Information processing method, program, and information processing system

The information processing method addresses the challenge of handling unstructured data by using a trained model to process data based on policy information, which can be dynamically adjusted on a design screen, resulting in improved efficiency and flexibility.

JP2025080209AActive Publication Date: 2025-05-23EXAWIZARDS INC
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2024005993
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-01-18
Publication Date
2025-05-23
Estimated Expiration
2043-11-13

AI Technical Summary

Technical Problem

Existing information processing methods struggle with efficiency and flexibility when handling information that includes unstructured data, as they are typically designed for structured data and lack the ability to adapt to changing processing requests.

Method used

An information processing method that involves acquiring unstructured data and policy information, using a trained model to process the data based on the policy information, and allowing policy information to be input or changed on a design screen where system components and data flows are arranged, with control over disclosure status.

Benefits of technology

This approach enhances the efficiency and flexibility of information processing by enabling effective handling of unstructured data and allowing for dynamic policy adjustments, thereby improving productivity and security.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025080209000001_ABST
    Figure 2025080209000001_ABST
Patent Text Reader

Abstract

To provide an information processing method, program, and information processing system, which improve efficiency and flexibility of information processing including unstructured data.SOLUTION: In an information processing system comprising a development support device and a user terminal communicably interconnected via a network, an information processing method comprises a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information regarding information processing, and a processing step of processing information using a trained model for processing information on the basis of the policy information upon input of the information and the policy information.SELECTED DRAWING: Figure 4
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

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

[0002] Patent Document 1 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. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2016-4437 A Summary of the Invention [Problem to be solved by the invention]

[0004] Generally, in the information processing method as 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 including unstructured data.

[0005] In consideration of the above, an object of the present invention is to improve efficiency and flexibility in information processing including unstructured data. [Means for solving the problem]

[0006] According to an information processing method of one embodiment, 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 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 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 system components prepared in advance 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 image and the flow image including the policy information input screen, and the disclosure status of the specified combination to others is controlled according to the status.

[0007] According to one embodiment of the program, an information processing device 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 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 system components prepared in advance and flow images showing the data flow between the system components, and a status can be set to either public, limited public, or private for each specified combination of the component image and the flow image including the policy information input screen, and the disclosure status of the specified combination to others is controlled according to the status.

[0008] According to one embodiment, the information processing system 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 executing processing using a trained model that performs processing based on the policy information when the information and the policy information are input, and 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 system components prepared in advance 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 image and the flow image including the policy information input screen, and the disclosure status of the specified combination to others is controlled according to the status. Effect of the Invention

[0009] According to one embodiment, it is possible to improve efficiency and flexibility in processing information including unstructured data. [Brief description of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating an example of a configuration of an information processing system according to a first embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of a server according to the first embodiment. [Diagram 3] FIG. 2 is a diagram illustrating an example of a functional configuration of a server according to the first embodiment. [Figure 4] FIG. 2 is a diagram showing an example of a processing flow of the information processing system according to the first embodiment. [Diagram 5] 2 is a diagram illustrating an example of a relationship between a design screen and an external tool in the information processing system according to the first embodiment. FIG. [Figure 6] FIG. 2 is a diagram showing an example of a design screen in the information processing system according to the first embodiment. [Figure 7] FIG. 11 is a diagram illustrating an example of a functional configuration of a server according to the second embodiment. [Figure 8] FIG. 11 is a diagram illustrating an example of a processing flow of an information processing system according to a second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] First embodiment A first embodiment of an information processing system according to the present invention will be described below with reference to Figures 1 to 6. In each drawing, the same or equivalent components and parts are given the same reference symbols. Also, the dimensional ratios in the drawings are exaggerated for the convenience of explanation and may differ from the actual ratios.

[0012] (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 is an information processing system or a control system configured by a combination including at least one of an information processing device, a sensor, and 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). In addition, the user 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 of the system designed by the user, and automatically builds an infrastructure capable of executing the system according to the design file.

[0013] (System Configuration) Fig. 1 is a diagram showing an example of a 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 of these.

[0014] 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 PC (Personal Computer), a smartphone, a tablet terminal, a server device, a microcomputer, a wearable device, or a combination of these.

[0015] The development support device 12 is an example of an information processing device that acquires information input from the 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.

[0016] (Hardware configuration) 2 is a block diagram showing a 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.

[0017] The processor 120 controls each component of the development support device 12 and realizes the functions of the development support device 12 by expanding 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 OS (Operating System) and a program 220 described below. The execution of these programs by the processor 120 realizes a part of the state visualization method according to this embodiment. The processor 120 is, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), or a combination of these.

[0018] 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 ROM (PROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), or a combination thereof. The RAM is, for example, a Dynamic RAM (DRAM), a Static RAM (SRAM), a Magnetoresistive RAM (MRAM), or a combination thereof.

[0019] The storage 124 stores an 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 of these.

[0020] 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 imaging device 16 via the network N and 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 thereto.

[0021] The input / output I / F 128 is an interface for connecting the input device 132 and the output device 130 to the development support device 12. The input device 132 is, for example, a mouse, a keyboard, a touch panel, a microphone, a scanner, a camera, various sensors, operation buttons, or a combination thereof. The output device 130 is, for example, a display, a projector, a printer, a speaker, a vibrator, or a combination thereof.

[0022] The drive device 134 reads and writes data on the disk medium 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 medium 109 is, for example, a CD (Compact Disc), a DVD (Digital Versatile Disc), an FD (Floppy Disk), an MO (Magneto-Optical disk), a BD (Blu-ray (registered trademark) Disc), or a combination thereof.

[0023] Note that in this embodiment, the program may be written in the memory 122 or the storage 124 at the manufacturing stage of the development support device 12, 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 the disk medium 136.

[0024] Moreover, the hardware configuration of the user terminal 14 is substantially the same as the hardware configuration of the development support device 12 described above, and therefore a detailed description thereof will be omitted.

[0025] (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 realizes various functions using the above-mentioned hardware resources. The development support device 12 has a communication unit 20, a storage unit 22, and a control unit 24 as functional configurations realized by the development support device 12. Each functional configuration is realized by the processor 120 reading and executing a program 220 stored in the memory 122 or storage 124.

[0026] 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. In addition, the communication unit 20 transmits information to the user terminal 14, and receives a request by the user U from the user terminal 14.

[0027] 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.

[0028] The trained model 222 is composed of at least one trained machine learning model. This trained model 222 is, for example, regarded as a large language model, which is a model trained with a large amount of text data from articles, books, websites, etc. on the Internet. When inputting text data called a prompt, it generates and outputs text data corresponding to the prompt. The language model in the trained model 222 of the present embodiment acquires information including unstructured data when necessary according to the prompt, performs processing, and generates text data as a processing result. Here, the "unstructured data" refers to data stored without being structured in a predefined method. On the other hand, "structured data" refers to data existing in specific fields in files or records. "Structured data" includes "semi-structured data".

[0029] Also, the trained model 222 performs processing according to a prompt based on policy information 224 described later. This policy information 224 is, for example, regarded as text data in natural language and indicates rules to be observed in processing. Specifically, it indicates in natural language that personal information leakage and outputs contrary to public order and good customs should not be performed. Note that the policy information is not limited to these and may be based on access control, data protection, security, regulations, guidelines, business plans, etc. Also, the policy information may be input by the user U, generated by the system, obtained from other data sources, or a combination thereof. 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, and may even be something other than text data such as voice or moving images. In other words, the policy information 224 instructs the system on the rules when processing structured data and unstructured data across the board.

[0030] The user information 226 is various information of the user U who has registered to use the information processing system 10. Specifically, the information includes user identification information for unique identification, user preference information such as interest information, user history information including past usage, and user attribute information such as occupation and job title.

[0031] Component information 228 is information related to system components prepared in advance. A system component is a component of a system. The 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 prepared system components may not include some of the above, or may include components other than the above.

[0032] The UI is a screen on which the output of the system is displayed. The endpoint is the address of an 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 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.

[0033] The component information 228 includes a component image c, a component setting, a registered component, and a flow image f.

[0034] The component images c are images corresponding to the types of system components prepared in advance. As the component images c, component images c corresponding to 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 are prepared.

[0035] The component settings are information indicating setting items according to the type of system component prepared in advance. The component settings include, for example, the name and contents of the component, but are not limited to this. For example, the setting items of the UI include the name of the UI, the contents of the UI, the entities to be displayed on the screen, and the display format of the entities. Furthermore, the setting items of the trained model include the name of the trained model, the contents of the trained model, and the input and output of the trained model. Furthermore, the setting items of the policy agent include the name of the policy agent, policy information assigned to the policy agent, and the like. Furthermore, the setting items of the action generator 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.).

[0036] The registered components are system components prepared in advance. The registered components can be prepared for each type of the system components prepared in advance. The user can select a registered component as the content of the component.

[0037] The flow image f is an image showing the data flow between system components, for example, arrows connecting the component images c, but is not limited to this.

[0038] 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 for the user to design a system. The design information 230 includes the arrangement of component images c arranged by the user, component settings of the arranged component images c, and the arrangement of flow images f arranged by the user.

[0039] The design file 232 is a file representing a system design generated from the design information 230. The design file 232 includes information indicating a component setting of a system component corresponding to a component image c arranged by the user and a data flow corresponding to a flow image f arranged by the user. The design file 232 is, for example, an XML file, a YAML file, or a JSON file, but is not limited thereto.

[0040] 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.

[0041] The control unit 24 is realized by the processor 120 reading and executing the program 220 from the memory 122 (see FIG. 2) and cooperating with other hardware configurations. 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.

[0042] 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. These pieces of information may be information stored in the storage unit 22, or may be information acquired from an external data source or the like. Furthermore, when 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 related to functions including external tools, sensors, etc. that can execute the processing results.

[0043] The information processing unit 244 performs information processing using the trained model 222. Specifically, when a prompt instructing a process is input by the user, text data is output as a processing result based on various information including policy information acquired by the information acquisition unit 242 based on the prompt. When information on a function capable of executing the processing result is acquired, the information processing unit 244 outputs the processing result using the function. That is, as an example, when a spreadsheet software is connected to the information processing system 10 as an external tool, information on the spreadsheet function is acquired as a function capable of executing the processing result. Then, the information processing unit 244 generates an execution instruction for the spreadsheet software based on the information so as to output the processing result using the spreadsheet function as necessary.

[0044] The information processing unit 244 also uses the user information 226 to execute processing according to at least one of the contents of the prompt and the policy information 224. That is, when the policy information 224 changes the processing result by the prompt according to the attributes of the user, the processing result is controlled using the user information 226. As a specific example of this processing, when a prompt inquiring about personal information is input from the user U, it is determined from the user information 226 of the user U whether the user U is a manager, and if the user U corresponds to a manager, processing is performed to output personal information in response to the prompt, whereas if the user U does not correspond to a manager, processing is performed not to output personal information without responding to the prompt. Furthermore, for the user U who inputs a prompt for an instruction of processing contrary to 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 capable of issuing a warning notice or restricting processing to the suspicious user U.

[0045] The display control unit 246 controls the display of the display in response to a user operation. For example, the display control unit 246 displays a design screen D on the display, and arranges a component image c and a flow image f on the design screen D in response to a user operation. The display control unit 246 stores the arrangement of the component image c arranged by the user, the component settings of the arranged component image c, and the arrangement of the flow image f arranged by the user in the storage unit 22 as design information 230.

[0046] The generating unit 248 generates a design file 232 based on the design information 230 stored in the storage unit 22. This generates a design file of a system 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 generating unit 248 stores the generated design file 232 in the storage unit 22.

[0047] The construction unit 250 constructs a system infrastructure based on the design file 232 stored in the memory unit 22 so that the system represented by the design file 232 can operate. The construction of the infrastructure includes starting up an API gateway, starting up a DB, starting 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 in the memory unit 22 as infrastructure information 234.

[0048] (Processing Executed by Information Processing System 10) Next, the operation of the information processing system 10 will be described. Fig. 4 is a flow chart 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 for terminating the operation of the information processing system 10, or information on the end of an operation from the user terminal 14 during the determination processing being executed (these are simply referred to as "termination operation"), the processor 120 ends the processing based on the program 220 being processed.

[0049] 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). Here, 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.

[0050] The selection area d1 is an area for selecting an operation target by the user, and is arranged on the left side of the design screen D. In the selection area d1, a cursor, a list of system components that can be arranged 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. In addition, a deploy button BT is arranged in the selection area d1. The deploy button BT is a button for deploying a system designed by the user.

[0051] The design area d2 is an area for the user to design a system, and is placed to the right of the selection area d1. Component images c and flow images f can be freely placed in the design area d2. In addition, component settings, including the name and contents of the component, can be added to the component image c placed in the design area d2.

[0052] 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 space 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 space d2. By the user repeating this operation, multiple component images c are placed in the design space d2.

[0053] Furthermore, the user selects a data flow in the selection area d1, and selects two component images c arranged in the design area d2. When the processor 120 accepts this user operation, it arranges 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.

[0054] Furthermore, the user selects a component image c arranged 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 contents of the system component. The user may select a registered component as the contents of the system component, or may directly input source code or natural language. Also, the contents of the system component may be left blank.

[0055] In the example of FIG. 5, component images c1 to c9 and flow images f1 to f11 are arranged in the design domain d2.

[0056] The component images c1, c2, and c3 are component images c corresponding to the endpoints, and are named "connector". The component images c corresponding to the endpoints are differentiated from the other component images c in terms of expression, such as by a mark (not shown) or a color different from the other component images c. This makes it easier to grasp the position 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 design screen of the system is scaled down on the user terminal 14, making it easier to grasp the flow of information in the system. In this embodiment, the expression of the component image c corresponding to the endpoints is made different from the other images, but this is not limited to the above, and the expressions of the other component images c may also be changed, or the entire component images c may each be expressed differently.

[0057] The component image c4 is a component image c corresponding to storage, and is named "data lake". The component image c5 is a component image c corresponding to a trained model, and is named "data processing". The component image c6 is a component image c corresponding to a function, and is named "data processing". The component image c7 is a component image c corresponding to a policy agent, and is named "policy agent". The component image c8 is a component image c corresponding to a trained model, and is named "LLMs". Note that the component image c8 is actually a proxy for the trained model. In other words, since a request is sent to the trained model via a proxy, it is possible to prevent a large number of requests from directly hitting a single trained model, and to distribute requests among multiple trained models. This can improve the performance of the system. In addition, by the proxy controlling the request and response, it is possible to filter inappropriate requests. This makes it possible to prevent unauthorized access to or attacks on the trained model itself. Furthermore, the request sent through the proxy can be preprocessed or processed in a form that is easy for the trained model to process. As an example, a request containing 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 multiple trained models are used, centralized data management is possible through the proxy, which maintains data consistency and makes troubleshooting easier. In addition, when the demand for the system increases, scaling is easy by adding new trained model instances through the proxy. It also becomes easy to switch to a different trained model.

[0058] The component image c9 is a component image c corresponding to an action generator, and is named "action generator."

[0059] The flow image f1 is a flow image f from the component image c1 to the component image c4. The flow image f2 is a flow image f from the component image c2 to the component image c4. The flow image f3 is a flow image f from the component image c3 to the component image c4. The flow image f4 is a flow image f that connects the component image c4 and the component image c5. The flow image f5 is a flow image f that connects the component image c4 and the component image c6. The flow image f6 is a flow image f that connects the component image c4 and the component image c7. The flow image f7 is a flow image f that connects the component image c4 and the component image c8. The flow image f8 is a flow image f that connects the component image c7 and the component image c8. The flow image f9 is a flow image f that connects the component image c8 and the 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.

[0060] As an example, the system in Figure 5 is a system that connects multiple data sources such as external tools and sensors, acquires information including unstructured data from each of them, processes it using a trained model including a large-scale language model, and then executes the processed results using an external tool, etc.

[0061] A user can design a system as described above by simply arranging the component image c and the flow image f on the design screen D. Note that the user operation for arranging the component image c and the flow image f is not limited to the above example.

[0062] 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.

[0063] When the user completes the system design, he / she selects the deploy button BT. When the deploy button BT is selected, the processor 120 stores the design information 230, including the layout of the component images c arranged by the user on the design screen D, the component settings of the arranged component images c, and the layout of the flow images f arranged by the user, in the storage unit 22 (step S106).

[0064] 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 (the generation unit 248) generates the design file 232 based on the arrangement of the 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 the flow images f arranged by the user. The generation unit 248 stores the generated design file 232 in the storage unit 22.

[0065] 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 in the storage unit 22 infrastructure information 234 relating to the constructed infrastructure.

[0066] 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), processor 120 ends the process. On the other hand, if an instruction to start execution has been issued (step S112: NO), processor 120 acquires a prompt and information necessary for processing based on the prompt (step S114).

[0067] The processor 120 acquires the policy information 224 related to the process (step S116), and executes the process based on the acquired information and the policy information 224 (step S118).

[0068] The processor 120 outputs the processing result (step S120) and ends the processing. This output includes displaying on the display of the user terminal 14, executing processing on external tools, sensors, data sources, etc. by the action generator, etc.

[0069] (Effects of the First Embodiment) According to the information processing system 10 of this embodiment, a processing information acquisition step of acquiring information including unstructured data required for processing, a policy information acquisition step of acquiring policy information for information processing, and a processing step of performing processing based on the information and the policy information are executed, so that the handling of information including unstructured data can be controlled based on the policy information 224. This makes it possible to improve the efficiency and flexibility of information processing including unstructured data.

[0070] In addition, because the policy information 224 is written in natural language, processing rules can be given to the system without the need for code or specialized language. Therefore, even non-technical people can easily build a system. In addition, because the policy information 224 can be widely expressed in natural language, processing can be controlled more specifically. Furthermore, by writing the policy information 224 in natural language, new ideas can be tried out immediately, making it possible to shorten development and testing times.

[0071] Furthermore, the policy information 224 can be at least one of input and modification on a policy information input screen PW displayed on a design screen that constructs a system by arranging a component image c corresponding to the type of system component prepared in advance and a flow image f showing the data flow between the system components. Therefore, the user U can design a desired system just by arranging the component image c and the flow image f. In addition, the contents of the system components can be freely added after arranging the component image c. Furthermore, since the policy information 224 can be input and modified on the same screen as the design screen, it becomes easy to formulate the policy information 224 while viewing the flow of information and processing. This further shortens the development time and makes it easier to perform stable operation by suppressing omissions and omissions of rules.

[0072] In addition, by arranging a policy agent (component image c7) that controls the contents and application destination of the policy information 224 on a design screen that constructs a system by arranging the component image c and the flow image f, the same policy information 224 can be applied even if a trained model, an external tool, etc. are replaced. In other words, it is possible to change only the configuration that is to be changed and redeploy the system with the previous configuration for the rest, without replacing the entire system due to partial changes. This makes it possible to update a system that is efficient and includes a configuration that changes greatly due to technological evolution, etc., while reducing time and cost.

[0073] Furthermore, since the action generator is capable of executing 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 processing result, the processing result can be made more practical, thereby improving productivity and efficiency.

[0074] Second Embodiment Next, an information processing system 500 according to a second embodiment of the present invention will be described with reference to Figures 7 and 8. The information processing system 500 according to the second embodiment has a basic configuration similar to that of 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.

[0075] (System Overview) As an example, the information processing system 500 is a system excluding the design system described in the first embodiment. In other words, it is a deployed system, and it is possible to update the policy information 224 and determine whether or not there is an inconsistency in the policy information 224 on the system.

[0076] (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 by the processor 120 reading and executing a program 600 stored in the memory 122 or the storage 124.

[0077] The storage unit 60 is realized by the memory 122 and the storage 124. In the storage unit 22, a program 600, a trained model 222, policy information 224, and user information 226 are stored.

[0078] The control unit 70 is realized by the processor 120 reading and executing the program 600 from the memory 122 (see FIG. 2) and cooperating with other hardware configurations. The control unit 70 includes an information acquisition unit 242, an information processing unit 700, and a display control unit 246.

[0079] 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 judges inconsistencies in the contents of the policy information 224, and notifies the user if there is an inconsistency as a result of the judgment. The inconsistency refers to a case where the contents of the policy information 224 lack consistency or are contradictory, and an example of the inconsistency is a case where information about a user performing access control described in the policy information 224 is different in multiple sentences. The notification may be a display of an alert to the user U indicating that there is an inconsistency in the policy information 224, or a display of text data of the policy information 224 to explicitly display the inconsistency, or other notification may be used.

[0080] The information processing unit 700 can update the policy information 224 based on the result of the processing performed based on the prompt. As a specific example, if there is policy information that is not explicitly described in the initial policy information 224 but should be described in the overall policy information 224 in terms of the tendency of the policy information 224, this is reflected in the policy information 224. In addition, when an instruction prompt for a process that is not described in the initial policy information 224 but is not suitable for execution in light of a legal viewpoint is input, the information processing unit 700 determines that the prompt is not suitable for execution and updates the policy information 224 to indicate that the instruction and similar processes will not be performed. In addition, the information processing unit 700 may update the policy information 224 to correct a typographical error, or to correct an inconsistency when it is determined that the above-mentioned policy information 224 has an inconsistency.

[0081] Furthermore, the information processing unit 700 judges whether the processing result is in accordance with the policy information 224, and outputs the processing result when it is judged to be in accordance with the policy information 224. On the other hand, when it is judged not to be in accordance with the policy information 224, the processing result is not output. In addition, when the processing result is not output, the processing may be performed again, and the processing result judged not to be output at that time may be added to the reprocessing instruction as an undesired processing. This makes it possible to make the processing result more in accordance with the policy information. Furthermore, a flag or the like may be set on the processing result judged not to be output and this may be listed, and the processing or reprocessing may be performed based on this list. This makes it possible to make the processing result more in accordance with the policy information. In addition, the judgment of whether the processing result is in accordance with the policy information 224 is performed using a trained model other than the trained model that performed the processing. This makes it possible to provide flexibility such as improved performance due to parallelization of processing and judgment and individual tuning. In this embodiment, the processing and judgment are performed using different trained models, but this is not limited to this, and they may be performed using the same trained model.

[0082] The display control unit 246 enables the processing results output by the information processing unit 700 to be output to the user terminal 14 .

[0083] (Processing performed 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 denoted by the same reference numerals, and the description thereof will be omitted.

[0084] After the process of step S114, the processor 120 determines whether or not the policy information 224 is registered (step S200). If the policy information 224 is not registered (step S200: NO), the processor 120 shifts the process to step S104. On the other hand, if the policy information 224 is registered (step S200: YES), the processor 120 shifts the process to step S116.

[0085] After the process of step S116, the processor 120 judges 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 moves the process 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).

[0086] The processor 120 determines whether the input of the policy information 224 has been completed (step S208). If the processor 120 determines that the input has not been completed (step S208: NO), the processor 120 proceeds to step S206. On the other hand, if the processor 120 determines that the input has been completed (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.

[0087] After the process of step S118, the processor 120 judges whether or not the process result conforms to the policy information 224 (step S214). If the process 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 shifts the process to step S118. On the other hand, if the process result conforms to the policy information 224 (step S214: YES), the processor 120 judges whether or not the policy information 224 needs to be updated based on the output result (step S218). If it is judged that the policy information 224 does not need to be updated (step S218: NO), the processor 120 shifts the process 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) and stores the policy information 224 in the memory unit 60 (step S222), and then proceeds to step S120.

[0088] (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 judging whether or not there is an inconsistency in the policy information 224, and therefore provides the same operational effects as the first embodiment. Furthermore, since the information processing system 500 allows the policy information to be updated based on the processing results in the processing steps, the policy information 224 can be made more realistic based on the actual operation situation. This makes it possible to obtain highly accurate output results.

[0089] Furthermore, the information processing system 500 judges whether or not there is an inconsistency in the contents of the policy information 224, and performs a notification step of notifying the user if there is an inconsistency, thereby making it possible to clarify the policy information 224. This can lead to improved reliability of the processing results.

[0090] (Variation 1) In the above-described embodiment, the configuration of the design system for constructing a system on the design screen based on the component image c and the flow image f of the first embodiment is not included, but the configuration may include the design system. Also, in the first embodiment, the configuration may not include the design system.

[0091] In addition, the above-described information processing system can be viewed from a different perspective. For example, the problem (purpose) to be solved by the information processing system according to the present embodiment can be viewed as "improving work efficiency by generating execution instructions of processing results in accordance with executable functions."

[0092] If the problem is understood as above, the invention as a means for solving the problem is, for example, as follows. "An information processing method executed by an information processing device, a processing information acquisition step of acquiring information necessary for processing; an executable information acquisition step of acquiring information about a function that can be executed as a result of the processing performed in the processing step; an execution instruction generating step of generating an execution instruction as necessary based on the information acquired in the executable information acquiring step and a processing result of the information; "An information processing method including the above."

[0093] According to the above configuration, since the executable information acquisition step of acquiring information on executable functions as a result of the processing performed in the processing step and the execution instruction generation step of generating an execution instruction as necessary 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 an external tool, 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.

[0094] (Variation 2) Furthermore, if the above-mentioned information processing system is viewed from a different perspective, the problem (purpose) that the information processing system of this embodiment aims to solve can also be viewed as "providing feedback to the user to input prompts that are in line with policy information when the user inputs prompts to instruct processing."

[0095] If the problem is understood as above, the invention as a means for solving the problem is, for example, as follows. "An information processing method executed by an information processing device, 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 a processing instruction and the information when the processing instruction and the information are input, and correcting the instruction to conform to the policy information when the instruction is contrary to the policy information, presenting the correction result, and then executing the processing; "An information processing method including the following."

[0096] According to the above configuration, if the prompt as a processing instruction is contrary to the policy information, the information processing device modifies the prompt so as to conform to the policy information, i.e., to comply with the policy information, and then performs the processing after presenting the modified result. This makes it possible to greatly affect the processing result by making the prompt itself, which has a large effect on the processing result, conform to the policy information. Furthermore, by presenting the modified result by the information processing device, the user can know how the prompt he or she input has been changed in light of the policy information, and therefore can input an appropriate prompt and formulate appropriate policy information. In other words, feedback to the user can encourage the user to input a prompt that conforms to the policy information, and can contribute to the formulation of effective policy information.

[0097] (Variation 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 is trying to solve can also be seen as "enabling rapid system construction."

[0098] If the problem is understood as above, the invention as a means for solving the problem is, for example, as follows. "An information processing method executed by an information processing device, 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 a process using a trained model that performs processing based on the policy information when the information and the policy information are input; Including, the policy information can be at least one of input and modification 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 data flows between the system components; a status can be set to any one of public, limited public, and private for each predetermined combination of the component image including the policy information input screen and the flow image, and the disclosure status of the predetermined combination to others is controlled according to the status; Information processing methods.”

[0099] 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 a combination of a part of the design screen of the entire system that uses open source processing or is opened and provided to others, the combination of the public parts can be reused or reused. This allows the system to be constructed quickly. It is also possible to obtain various benefits through providing to others. On the other hand, by extracting and publishing a combination of a part of the design screen of the entire in-house system that is provided only to related parties, the system can be constructed quickly while controlling the scope of disclosure and information security. Furthermore, by extracting and publishing a combination of a part including know-how or confidential information from the design screen of the entire in-house system, information security can be improved. 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, so that both rapid system construction and information security can be achieved.

[0100] <Additional Notes> The present embodiment includes the following disclosure.

[0101] (Appendix 1) An information processing method executed by an information processing device, 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 a process using a trained model that performs processing based on the policy information when the information and the policy information are input; An information processing method comprising:

[0102] (Appendix 2) the policy information is information in natural language; 2. An information processing method as described in Appendix 1.

[0103] (Appendix 3) The policy information can be updated based on a processing result in the processing step. 2. An information processing method as described in Appendix 1.

[0104] (Appendix 4) a notification step of determining whether or not there is an inconsistency in the policy information and notifying the user if there is an inconsistency; 2. An information processing method as described in Appendix 1.

[0105] (Appendix 5) The policy information can be at least one of input and modification on a policy information input screen displayed on a design screen for constructing a system by arranging component images corresponding to the types of system components prepared in advance and flow images showing data flows between the system components. 2. An information processing method as described in Appendix 1.

[0106] (Appendix 6) 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 when it is determined that the processing result does not comply with the policy information; 2. An information processing method as described in Appendix 1.

[0107] (Appendix 7) an executable information acquisition step of acquiring information about a function that can be executed as a result of the processing performed in the processing step; an execution instruction generating step of generating an execution instruction as necessary based on the information acquired in the executable information acquiring step and a processing result of the information, 2. An information processing method as described in Appendix 1.

[0108] (Appendix 8) In the information processing device, a processing information acquisition step of acquiring information necessary for processing; a policy information acquisition step of acquiring policy information for processing the information; a processing step of performing processing based on the information and the policy information; A program for executing an information processing method including the steps of:

[0109] (Appendix 9) An information processing system executed by an information processing device, a processing information acquisition step of acquiring information necessary for processing; a policy information acquisition step of acquiring policy information for processing the information; a processing step of performing processing based on the information and the policy information; An information processing system that performs the above.

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

[0111] 10. Information Processing Systems 220 Programs 222 trained models 224 Policy Information 500 Information Processing Systems 600 Programs

Claims

1. An information processing method executed by an information processing device, 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 a process using a trained model that performs processing based on the policy information when the information and the policy information are input; Including, the policy information can be at least one of input and modification 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 data flows between the system components; a status can be set to any one of public, limited public, and private for each predetermined combination of the component image including the policy information input screen and the flow image, and the disclosure status of the predetermined combination to others is controlled according to the status; Information processing methods.

2. the policy information is information in natural language; The information processing method according to claim 1 .

3. The policy information can be updated based on a processing result in the processing step. The information processing method according to claim 1 .

4. a notification step of determining whether or not there is an inconsistency in the policy information and notifying the user if there is an inconsistency; The information processing method according to claim 1 .

5. 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 when it is determined that the processing result does not comply with the policy information; The information processing method according to claim 1 .

6. an executable information acquisition step of acquiring information about a function that can be executed as a result of the processing performed in the processing step; an execution instruction generating step of generating an execution instruction as necessary based on the information acquired in the executable information acquiring step and a processing result of the information, The information processing method according to claim 1 .

7. In the information processing device, 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 a process using a trained model that performs processing based on the policy information when the information and the policy information are input; Including, the policy information can be at least one of input and modification 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 data flows between the system components; a status can be set to any one of public, limited public, and private for each predetermined combination of the component image including the policy information input screen and the flow image, and the disclosure status of the predetermined combination to others is controlled according to the status; A program for executing an information processing method.

8. An information processing system executed by an information processing device, 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 a process using a trained model that performs processing based on the policy information when the information and the policy information are input; In addition to carrying out the above, the policy information can be at least one of input and modification 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 data flows between the system components; a status can be set to any one of public, limited public, and private for each predetermined combination of the component image including the policy information input screen and the flow image, and the disclosure status of the predetermined combination to others is controlled according to the status; Information processing system.

Citation Information

Patent Citations

  • Database access right setting management system

    JP2014089674A

  • Information processing method, information processing device, and program

    JP7170157B1

  • Systems, methods, and devices for automation and integration of credentialing and authentication in workflows associated with computing platforms

    US20220335110A1

  • Information processing system, information processor, information processing method and program

    JP2016004437A