between the system components. (Supplementary Note 31) The information processing method according to any one of Supplementary Notes 26 to 30, comprising: an executable information acquisition step of acquiring information on functions that can be executed as a result of processing performed in the processing step; and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information.(Supplementary Note 32) A program for causing an information processing device to execute an information processing method, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of, when a processing instruction and the information are input, executing the processing using a trained model that performs processing based on the instruction and the information, and if the instruction is contrary to the policy information, correcting the instruction to conform to the policy information and presenting the result of the correction before executing the processing. (Supplementary Note 33) An information processing system executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of, when a processing instruction and the information are input, executing the processing using a trained model that performs processing based on the instruction and the information, and if the instruction is contrary to the policy information, correcting the instruction to conform to the policy information and presenting the result of the correction before executing the processing. (Supplementary Note 34) An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of executing the processing using a trained model that performs processing based on the policy information when the information and the policy information are input, wherein the policy information can be input and / or changed in a policy information input screen that is displayed on a design screen for constructing a system by arranging component images corresponding to types of pre-prepared system components and flow images that indicate data flows between the system components, and wherein a status can be set to public, limited public, or private for each predetermined combination of the component images and the flow images including the policy information input screen, and wherein the disclosure status of the predetermined combination to others is controlled in accordance with the status. (Supplementary Note 35) The information processing method according to Supplementary Note 34, wherein the policy information is information in natural language.(Supplementary Note 36) The information processing method according to Supplementary Note 34 or Supplementary Note 35, wherein the policy information can be updated based on the processing results of the processing steps. (Supplementary Note 37) The information processing method according to any one of Supplementary Notes 34 to 36, comprising a notification step of determining whether or not there is an inconsistency in the content of the policy information, and issuing a notification if there is an inconsistency. (Supplementary Note 38) The information processing method according to any one of Supplementary Notes 34 to 37, comprising a determination step of acquiring a processing result performed in the processing step, determining whether the processing result is in accordance with the policy information, and restricting output of the processing result if it is determined that the processing result is not in accordance with the policy information. (Supplementary Note 39) The information processing method according to any one of Supplementary Notes 34 to 38, including: an executable information acquisition step of acquiring information on an executable function as a processing result performed in the processing step; and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information. (Supplementary Note 40) A program for causing an information processing device to execute an information processing method, comprising: a processing information acquisition step for acquiring information including unstructured data required for processing; a policy information acquisition step for acquiring policy information for processing the information; and a processing step for executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, wherein the policy information can be input and / or changed in a policy information input screen that is displayed on a design screen for constructing a system by arranging component images corresponding to types of pre-prepared system components and flow images that indicate data flows between the system components, and a status can be set to public, limited public, or private for each predetermined combination of the component image and the flow image including the policy information input screen, and the disclosure status of the predetermined combination to others is controlled in accordance with the status.(Supplementary Note 41) An information processing system executed by an information processing device, comprising: a processing information acquisition step for acquiring information including unstructured data required for processing; a policy information acquisition step for acquiring policy information for processing the information; and a processing step for executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input; wherein the policy information can be input and / or changed on a policy information input screen that is displayed on a design screen for constructing a system by arranging component images corresponding to types of pre-prepared system components and flow images that indicate the data flow between the system components; and wherein a status can be set to public, limited public, or private for each predetermined combination of the component image and the flow image including the policy information input screen, and the information processing system controls the disclosure status of the predetermined combination to others in accordance with the status. (Supplementary Note 42) An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information necessary for processing, a processing step of executing processing using a trained model that performs processing when the information is input, an executable information acquisition step of acquiring information about executable functions as a result of the processing performed in the processing step, and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information, wherein the executable information acquisition step and the execution instruction generation step are executed by an action generator displayed on a design screen that constructs a system by arranging component images corresponding to types of system components prepared in advance and flow images that indicate data flows between the system components. (Supplementary Note 43) The information processing method according to Supplementary Note 42, wherein at least one of a name and information about a destination of an execution instruction generated by the action generator is configurable for the action generator.(Supplementary Note 44) A program for causing an information processing device to execute an information processing method, comprising: a processing information acquisition step of acquiring information necessary for processing, a processing step of executing a process using a trained model that performs processing when the information is input, an executable information acquisition step of acquiring information about an executable function as a result of the processing performed in the processing step, and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information, wherein the executable information acquisition step and the execution instruction generation step are executed by an action generator displayed on a design screen that constructs a system by arranging component images corresponding to types of system components prepared in advance and flow images that indicate data flows between the system components. (Supplementary Note 45) The program according to Supplementary Note 44, wherein at least one of a name and information about a destination of an execution instruction generated by the action generator is configurable for the action generator. (Supplementary Note 46) An information processing system executed by an information processing device, comprising: a processing information acquisition step of acquiring information necessary for processing, a processing step of executing processing using a trained model that performs processing when the information is input, an executable information acquisition step of acquiring information about executable functions as a result of the processing performed in the processing step, and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information, wherein the executable information acquisition step and the execution instruction generation step are executed by an action generator displayed on a design screen that constructs a system by arranging component images corresponding to types of system components prepared in advance and flow images that indicate data flows between the system components. (Supplementary Note 47) The information processing system according to Supplementary Note 46, wherein at least one of a name and information about a destination of an execution instruction generated by the action generator is configurable for the action generator.

[0110] The embodiments disclosed herein are illustrative in all respects and should not be considered limiting. The scope of the present disclosure is defined by the claims, not by the meaning described above, and is intended to include all modifications within the meaning and scope of the claims. Furthermore, the present disclosure is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present disclosure.

[0111] The disclosures of Japanese Patent Application No. 2023-193286 filed on November 13, 2023, Japanese Patent Application No. 2024-005991 filed on January 18, 2024, Japanese Patent Application No. 2024-005992 filed on January 18, 2024, and Japanese Patent Application No. 2024-005993 filed on January 18, 2024 are incorporated herein by reference in their entirety. All documents, patent applications, and technical standards described herein are incorporated herein by reference to the same extent as if each individual document, patent application, and technical standard was specifically and individually indicated to be incorporated by reference.

Claims

1. An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; and a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, wherein the policy information can be updated based on the processing results in the processing steps.

2. An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; and a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, the information processing method further comprising a notification step of determining whether or not there is an inconsistency in the content of the policy information, and notifying the user if there is an inconsistency.

3. An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; and a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, wherein the policy information can be input and / or changed on a policy information input screen displayed on a design screen that constructs a system by arranging component images corresponding to types of pre-prepared system components and flow images showing the data flow between the system components.

4. An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input; and a determination step of acquiring a processing result performed in the processing step, determining whether the processing result is in accordance with the policy information, and restricting the output of the processing result if it is determined that the processing result is not in accordance with the policy information.

5. An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for the processing of the information; a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input; an executable information acquisition step of acquiring information regarding executable functions as a result of the processing performed in the processing step; and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information.

6. The information processing method according to any one of claims 1 to 5, wherein the policy information is information in a natural language.

7. A program for causing an information processing device to execute an information processing method, the method including: a processing information acquisition step for acquiring information necessary for processing; a policy information acquisition step for acquiring policy information for processing the information; and a processing step for performing processing based on the information and the policy information, wherein the policy information can be updated based on the processing results in the processing steps.

8. A program for causing an information processing device to execute an information processing method, the information processing method including: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; and a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, the program including: a notification step of determining whether or not there is an inconsistency in the content of the policy information, and notifying if such an inconsistency is found.

9. A program for causing an information processing device to execute an information processing method, comprising: a processing information acquisition step for acquiring information including unstructured data required for processing; a policy information acquisition step for acquiring policy information for processing the information; and a processing step for executing processing using a trained model which performs processing based on the policy information when the information and the policy information are input, wherein the policy information can be input and / or changed on a policy information input screen displayed on a design screen for constructing a system by arranging component images corresponding to types of pre-prepared system components and flow images showing the data flow between the system components.

10. A program for causing an information processing device to execute an information processing method including: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input; and a determination step of acquiring a processing result performed in the processing step, determining whether the processing result is in accordance with the policy information, and restricting the output of the processing result if it is determined that the processing result is not in accordance with the policy information.

11. A program for causing an information processing device to execute an information processing method including: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for the processing of the information; a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input; an executable information acquisition step of acquiring information regarding executable functions as a result of the processing performed in the processing step; and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information.

12. An information processing system executed by an information processing device, which performs a processing information acquisition step of acquiring information necessary for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of performing processing based on the information and the policy information, and wherein the policy information can be updated based on the processing results in the processing steps.

13. An information processing system executed by an information processing device, which performs a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for processing the information, and a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, and also performs a notification step of determining whether or not there is an inconsistency in the content of the policy information, and notifying if such an inconsistency is found.

14. An information processing system executed by an information processing device, comprising: a processing information acquisition step for acquiring information including unstructured data required for processing; a policy information acquisition step for acquiring policy information for processing the information; and a processing step for executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, wherein the policy information can be at least one of input and change on a policy information input screen displayed on a design screen that constructs a system by arranging component images corresponding to types of system components prepared in advance and flow images showing data flows between the system components.

15. An information processing system executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for the processing of the information; a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input; and a determination step of acquiring a processing result performed in the processing step, determining whether the processing result is in accordance with the policy information, and restricting the output of the processing result if it is determined that the processing result is not in accordance with the policy information.

16. An information processing system executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for the processing of the information; a processing step of executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input; an executable information acquisition step of acquiring information regarding executable functions as a result of the processing performed in the processing step; and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information.

17. An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for the processing of the information; and a processing step of executing the processing using a trained model that performs processing based on processing instructions and the information when the instructions and the information are input, and if the instructions are contrary to the policy information, correcting the instructions to comply with the policy information and presenting the correction result before executing the processing.

18. The information processing method according to claim 17, wherein the policy information is information in a natural language.

19. The information processing method according to claim 17, wherein the policy information can be updated based on a processing result in the processing step.

20. The information processing method according to claim 17, further comprising a step of determining whether or not there is an inconsistency in the contents of said policy information, and issuing a notification if said inconsistency is found.

21. The information processing method according to claim 17, wherein the policy information can be input and / or modified on a policy information input screen displayed on a design screen for constructing a system by arranging component images corresponding to pre-prepared types of system components and flow images showing data flows between the system components.

22. An information processing method as described in claim 17, comprising: an executable information acquisition step for acquiring information regarding functions that can be executed as a result of the processing performed in the processing step; and an execution instruction generation step for generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information.

23. A program for causing an information processing device to execute an information processing method including: a processing information acquisition step for acquiring information including unstructured data required for processing; a policy information acquisition step for acquiring policy information for the processing of the information; and a processing step for executing processing using a trained model that performs processing based on processing instructions and the information when the instructions and the information are input, and, if the instructions are contrary to the policy information, correcting the instructions to comply with the policy information and presenting the results of the correction before executing the processing.

24. An information processing system executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for the processing of the information; and a processing step of executing the processing using a trained model that performs processing based on processing instructions and the information when the instructions and the information are input, and, if the instructions are contrary to the policy information, correcting the instructions to comply with the policy information and presenting the correction result before executing the processing.

25. An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information including unstructured data required for processing; a policy information acquisition step of acquiring policy information for processing the information; and a processing step of executing processing using a trained model which performs processing based on the policy information when the information and the policy information are input, wherein the policy information can be at least one of input and change in a policy information input screen displayed on a design screen for constructing a system by arranging component images corresponding to types of pre-prepared system components and flow images showing data flows between the system components; and a status can be set to either public, limited public or private for each specified combination of the component images and the flow images including the policy information input screen, and the disclosure status of the specified combination to others is controlled in accordance with the status.

26. The information processing method according to claim 25, wherein the policy information is information in a natural language.

27. The information processing method according to claim 25, wherein the policy information can be updated based on a processing result in the processing step.

28. The information processing method according to claim 25, further comprising a step of determining whether or not there is an inconsistency in the contents of said policy information, and issuing a notification if said inconsistency is found.

29. An information processing method as set forth in claim 25, further comprising a determination step of acquiring a processing result performed in said processing step, determining whether said processing result complies with said policy information, and restricting output of said processing result if it is determined that said processing result does not comply with said policy information.

30. An information processing method as set forth in claim 25, comprising: an executable information acquisition step for acquiring information regarding a function that can be executed as a result of the processing performed in the processing step; and an execution instruction generation step for generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information.

31. A program for causing an information processing device to execute an information processing method, comprising: a processing information acquisition step for acquiring information including unstructured data required for processing; a policy information acquisition step for acquiring policy information for processing the information; and a processing step for executing processing using a trained model which performs processing based on the policy information when the information and the policy information are input, wherein the policy information can be at least one of input and change in a policy information input screen displayed on a design screen for constructing a system by arranging component images corresponding to types of pre-prepared system components and flow images showing data flows between the system components, and a status can be set to either public, limited public, or private for each specified combination of the component images and the flow images including the policy information input screen, and the disclosure status of the specified combination to others is controlled in accordance with the status.

32. An information processing system executed by an information processing device, comprising: a processing information acquisition step for acquiring information including unstructured data required for processing; a policy information acquisition step for acquiring policy information for processing the information; and a processing step for executing processing using a trained model which performs processing based on the policy information when the information and the policy information are input; wherein the policy information can be at least one of input and change in a policy information input screen displayed on a design screen for constructing a system by arranging component images corresponding to types of system components prepared in advance and flow images showing data flows between the system components; and wherein a status can be set to public, limited public, or private for each specified combination of the component images and the flow images including the policy information input screen, and the disclosure status of the specified combination to others is controlled in accordance with the status.

33. An information processing method executed by an information processing device, comprising: a processing information acquisition step of acquiring information necessary for processing; a processing step of executing a process using a trained model that performs processing when the information is input; an executable information acquisition step of acquiring information regarding executable functions as a result of the processing performed in the processing step; and an execution instruction generation step of generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information, wherein the executable information acquisition step and the execution instruction generation step are executed by an action generator displayed on a design screen that constructs a system by arranging component images corresponding to types of system components prepared in advance and flow images showing data flows between the system components.

34. The information processing method according to claim 33, wherein at least one of a name and information on a destination of an execution instruction generated by said action generator can be set for said action generator.

35. A program for causing an information processing device to execute an information processing method, comprising: a processing information acquisition step for acquiring information necessary for processing; a processing step for executing a process using a trained model that performs processing when the information is input; an executable information acquisition step for acquiring information regarding executable functions as a result of the processing performed in the processing step; and an execution instruction generation step for generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information, wherein the executable information acquisition step and the execution instruction generation step are executed by an action generator displayed on a design screen that constructs a system by arranging component images corresponding to types of system components prepared in advance and flow images showing data flows between the system components.

36. The program according to claim 35, wherein at least one of a name and information on a destination of an execution instruction generated by said action generator can be set for said action generator.

37. An information processing system executed by an information processing device, comprising: a processing information acquisition step for acquiring information necessary for processing; a processing step for executing processing using a trained model that performs processing when the information is input; an executable information acquisition step for acquiring information regarding executable functions as a result of the processing performed in the processing step; and an execution instruction generation step for generating an execution instruction as necessary based on the information acquired in the executable information acquisition step and the processing result of the information, wherein the executable information acquisition step and the execution instruction generation step are executed by an action generator displayed on a design screen that constructs a system by arranging component images corresponding to types of system components prepared in advance and flow images showing data flows between the system components.

38. The information processing system according to claim 37, wherein at least one of a name and information on a destination of an execution instruction generated by said action generator can be set for said action generator.

Images