System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring information input from a user; means for analyzing the acquired information; means for automatically generating a business model diagram including characters and their relationships and a data flow and a risk checklist based on the analyzed information; and means for outputting the automatically generated business model diagram and risk checklist.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] When planning a service, system development proposal, or planning a seminar or exhibition, it's easy for oversights to occur when creating the framework. This is because it depends on the planner's skills and experience, and problems with the business model often become apparent after the service launch. Additionally, complex corporate sales flows are not uniformly represented for each project, leading to inadequate risk checks. By resolving these issues and conducting comprehensive risk checks before the service launch, it's necessary to improve the accuracy of plans and the speed of the approval process. [Means for solving the problem]

[0005] The present invention provides a system including a means for acquiring information input by a user, a means for analyzing the acquired information, a means for automatically generating a business model diagram including characters and their relationships and data flows based on the analyzed information, and a risk checklist, and a means for outputting the automatically generated business model diagram and risk checklist. This automatically generates a business model, data flows, and risk checklist, reducing oversights during the creation of a framework. Furthermore, by analyzing the acquired information using natural language processing technology, the system performs advanced analysis based on the user's input information and provides multi-modal output, thereby improving the efficiency and accuracy of proposals and plans.

[0006] A "user" is an entity that utilizes a system to input information and receive its output.

[0007] "Input information" refers to data such as text or voice data that a user provides to the system.

[0008] The "means of acquisition" refers to a module or interface that has the function of collecting information input by the user.

[0009] The "means for analysis" is a module that has the function of analyzing the acquired information and extracting entities, relationships, data flows, etc.

[0010] An "entity" is a basic element extracted as a result of analysis of characters, organizations, etc.

[0011] "Relationships" are information that indicates interactions and business relationships between entities.

[0012] "Data flow" is information that indicates how data flows between entities.

[0013] A "business model" is a diagram that visually represents entities, their relationships, and data flows.

[0014] A "risk checklist" is a list that lists the risk factors of a proposal or project.

[0015] The "means for automatic generation" is a module that has the function of generating a business model diagram and a risk checklist based on the analyzed information.

[0016] The "output means" is a module that has the function of providing the generated business model diagram and risk checklist to the user.

[0017] "Natural language processing technology" is a computer technology for analyzing text data and extracting meaning.

[0018] A "multi-modal output" is multiple output results with different formats or visual representations. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention is a system that allows users to easily organize and visualize information necessary for planning services, proposing system development, planning seminars and exhibitions, etc. This system acquires input information from the user, analyzes that information, and automatically generates a business model diagram and risk checklist that includes the characters, their relationships, and data flows, and provides them to the user.

[0041] Program processing and natural language explanation

[0042] 1. Getting User Input

[0043] Users provide information for service planning and system development proposals through a web-based chat interface or voice input interface. For example, a user might input, "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[0044] 2. Text Analysis

[0045] The server analyzes the input text data using natural language processing (NLP) tools and extracts entities (characters) from within the text. In this case, "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified as entities.

[0046] 3. Extracting Relationships

[0047] The server analyzes the relationships between the extracted entities, identifying relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[0048] 4. Data flow analysis

[0049] The server analyzes the data flow between entities, for example, identifying data flow from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0050] 5. Analysis of contract type

[0051] The server analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[0052] 6. Generate a Business Model

[0053] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[0054] 7. Generate a risk checklist

[0055] The server generates a risk checklist and a list of outstanding items to complement the business model.

[0056] 8. Return to User

[0057] The server provides the generated business model and risk checklist to the user, with the option to export it as a Google Slides file.

[0058] Specific examples

[0059] As a specific example, consider the case where information on a proposed supply chain management system is input.

[0060] scene:

[0061] A user enters, "Supplier A provides the raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[0062] Specific processing flow:

[0063] 1. Getting User Input

[0064] The user enters the above information through the chat interface.

[0065] 2. Text Analysis

[0066] The server analyzes the input information using natural language processing (NLP) technology and extracts entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0067] 3. Extracting Relationships

[0068] The server analyzes the relationships between entities and identifies relationships such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to distributor C," and "Distributor C sells to consumers."

[0069] 4. Data flow analysis

[0070] The server analyzes the data flow between entities and determines that data flows from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0071] 5. Analysis of contract type

[0072] The server identifies "a contract between Supplier A and Logistics Partner B," "a contract between Logistics Partner B and Distributor C," and "a contract between Distributor C and the Consumer."

[0073] 6. Generate a Business Model

[0074] The server generates a business model diagram based on these analysis results and outputs it in Google Slides format.

[0075] 7. Generate a risk checklist

[0076] The server generates a risk checklist and a list of outstanding items.

[0077] 8. Return to User

[0078] The server provides the generated business model diagram and risk checklist to the user, who can then use this information to efficiently plan services and propose system development.

[0079] This allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists, preventing oversights when creating frameworks and improving the accuracy and efficiency of service plans and system development proposals.

[0080] The processing flow will be explained below.

[0081] Step 1:

[0082] Users use a web-based chat interface or voice input interface to input information for service planning or system development proposals, including specific details such as "Supplier A will provide the raw materials, logistics partner B will handle the transportation, and sales agent C will sell the products to consumers."

[0083] Step 2:

[0084] The server acquires the information entered by the user, such as data entered through a chat interface or a voice input interface, and temporarily stores the data for further analysis.

[0085] Step 3:

[0086] The server analyzes the acquired text data using natural language processing (NLP) technology. This analysis extracts entities (characters) from the text. Specific entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified.

[0087] Step 4:

[0088] The server extracts relationships between the analyzed entities, such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to sales agent C," and "Sales agent C sells to consumers."

[0089] Step 5:

[0090] The server analyzes the data flow between entities. This analysis identifies which data flows from which entity to which entity. For example, data flows from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0091] Step 6:

[0092] The server analyzes the contract type between each entity, and identifies contract types such as "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[0093] Step 7:

[0094] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[0095] Step 8:

[0096] The server generates a risk checklist and a list of outstanding issues to complement the business model diagram, thereby clarifying the risks and outstanding issues that users should consider when planning or proposing a project.

[0097] Step 9:

[0098] The server then provides the generated business model and risk checklist to the user, who can then download this information as a Google Slides file for use in meetings or to prepare proposals.

[0099] As a concrete example, let's consider the case of inputting information for a proposed supply chain management system. A user would enter through a chat interface, "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells the products to consumers." The server retrieves this information and uses NLP technology to analyze entities, their relationships, and data flows. It then automatically generates a business model diagram and risk checklist, which are presented to the user in Google Slides format.

[0100] Example 1

[0101] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0102] In conventional service planning and system development proposals, the task of organizing and visualizing the necessary information requires a great deal of time and effort. Furthermore, insufficient information organization and visualization increases the likelihood of oversights and misunderstandings, making risk management difficult. Therefore, there is a need for a system that can automatically analyze the information provided by users, automatically generate business model diagrams and risk checklists, and visualize the information efficiently and accurately.

[0103] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0104] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information using natural language processing technology, and means for automatically generating a business model diagram including entities, their relationships, and data flows, and a risk checklist based on the analyzed information. This makes it possible to efficiently and accurately analyze information provided by a user and quickly create a visually represented business model diagram and risk checklist.

[0105] A "user" is an entity that utilizes the system to provide information and receive visualized business models and risk checklists.

[0106] The "server" is a computer system that analyzes information obtained from users and generates business model diagrams and risk checklists.

[0107] "Information" refers to text and data related to service plans and system development proposals entered by users.

[0108] "Natural language processing technology" is a set of algorithms and techniques used to analyze input information and extract entities and relationships.

[0109] "Entity" refers to a character, organization, object, concept, etc. that is a major element in a business model diagram.

[0110] A "relationship" represents the interaction or association between entities, and clarifies their roles and connections in a business process.

[0111] "Data flow" refers to the flow of data exchanged between entities, and indicates the path along which information travels.

[0112] A "business model diagram" is a visual representation of entities, their relationships, and data flows.

[0113] A "risk checklist" is a list of potential risks and unresolved issues that is generated to complement a business model diagram.

[0114] "Output means" refers to a method or tool for providing the generated business model diagram and risk checklist to the user.

[0115] This invention is a system that allows users to easily organize and visualize information necessary for planning services, proposing system development, planning seminars and exhibitions, etc. This system acquires input information from the user, analyzes that information, and automatically generates a business model diagram and risk checklist that includes the characters, their relationships, and data flows, and provides them to the user.

[0116] Specifically, the following hardware and software are used:

[0117] Hardware: Servers and terminals (PCs, smartphones)

[0118] Software: Natural Language Processing (NLP) libraries (SpaCy, NLTK), relation extraction models, visualization tools (matplotlib, Graphviz), Google Slides

[0119] Users can use their devices to provide information for service planning and system development proposals through a web-based chat interface or voice input interface. For example, they can enter text such as "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[0120] The server receives the input text data and performs natural language processing using SpaCy and NLTK. First, it tokenizes the text data and then performs entity recognition to extract entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0121] The server then uses the relationship extraction model to analyze the relationships between entities, such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[0122] The server then analyzes the data flow of the entities by referring to business rules and standard data flow diagram templates, identifying the data flow from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0123] The server also retrieves contract information from a pre-registered database and analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[0124] The server automatically generates a business model diagram based on these analysis results and outputs it in Google Slides format, which visually represents entities, their relationships, and data flows.

[0125] Additionally, the server generates risk checklists and backlogs, which are used to identify and manage risks in service planning and system development.

[0126] Finally, the server provides the generated business model and risk checklist to the user, including the option to provide them as downloadable files in Google Slides format, which the user can download and use via their device.

[0127] For example, if a user enters "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells products to consumers," the system will automatically analyze the entities, their relationships, and data flows, and based on that, generate a business model diagram and risk checklist, which it will provide to the user.

[0128] This allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists, preventing oversights when creating frameworks and improving the accuracy and efficiency of service plans and system development proposals.

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1:

[0131] A user uses a terminal to access a web-based chat interface or voice input interface and inputs the information required for service planning or system development proposals. The input information is sent to the server as text data. For example, a user might input, "Supplier A will provide the raw materials, and logistics partner B will be responsible for transportation." This text data becomes the input data for the next analysis step.

[0132] Step 2:

[0133] The server analyzes the received text data using a natural language processing tool (e.g., SpaCy or NLTK). First, the server tokenizes the text and then performs entity recognition. In this process, entity information such as "Supplier A," "Logistics Partner B," and "Sales Agent C" is extracted from the text data. The extracted entity information becomes the input data for the next relationship analysis step.

[0134] Step 3:

[0135] The server applies a relationship extraction model to analyze the relationships between the extracted entities. For example, it identifies relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers." The analyzed relationship information becomes input data for the next data flow analysis step.

[0136] Step 4:

[0137] The server analyzes the data flow between entities by referring to business rules and standard data flow diagram templates. For example, it identifies data flows such as "from supplier A to logistics partner B," "from logistics partner B to sales agent C," and "from sales agent C to consumers." The analyzed data flow information becomes input data for the next step, contract form analysis.

[0138] Step 5:

[0139] The server retrieves contract information from a pre-registered database and analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and the consumer." The analyzed contract type information becomes input data for the next business model diagram generation step.

[0140] Step 6:

[0141] The server automatically generates a business model diagram based on these analysis results. Specifically, it creates a diagram in Google Slides format that visually represents entities, relationships, data flows, and contract types. This generated business model diagram serves as input data for the next step, risk checklist generation.

[0142] Step 7:

[0143] The server generates a risk checklist and a list of unsorted items to complement the business model diagram. The generated risk checklist becomes input data for the next step of returning the item to the user.

[0144] Step 8:

[0145] The server provides the generated business model and risk checklist to the user, including the option to output them as Google Slides files with a download link. Users can download and use these materials via their devices.

[0146] (Application example 1)

[0147] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0148] In today's business environment, efficient organization and visualization of large amounts of information is required to quickly and accurately plan services and propose system development. However, manually organizing information and creating business model diagrams and risk checklists takes time and effort, so more efficient methods are needed. Furthermore, if users could perform these tasks using smartphones, business efficiency could be further improved.

[0149] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0150] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information, means for automatically generating a business model diagram including characters, their relationships, and data flows, and a risk checklist based on the analyzed information, means for generating prompt sentences to be input into the generative AI model, and means for providing the business model diagram and risk checklist to the user via a smartphone. This enables the user to use their smartphone to efficiently and quickly automatically generate the business model diagram and risk checklist required for service planning and system development proposals, preventing oversights.

[0151] "User input" refers to the information or data that a user provides to the system, from which the business model diagram and risk checklist are generated.

[0152] "Text analysis" is the process of extracting and analyzing entities such as characters and their relationships based on acquired text data using natural language processing technology.

[0153] "Actors" refers to the various actors within the business model, including suppliers, logistics partners, agents, and consumers.

[0154] "Relationships" refer to the mutual interests, contractual structures, data flows, etc. between the parties involved, and are one of the components of a business model diagram.

[0155] "Data flow" shows the flow of data between actors, and visually represents the movement of information in a supply chain.

[0156] A "business model diagram" is a diagram that visually represents the characters, their relationships, data flow, etc., and serves as the basis for service planning and system development proposals.

[0157] A "risk checklist" is a list of risks and matters to be considered that are identified based on the business model diagram, and is used to improve the accuracy and efficiency of proposals.

[0158] A "generative AI model" refers to an artificial intelligence model that generates business model diagrams and risk checklists based on user-entered information.

[0159] A "prompt sentence" is an input sentence that causes the generative AI model to extract and generate specific information, and is automatically generated by the system.

[0160] "Smartphone provision" refers to the means of providing the generated business model diagram and risk checklist to the user via a smartphone.

[0161] The present invention relates to a system that allows users to quickly and efficiently plan services and propose system development. This system acquires information entered by the user, analyzes it, automatically generates a business model diagram and a risk checklist, and provides them to the user via a smartphone.

[0162] The system is comprised of the following hardware and software:

[0163] 1. Hardware:

[0164] Smartphone (iOS / Android)

[0165] Cloud Server

[0166] 2. Software:

[0167] Google Cloud Natural Language API (Natural Language Processing)

[0168] Google BigQuery (data analysis)

[0169] Google Slides API (Business model generation)

[0170] Google Sheets API (risk checklist generation)

[0171] The specific processing flow of the system:

[0172] 1. Getting user input:

[0173] Users use the chat interface or voice input function of their smartphone to input the information needed to plan a service or propose a system development, for example, "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[0174] 2. Text Analysis:

[0175] The smartphone sends the acquired input information to a cloud server, which uses the Google Cloud Natural Language API to analyze the input information and extract the characters and their relationships. For example, it identifies entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0176] 3. Relationship and data flow analysis:

[0177] The server uses Google BigQuery to analyze the relationships and data flows between the extracted entities, identifying relationships such as "Supplier A supplies to Logistics Partner B, who transports to Distributor C."

[0178] 4. Analysis of contract type:

[0179] In parallel with the relationship analysis, the contractual arrangements between each entity are also identified, such as "a contract between supplier A and logistics partner B."

[0180] 5. Generate a Business Model:

[0181] Based on the analysis results, the server uses the Google Slides API to generate a business model diagram, which is a visual representation of entities, their relationships, and data flows.

[0182] 6. Generate a risk checklist:

[0183] Additionally, the server uses Google Sheets API to generate a risk checklist and a list of outstanding items based on the business model.

[0184] 7. Return to User:

[0185] The generated business model diagram and risk checklist are provided to users via their smartphones, allowing them to instantly check the business model diagram and risk checklist on their smartphones, improving the accuracy and efficiency of service planning and system development proposals.

[0186] Use the following prompt as an example:

[0187] "Supplier A provides raw materials and logistics partner B handles transportation. Analyze this information and generate a business model diagram with actors, their relationships, and data flows, along with a risk checklist."

[0188] Based on such prompts, the generative AI model can automatically generate a business model diagram and a risk checklist, significantly improving the user's work efficiency.

[0189] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0190] Step 1:

[0191] Users use their smartphones to input the information necessary for service planning and system development proposals through a chat interface or voice input function. This information becomes the initial data for the system. For example, they might input, "The supplier will provide the raw materials, and the shipping company will be responsible for transportation." The input data is captured on the smartphone and sent to the cloud server.

[0192] Step 2:

[0193] The server analyzes the acquired user input using the Google Cloud Natural Language API. If the input data is in text format, the API performs syntactic analysis of the text and extracts entities (characters) in the sentence. Specifically, entities such as "supplier," "transport company," "sales agent," and "consumer" are identified. The data input is text data, and the output is a list of entities.

[0194] Step 3:

[0195] The server uses Google BigQuery to analyze the relationships and data flows between the extracted entities. For example, it clarifies relationships such as "Suppliers supply raw materials to transport companies, and transport companies send goods to sales agents." The input required for analysis is a list of entities, and the output is structured data that shows the relationships and data flows.

[0196] Step 4:

[0197] The server also simultaneously analyzes the contract type. After identifying the relationships between entities, it identifies the contract type between each entity, identifying, for example, a "contract between a supplier and a shipping company." The input required for this analysis is relationship data, and the output is structured data including the contract type.

[0198] Step 5:

[0199] Based on the analysis results, the server generates a business model using the Google Slides API. A business model visually represents entities, their relationships, and data flows. The input is the analyzed data, and the output is a business model in Google Slides format.

[0200] Step 6:

[0201] The server uses the Google Sheets API to generate a risk checklist and a list of outstanding items based on the business model. The risk checklist lists potential risks and items to be considered in the service plan. The input is the business model data, and the output is a checklist in Google Sheets format.

[0202] Step 7:

[0203] The server provides the generated business model diagram and risk checklist to the user via smartphone. The user can check and download this data on their smartphone. Ultimately, the user can use the generated materials to create service plans and system development proposals.

[0204] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0205] This invention relates to a system that acquires input information from users, analyzes it, and automatically generates a business model diagram including the characters, their relationships, and data flows, and also provides a risk checklist. Furthermore, by integrating an emotion engine that recognizes the user's emotions, it has the function of optimizing output based on the user's emotions.

[0206] Program processing and natural language explanation

[0207] 1. Getting User Input

[0208] Users use a web-based chat interface or voice input interface to input information for service planning and system development proposals. For example, a user might input, "Supplier A will provide the raw materials, logistics partner B will handle the transportation, and sales agent C will sell the products to consumers."

[0209] 2. Text Analysis

[0210] The server analyzes the input text data using natural language processing (NLP) tools and extracts entities (characters) from the text, such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0211] 3. Extracting Relationships

[0212] The server analyzes the relationships between the extracted entities, for example, identifying relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[0213] 4. Data flow analysis

[0214] The server analyzes the data flow between entities, for example, identifying data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Distributor C," and "Distributor C to Consumer."

[0215] 5. Analysis of contract type

[0216] The server analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[0217] 6. Generate a Business Model

[0218] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[0219] 7. Generate a risk checklist

[0220] The server generates a risk checklist and a list of outstanding items to complement the business model.

[0221] 8. User Emotion Recognition

[0222] The server analyzes the user's input information using an emotion engine to recognize the user's emotional state, which can include positive, negative, or neutral emotions.

[0223] 9. Optimize your output

[0224] The server optimizes the content and structure of the generated business model diagram and risk checklist based on the user's emotional state recognized by the emotion engine. For example, if the user's emotion is positive, the provided output will include more encouraging information, while if the user's emotion is negative, the server will emphasize information that supports problem solving.

[0225] 10. Return to User

[0226] The server provides users with optimized business models and risk checklists, which can then be downloaded as Google Slides files for use in meetings and proposals.

[0227] Specific examples

[0228] As a specific example, consider the case where a user inputs information for a proposed supply chain management system.

[0229] scene:

[0230] A user enters, "Supplier A provides the raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[0231] Specific processing flow:

[0232] 1. Getting User Input

[0233] The user enters the above information through the chat interface.

[0234] 2. Text Analysis

[0235] The server analyzes the input information using natural language processing (NLP) technology and extracts entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0236] 3. Extracting Relationships

[0237] The server analyzes the relationships between entities and identifies relationships such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to sales agent C," and "Sales agent C sells to consumers."

[0238] 4. Data flow analysis

[0239] The server analyzes the data flow between entities and identifies data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0240] 5. Analysis of contract type

[0241] The server identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and distributor C," and "a contract between distributor C and the consumer."

[0242] 6. Generate a Business Model

[0243] The server generates a business model diagram based on these analysis results and outputs it in Google Slides format.

[0244] 7. Generate a risk checklist

[0245] The server generates a risk checklist and a list of outstanding items.

[0246] 8. User Emotion Recognition

[0247] The server uses an emotion engine to analyze the user's emotions and adjusts the output based on that information, for example, if the user is in a positive state.

[0248] 9. Optimize your output

[0249] The server optimizes the contents of the created business model diagram and risk checklist based on the user's feelings.

[0250] 10. Return to User

[0251] The server provides the user with an optimized business model diagram and a risk checklist, and the user can make effective proposals and plans based on these.

[0252] This system allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists. Furthermore, by combining it with an emotion engine, the output is optimized to the user's current emotions, improving the accuracy and efficiency of proposals and plans.

[0253] The processing flow will be explained below.

[0254] Step 1:

[0255] Users use a web-based chat interface or voice input interface to input information for service planning and system development proposals, such as "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[0256] Step 2:

[0257] The server acquires the information entered by the user, such as data entered through a chat interface or a voice input interface, and temporarily stores the data for further analysis.

[0258] Step 3:

[0259] The server analyzes the acquired text data using natural language processing (NLP) technology. This analysis extracts entities (characters) from the text. For example, "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified as entities.

[0260] Step 4:

[0261] The server analyzes the relationships between the extracted entities, for example, identifying relationships such as "Supplier A supplies raw materials to Logistics Partner B," "Logistics Partner B transports goods to Sales Agent C," and "Sales Agent C sells goods to consumers."

[0262] Step 5:

[0263] The server analyzes data flows between entities. This analysis identifies which data flows from which entity to which entity. For example, data flows such as "raw material data moves from supplier A to logistics partner B," "product data moves from logistics partner B to sales agent C," and "sales data moves from sales agent C to consumers."

[0264] Step 6:

[0265] The server analyzes the contractual arrangements between each entity, for example, identifying a "supply contract between supplier A and logistics partner B," a "transportation contract between logistics partner B and distributor C," and a "sales contract between distributor C and a consumer."

[0266] Step 7:

[0267] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[0268] Step 8:

[0269] The server generates a risk checklist and a list of outstanding issues to complement the business model diagram, thereby clarifying the risks and outstanding issues that users should consider when planning or proposing.

[0270] Step 9:

[0271] The server analyzes the user's input information using an emotion engine to recognize the user's emotional state, which may include positive, negative, or neutral emotions.

[0272] Step 10:

[0273] The server optimizes the content and structure of the generated business model diagram and risk checklist based on the user's emotional state recognized by the emotion engine. For example, if the user's emotion is positive, the provided output will include more encouraging information, while if the user's emotion is negative, the server will emphasize information that supports problem solving.

[0274] Step 11:

[0275] The server provides users with optimized business models and risk checklists, which can then be downloaded as Google Slides files for use in meetings and proposals.

[0276] As a concrete example, when a user inputs information for a proposed supply chain management system, he / she inputs "Supplier A provides raw materials, logistics partner B is responsible for transportation, and sales agent C sells the products to consumers" in step 1. The server processes steps 2 to 10 and finally provides an optimized business model diagram and risk checklist.

[0277] Example 2

[0278] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0279] In conventional systems, it takes a great deal of time and effort for users to create business model diagrams and generate risk checklists. Furthermore, because optimization is not performed taking into account the user's emotional state, it is difficult to obtain output that meets the user's needs. A new technology was needed to solve these issues.

[0280] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0281] In this invention, the server includes: means for acquiring information input by a user; means for analyzing the acquired information using natural language processing technology; means for automatically generating a business model diagram including entities, their relationships, and data flows based on the analyzed information; means for generating a risk checklist that complements the business model diagram; means for recognizing the emotional state of the user from the acquired information; means for optimizing the contents of the business model diagram and the risk checklist based on the recognized emotional state; and means for outputting the automatically generated business model diagram and risk checklist. This enables a user to simply input information, and the server to automatically generate a business model diagram and a risk checklist, and further enables an optimized output to be obtained based on the user's emotional state.

[0282] "User" means an individual or organization that utilizes the system to enter and verify information.

[0283] A "server" is a computing device that receives input information from a user, analyzes it, and generates and outputs various data.

[0284] "Natural language processing technology" is a technology that enables the analysis, understanding, and generation of human language.

[0285] An "entity" is an individual element or subject that appears in a business model.

[0286] A "relationship" indicates the interaction and division of roles between entities.

[0287] "Data flow" refers to how data or information flows between entities.

[0288] A "business model" is a visual representation of entities, their relationships, and data flows.

[0289] A "risk checklist" is a list of potential risks and unresolved issues in a business model.

[0290] "Emotional state" refers to the emotional state or tendency that can be read from the user's input information.

[0291] "Output optimization" refers to adjusting the content and structure of the information being output based on the user's emotional state.

[0292] This invention relates to a system that acquires input information from users, analyzes it, and automatically generates a business model diagram including the characters, their relationships, and data flows, and also provides a risk checklist. Furthermore, by integrating an emotion engine that recognizes the user's emotions, it has the function of optimizing output based on the user's emotions.

[0293] 1. Getting User Input

[0294] Users use their devices to input information into a web-based chat interface or voice input interface, built with HTML, CSS, and JavaScript, using the SpeechRecognition API for voice input. For example, they might input, "Supplier A provides the raw materials, logistics partner B handles the transportation, and sales agent C sells the products to consumers."

[0295] 2. Text Data Analysis

[0296] The server receives input data from users and analyzes the text using NLP (Natural Language Processing) tools. Libraries such as SpaCy and NLTK are used for this analysis. The server is built in Python and uses web frameworks such as Flask for processing.

[0297] 3. Entity Extraction

[0298] The server uses natural language processing technology to extract entities (e.g., suppliers, logistics partners, sales agents, consumers, etc.) from the input text. The entity extraction is performed using SpaCy's Named Entity Recognition (NER) function.

[0299] 4. Relationship Analysis

[0300] The server analyzes the relationships between the extracted entities using predefined business rules and logic, such as "Supplier supplies to logistics partner," "Logistics partner transports to distributor," and "Distributor sells to consumer."

[0301] 5. Data Flow Analysis

[0302] The server analyzes the data flow between entities, identifying data flows such as "Supplier to Logistics Partner," "Logistics Partner to Distributor," and "Distributor to Consumer."

[0303] 6. Identification of contract type

[0304] The server analyzes the contract types between entities using predefined contract templates and rules to identify contracts such as a "supply contract between a supplier and a logistics partner," a "transportation contract between a logistics partner and a distributor," or a "sales contract between a distributor and a consumer."

[0305] 7. Generate a Business Model

[0306] The server automatically generates a business model diagram based on the analysis results, using Graphviz or Google Slides API, which visually represents entities, their relationships, and data flows.

[0307] 8. Generate a risk checklist

[0308] The server generates a risk checklist and a list of outstanding items to complement the business model. The items in the risk checklist are predefined and cover the risks associated with the business model.

[0309] 9. Recognition of user emotions using an emotion engine

[0310] The server uses an emotion engine to recognize the emotional state of the user input, using a Sentiment Analysis library (e.g., VADER, TextBlob) to identify positive, negative, neutral, and other emotional states.

[0311] 10. Output optimization

[0312] The server optimizes the content and structure of the output based on the user's emotional state as recognized by the emotion engine: in a positive emotional state, encouraging messages and success stories are emphasized, while in a negative emotional state, information that helps solve problems is emphasized.

[0313] 11. Return to User

[0314] The server provides users with optimized business models and risk checklists, which can be downloaded as Google Slides files for use in meetings and proposals.

[0315] Prompt Sentence Examples

[0316] Generate a business model diagram and risk checklist for the following scenario: "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[0317] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0318] Step 1:

[0319] A user uses their device to input information into a web-based chat interface or voice input interface, for example, "Supplier A provides the raw materials, logistics partner B handles the transportation, and sales agent C sells the goods to the consumer." This input is sent to the server as text data.

[0320] Input: Text information entered by the user

[0321] Output: Text data sent to the server

[0322] Step 2:

[0323] The server analyzes the received text data using natural language processing (NLP) tools such as SpaCy and NLTK. The server understands the context and meaning of the text data and performs syntactic analysis.

[0324] Input: Text data sent by the user

[0325] Output: Parsed text data (including tokenization and parsing results)

[0326] What happens: The server parses the sentence structure using SpaCy's .parser() method.

[0327] Step 3:

[0328] The server extracts entities from the parsed text data using SpaCy's Named Entity Recognition (NER) function, for example, to identify "Supplier A," "Logistics Partner B," "Distributor C," and "Consumer."

[0329] Input: Parsed text data

[0330] Output: A list of extracted entities

[0331] What happens: The server uses SpaCy's .ner() method to extract the specific entity.

[0332] Step 4:

[0333] The server analyzes the relationships between the extracted entities using predefined business rules and logic. For example, it identifies relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Distributor C," and "Distributor C sells to consumers."

[0334] Input: A list of extracted entities

[0335] Output: Relationship identification results

[0336] What it does: The server uses a Python rule-based algorithm to identify relationships between entities.

[0337] Step 5:

[0338] The server analyzes the data flow between entities, identifying data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Distributor C," and "Distributor C to Consumer."

[0339] Input: Entities and their relationships

[0340] Output: Data flow identification results

[0341] Specific operation: The server executes a data flow analysis algorithm to identify the flow of data between entities.

[0342] Step 6:

[0343] The server analyzes the contract types between each entity using predefined contract templates and rules to identify "supply contract between supplier A and logistics partner B," "transportation contract between logistics partner B and distributor C," and "sales contract between distributor C and consumer."

[0344] Input: Entities and their relationships, data flow

[0345] Output: Contract type identification result

[0346] Specific operation: The server identifies the contract type based on the contract template.

[0347] Step 7:

[0348] The server automatically generates a business model based on the analysis results, using Graphviz and Google Slides APIs. The generated business model visually represents entities, their relationships, and data flows.

[0349] Input: Identification of entities, relationships, data flows, and contract types

[0350] Output: Auto-generated business model diagram (Google Slides format)

[0351] Specific operation: The server generates a business model using Graphviz or Google Slides API.

[0352] Step 8:

[0353] The server generates a risk checklist that complements the business model diagram, utilizing predefined risk items and checklists.

[0354] Input: Business Model

[0355] Output: Risk checklist and list of outstanding items

[0356] Specific operation: The server generates a risk checklist based on predefined risk items.

[0357] Step 9:

[0358] The server uses an emotion engine to recognize the emotional state of the user input, using a Sentiment Analysis library (e.g., VADER, TextBlob) to identify positive, negative, neutral, and other emotional states.

[0359] Input: User input information

[0360] Output: User's emotional state (positive, negative, neutral)

[0361] Specific behavior: The server uses the Sentiment Analysis library to identify the emotional state.

[0362] Step 10:

[0363] The server optimizes the content and structure of the output based on the user's emotional state as recognized by the emotion engine. In a positive emotional state, encouraging messages and success stories are emphasized, while in a negative emotional state, information that helps solve problems is emphasized.

[0364] Input: User's emotional state, business model, risk checklist

[0365] Output: Optimized business model, risk checklist

[0366] What it does: The server runs an algorithm to adjust output content based on emotional state.

[0367] Step 11:

[0368] The server provides users with optimized business models and risk checklists, and the generated output can be downloaded as a Google Slides file for use in meetings or to prepare proposals.

[0369] Inputs: Optimized business model, risk checklist

[0370] Output: Downloadable Google Slides file

[0371] Specific operation: The server provides the generated file to the user's device and sends a download link.

[0372] (Application example 2)

[0373] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0374] In the operation management of autonomous vehicles, there is a problem that it is difficult to grasp the vehicle operation plan and data flow effectively and quickly and to carry out appropriate risk management.In addition, it is difficult to provide optimal information according to the emotions and situation of the operation manager, which reduces the accuracy of decision-making, and it is necessary to solve this problem.

[0375] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0376] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information, means for automatically generating a business process model diagram including characters, their relationships, and data flows, and a risk checklist based on the analyzed information, means for outputting the automatically generated business process model diagram and risk checklist, means for extracting entities from the acquired information and analyzing relationships and data flows, means for generating a traffic control diagram and risk checklist and optimizing output through emotion recognition, and means for recognizing user emotions and providing optimized output. This enables operations managers to easily understand operation plans and risks and provide optimal information according to their emotional state at the time.

[0377] A "user" is a person who operates the system and provides input information.

[0378] "Information" refers to the content of reports and instructions processed by the system, such as data and instructions entered by a user.

[0379] "Analysis" refers to the processing and analysis of acquired information to identify relevant entities, relationships, and data flows.

[0380] An "entity" refers to an element with a specific role, such as a character or object identified within the system.

[0381] A "relationship" represents an interaction or connectivity between entities.

[0382] "Data flow" refers to the flow of data or information between entities.

[0383] A "business model diagram" is a diagram that visually represents entities, their relationships, and data flows.

[0384] A "risk checklist" is a list of risks and precautions related to the business model diagram.

[0385] "Emotion recognition" is the process of identifying a user's emotional state from input information, facial expressions, voice, etc.

[0386] "Optimization" refers to adjusting the content and format of output based on analyzed information and perceived emotional state.

[0387] A specific system for implementing this invention is intended for operation management of autonomous vehicles, and is realized as an application installed on a smartphone.

[0388] System Overview

[0389] Hardware and software used

[0390] Natural Language Processing (NLP): Uses the Google Cloud Natural Language API.

[0391] Emotion recognition engine: Uses Microsoft Azure Emotion API.

[0392] Data visualization: Using D3.js.

[0393] Frontend: Uses React Native.

[0394] Backend: Uses Node.js, Express.js, and MongoDB.

[0395] Explanation of program processing

[0396] 1. Getting User Input

[0397] Users can input operation plans via chat or voice input through a smartphone application.

[0398] For voice input, it converts it to a string using the Google Cloud Speech-to-Text API.

[0399] 2. Text Data Analysis

[0400] The server analyzes the input text data using the Google Cloud Natural Language API and extracts entities.

[0401] 3. Relationship and data flow analysis

[0402] The server analyzes the relationships between the extracted entities and identifies the data flow.

[0403] 4. Analysis of contract type

[0404] The server analyzes the contract between the entities and identifies the required information.

[0405] 5. Generation of Operation Control Chart

[0406] The server uses D3.js to generate a visual traffic control diagram.

[0407] 6. Generate a risk checklist

[0408] The server stores the risk factors in MongoDB and generates a risk checklist.

[0409] 7. Emotion recognition

[0410] The server analyzes the user's emotions using the Microsoft Azure Emotion API.

[0411] 8. Optimizing Output

[0412] The server adjusts the content and display method of the operation control chart and risk checklist based on the user's emotions.

[0413] 9. Return to User

[0414] The server returns the optimized operation control chart and risk checklist to the user using React Native.

[0415] Specific examples

[0416] Example of user input

[0417] A dispatcher opens a smartphone app and types, "Vehicle A will depart at 8:00 AM, deliver a package to distribution center B, and then head to distribution center C."

[0418] 1. Text Analysis

[0419] The servers "Vehicle A," "Distribution Center B," and "Distribution Center C" are extracted.

[0420] 2. Relationship and data flow analysis

[0421] The relationships between the extracted entities are analyzed as "Vehicle A delivers cargo to distribution center B" and "Vehicle A heads to distribution center C."

[0422] 3. Analysis of contract type

[0423] The server identifies the "delivery contract between vehicle A and distribution center B."

[0424] 4. Generate operation control charts and risk checklists

[0425] The server uses D3.js to generate operational management diagrams and creates risk checklists based on risk factors stored in MongoDB.

[0426] 5. Emotion recognition and output optimization

[0427] The server analyzes the emotional state, such as "positive" or "negative," and highlights information such as "What to do if distribution center B is congested" in the checklist.

[0428] Prompt Sentence Examples

[0429] 1. "Please enter your flight schedule."

[0430] 2. "Vehicle A departs at 8:00 AM, delivers a package to distribution center B, and then heads to distribution center C."

[0431] 3. "I want to know what to do if Distribution Center B is busy."

[0432] In this way, operation managers can easily understand operation plans and risks, and provide optimal information according to the emotional state of the driver at the time.

[0433] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0434] Step 1:

[0435] Getting User Input

[0436] Users launch the smartphone application and enter their trip plan using a chat interface or voice input. In the latter case, the device converts the speech into text using the Google Cloud Speech-to-Text API, resulting in a text version of the trip plan.

[0437] Step 2:

[0438] Text data analysis

[0439] The server receives the acquired text data and analyzes it using the Google Cloud Natural Language API. During the analysis process, entities (vehicle, distribution center, time, etc.) are extracted from the text. The input is the text data from the user, and the output is a list of extracted entities.

[0440] Step 3:

[0441] Relationship and data flow analysis

[0442] The server analyzes the relationships between the extracted entities and identifies the interactions and data flows between them. The analysis yields relationships such as "Vehicle A delivers packages to distribution center B." The input is a list of entities, and the output is information indicating the relationships and data flows.

[0443] Step 4:

[0444] Contract type analysis

[0445] The server identifies the contract type between each entity based on the relationship and entity information. A contract type such as "Delivery contract between vehicle A and distribution center B" can be obtained. The input is relationship and entity information, and the output is contract type information.

[0446] Step 5:

[0447] Generate operation control charts

[0448] The server uses D3.js to generate a visual control diagram, which visually represents entities, their relationships, and data flows. The inputs are entity, relationship, and data flow information, and the output is the control diagram.

[0449] Step 6:

[0450] Generate a risk checklist

[0451] The server retrieves risk factors related to the operation plan from MongoDB and generates a risk checklist. The risk factors are linked based on the operation control diagram. The input is the operation control diagram and the output is the risk checklist.

[0452] Step 7:

[0453] emotion recognition

[0454] The server uses the Microsoft Azure Emotion API to analyze the user's emotional state based on their input, facial expression, and voice. The analysis results in the user's emotional state (positive, negative, or neutral). The input is the user's facial expression and voice data, and the output is information about their emotional state.

[0455] Step 8:

[0456] Output optimization

[0457] The server adjusts the content and display method of the operation control chart and risk checklist based on the analyzed user's emotional state. For example, if the emotion is negative, it highlights cautions and risk avoidance measures. The inputs are the emotional state, operation control chart, and risk checklist, and the output is optimized output.

[0458] Step 9:

[0459] Return to user

[0460] The server generates an optimized operation control chart and risk checklist and returns them to the user's smartphone using React Native. The input is the optimized operation control chart and risk checklist, and the output is the information displayed on the user's smartphone.

[0461] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0462] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0463] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0464] [Second embodiment]

[0465] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0466] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0467] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0468] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0469] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0470] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0471] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0472] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0473] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0474] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0475] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0476] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0477] This invention is a system that allows users to easily organize and visualize information necessary for planning services, proposing system development, planning seminars and exhibitions, etc. This system acquires input information from the user, analyzes that information, and automatically generates a business model diagram and risk checklist that includes the characters, their relationships, and data flows, and provides them to the user.

[0478] Program processing and natural language explanation

[0479] 1. Getting User Input

[0480] Users provide information for service planning and system development proposals through a web-based chat interface or voice input interface. For example, a user might input, "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[0481] 2. Text Analysis

[0482] The server analyzes the input text data using natural language processing (NLP) tools and extracts entities (characters) from within the text. In this case, "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified as entities.

[0483] 3. Extracting Relationships

[0484] The server analyzes the relationships between the extracted entities, identifying relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[0485] 4. Data flow analysis

[0486] The server analyzes the data flow between entities, for example, identifying data flow from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0487] 5. Analysis of contract type

[0488] The server analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[0489] 6. Generate a Business Model

[0490] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[0491] 7. Generate a risk checklist

[0492] The server generates a risk checklist and a list of outstanding items to complement the business model.

[0493] 8. Return to User

[0494] The server provides the generated business model and risk checklist to the user, with the option to export it as a Google Slides file.

[0495] Specific examples

[0496] As a specific example, consider the case where information on a proposed supply chain management system is input.

[0497] scene:

[0498] A user enters, "Supplier A provides the raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[0499] Specific processing flow:

[0500] 1. Getting User Input

[0501] The user enters the above information through the chat interface.

[0502] 2. Text Analysis

[0503] The server analyzes the input information using natural language processing (NLP) technology and extracts entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0504] 3. Extracting Relationships

[0505] The server analyzes the relationships between entities and identifies relationships such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to distributor C," and "Distributor C sells to consumers."

[0506] 4. Data flow analysis

[0507] The server analyzes the data flow between entities and determines that data flows from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0508] 5. Analysis of contract type

[0509] The server identifies "a contract between Supplier A and Logistics Partner B," "a contract between Logistics Partner B and Distributor C," and "a contract between Distributor C and the Consumer."

[0510] 6. Generate a Business Model

[0511] The server generates a business model diagram based on these analysis results and outputs it in Google Slides format.

[0512] 7. Generate a risk checklist

[0513] The server generates a risk checklist and a list of outstanding items.

[0514] 8. Return to User

[0515] The server provides the generated business model diagram and risk checklist to the user, who can then use this information to efficiently plan services and propose system development.

[0516] This allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists, preventing oversights when creating frameworks and improving the accuracy and efficiency of service plans and system development proposals.

[0517] The processing flow will be explained below.

[0518] Step 1:

[0519] Users use a web-based chat interface or voice input interface to input information for service planning or system development proposals, including specific details such as "Supplier A will provide the raw materials, logistics partner B will handle the transportation, and sales agent C will sell the products to consumers."

[0520] Step 2:

[0521] The server acquires the information entered by the user, such as data entered through a chat interface or a voice input interface, and temporarily stores the data for further analysis.

[0522] Step 3:

[0523] The server analyzes the acquired text data using natural language processing (NLP) technology. This analysis extracts entities (characters) from the text. Specific entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified.

[0524] Step 4:

[0525] The server extracts relationships between the analyzed entities, such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to sales agent C," and "Sales agent C sells to consumers."

[0526] Step 5:

[0527] The server analyzes the data flow between entities. This analysis identifies which data flows from which entity to which entity. For example, data flows from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0528] Step 6:

[0529] The server analyzes the contract type between each entity, and identifies contract types such as "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[0530] Step 7:

[0531] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[0532] Step 8:

[0533] The server generates a risk checklist and a list of outstanding issues to complement the business model diagram, thereby clarifying the risks and outstanding issues that users should consider when planning or proposing a project.

[0534] Step 9:

[0535] The server then provides the generated business model and risk checklist to the user, who can then download this information as a Google Slides file for use in meetings or to prepare proposals.

[0536] As a concrete example, let's consider the case of inputting information for a proposed supply chain management system. A user would enter through a chat interface, "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells the products to consumers." The server retrieves this information and uses NLP technology to analyze entities, their relationships, and data flows. It then automatically generates a business model diagram and risk checklist, which are presented to the user in Google Slides format.

[0537] Example 1

[0538] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0539] In conventional service planning and system development proposals, the task of organizing and visualizing the necessary information requires a great deal of time and effort. Furthermore, insufficient information organization and visualization increases the likelihood of oversights and misunderstandings, making risk management difficult. Therefore, there is a need for a system that can automatically analyze the information provided by users, automatically generate business model diagrams and risk checklists, and visualize the information efficiently and accurately.

[0540] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0541] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information using natural language processing technology, and means for automatically generating a business model diagram including entities, their relationships, and data flows, and a risk checklist based on the analyzed information. This makes it possible to efficiently and accurately analyze information provided by a user and quickly create a visually represented business model diagram and risk checklist.

[0542] A "user" is an entity that utilizes the system to provide information and receive visualized business models and risk checklists.

[0543] The "server" is a computer system that analyzes information obtained from users and generates business model diagrams and risk checklists.

[0544] "Information" refers to text and data related to service plans and system development proposals entered by users.

[0545] "Natural language processing technology" is a set of algorithms and techniques used to analyze input information and extract entities and relationships.

[0546] "Entity" refers to a character, organization, object, concept, etc. that is a major element in a business model diagram.

[0547] A "relationship" represents the interaction or association between entities, and clarifies their roles and connections in a business process.

[0548] "Data flow" refers to the flow of data exchanged between entities, and indicates the path along which information travels.

[0549] A "business model diagram" is a visual representation of entities, their relationships, and data flows.

[0550] A "risk checklist" is a list of potential risks and unresolved issues that is generated to complement a business model diagram.

[0551] "Output means" refers to a method or tool for providing the generated business model diagram and risk checklist to the user.

[0552] This invention is a system that allows users to easily organize and visualize information necessary for planning services, proposing system development, planning seminars and exhibitions, etc. This system acquires input information from the user, analyzes that information, and automatically generates a business model diagram and risk checklist that includes the characters, their relationships, and data flows, and provides them to the user.

[0553] Specifically, the following hardware and software are used:

[0554] Hardware: Servers and terminals (PCs, smartphones)

[0555] Software: Natural Language Processing (NLP) libraries (SpaCy, NLTK), relation extraction models, visualization tools (matplotlib, Graphviz), Google Slides

[0556] Users can use their devices to provide information for service planning and system development proposals through a web-based chat interface or voice input interface. For example, they can enter text such as "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[0557] The server receives the input text data and performs natural language processing using SpaCy and NLTK. First, it tokenizes the text data and then performs entity recognition to extract entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0558] The server then uses the relationship extraction model to analyze the relationships between entities, such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[0559] The server then analyzes the data flow of the entities by referring to business rules and standard data flow diagram templates, identifying the data flow from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0560] The server also retrieves contract information from a pre-registered database and analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[0561] The server automatically generates a business model diagram based on these analysis results and outputs it in Google Slides format, which visually represents entities, their relationships, and data flows.

[0562] Additionally, the server generates risk checklists and backlogs, which are used to identify and manage risks in service planning and system development.

[0563] Finally, the server provides the generated business model and risk checklist to the user, including the option to provide them as downloadable files in Google Slides format, which the user can download and use via their device.

[0564] For example, if a user enters "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells products to consumers," the system will automatically analyze the entities, their relationships, and data flows, and based on that, generate a business model diagram and risk checklist, which it will provide to the user.

[0565] This allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists, preventing oversights when creating frameworks and improving the accuracy and efficiency of service plans and system development proposals.

[0566] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0567] Step 1:

[0568] A user uses a terminal to access a web-based chat interface or voice input interface and inputs the information required for service planning or system development proposals. The input information is sent to the server as text data. For example, a user might input, "Supplier A will provide the raw materials, and logistics partner B will be responsible for transportation." This text data becomes the input data for the next analysis step.

[0569] Step 2:

[0570] The server analyzes the received text data using a natural language processing tool (e.g., SpaCy or NLTK). First, the server tokenizes the text and then performs entity recognition. In this process, entity information such as "Supplier A," "Logistics Partner B," and "Sales Agent C" is extracted from the text data. The extracted entity information becomes the input data for the next relationship analysis step.

[0571] Step 3:

[0572] The server applies a relationship extraction model to analyze the relationships between the extracted entities. For example, it identifies relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers." The analyzed relationship information becomes input data for the next data flow analysis step.

[0573] Step 4:

[0574] The server analyzes the data flow between entities by referring to business rules and standard data flow diagram templates. For example, it identifies data flows such as "from supplier A to logistics partner B," "from logistics partner B to sales agent C," and "from sales agent C to consumers." The analyzed data flow information becomes input data for the next step, contract form analysis.

[0575] Step 5:

[0576] The server retrieves contract information from a pre-registered database and analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and the consumer." The analyzed contract type information becomes input data for the next business model diagram generation step.

[0577] Step 6:

[0578] The server automatically generates a business model diagram based on these analysis results. Specifically, it creates a diagram in Google Slides format that visually represents entities, relationships, data flows, and contract types. This generated business model diagram serves as input data for the next step, risk checklist generation.

[0579] Step 7:

[0580] The server generates a risk checklist and a list of unsorted items to complement the business model diagram. The generated risk checklist becomes input data for the next step of returning the item to the user.

[0581] Step 8:

[0582] The server provides the generated business model and risk checklist to the user, including the option to output them as Google Slides files with a download link. Users can download and use these materials via their devices.

[0583] (Application example 1)

[0584] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0585] In today's business environment, efficient organization and visualization of large amounts of information is required to quickly and accurately plan services and propose system development. However, manually organizing information and creating business model diagrams and risk checklists takes time and effort, so more efficient methods are needed. Furthermore, if users could perform these tasks using smartphones, business efficiency could be further improved.

[0586] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0587] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information, means for automatically generating a business model diagram including characters, their relationships, and data flows, and a risk checklist based on the analyzed information, means for generating prompt sentences to be input into the generative AI model, and means for providing the business model diagram and risk checklist to the user via a smartphone. This enables the user to use their smartphone to efficiently and quickly automatically generate the business model diagram and risk checklist required for service planning and system development proposals, preventing oversights.

[0588] "User input" refers to the information or data that a user provides to the system, from which the business model diagram and risk checklist are generated.

[0589] "Text analysis" is the process of extracting and analyzing entities such as characters and their relationships based on acquired text data using natural language processing technology.

[0590] "Actors" refers to the various actors within the business model, including suppliers, logistics partners, agents, and consumers.

[0591] "Relationships" refer to the mutual interests, contractual structures, data flows, etc. between the parties involved, and are one of the components of a business model diagram.

[0592] "Data flow" shows the flow of data between actors, and visually represents the movement of information in a supply chain.

[0593] A "business model diagram" is a diagram that visually represents the characters, their relationships, data flow, etc., and serves as the basis for service planning and system development proposals.

[0594] A "risk checklist" is a list of risks and matters to be considered that are identified based on the business model diagram, and is used to improve the accuracy and efficiency of proposals.

[0595] A "generative AI model" refers to an artificial intelligence model that generates business model diagrams and risk checklists based on user-entered information.

[0596] A "prompt sentence" is an input sentence that causes the generative AI model to extract and generate specific information, and is automatically generated by the system.

[0597] "Smartphone provision" refers to the means of providing the generated business model diagram and risk checklist to the user via a smartphone.

[0598] The present invention relates to a system that allows users to quickly and efficiently plan services and propose system development. This system acquires information entered by the user, analyzes it, automatically generates a business model diagram and a risk checklist, and provides them to the user via a smartphone.

[0599] The system is comprised of the following hardware and software:

[0600] 1. Hardware:

[0601] Smartphone (iOS / Android)

[0602] Cloud Server

[0603] 2. Software:

[0604] Google Cloud Natural Language API (Natural Language Processing)

[0605] Google BigQuery (data analysis)

[0606] Google Slides API (Business model generation)

[0607] Google Sheets API (risk checklist generation)

[0608] The specific processing flow of the system:

[0609] 1. Getting user input:

[0610] Users use the chat interface or voice input function of their smartphone to input the information needed to plan a service or propose a system development, for example, "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[0611] 2. Text Analysis:

[0612] The smartphone sends the acquired input information to a cloud server, which uses the Google Cloud Natural Language API to analyze the input information and extract the characters and their relationships. For example, it identifies entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0613] 3. Relationship and data flow analysis:

[0614] The server uses Google BigQuery to analyze the relationships and data flows between the extracted entities, identifying relationships such as "Supplier A supplies to Logistics Partner B, who transports to Distributor C."

[0615] 4. Analysis of contract type:

[0616] In parallel with the relationship analysis, the contractual arrangements between each entity are also identified, such as "a contract between supplier A and logistics partner B."

[0617] 5. Generate a Business Model:

[0618] Based on the analysis results, the server uses the Google Slides API to generate a business model diagram, which is a visual representation of entities, their relationships, and data flows.

[0619] 6. Generate a risk checklist:

[0620] Additionally, the server uses Google Sheets API to generate a risk checklist and a list of outstanding items based on the business model.

[0621] 7. Return to User:

[0622] The generated business model diagram and risk checklist are provided to users via their smartphones, allowing them to instantly check the business model diagram and risk checklist on their smartphones, improving the accuracy and efficiency of service planning and system development proposals.

[0623] Use the following prompt as an example:

[0624] "Supplier A provides raw materials and logistics partner B handles transportation. Analyze this information and generate a business model diagram with actors, their relationships, and data flows, along with a risk checklist."

[0625] Based on such prompts, the generative AI model can automatically generate a business model diagram and a risk checklist, significantly improving the user's work efficiency.

[0626] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0627] Step 1:

[0628] Users use their smartphones to input the information necessary for service planning and system development proposals through a chat interface or voice input function. This information becomes the initial data for the system. For example, they might input, "The supplier will provide the raw materials, and the shipping company will be responsible for transportation." The input data is captured on the smartphone and sent to the cloud server.

[0629] Step 2:

[0630] The server analyzes the acquired user input using the Google Cloud Natural Language API. If the input data is in text format, the API performs syntactic analysis of the text and extracts entities (characters) in the sentence. Specifically, entities such as "supplier," "transport company," "sales agent," and "consumer" are identified. The data input is text data, and the output is a list of entities.

[0631] Step 3:

[0632] The server uses Google BigQuery to analyze the relationships and data flows between the extracted entities. For example, it clarifies relationships such as "Suppliers supply raw materials to transport companies, and transport companies send goods to sales agents." The input required for analysis is a list of entities, and the output is structured data that shows the relationships and data flows.

[0633] Step 4:

[0634] The server also simultaneously analyzes the contract type. After identifying the relationships between entities, it identifies the contract type between each entity, identifying, for example, a "contract between a supplier and a shipping company." The input required for this analysis is relationship data, and the output is structured data including the contract type.

[0635] Step 5:

[0636] Based on the analysis results, the server generates a business model using the Google Slides API. A business model visually represents entities, their relationships, and data flows. The input is the analyzed data, and the output is a business model in Google Slides format.

[0637] Step 6:

[0638] The server uses the Google Sheets API to generate a risk checklist and a list of outstanding items based on the business model. The risk checklist lists potential risks and items to be considered in the service plan. The input is the business model data, and the output is a checklist in Google Sheets format.

[0639] Step 7:

[0640] The server provides the generated business model diagram and risk checklist to the user via smartphone. The user can check and download this data on their smartphone. Ultimately, the user can use the generated materials to create service plans and system development proposals.

[0641] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0642] This invention relates to a system that acquires input information from users, analyzes it, and automatically generates a business model diagram including the characters, their relationships, and data flows, and also provides a risk checklist. Furthermore, by integrating an emotion engine that recognizes the user's emotions, it has the function of optimizing output based on the user's emotions.

[0643] Program processing and natural language explanation

[0644] 1. Getting User Input

[0645] Users use a web-based chat interface or voice input interface to input information for service planning and system development proposals. For example, a user might input, "Supplier A will provide the raw materials, logistics partner B will handle the transportation, and sales agent C will sell the products to consumers."

[0646] 2. Text Analysis

[0647] The server analyzes the input text data using natural language processing (NLP) tools and extracts entities (characters) from the text, such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0648] 3. Extracting Relationships

[0649] The server analyzes the relationships between the extracted entities, for example, identifying relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[0650] 4. Data flow analysis

[0651] The server analyzes the data flow between entities, for example, identifying data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Distributor C," and "Distributor C to Consumer."

[0652] 5. Analysis of contract type

[0653] The server analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[0654] 6. Generate a Business Model

[0655] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[0656] 7. Generate a risk checklist

[0657] The server generates a risk checklist and a list of outstanding items to complement the business model.

[0658] 8. User Emotion Recognition

[0659] The server analyzes the user's input information using an emotion engine to recognize the user's emotional state, which can include positive, negative, or neutral emotions.

[0660] 9. Optimize your output

[0661] The server optimizes the content and structure of the generated business model diagram and risk checklist based on the user's emotional state recognized by the emotion engine. For example, if the user's emotion is positive, the provided output will include more encouraging information, while if the user's emotion is negative, the server will emphasize information that supports problem solving.

[0662] 10. Return to User

[0663] The server provides users with optimized business models and risk checklists, which can then be downloaded as Google Slides files for use in meetings and proposals.

[0664] Specific examples

[0665] As a specific example, consider the case where a user inputs information for a proposed supply chain management system.

[0666] scene:

[0667] A user enters, "Supplier A provides the raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[0668] Specific processing flow:

[0669] 1. Getting User Input

[0670] The user enters the above information through the chat interface.

[0671] 2. Text Analysis

[0672] The server analyzes the input information using natural language processing (NLP) technology and extracts entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0673] 3. Extracting Relationships

[0674] The server analyzes the relationships between entities and identifies relationships such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to sales agent C," and "Sales agent C sells to consumers."

[0675] 4. Data flow analysis

[0676] The server analyzes the data flow between entities and identifies data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0677] 5. Analysis of contract type

[0678] The server identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and distributor C," and "a contract between distributor C and the consumer."

[0679] 6. Generate a Business Model

[0680] The server generates a business model diagram based on these analysis results and outputs it in Google Slides format.

[0681] 7. Generate a risk checklist

[0682] The server generates a risk checklist and a list of outstanding items.

[0683] 8. User Emotion Recognition

[0684] The server uses an emotion engine to analyze the user's emotions and adjusts the output based on that information, for example, if the user is in a positive state.

[0685] 9. Optimize your output

[0686] The server optimizes the contents of the created business model diagram and risk checklist based on the user's feelings.

[0687] 10. Return to User

[0688] The server provides the user with an optimized business model diagram and a risk checklist, and the user can make effective proposals and plans based on these.

[0689] This system allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists. Furthermore, by combining it with an emotion engine, the output is optimized to the user's current emotions, improving the accuracy and efficiency of proposals and plans.

[0690] The processing flow will be explained below.

[0691] Step 1:

[0692] Users use a web-based chat interface or voice input interface to input information for service planning and system development proposals, such as "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[0693] Step 2:

[0694] The server acquires the information entered by the user, such as data entered through a chat interface or a voice input interface, and temporarily stores the data for further analysis.

[0695] Step 3:

[0696] The server analyzes the acquired text data using natural language processing (NLP) technology. This analysis extracts entities (characters) from the text. For example, "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified as entities.

[0697] Step 4:

[0698] The server analyzes the relationships between the extracted entities, for example, identifying relationships such as "Supplier A supplies raw materials to Logistics Partner B," "Logistics Partner B transports goods to Sales Agent C," and "Sales Agent C sells goods to consumers."

[0699] Step 5:

[0700] The server analyzes data flows between entities. This analysis identifies which data flows from which entity to which entity. For example, data flows such as "raw material data moves from supplier A to logistics partner B," "product data moves from logistics partner B to sales agent C," and "sales data moves from sales agent C to consumers."

[0701] Step 6:

[0702] The server analyzes the contractual arrangements between each entity, for example, identifying a "supply contract between supplier A and logistics partner B," a "transportation contract between logistics partner B and distributor C," and a "sales contract between distributor C and a consumer."

[0703] Step 7:

[0704] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[0705] Step 8:

[0706] The server generates a risk checklist and a list of outstanding issues to complement the business model diagram, thereby clarifying the risks and outstanding issues that users should consider when planning or proposing.

[0707] Step 9:

[0708] The server analyzes the user's input information using an emotion engine to recognize the user's emotional state, which may include positive, negative, or neutral emotions.

[0709] Step 10:

[0710] The server optimizes the content and structure of the generated business model diagram and risk checklist based on the user's emotional state recognized by the emotion engine. For example, if the user's emotion is positive, the provided output will include more encouraging information, while if the user's emotion is negative, the server will emphasize information that supports problem solving.

[0711] Step 11:

[0712] The server provides users with optimized business models and risk checklists, which can then be downloaded as Google Slides files for use in meetings and proposals.

[0713] As a concrete example, when a user inputs information for a proposed supply chain management system, he / she inputs "Supplier A provides raw materials, logistics partner B is responsible for transportation, and sales agent C sells the products to consumers" in step 1. The server processes steps 2 to 10 and finally provides an optimized business model diagram and risk checklist.

[0714] Example 2

[0715] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0716] In conventional systems, it takes a great deal of time and effort for users to create business model diagrams and generate risk checklists. Furthermore, because optimization is not performed taking into account the user's emotional state, it is difficult to obtain output that meets the user's needs. A new technology was needed to solve these issues.

[0717] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0718] In this invention, the server includes: means for acquiring information input by a user; means for analyzing the acquired information using natural language processing technology; means for automatically generating a business model diagram including entities, their relationships, and data flows based on the analyzed information; means for generating a risk checklist that complements the business model diagram; means for recognizing the emotional state of the user from the acquired information; means for optimizing the contents of the business model diagram and the risk checklist based on the recognized emotional state; and means for outputting the automatically generated business model diagram and risk checklist. This enables a user to simply input information, and the server to automatically generate a business model diagram and a risk checklist, and further enables an optimized output to be obtained based on the user's emotional state.

[0719] "User" means an individual or organization that utilizes the system to enter and verify information.

[0720] A "server" is a computing device that receives input information from a user, analyzes it, and generates and outputs various data.

[0721] "Natural language processing technology" is a technology that enables the analysis, understanding, and generation of human language.

[0722] An "entity" is an individual element or subject that appears in a business model.

[0723] A "relationship" indicates the interaction and division of roles between entities.

[0724] "Data flow" refers to how data or information flows between entities.

[0725] A "business model" is a visual representation of entities, their relationships, and data flows.

[0726] A "risk checklist" is a list of potential risks and unresolved issues in a business model.

[0727] "Emotional state" refers to the emotional state or tendency that can be read from the user's input information.

[0728] "Output optimization" refers to adjusting the content and structure of the information being output based on the user's emotional state.

[0729] This invention relates to a system that acquires input information from users, analyzes it, and automatically generates a business model diagram including the characters, their relationships, and data flows, and also provides a risk checklist. Furthermore, by integrating an emotion engine that recognizes the user's emotions, it has the function of optimizing output based on the user's emotions.

[0730] 1. Getting User Input

[0731] Users use their devices to input information into a web-based chat interface or voice input interface, built with HTML, CSS, and JavaScript, using the SpeechRecognition API for voice input. For example, they might input, "Supplier A provides the raw materials, logistics partner B handles the transportation, and sales agent C sells the products to consumers."

[0732] 2. Text Data Analysis

[0733] The server receives input data from users and analyzes the text using NLP (Natural Language Processing) tools. Libraries such as SpaCy and NLTK are used for this analysis. The server is built in Python and uses web frameworks such as Flask for processing.

[0734] 3. Entity Extraction

[0735] The server uses natural language processing technology to extract entities (e.g., suppliers, logistics partners, sales agents, consumers, etc.) from the input text. The entity extraction is performed using SpaCy's Named Entity Recognition (NER) function.

[0736] 4. Relationship Analysis

[0737] The server analyzes the relationships between the extracted entities using predefined business rules and logic, such as "Supplier supplies to logistics partner," "Logistics partner transports to distributor," and "Distributor sells to consumer."

[0738] 5. Data Flow Analysis

[0739] The server analyzes the data flow between entities, identifying data flows such as "Supplier to Logistics Partner," "Logistics Partner to Distributor," and "Distributor to Consumer."

[0740] 6. Identification of contract type

[0741] The server analyzes the contract types between entities using predefined contract templates and rules to identify contracts such as a "supply contract between a supplier and a logistics partner," a "transportation contract between a logistics partner and a distributor," or a "sales contract between a distributor and a consumer."

[0742] 7. Generate a Business Model

[0743] The server automatically generates a business model diagram based on the analysis results, using Graphviz or Google Slides API, which visually represents entities, their relationships, and data flows.

[0744] 8. Generate a risk checklist

[0745] The server generates a risk checklist and a list of outstanding items to complement the business model. The items in the risk checklist are predefined and cover the risks associated with the business model.

[0746] 9. Recognition of user emotions using an emotion engine

[0747] The server uses an emotion engine to recognize the emotional state of the user input, using a Sentiment Analysis library (e.g., VADER, TextBlob) to identify positive, negative, neutral, and other emotional states.

[0748] 10. Output optimization

[0749] The server optimizes the content and structure of the output based on the user's emotional state as recognized by the emotion engine: in a positive emotional state, encouraging messages and success stories are emphasized, while in a negative emotional state, information that helps solve problems is emphasized.

[0750] 11. Return to User

[0751] The server provides users with optimized business models and risk checklists, which can be downloaded as Google Slides files for use in meetings and proposals.

[0752] Prompt Sentence Examples

[0753] Generate a business model diagram and risk checklist for the following scenario: "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[0754] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0755] Step 1:

[0756] A user uses their device to input information into a web-based chat interface or voice input interface, for example, "Supplier A provides the raw materials, logistics partner B handles the transportation, and sales agent C sells the goods to the consumer." This input is sent to the server as text data.

[0757] Input: Text information entered by the user

[0758] Output: Text data sent to the server

[0759] Step 2:

[0760] The server analyzes the received text data using natural language processing (NLP) tools such as SpaCy and NLTK. The server understands the context and meaning of the text data and performs syntactic analysis.

[0761] Input: Text data sent by the user

[0762] Output: Parsed text data (including tokenization and parsing results)

[0763] What happens: The server parses the sentence structure using SpaCy's .parser() method.

[0764] Step 3:

[0765] The server extracts entities from the parsed text data using SpaCy's Named Entity Recognition (NER) function, for example, to identify "Supplier A," "Logistics Partner B," "Distributor C," and "Consumer."

[0766] Input: Parsed text data

[0767] Output: A list of extracted entities

[0768] What happens: The server uses SpaCy's .ner() method to extract the specific entity.

[0769] Step 4:

[0770] The server analyzes the relationships between the extracted entities using predefined business rules and logic. For example, it identifies relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Distributor C," and "Distributor C sells to consumers."

[0771] Input: A list of extracted entities

[0772] Output: Relationship identification results

[0773] What it does: The server uses a Python rule-based algorithm to identify relationships between entities.

[0774] Step 5:

[0775] The server analyzes the data flow between entities, identifying data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Distributor C," and "Distributor C to Consumer."

[0776] Input: Entities and their relationships

[0777] Output: Data flow identification results

[0778] Specific operation: The server executes a data flow analysis algorithm to identify the flow of data between entities.

[0779] Step 6:

[0780] The server analyzes the contract types between each entity using predefined contract templates and rules to identify "supply contract between supplier A and logistics partner B," "transportation contract between logistics partner B and distributor C," and "sales contract between distributor C and consumer."

[0781] Input: Entities and their relationships, data flow

[0782] Output: Contract type identification result

[0783] Specific operation: The server identifies the contract type based on the contract template.

[0784] Step 7:

[0785] The server automatically generates a business model based on the analysis results, using Graphviz and Google Slides APIs. The generated business model visually represents entities, their relationships, and data flows.

[0786] Input: Identification of entities, relationships, data flows, and contract types

[0787] Output: Auto-generated business model diagram (Google Slides format)

[0788] Specific operation: The server generates a business model using Graphviz or Google Slides API.

[0789] Step 8:

[0790] The server generates a risk checklist that complements the business model diagram, utilizing predefined risk items and checklists.

[0791] Input: Business Model

[0792] Output: Risk checklist and list of outstanding items

[0793] Specific operation: The server generates a risk checklist based on predefined risk items.

[0794] Step 9:

[0795] The server uses an emotion engine to recognize the emotional state of the user input, using a Sentiment Analysis library (e.g., VADER, TextBlob) to identify positive, negative, neutral, and other emotional states.

[0796] Input: User input information

[0797] Output: User's emotional state (positive, negative, neutral)

[0798] Specific behavior: The server uses the Sentiment Analysis library to identify the emotional state.

[0799] Step 10:

[0800] The server optimizes the content and structure of the output based on the user's emotional state as recognized by the emotion engine. In a positive emotional state, encouraging messages and success stories are emphasized, while in a negative emotional state, information that helps solve problems is emphasized.

[0801] Input: User's emotional state, business model, risk checklist

[0802] Output: Optimized business model, risk checklist

[0803] What it does: The server runs an algorithm to adjust output content based on emotional state.

[0804] Step 11:

[0805] The server provides users with optimized business models and risk checklists, and the generated output can be downloaded as a Google Slides file for use in meetings or to prepare proposals.

[0806] Inputs: Optimized business model, risk checklist

[0807] Output: Downloadable Google Slides file

[0808] Specific operation: The server provides the generated file to the user's device and sends a download link.

[0809] (Application example 2)

[0810] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0811] In the operation management of autonomous vehicles, there is a problem that it is difficult to grasp the vehicle operation plan and data flow effectively and quickly and to carry out appropriate risk management.In addition, it is difficult to provide optimal information according to the emotions and situation of the operation manager, which reduces the accuracy of decision-making, and it is necessary to solve this problem.

[0812] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0813] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information, means for automatically generating a business process model diagram including characters, their relationships, and data flows, and a risk checklist based on the analyzed information, means for outputting the automatically generated business process model diagram and risk checklist, means for extracting entities from the acquired information and analyzing relationships and data flows, means for generating a traffic control diagram and risk checklist and optimizing output through emotion recognition, and means for recognizing user emotions and providing optimized output. This enables operations managers to easily understand operation plans and risks and provide optimal information according to their emotional state at the time.

[0814] A "user" is a person who operates the system and provides input information.

[0815] "Information" refers to the content of reports and instructions processed by the system, such as data and instructions entered by a user.

[0816] "Analysis" refers to the processing and analysis of acquired information to identify relevant entities, relationships, and data flows.

[0817] An "entity" refers to an element with a specific role, such as a character or object identified within the system.

[0818] A "relationship" represents an interaction or connectivity between entities.

[0819] "Data flow" refers to the flow of data or information between entities.

[0820] A "business model diagram" is a diagram that visually represents entities, their relationships, and data flows.

[0821] A "risk checklist" is a list of risks and precautions related to the business model diagram.

[0822] "Emotion recognition" is the process of identifying a user's emotional state from input information, facial expressions, voice, etc.

[0823] "Optimization" refers to adjusting the content and format of output based on analyzed information and perceived emotional state.

[0824] A specific system for implementing this invention is intended for operation management of autonomous vehicles, and is realized as an application installed on a smartphone.

[0825] System Overview

[0826] Hardware and software used

[0827] Natural Language Processing (NLP): Uses the Google Cloud Natural Language API.

[0828] Emotion recognition engine: Uses Microsoft Azure Emotion API.

[0829] Data visualization: Using D3.js.

[0830] Frontend: Uses React Native.

[0831] Backend: Uses Node.js, Express.js, and MongoDB.

[0832] Explanation of program processing

[0833] 1. Getting User Input

[0834] Users can input operation plans via chat or voice input through a smartphone application.

[0835] For voice input, it converts it to a string using the Google Cloud Speech-to-Text API.

[0836] 2. Text Data Analysis

[0837] The server analyzes the input text data using the Google Cloud Natural Language API and extracts entities.

[0838] 3. Relationship and data flow analysis

[0839] The server analyzes the relationships between the extracted entities and identifies the data flow.

[0840] 4. Analysis of contract type

[0841] The server analyzes the contract between the entities and identifies the required information.

[0842] 5. Generation of Operation Control Chart

[0843] The server uses D3.js to generate a visual traffic control diagram.

[0844] 6. Generate a risk checklist

[0845] The server stores the risk factors in MongoDB and generates a risk checklist.

[0846] 7. Emotion recognition

[0847] The server analyzes the user's emotions using the Microsoft Azure Emotion API.

[0848] 8. Optimizing Output

[0849] The server adjusts the content and display method of the operation control chart and risk checklist based on the user's emotions.

[0850] 9. Return to User

[0851] The server returns the optimized operation control chart and risk checklist to the user using React Native.

[0852] Specific examples

[0853] Example of user input

[0854] A dispatcher opens a smartphone app and types, "Vehicle A will depart at 8:00 AM, deliver a package to distribution center B, and then head to distribution center C."

[0855] 1. Text Analysis

[0856] The servers "Vehicle A," "Distribution Center B," and "Distribution Center C" are extracted.

[0857] 2. Relationship and data flow analysis

[0858] The relationships between the extracted entities are analyzed as "Vehicle A delivers cargo to distribution center B" and "Vehicle A heads to distribution center C."

[0859] 3. Analysis of contract type

[0860] The server identifies the "delivery contract between vehicle A and distribution center B."

[0861] 4. Generate operation control charts and risk checklists

[0862] The server uses D3.js to generate operational management diagrams and creates risk checklists based on risk factors stored in MongoDB.

[0863] 5. Emotion recognition and output optimization

[0864] The server analyzes the emotional state, such as "positive" or "negative," and highlights information such as "What to do if distribution center B is congested" in the checklist.

[0865] Prompt Sentence Examples

[0866] 1. "Please enter your flight schedule."

[0867] 2. "Vehicle A departs at 8:00 AM, delivers a package to distribution center B, and then heads to distribution center C."

[0868] 3. "I want to know what to do if Distribution Center B is busy."

[0869] In this way, operation managers can easily understand operation plans and risks, and provide optimal information according to the emotional state of the driver at the time.

[0870] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0871] Step 1:

[0872] Getting User Input

[0873] Users launch the smartphone application and enter their trip plan using a chat interface or voice input. In the latter case, the device converts the speech into text using the Google Cloud Speech-to-Text API, resulting in a text version of the trip plan.

[0874] Step 2:

[0875] Text data analysis

[0876] The server receives the acquired text data and analyzes it using the Google Cloud Natural Language API. During the analysis process, entities (vehicle, distribution center, time, etc.) are extracted from the text. The input is the text data from the user, and the output is a list of extracted entities.

[0877] Step 3:

[0878] Relationship and data flow analysis

[0879] The server analyzes the relationships between the extracted entities and identifies the interactions and data flows between them. The analysis yields relationships such as "Vehicle A delivers packages to distribution center B." The input is a list of entities, and the output is information indicating the relationships and data flows.

[0880] Step 4:

[0881] Contract type analysis

[0882] The server identifies the contract type between each entity based on the relationship and entity information. A contract type such as "Delivery contract between vehicle A and distribution center B" can be obtained. The input is relationship and entity information, and the output is contract type information.

[0883] Step 5:

[0884] Generate operation control charts

[0885] The server uses D3.js to generate a visual control diagram, which visually represents entities, their relationships, and data flows. The inputs are entity, relationship, and data flow information, and the output is the control diagram.

[0886] Step 6:

[0887] Generate a risk checklist

[0888] The server retrieves risk factors related to the operation plan from MongoDB and generates a risk checklist. The risk factors are linked based on the operation control diagram. The input is the operation control diagram and the output is the risk checklist.

[0889] Step 7:

[0890] emotion recognition

[0891] The server uses the Microsoft Azure Emotion API to analyze the user's emotional state based on their input, facial expression, and voice. The analysis results in the user's emotional state (positive, negative, or neutral). The input is the user's facial expression and voice data, and the output is information about their emotional state.

[0892] Step 8:

[0893] Output optimization

[0894] The server adjusts the content and display method of the operation control chart and risk checklist based on the analyzed user's emotional state. For example, if the emotion is negative, it highlights cautions and risk avoidance measures. The inputs are the emotional state, operation control chart, and risk checklist, and the output is optimized output.

[0895] Step 9:

[0896] Return to user

[0897] The server generates an optimized operation control chart and risk checklist and returns them to the user's smartphone using React Native. The input is the optimized operation control chart and risk checklist, and the output is the information displayed on the user's smartphone.

[0898] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0899] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0900] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0901] [Third embodiment]

[0902] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0903] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0904] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0905] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0906] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0907] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0908] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0909] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0910] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0911] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0912] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0913] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0914] This invention is a system that allows users to easily organize and visualize information necessary for planning services, proposing system development, planning seminars and exhibitions, etc. This system acquires input information from the user, analyzes that information, and automatically generates a business model diagram and risk checklist that includes the characters, their relationships, and data flows, and provides them to the user.

[0915] Program processing and natural language explanation

[0916] 1. Getting User Input

[0917] Users provide information for service planning and system development proposals through a web-based chat interface or voice input interface. For example, a user might input, "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[0918] 2. Text Analysis

[0919] The server analyzes the input text data using natural language processing (NLP) tools and extracts entities (characters) from within the text. In this case, "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified as entities.

[0920] 3. Extracting Relationships

[0921] The server analyzes the relationships between the extracted entities, identifying relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[0922] 4. Data flow analysis

[0923] The server analyzes the data flow between entities, for example, identifying data flow from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0924] 5. Analysis of contract type

[0925] The server analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[0926] 6. Generate a Business Model

[0927] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[0928] 7. Generate a risk checklist

[0929] The server generates a risk checklist and a list of outstanding items to complement the business model.

[0930] 8. Return to User

[0931] The server provides the generated business model and risk checklist to the user, with the option to export it as a Google Slides file.

[0932] Specific examples

[0933] As a specific example, consider the case where information on a proposed supply chain management system is input.

[0934] scene:

[0935] A user enters, "Supplier A provides the raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[0936] Specific processing flow:

[0937] 1. Getting User Input

[0938] The user enters the above information through the chat interface.

[0939] 2. Text Analysis

[0940] The server analyzes the input information using natural language processing (NLP) technology and extracts entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0941] 3. Extracting Relationships

[0942] The server analyzes the relationships between entities and identifies relationships such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to distributor C," and "Distributor C sells to consumers."

[0943] 4. Data flow analysis

[0944] The server analyzes the data flow between entities and determines that data flows from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0945] 5. Analysis of contract type

[0946] The server identifies "a contract between Supplier A and Logistics Partner B," "a contract between Logistics Partner B and Distributor C," and "a contract between Distributor C and the Consumer."

[0947] 6. Generate a Business Model

[0948] The server generates a business model diagram based on these analysis results and outputs it in Google Slides format.

[0949] 7. Generate a risk checklist

[0950] The server generates a risk checklist and a list of outstanding items.

[0951] 8. Return to User

[0952] The server provides the generated business model diagram and risk checklist to the user, who can then use this information to efficiently plan services and propose system development.

[0953] This allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists, preventing oversights when creating frameworks and improving the accuracy and efficiency of service plans and system development proposals.

[0954] The processing flow will be explained below.

[0955] Step 1:

[0956] Users use a web-based chat interface or voice input interface to input information for service planning or system development proposals, including specific details such as "Supplier A will provide the raw materials, logistics partner B will handle the transportation, and sales agent C will sell the products to consumers."

[0957] Step 2:

[0958] The server acquires the information entered by the user, such as data entered through a chat interface or a voice input interface, and temporarily stores the data for further analysis.

[0959] Step 3:

[0960] The server analyzes the acquired text data using natural language processing (NLP) technology. This analysis extracts entities (characters) from the text. Specific entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified.

[0961] Step 4:

[0962] The server extracts relationships between the analyzed entities, such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to sales agent C," and "Sales agent C sells to consumers."

[0963] Step 5:

[0964] The server analyzes the data flow between entities. This analysis identifies which data flows from which entity to which entity. For example, data flows from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0965] Step 6:

[0966] The server analyzes the contract type between each entity, and identifies contract types such as "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[0967] Step 7:

[0968] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[0969] Step 8:

[0970] The server generates a risk checklist and a list of outstanding issues to complement the business model diagram, thereby clarifying the risks and outstanding issues that users should consider when planning or proposing a project.

[0971] Step 9:

[0972] The server then provides the generated business model and risk checklist to the user, who can then download this information as a Google Slides file for use in meetings or to prepare proposals.

[0973] As a concrete example, let's consider the case of inputting information for a proposed supply chain management system. A user would enter through a chat interface, "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells the products to consumers." The server retrieves this information and uses NLP technology to analyze entities, their relationships, and data flows. It then automatically generates a business model diagram and risk checklist, which are presented to the user in Google Slides format.

[0974] Example 1

[0975] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0976] In conventional service planning and system development proposals, the task of organizing and visualizing the necessary information requires a great deal of time and effort. Furthermore, insufficient information organization and visualization increases the likelihood of oversights and misunderstandings, making risk management difficult. Therefore, there is a need for a system that can automatically analyze the information provided by users, automatically generate business model diagrams and risk checklists, and visualize the information efficiently and accurately.

[0977] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0978] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information using natural language processing technology, and means for automatically generating a business model diagram including entities, their relationships, and data flows, and a risk checklist based on the analyzed information. This makes it possible to efficiently and accurately analyze information provided by a user and quickly create a visually represented business model diagram and risk checklist.

[0979] A "user" is an entity that utilizes the system to provide information and receive visualized business models and risk checklists.

[0980] The "server" is a computer system that analyzes information obtained from users and generates business model diagrams and risk checklists.

[0981] "Information" refers to text and data related to service plans and system development proposals entered by users.

[0982] "Natural language processing technology" is a set of algorithms and techniques used to analyze input information and extract entities and relationships.

[0983] "Entity" refers to a character, organization, object, concept, etc. that is a major element in a business model diagram.

[0984] A "relationship" represents the interaction or association between entities, and clarifies their roles and connections in a business process.

[0985] "Data flow" refers to the flow of data exchanged between entities, and indicates the path along which information travels.

[0986] A "business model diagram" is a visual representation of entities, their relationships, and data flows.

[0987] A "risk checklist" is a list of potential risks and unresolved issues that is generated to complement a business model diagram.

[0988] "Output means" refers to a method or tool for providing the generated business model diagram and risk checklist to the user.

[0989] This invention is a system that allows users to easily organize and visualize information necessary for planning services, proposing system development, planning seminars and exhibitions, etc. This system acquires input information from the user, analyzes that information, and automatically generates a business model diagram and risk checklist that includes the characters, their relationships, and data flows, and provides them to the user.

[0990] Specifically, the following hardware and software are used:

[0991] Hardware: Servers and terminals (PCs, smartphones)

[0992] Software: Natural Language Processing (NLP) libraries (SpaCy, NLTK), relation extraction models, visualization tools (matplotlib, Graphviz), Google Slides

[0993] Users can use their devices to provide information for service planning and system development proposals through a web-based chat interface or voice input interface. For example, they can enter text such as "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[0994] The server receives the input text data and performs natural language processing using SpaCy and NLTK. First, it tokenizes the text data and then performs entity recognition to extract entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[0995] The server then uses the relationship extraction model to analyze the relationships between entities, such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[0996] The server then analyzes the data flow of the entities by referring to business rules and standard data flow diagram templates, identifying the data flow from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[0997] The server also retrieves contract information from a pre-registered database and analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[0998] The server automatically generates a business model diagram based on these analysis results and outputs it in Google Slides format, which visually represents entities, their relationships, and data flows.

[0999] Additionally, the server generates risk checklists and backlogs, which are used to identify and manage risks in service planning and system development.

[1000] Finally, the server provides the generated business model and risk checklist to the user, including the option to provide them as downloadable files in Google Slides format, which the user can download and use via their device.

[1001] For example, if a user enters "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells products to consumers," the system will automatically analyze the entities, their relationships, and data flows, and based on that, generate a business model diagram and risk checklist, which it will provide to the user.

[1002] This allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists, preventing oversights when creating frameworks and improving the accuracy and efficiency of service plans and system development proposals.

[1003] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1004] Step 1:

[1005] A user uses a terminal to access a web-based chat interface or voice input interface and inputs the information required for service planning or system development proposals. The input information is sent to the server as text data. For example, a user might input, "Supplier A will provide the raw materials, and logistics partner B will be responsible for transportation." This text data becomes the input data for the next analysis step.

[1006] Step 2:

[1007] The server analyzes the received text data using a natural language processing tool (e.g., SpaCy or NLTK). First, the server tokenizes the text and then performs entity recognition. In this process, entity information such as "Supplier A," "Logistics Partner B," and "Sales Agent C" is extracted from the text data. The extracted entity information becomes the input data for the next relationship analysis step.

[1008] Step 3:

[1009] The server applies a relationship extraction model to analyze the relationships between the extracted entities. For example, it identifies relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers." The analyzed relationship information becomes input data for the next data flow analysis step.

[1010] Step 4:

[1011] The server analyzes the data flow between entities by referring to business rules and standard data flow diagram templates. For example, it identifies data flows such as "from supplier A to logistics partner B," "from logistics partner B to sales agent C," and "from sales agent C to consumers." The analyzed data flow information becomes input data for the next step, contract form analysis.

[1012] Step 5:

[1013] The server retrieves contract information from a pre-registered database and analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and the consumer." The analyzed contract type information becomes input data for the next business model diagram generation step.

[1014] Step 6:

[1015] The server automatically generates a business model diagram based on these analysis results. Specifically, it creates a diagram in Google Slides format that visually represents entities, relationships, data flows, and contract types. This generated business model diagram serves as input data for the next step, risk checklist generation.

[1016] Step 7:

[1017] The server generates a risk checklist and a list of unsorted items to complement the business model diagram. The generated risk checklist becomes input data for the next step of returning the item to the user.

[1018] Step 8:

[1019] The server provides the generated business model and risk checklist to the user, including the option to output them as Google Slides files with a download link. Users can download and use these materials via their devices.

[1020] (Application example 1)

[1021] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1022] In today's business environment, efficient organization and visualization of large amounts of information is required to quickly and accurately plan services and propose system development. However, manually organizing information and creating business model diagrams and risk checklists takes time and effort, so more efficient methods are needed. Furthermore, if users could perform these tasks using smartphones, business efficiency could be further improved.

[1023] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1024] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information, means for automatically generating a business model diagram including characters, their relationships, and data flows, and a risk checklist based on the analyzed information, means for generating prompt sentences to be input into the generative AI model, and means for providing the business model diagram and risk checklist to the user via a smartphone. This enables the user to use their smartphone to efficiently and quickly automatically generate the business model diagram and risk checklist required for service planning and system development proposals, preventing oversights.

[1025] "User input" refers to the information or data that a user provides to the system, from which the business model diagram and risk checklist are generated.

[1026] "Text analysis" is the process of extracting and analyzing entities such as characters and their relationships based on acquired text data using natural language processing technology.

[1027] "Actors" refers to the various actors within the business model, including suppliers, logistics partners, agents, and consumers.

[1028] "Relationships" refer to the mutual interests, contractual structures, data flows, etc. between the parties involved, and are one of the components of a business model diagram.

[1029] "Data flow" shows the flow of data between actors, and visually represents the movement of information in a supply chain.

[1030] A "business model diagram" is a diagram that visually represents the characters, their relationships, data flow, etc., and serves as the basis for service planning and system development proposals.

[1031] A "risk checklist" is a list of risks and matters to be considered that are identified based on the business model diagram, and is used to improve the accuracy and efficiency of proposals.

[1032] A "generative AI model" refers to an artificial intelligence model that generates business model diagrams and risk checklists based on user-entered information.

[1033] A "prompt sentence" is an input sentence that causes the generative AI model to extract and generate specific information, and is automatically generated by the system.

[1034] "Smartphone provision" refers to the means of providing the generated business model diagram and risk checklist to the user via a smartphone.

[1035] The present invention relates to a system that allows users to quickly and efficiently plan services and propose system development. This system acquires information entered by the user, analyzes it, automatically generates a business model diagram and a risk checklist, and provides them to the user via a smartphone.

[1036] The system is comprised of the following hardware and software:

[1037] 1. Hardware:

[1038] Smartphone (iOS / Android)

[1039] Cloud Server

[1040] 2. Software:

[1041] Google Cloud Natural Language API (Natural Language Processing)

[1042] Google BigQuery (data analysis)

[1043] Google Slides API (Business model generation)

[1044] Google Sheets API (risk checklist generation)

[1045] The specific processing flow of the system:

[1046] 1. Getting user input:

[1047] Users use the chat interface or voice input function of their smartphone to input the information needed to plan a service or propose a system development, for example, "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[1048] 2. Text Analysis:

[1049] The smartphone sends the acquired input information to a cloud server, which uses the Google Cloud Natural Language API to analyze the input information and extract the characters and their relationships. For example, it identifies entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[1050] 3. Relationship and data flow analysis:

[1051] The server uses Google BigQuery to analyze the relationships and data flows between the extracted entities, identifying relationships such as "Supplier A supplies to Logistics Partner B, who transports to Distributor C."

[1052] 4. Analysis of contract type:

[1053] In parallel with the relationship analysis, the contractual arrangements between each entity are also identified, such as "a contract between supplier A and logistics partner B."

[1054] 5. Generate a Business Model:

[1055] Based on the analysis results, the server uses the Google Slides API to generate a business model diagram, which is a visual representation of entities, their relationships, and data flows.

[1056] 6. Generate a risk checklist:

[1057] Additionally, the server uses Google Sheets API to generate a risk checklist and a list of outstanding items based on the business model.

[1058] 7. Return to User:

[1059] The generated business model diagram and risk checklist are provided to users via their smartphones, allowing them to instantly check the business model diagram and risk checklist on their smartphones, improving the accuracy and efficiency of service planning and system development proposals.

[1060] Use the following prompt as an example:

[1061] "Supplier A provides raw materials and logistics partner B handles transportation. Analyze this information and generate a business model diagram with actors, their relationships, and data flows, along with a risk checklist."

[1062] Based on such prompts, the generative AI model can automatically generate a business model diagram and a risk checklist, significantly improving the user's work efficiency.

[1063] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1064] Step 1:

[1065] Users use their smartphones to input the information necessary for service planning and system development proposals through a chat interface or voice input function. This information becomes the initial data for the system. For example, they might input, "The supplier will provide the raw materials, and the shipping company will be responsible for transportation." The input data is captured on the smartphone and sent to the cloud server.

[1066] Step 2:

[1067] The server analyzes the acquired user input using the Google Cloud Natural Language API. If the input data is in text format, the API performs syntactic analysis of the text and extracts entities (characters) in the sentence. Specifically, entities such as "supplier," "transport company," "sales agent," and "consumer" are identified. The data input is text data, and the output is a list of entities.

[1068] Step 3:

[1069] The server uses Google BigQuery to analyze the relationships and data flows between the extracted entities. For example, it clarifies relationships such as "Suppliers supply raw materials to transport companies, and transport companies send goods to sales agents." The input required for analysis is a list of entities, and the output is structured data that shows the relationships and data flows.

[1070] Step 4:

[1071] The server also simultaneously analyzes the contract type. After identifying the relationships between entities, it identifies the contract type between each entity, identifying, for example, a "contract between a supplier and a shipping company." The input required for this analysis is relationship data, and the output is structured data including the contract type.

[1072] Step 5:

[1073] Based on the analysis results, the server generates a business model using the Google Slides API. A business model visually represents entities, their relationships, and data flows. The input is the analyzed data, and the output is a business model in Google Slides format.

[1074] Step 6:

[1075] The server uses the Google Sheets API to generate a risk checklist and a list of outstanding items based on the business model. The risk checklist lists potential risks and items to be considered in the service plan. The input is the business model data, and the output is a checklist in Google Sheets format.

[1076] Step 7:

[1077] The server provides the generated business model diagram and risk checklist to the user via smartphone. The user can check and download this data on their smartphone. Ultimately, the user can use the generated materials to create service plans and system development proposals.

[1078] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1079] This invention relates to a system that acquires input information from users, analyzes it, and automatically generates a business model diagram including the characters, their relationships, and data flows, and also provides a risk checklist. Furthermore, by integrating an emotion engine that recognizes the user's emotions, it has the function of optimizing output based on the user's emotions.

[1080] Program processing and natural language explanation

[1081] 1. Getting User Input

[1082] Users use a web-based chat interface or voice input interface to input information for service planning and system development proposals. For example, a user might input, "Supplier A will provide the raw materials, logistics partner B will handle the transportation, and sales agent C will sell the products to consumers."

[1083] 2. Text Analysis

[1084] The server analyzes the input text data using natural language processing (NLP) tools and extracts entities (characters) from the text, such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[1085] 3. Extracting Relationships

[1086] The server analyzes the relationships between the extracted entities, for example, identifying relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[1087] 4. Data flow analysis

[1088] The server analyzes the data flow between entities, for example, identifying data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Distributor C," and "Distributor C to Consumer."

[1089] 5. Analysis of contract type

[1090] The server analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[1091] 6. Generate a Business Model

[1092] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[1093] 7. Generate a risk checklist

[1094] The server generates a risk checklist and a list of outstanding items to complement the business model.

[1095] 8. User Emotion Recognition

[1096] The server analyzes the user's input information using an emotion engine to recognize the user's emotional state, which can include positive, negative, or neutral emotions.

[1097] 9. Optimize your output

[1098] The server optimizes the content and structure of the generated business model diagram and risk checklist based on the user's emotional state recognized by the emotion engine. For example, if the user's emotion is positive, the provided output will include more encouraging information, while if the user's emotion is negative, the server will emphasize information that supports problem solving.

[1099] 10. Return to User

[1100] The server provides users with optimized business models and risk checklists, which can then be downloaded as Google Slides files for use in meetings and proposals.

[1101] Specific examples

[1102] As a specific example, consider the case where a user inputs information for a proposed supply chain management system.

[1103] scene:

[1104] A user enters, "Supplier A provides the raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[1105] Specific processing flow:

[1106] 1. Getting User Input

[1107] The user enters the above information through the chat interface.

[1108] 2. Text Analysis

[1109] The server analyzes the input information using natural language processing (NLP) technology and extracts entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[1110] 3. Extracting Relationships

[1111] The server analyzes the relationships between entities and identifies relationships such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to sales agent C," and "Sales agent C sells to consumers."

[1112] 4. Data flow analysis

[1113] The server analyzes the data flow between entities and identifies data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[1114] 5. Analysis of contract type

[1115] The server identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and distributor C," and "a contract between distributor C and the consumer."

[1116] 6. Generate a Business Model

[1117] The server generates a business model diagram based on these analysis results and outputs it in Google Slides format.

[1118] 7. Generate a risk checklist

[1119] The server generates a risk checklist and a list of outstanding items.

[1120] 8. User Emotion Recognition

[1121] The server uses an emotion engine to analyze the user's emotions and adjusts the output based on that information, for example, if the user is in a positive state.

[1122] 9. Optimize your output

[1123] The server optimizes the contents of the created business model diagram and risk checklist based on the user's feelings.

[1124] 10. Return to User

[1125] The server provides the user with an optimized business model diagram and a risk checklist, and the user can make effective proposals and plans based on these.

[1126] This system allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists. Furthermore, by combining it with an emotion engine, the output is optimized to the user's current emotions, improving the accuracy and efficiency of proposals and plans.

[1127] The processing flow will be explained below.

[1128] Step 1:

[1129] Users use a web-based chat interface or voice input interface to input information for service planning and system development proposals, such as "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[1130] Step 2:

[1131] The server acquires the information entered by the user, such as data entered through a chat interface or a voice input interface, and temporarily stores the data for further analysis.

[1132] Step 3:

[1133] The server analyzes the acquired text data using natural language processing (NLP) technology. This analysis extracts entities (characters) from the text. For example, "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified as entities.

[1134] Step 4:

[1135] The server analyzes the relationships between the extracted entities, for example, identifying relationships such as "Supplier A supplies raw materials to Logistics Partner B," "Logistics Partner B transports goods to Sales Agent C," and "Sales Agent C sells goods to consumers."

[1136] Step 5:

[1137] The server analyzes data flows between entities. This analysis identifies which data flows from which entity to which entity. For example, data flows such as "raw material data moves from supplier A to logistics partner B," "product data moves from logistics partner B to sales agent C," and "sales data moves from sales agent C to consumers."

[1138] Step 6:

[1139] The server analyzes the contractual arrangements between each entity, for example, identifying a "supply contract between supplier A and logistics partner B," a "transportation contract between logistics partner B and distributor C," and a "sales contract between distributor C and a consumer."

[1140] Step 7:

[1141] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[1142] Step 8:

[1143] The server generates a risk checklist and a list of outstanding issues to complement the business model diagram, thereby clarifying the risks and outstanding issues that users should consider when planning or proposing.

[1144] Step 9:

[1145] The server analyzes the user's input information using an emotion engine to recognize the user's emotional state, which may include positive, negative, or neutral emotions.

[1146] Step 10:

[1147] The server optimizes the content and structure of the generated business model diagram and risk checklist based on the user's emotional state recognized by the emotion engine. For example, if the user's emotion is positive, the provided output will include more encouraging information, while if the user's emotion is negative, the server will emphasize information that supports problem solving.

[1148] Step 11:

[1149] The server provides users with optimized business models and risk checklists, which can then be downloaded as Google Slides files for use in meetings and proposals.

[1150] As a concrete example, when a user inputs information for a proposed supply chain management system, he / she inputs "Supplier A provides raw materials, logistics partner B is responsible for transportation, and sales agent C sells the products to consumers" in step 1. The server processes steps 2 to 10 and finally provides an optimized business model diagram and risk checklist.

[1151] Example 2

[1152] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1153] In conventional systems, it takes a great deal of time and effort for users to create business model diagrams and generate risk checklists. Furthermore, because optimization is not performed taking into account the user's emotional state, it is difficult to obtain output that meets the user's needs. A new technology was needed to solve these issues.

[1154] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1155] In this invention, the server includes: means for acquiring information input by a user; means for analyzing the acquired information using natural language processing technology; means for automatically generating a business model diagram including entities, their relationships, and data flows based on the analyzed information; means for generating a risk checklist that complements the business model diagram; means for recognizing the emotional state of the user from the acquired information; means for optimizing the contents of the business model diagram and the risk checklist based on the recognized emotional state; and means for outputting the automatically generated business model diagram and risk checklist. This enables a user to simply input information, and the server to automatically generate a business model diagram and a risk checklist, and further enables an optimized output to be obtained based on the user's emotional state.

[1156] "User" means an individual or organization that utilizes the system to enter and verify information.

[1157] A "server" is a computing device that receives input information from a user, analyzes it, and generates and outputs various data.

[1158] "Natural language processing technology" is a technology that enables the analysis, understanding, and generation of human language.

[1159] An "entity" is an individual element or subject that appears in a business model.

[1160] A "relationship" indicates the interaction and division of roles between entities.

[1161] "Data flow" refers to how data or information flows between entities.

[1162] A "business model" is a visual representation of entities, their relationships, and data flows.

[1163] A "risk checklist" is a list of potential risks and unresolved issues in a business model.

[1164] "Emotional state" refers to the emotional state or tendency that can be read from the user's input information.

[1165] "Output optimization" refers to adjusting the content and structure of the information being output based on the user's emotional state.

[1166] This invention relates to a system that acquires input information from users, analyzes it, and automatically generates a business model diagram including the characters, their relationships, and data flows, and also provides a risk checklist. Furthermore, by integrating an emotion engine that recognizes the user's emotions, it has the function of optimizing output based on the user's emotions.

[1167] 1. Getting User Input

[1168] Users use their devices to input information into a web-based chat interface or voice input interface, built with HTML, CSS, and JavaScript, using the SpeechRecognition API for voice input. For example, they might input, "Supplier A provides the raw materials, logistics partner B handles the transportation, and sales agent C sells the products to consumers."

[1169] 2. Text Data Analysis

[1170] The server receives input data from users and analyzes the text using NLP (Natural Language Processing) tools. Libraries such as SpaCy and NLTK are used for this analysis. The server is built in Python and uses web frameworks such as Flask for processing.

[1171] 3. Entity Extraction

[1172] The server uses natural language processing technology to extract entities (e.g., suppliers, logistics partners, sales agents, consumers, etc.) from the input text. The entity extraction is performed using SpaCy's Named Entity Recognition (NER) function.

[1173] 4. Relationship Analysis

[1174] The server analyzes the relationships between the extracted entities using predefined business rules and logic, such as "Supplier supplies to logistics partner," "Logistics partner transports to distributor," and "Distributor sells to consumer."

[1175] 5. Data Flow Analysis

[1176] The server analyzes the data flow between entities, identifying data flows such as "Supplier to Logistics Partner," "Logistics Partner to Distributor," and "Distributor to Consumer."

[1177] 6. Identification of contract type

[1178] The server analyzes the contract types between entities using predefined contract templates and rules to identify contracts such as a "supply contract between a supplier and a logistics partner," a "transportation contract between a logistics partner and a distributor," or a "sales contract between a distributor and a consumer."

[1179] 7. Generate a Business Model

[1180] The server automatically generates a business model diagram based on the analysis results, using Graphviz or Google Slides API, which visually represents entities, their relationships, and data flows.

[1181] 8. Generate a risk checklist

[1182] The server generates a risk checklist and a list of outstanding items to complement the business model. The items in the risk checklist are predefined and cover the risks associated with the business model.

[1183] 9. Recognition of user emotions using an emotion engine

[1184] The server uses an emotion engine to recognize the emotional state of the user input, using a Sentiment Analysis library (e.g., VADER, TextBlob) to identify positive, negative, neutral, and other emotional states.

[1185] 10. Output optimization

[1186] The server optimizes the content and structure of the output based on the user's emotional state as recognized by the emotion engine: in a positive emotional state, encouraging messages and success stories are emphasized, while in a negative emotional state, information that helps solve problems is emphasized.

[1187] 11. Return to User

[1188] The server provides users with optimized business models and risk checklists, which can be downloaded as Google Slides files for use in meetings and proposals.

[1189] Prompt Sentence Examples

[1190] Generate a business model diagram and risk checklist for the following scenario: "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[1191] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1192] Step 1:

[1193] A user uses their device to input information into a web-based chat interface or voice input interface, for example, "Supplier A provides the raw materials, logistics partner B handles the transportation, and sales agent C sells the goods to the consumer." This input is sent to the server as text data.

[1194] Input: Text information entered by the user

[1195] Output: Text data sent to the server

[1196] Step 2:

[1197] The server analyzes the received text data using natural language processing (NLP) tools such as SpaCy and NLTK. The server understands the context and meaning of the text data and performs syntactic analysis.

[1198] Input: Text data sent by the user

[1199] Output: Parsed text data (including tokenization and parsing results)

[1200] What happens: The server parses the sentence structure using SpaCy's .parser() method.

[1201] Step 3:

[1202] The server extracts entities from the parsed text data using SpaCy's Named Entity Recognition (NER) function, for example, to identify "Supplier A," "Logistics Partner B," "Distributor C," and "Consumer."

[1203] Input: Parsed text data

[1204] Output: A list of extracted entities

[1205] What happens: The server uses SpaCy's .ner() method to extract the specific entity.

[1206] Step 4:

[1207] The server analyzes the relationships between the extracted entities using predefined business rules and logic. For example, it identifies relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Distributor C," and "Distributor C sells to consumers."

[1208] Input: A list of extracted entities

[1209] Output: Relationship identification results

[1210] What it does: The server uses a Python rule-based algorithm to identify relationships between entities.

[1211] Step 5:

[1212] The server analyzes the data flow between entities, identifying data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Distributor C," and "Distributor C to Consumer."

[1213] Input: Entities and their relationships

[1214] Output: Data flow identification results

[1215] Specific operation: The server executes a data flow analysis algorithm to identify the flow of data between entities.

[1216] Step 6:

[1217] The server analyzes the contract types between each entity using predefined contract templates and rules to identify "supply contract between supplier A and logistics partner B," "transportation contract between logistics partner B and distributor C," and "sales contract between distributor C and consumer."

[1218] Input: Entities and their relationships, data flow

[1219] Output: Contract type identification result

[1220] Specific operation: The server identifies the contract type based on the contract template.

[1221] Step 7:

[1222] The server automatically generates a business model based on the analysis results, using Graphviz and Google Slides APIs. The generated business model visually represents entities, their relationships, and data flows.

[1223] Input: Identification of entities, relationships, data flows, and contract types

[1224] Output: Auto-generated business model diagram (Google Slides format)

[1225] Specific operation: The server generates a business model using Graphviz or Google Slides API.

[1226] Step 8:

[1227] The server generates a risk checklist that complements the business model diagram, utilizing predefined risk items and checklists.

[1228] Input: Business Model

[1229] Output: Risk checklist and list of outstanding items

[1230] Specific operation: The server generates a risk checklist based on predefined risk items.

[1231] Step 9:

[1232] The server uses an emotion engine to recognize the emotional state of the user input, using a Sentiment Analysis library (e.g., VADER, TextBlob) to identify positive, negative, neutral, and other emotional states.

[1233] Input: User input information

[1234] Output: User's emotional state (positive, negative, neutral)

[1235] Specific behavior: The server uses the Sentiment Analysis library to identify the emotional state.

[1236] Step 10:

[1237] The server optimizes the content and structure of the output based on the user's emotional state as recognized by the emotion engine. In a positive emotional state, encouraging messages and success stories are emphasized, while in a negative emotional state, information that helps solve problems is emphasized.

[1238] Input: User's emotional state, business model, risk checklist

[1239] Output: Optimized business model, risk checklist

[1240] What it does: The server runs an algorithm to adjust output content based on emotional state.

[1241] Step 11:

[1242] The server provides users with optimized business models and risk checklists, and the generated output can be downloaded as a Google Slides file for use in meetings or to prepare proposals.

[1243] Inputs: Optimized business model, risk checklist

[1244] Output: Downloadable Google Slides file

[1245] Specific operation: The server provides the generated file to the user's device and sends a download link.

[1246] (Application example 2)

[1247] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1248] In the operation management of autonomous vehicles, there is a problem that it is difficult to grasp the vehicle operation plan and data flow effectively and quickly and to carry out appropriate risk management.In addition, it is difficult to provide optimal information according to the emotions and situation of the operation manager, which reduces the accuracy of decision-making, and it is necessary to solve this problem.

[1249] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1250] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information, means for automatically generating a business process model diagram including characters, their relationships, and data flows, and a risk checklist based on the analyzed information, means for outputting the automatically generated business process model diagram and risk checklist, means for extracting entities from the acquired information and analyzing relationships and data flows, means for generating a traffic control diagram and risk checklist and optimizing output through emotion recognition, and means for recognizing user emotions and providing optimized output. This enables operations managers to easily understand operation plans and risks and provide optimal information according to their emotional state at the time.

[1251] A "user" is a person who operates the system and provides input information.

[1252] "Information" refers to the content of reports and instructions processed by the system, such as data and instructions entered by a user.

[1253] "Analysis" refers to the processing and analysis of acquired information to identify relevant entities, relationships, and data flows.

[1254] An "entity" refers to an element with a specific role, such as a character or object identified within the system.

[1255] A "relationship" represents an interaction or connectivity between entities.

[1256] "Data flow" refers to the flow of data or information between entities.

[1257] A "business model diagram" is a diagram that visually represents entities, their relationships, and data flows.

[1258] A "risk checklist" is a list of risks and precautions related to the business model diagram.

[1259] "Emotion recognition" is the process of identifying a user's emotional state from input information, facial expressions, voice, etc.

[1260] "Optimization" refers to adjusting the content and format of output based on analyzed information and perceived emotional state.

[1261] A specific system for implementing this invention is intended for operation management of autonomous vehicles, and is realized as an application installed on a smartphone.

[1262] System Overview

[1263] Hardware and software used

[1264] Natural Language Processing (NLP): Uses the Google Cloud Natural Language API.

[1265] Emotion recognition engine: Uses Microsoft Azure Emotion API.

[1266] Data visualization: Using D3.js.

[1267] Frontend: Uses React Native.

[1268] Backend: Uses Node.js, Express.js, and MongoDB.

[1269] Explanation of program processing

[1270] 1. Getting User Input

[1271] Users can input operation plans via chat or voice input through a smartphone application.

[1272] For voice input, it converts it to a string using the Google Cloud Speech-to-Text API.

[1273] 2. Text Data Analysis

[1274] The server analyzes the input text data using the Google Cloud Natural Language API and extracts entities.

[1275] 3. Relationship and data flow analysis

[1276] The server analyzes the relationships between the extracted entities and identifies the data flow.

[1277] 4. Analysis of contract type

[1278] The server analyzes the contract between the entities and identifies the required information.

[1279] 5. Generation of Operation Control Chart

[1280] The server uses D3.js to generate a visual traffic control diagram.

[1281] 6. Generate a risk checklist

[1282] The server stores the risk factors in MongoDB and generates a risk checklist.

[1283] 7. Emotion recognition

[1284] The server analyzes the user's emotions using the Microsoft Azure Emotion API.

[1285] 8. Optimizing Output

[1286] The server adjusts the content and display method of the operation control chart and risk checklist based on the user's emotions.

[1287] 9. Return to User

[1288] The server returns the optimized operation control chart and risk checklist to the user using React Native.

[1289] Specific examples

[1290] Example of user input

[1291] A dispatcher opens a smartphone app and types, "Vehicle A will depart at 8:00 AM, deliver a package to distribution center B, and then head to distribution center C."

[1292] 1. Text Analysis

[1293] The servers "Vehicle A," "Distribution Center B," and "Distribution Center C" are extracted.

[1294] 2. Relationship and data flow analysis

[1295] The relationships between the extracted entities are analyzed as "Vehicle A delivers cargo to distribution center B" and "Vehicle A heads to distribution center C."

[1296] 3. Analysis of contract type

[1297] The server identifies the "delivery contract between vehicle A and distribution center B."

[1298] 4. Generate operation control charts and risk checklists

[1299] The server uses D3.js to generate operational management diagrams and creates risk checklists based on risk factors stored in MongoDB.

[1300] 5. Emotion recognition and output optimization

[1301] The server analyzes the emotional state, such as "positive" or "negative," and highlights information such as "What to do if distribution center B is congested" in the checklist.

[1302] Prompt Sentence Examples

[1303] 1. "Please enter your flight schedule."

[1304] 2. "Vehicle A departs at 8:00 AM, delivers a package to distribution center B, and then heads to distribution center C."

[1305] 3. "I want to know what to do if Distribution Center B is busy."

[1306] In this way, operation managers can easily understand operation plans and risks, and provide optimal information according to the emotional state of the driver at the time.

[1307] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1308] Step 1:

[1309] Getting User Input

[1310] Users launch the smartphone application and enter their trip plan using a chat interface or voice input. In the latter case, the device converts the speech into text using the Google Cloud Speech-to-Text API, resulting in a text version of the trip plan.

[1311] Step 2:

[1312] Text data analysis

[1313] The server receives the acquired text data and analyzes it using the Google Cloud Natural Language API. During the analysis process, entities (vehicle, distribution center, time, etc.) are extracted from the text. The input is the text data from the user, and the output is a list of extracted entities.

[1314] Step 3:

[1315] Relationship and data flow analysis

[1316] The server analyzes the relationships between the extracted entities and identifies the interactions and data flows between them. The analysis yields relationships such as "Vehicle A delivers packages to distribution center B." The input is a list of entities, and the output is information indicating the relationships and data flows.

[1317] Step 4:

[1318] Contract type analysis

[1319] The server identifies the contract type between each entity based on the relationship and entity information. A contract type such as "Delivery contract between vehicle A and distribution center B" can be obtained. The input is relationship and entity information, and the output is contract type information.

[1320] Step 5:

[1321] Generate operation control charts

[1322] The server uses D3.js to generate a visual control diagram, which visually represents entities, their relationships, and data flows. The inputs are entity, relationship, and data flow information, and the output is the control diagram.

[1323] Step 6:

[1324] Generate a risk checklist

[1325] The server retrieves risk factors related to the operation plan from MongoDB and generates a risk checklist. The risk factors are linked based on the operation control diagram. The input is the operation control diagram and the output is the risk checklist.

[1326] Step 7:

[1327] emotion recognition

[1328] The server uses the Microsoft Azure Emotion API to analyze the user's emotional state based on their input, facial expression, and voice. The analysis results in the user's emotional state (positive, negative, or neutral). The input is the user's facial expression and voice data, and the output is information about their emotional state.

[1329] Step 8:

[1330] Output optimization

[1331] The server adjusts the content and display method of the operation control chart and risk checklist based on the analyzed user's emotional state. For example, if the emotion is negative, it highlights cautions and risk avoidance measures. The inputs are the emotional state, operation control chart, and risk checklist, and the output is optimized output.

[1332] Step 9:

[1333] Return to user

[1334] The server generates an optimized operation control chart and risk checklist and returns them to the user's smartphone using React Native. The input is the optimized operation control chart and risk checklist, and the output is the information displayed on the user's smartphone.

[1335] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1336] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1337] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1338] [Fourth embodiment]

[1339] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1340] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1341] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1342] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1343] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1344] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1345] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1346] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1347] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1348] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1349] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1350] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1351] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1352] This invention is a system that allows users to easily organize and visualize information necessary for planning services, proposing system development, planning seminars and exhibitions, etc. This system acquires input information from the user, analyzes that information, and automatically generates a business model diagram and risk checklist that includes the characters, their relationships, and data flows, and provides them to the user.

[1353] Program processing and natural language explanation

[1354] 1. Getting User Input

[1355] Users provide information for service planning and system development proposals through a web-based chat interface or voice input interface. For example, a user might input, "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[1356] 2. Text Analysis

[1357] The server analyzes the input text data using natural language processing (NLP) tools and extracts entities (characters) from within the text. In this case, "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified as entities.

[1358] 3. Extracting Relationships

[1359] The server analyzes the relationships between the extracted entities, identifying relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[1360] 4. Data flow analysis

[1361] The server analyzes the data flow between entities, for example, identifying data flow from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[1362] 5. Analysis of contract type

[1363] The server analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[1364] 6. Generate a Business Model

[1365] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[1366] 7. Generate a risk checklist

[1367] The server generates a risk checklist and a list of outstanding items to complement the business model.

[1368] 8. Return to User

[1369] The server provides the generated business model and risk checklist to the user, with the option to export it as a Google Slides file.

[1370] Specific examples

[1371] As a specific example, consider the case where information on a proposed supply chain management system is input.

[1372] scene:

[1373] A user enters, "Supplier A provides the raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[1374] Specific processing flow:

[1375] 1. Getting User Input

[1376] The user enters the above information through the chat interface.

[1377] 2. Text Analysis

[1378] The server analyzes the input information using natural language processing (NLP) technology and extracts entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[1379] 3. Extracting Relationships

[1380] The server analyzes the relationships between entities and identifies relationships such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to distributor C," and "Distributor C sells to consumers."

[1381] 4. Data flow analysis

[1382] The server analyzes the data flow between entities and determines that data flows from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[1383] 5. Analysis of contract type

[1384] The server identifies "a contract between Supplier A and Logistics Partner B," "a contract between Logistics Partner B and Distributor C," and "a contract between Distributor C and the Consumer."

[1385] 6. Generate a Business Model

[1386] The server generates a business model diagram based on these analysis results and outputs it in Google Slides format.

[1387] 7. Generate a risk checklist

[1388] The server generates a risk checklist and a list of outstanding items.

[1389] 8. Return to User

[1390] The server provides the generated business model diagram and risk checklist to the user, who can then use this information to efficiently plan services and propose system development.

[1391] This allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists, preventing oversights when creating frameworks and improving the accuracy and efficiency of service plans and system development proposals.

[1392] The processing flow will be explained below.

[1393] Step 1:

[1394] Users use a web-based chat interface or voice input interface to input information for service planning or system development proposals, including specific details such as "Supplier A will provide the raw materials, logistics partner B will handle the transportation, and sales agent C will sell the products to consumers."

[1395] Step 2:

[1396] The server acquires the information entered by the user, such as data entered through a chat interface or a voice input interface, and temporarily stores the data for further analysis.

[1397] Step 3:

[1398] The server analyzes the acquired text data using natural language processing (NLP) technology. This analysis extracts entities (characters) from the text. Specific entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified.

[1399] Step 4:

[1400] The server extracts relationships between the analyzed entities, such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to sales agent C," and "Sales agent C sells to consumers."

[1401] Step 5:

[1402] The server analyzes the data flow between entities. This analysis identifies which data flows from which entity to which entity. For example, data flows from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[1403] Step 6:

[1404] The server analyzes the contract type between each entity, and identifies contract types such as "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[1405] Step 7:

[1406] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[1407] Step 8:

[1408] The server generates a risk checklist and a list of outstanding issues to complement the business model diagram, thereby clarifying the risks and outstanding issues that users should consider when planning or proposing a project.

[1409] Step 9:

[1410] The server then provides the generated business model and risk checklist to the user, who can then download this information as a Google Slides file for use in meetings or to prepare proposals.

[1411] As a concrete example, let's consider the case of inputting information for a proposed supply chain management system. A user would enter through a chat interface, "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells the products to consumers." The server retrieves this information and uses NLP technology to analyze entities, their relationships, and data flows. It then automatically generates a business model diagram and risk checklist, which are presented to the user in Google Slides format.

[1412] Example 1

[1413] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1414] In conventional service planning and system development proposals, the task of organizing and visualizing the necessary information requires a great deal of time and effort. Furthermore, insufficient information organization and visualization increases the likelihood of oversights and misunderstandings, making risk management difficult. Therefore, there is a need for a system that can automatically analyze the information provided by users, automatically generate business model diagrams and risk checklists, and visualize the information efficiently and accurately.

[1415] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1416] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information using natural language processing technology, and means for automatically generating a business model diagram including entities, their relationships, and data flows, and a risk checklist based on the analyzed information. This makes it possible to efficiently and accurately analyze information provided by a user and quickly create a visually represented business model diagram and risk checklist.

[1417] A "user" is an entity that utilizes the system to provide information and receive visualized business models and risk checklists.

[1418] The "server" is a computer system that analyzes information obtained from users and generates business model diagrams and risk checklists.

[1419] "Information" refers to text and data related to service plans and system development proposals entered by users.

[1420] "Natural language processing technology" is a set of algorithms and techniques used to analyze input information and extract entities and relationships.

[1421] "Entity" refers to a character, organization, object, concept, etc. that is a major element in a business model diagram.

[1422] A "relationship" represents the interaction or association between entities, and clarifies their roles and connections in a business process.

[1423] "Data flow" refers to the flow of data exchanged between entities, and indicates the path along which information travels.

[1424] A "business model diagram" is a visual representation of entities, their relationships, and data flows.

[1425] A "risk checklist" is a list of potential risks and unresolved issues that is generated to complement a business model diagram.

[1426] "Output means" refers to a method or tool for providing the generated business model diagram and risk checklist to the user.

[1427] This invention is a system that allows users to easily organize and visualize information necessary for planning services, proposing system development, planning seminars and exhibitions, etc. This system acquires input information from the user, analyzes that information, and automatically generates a business model diagram and risk checklist that includes the characters, their relationships, and data flows, and provides them to the user.

[1428] Specifically, the following hardware and software are used:

[1429] Hardware: Servers and terminals (PCs, smartphones)

[1430] Software: Natural Language Processing (NLP) libraries (SpaCy, NLTK), relation extraction models, visualization tools (matplotlib, Graphviz), Google Slides

[1431] Users can use their devices to provide information for service planning and system development proposals through a web-based chat interface or voice input interface. For example, they can enter text such as "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[1432] The server receives the input text data and performs natural language processing using SpaCy and NLTK. First, it tokenizes the text data and then performs entity recognition to extract entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[1433] The server then uses the relationship extraction model to analyze the relationships between entities, such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[1434] The server then analyzes the data flow of the entities by referring to business rules and standard data flow diagram templates, identifying the data flow from "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[1435] The server also retrieves contract information from a pre-registered database and analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[1436] The server automatically generates a business model diagram based on these analysis results and outputs it in Google Slides format, which visually represents entities, their relationships, and data flows.

[1437] Additionally, the server generates risk checklists and backlogs, which are used to identify and manage risks in service planning and system development.

[1438] Finally, the server provides the generated business model and risk checklist to the user, including the option to provide them as downloadable files in Google Slides format, which the user can download and use via their device.

[1439] For example, if a user enters "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells products to consumers," the system will automatically analyze the entities, their relationships, and data flows, and based on that, generate a business model diagram and risk checklist, which it will provide to the user.

[1440] This allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists, preventing oversights when creating frameworks and improving the accuracy and efficiency of service plans and system development proposals.

[1441] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1442] Step 1:

[1443] A user uses a terminal to access a web-based chat interface or voice input interface and inputs the information required for service planning or system development proposals. The input information is sent to the server as text data. For example, a user might input, "Supplier A will provide the raw materials, and logistics partner B will be responsible for transportation." This text data becomes the input data for the next analysis step.

[1444] Step 2:

[1445] The server analyzes the received text data using a natural language processing tool (e.g., SpaCy or NLTK). First, the server tokenizes the text and then performs entity recognition. In this process, entity information such as "Supplier A," "Logistics Partner B," and "Sales Agent C" is extracted from the text data. The extracted entity information becomes the input data for the next relationship analysis step.

[1446] Step 3:

[1447] The server applies a relationship extraction model to analyze the relationships between the extracted entities. For example, it identifies relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers." The analyzed relationship information becomes input data for the next data flow analysis step.

[1448] Step 4:

[1449] The server analyzes the data flow between entities by referring to business rules and standard data flow diagram templates. For example, it identifies data flows such as "from supplier A to logistics partner B," "from logistics partner B to sales agent C," and "from sales agent C to consumers." The analyzed data flow information becomes input data for the next step, contract form analysis.

[1450] Step 5:

[1451] The server retrieves contract information from a pre-registered database and analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and the consumer." The analyzed contract type information becomes input data for the next business model diagram generation step.

[1452] Step 6:

[1453] The server automatically generates a business model diagram based on these analysis results. Specifically, it creates a diagram in Google Slides format that visually represents entities, relationships, data flows, and contract types. This generated business model diagram serves as input data for the next step, risk checklist generation.

[1454] Step 7:

[1455] The server generates a risk checklist and a list of unsorted items to complement the business model diagram. The generated risk checklist becomes input data for the next step of returning the item to the user.

[1456] Step 8:

[1457] The server provides the generated business model and risk checklist to the user, including the option to output them as Google Slides files with a download link. Users can download and use these materials via their devices.

[1458] (Application example 1)

[1459] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1460] In today's business environment, efficient organization and visualization of large amounts of information is required to quickly and accurately plan services and propose system development. However, manually organizing information and creating business model diagrams and risk checklists takes time and effort, so more efficient methods are needed. Furthermore, if users could perform these tasks using smartphones, business efficiency could be further improved.

[1461] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1462] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information, means for automatically generating a business model diagram including characters, their relationships, and data flows, and a risk checklist based on the analyzed information, means for generating prompt sentences to be input into the generative AI model, and means for providing the business model diagram and risk checklist to the user via a smartphone. This enables the user to use their smartphone to efficiently and quickly automatically generate the business model diagram and risk checklist required for service planning and system development proposals, preventing oversights.

[1463] "User input" refers to the information or data that a user provides to the system, from which the business model diagram and risk checklist are generated.

[1464] "Text analysis" is the process of extracting and analyzing entities such as characters and their relationships based on acquired text data using natural language processing technology.

[1465] "Actors" refers to the various actors within the business model, including suppliers, logistics partners, agents, and consumers.

[1466] "Relationships" refer to the mutual interests, contractual structures, data flows, etc. between the parties involved, and are one of the components of a business model diagram.

[1467] "Data flow" shows the flow of data between actors, and visually represents the movement of information in a supply chain.

[1468] A "business model diagram" is a diagram that visually represents the characters, their relationships, data flow, etc., and serves as the basis for service planning and system development proposals.

[1469] A "risk checklist" is a list of risks and matters to be considered that are identified based on the business model diagram, and is used to improve the accuracy and efficiency of proposals.

[1470] A "generative AI model" refers to an artificial intelligence model that generates business model diagrams and risk checklists based on user-entered information.

[1471] A "prompt sentence" is an input sentence that causes the generative AI model to extract and generate specific information, and is automatically generated by the system.

[1472] "Smartphone provision" refers to the means of providing the generated business model diagram and risk checklist to the user via a smartphone.

[1473] The present invention relates to a system that allows users to quickly and efficiently plan services and propose system development. This system acquires information entered by the user, analyzes it, automatically generates a business model diagram and a risk checklist, and provides them to the user via a smartphone.

[1474] The system is comprised of the following hardware and software:

[1475] 1. Hardware:

[1476] Smartphone (iOS / Android)

[1477] Cloud Server

[1478] 2. Software:

[1479] Google Cloud Natural Language API (Natural Language Processing)

[1480] Google BigQuery (data analysis)

[1481] Google Slides API (Business model generation)

[1482] Google Sheets API (risk checklist generation)

[1483] The specific processing flow of the system:

[1484] 1. Getting user input:

[1485] Users use the chat interface or voice input function of their smartphone to input the information needed to plan a service or propose a system development, for example, "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[1486] 2. Text Analysis:

[1487] The smartphone sends the acquired input information to a cloud server, which uses the Google Cloud Natural Language API to analyze the input information and extract the characters and their relationships. For example, it identifies entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[1488] 3. Relationship and data flow analysis:

[1489] The server uses Google BigQuery to analyze the relationships and data flows between the extracted entities, identifying relationships such as "Supplier A supplies to Logistics Partner B, who transports to Distributor C."

[1490] 4. Analysis of contract type:

[1491] In parallel with the relationship analysis, the contractual arrangements between each entity are also identified, such as "a contract between supplier A and logistics partner B."

[1492] 5. Generate a Business Model:

[1493] Based on the analysis results, the server uses the Google Slides API to generate a business model diagram, which is a visual representation of entities, their relationships, and data flows.

[1494] 6. Generate a risk checklist:

[1495] Additionally, the server uses Google Sheets API to generate a risk checklist and a list of outstanding items based on the business model.

[1496] 7. Return to User:

[1497] The generated business model diagram and risk checklist are provided to users via their smartphones, allowing them to instantly check the business model diagram and risk checklist on their smartphones, improving the accuracy and efficiency of service planning and system development proposals.

[1498] Use the following prompt as an example:

[1499] "Supplier A provides raw materials and logistics partner B handles transportation. Analyze this information and generate a business model diagram with actors, their relationships, and data flows, along with a risk checklist."

[1500] Based on such prompts, the generative AI model can automatically generate a business model diagram and a risk checklist, significantly improving the user's work efficiency.

[1501] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1502] Step 1:

[1503] Users use their smartphones to input the information necessary for service planning and system development proposals through a chat interface or voice input function. This information becomes the initial data for the system. For example, they might input, "The supplier will provide the raw materials, and the shipping company will be responsible for transportation." The input data is captured on the smartphone and sent to the cloud server.

[1504] Step 2:

[1505] The server analyzes the acquired user input using the Google Cloud Natural Language API. If the input data is in text format, the API performs syntactic analysis of the text and extracts entities (characters) in the sentence. Specifically, entities such as "supplier," "transport company," "sales agent," and "consumer" are identified. The data input is text data, and the output is a list of entities.

[1506] Step 3:

[1507] The server uses Google BigQuery to analyze the relationships and data flows between the extracted entities. For example, it clarifies relationships such as "Suppliers supply raw materials to transport companies, and transport companies send goods to sales agents." The input required for analysis is a list of entities, and the output is structured data that shows the relationships and data flows.

[1508] Step 4:

[1509] The server also simultaneously analyzes the contract type. After identifying the relationships between entities, it identifies the contract type between each entity, identifying, for example, a "contract between a supplier and a shipping company." The input required for this analysis is relationship data, and the output is structured data including the contract type.

[1510] Step 5:

[1511] Based on the analysis results, the server generates a business model using the Google Slides API. A business model visually represents entities, their relationships, and data flows. The input is the analyzed data, and the output is a business model in Google Slides format.

[1512] Step 6:

[1513] The server uses the Google Sheets API to generate a risk checklist and a list of outstanding items based on the business model. The risk checklist lists potential risks and items to be considered in the service plan. The input is the business model data, and the output is a checklist in Google Sheets format.

[1514] Step 7:

[1515] The server provides the generated business model diagram and risk checklist to the user via smartphone. The user can check and download this data on their smartphone. Ultimately, the user can use the generated materials to create service plans and system development proposals.

[1516] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1517] This invention relates to a system that acquires input information from users, analyzes it, and automatically generates a business model diagram including the characters, their relationships, and data flows, and also provides a risk checklist. Furthermore, by integrating an emotion engine that recognizes the user's emotions, it has the function of optimizing output based on the user's emotions.

[1518] Program processing and natural language explanation

[1519] 1. Getting User Input

[1520] Users use a web-based chat interface or voice input interface to input information for service planning and system development proposals. For example, a user might input, "Supplier A will provide the raw materials, logistics partner B will handle the transportation, and sales agent C will sell the products to consumers."

[1521] 2. Text Analysis

[1522] The server analyzes the input text data using natural language processing (NLP) tools and extracts entities (characters) from the text, such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[1523] 3. Extracting Relationships

[1524] The server analyzes the relationships between the extracted entities, for example, identifying relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Sales Agent C," and "Sales Agent C sells to consumers."

[1525] 4. Data flow analysis

[1526] The server analyzes the data flow between entities, for example, identifying data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Distributor C," and "Distributor C to Consumer."

[1527] 5. Analysis of contract type

[1528] The server analyzes the contract type between each entity. For example, it identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and sales agent C," and "a contract between sales agent C and a consumer."

[1529] 6. Generate a Business Model

[1530] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[1531] 7. Generate a risk checklist

[1532] The server generates a risk checklist and a list of outstanding items to complement the business model.

[1533] 8. User Emotion Recognition

[1534] The server analyzes the user's input information using an emotion engine to recognize the user's emotional state, which can include positive, negative, or neutral emotions.

[1535] 9. Optimize your output

[1536] The server optimizes the content and structure of the generated business model diagram and risk checklist based on the user's emotional state recognized by the emotion engine. For example, if the user's emotion is positive, the provided output will include more encouraging information, while if the user's emotion is negative, the server will emphasize information that supports problem solving.

[1537] 10. Return to User

[1538] The server provides users with optimized business models and risk checklists, which can then be downloaded as Google Slides files for use in meetings and proposals.

[1539] Specific examples

[1540] As a specific example, consider the case where a user inputs information for a proposed supply chain management system.

[1541] scene:

[1542] A user enters, "Supplier A provides the raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[1543] Specific processing flow:

[1544] 1. Getting User Input

[1545] The user enters the above information through the chat interface.

[1546] 2. Text Analysis

[1547] The server analyzes the input information using natural language processing (NLP) technology and extracts entities such as "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer."

[1548] 3. Extracting Relationships

[1549] The server analyzes the relationships between entities and identifies relationships such as "Supplier A supplies to logistics partner B," "Logistics partner B transports to sales agent C," and "Sales agent C sells to consumers."

[1550] 4. Data flow analysis

[1551] The server analyzes the data flow between entities and identifies data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Sales Agent C," and "Sales Agent C to Consumer."

[1552] 5. Analysis of contract type

[1553] The server identifies "a contract between supplier A and logistics partner B," "a contract between logistics partner B and distributor C," and "a contract between distributor C and the consumer."

[1554] 6. Generate a Business Model

[1555] The server generates a business model diagram based on these analysis results and outputs it in Google Slides format.

[1556] 7. Generate a risk checklist

[1557] The server generates a risk checklist and a list of outstanding items.

[1558] 8. User Emotion Recognition

[1559] The server uses an emotion engine to analyze the user's emotions and adjusts the output based on that information, for example, if the user is in a positive state.

[1560] 9. Optimize your output

[1561] The server optimizes the contents of the created business model diagram and risk checklist based on the user's feelings.

[1562] 10. Return to User

[1563] The server provides the user with an optimized business model diagram and a risk checklist, and the user can make effective proposals and plans based on these.

[1564] This system allows users to easily input information, and the system automatically generates and provides business model diagrams and risk checklists. Furthermore, by combining it with an emotion engine, the output is optimized to the user's current emotions, improving the accuracy and efficiency of proposals and plans.

[1565] The processing flow will be explained below.

[1566] Step 1:

[1567] Users use a web-based chat interface or voice input interface to input information for service planning and system development proposals, such as "Supplier A will provide the raw materials, and logistics partner B will handle the transportation."

[1568] Step 2:

[1569] The server acquires the information entered by the user, such as data entered through a chat interface or a voice input interface, and temporarily stores the data for further analysis.

[1570] Step 3:

[1571] The server analyzes the acquired text data using natural language processing (NLP) technology. This analysis extracts entities (characters) from the text. For example, "Supplier A," "Logistics Partner B," "Sales Agent C," and "Consumer" are identified as entities.

[1572] Step 4:

[1573] The server analyzes the relationships between the extracted entities, for example, identifying relationships such as "Supplier A supplies raw materials to Logistics Partner B," "Logistics Partner B transports goods to Sales Agent C," and "Sales Agent C sells goods to consumers."

[1574] Step 5:

[1575] The server analyzes data flows between entities. This analysis identifies which data flows from which entity to which entity. For example, data flows such as "raw material data moves from supplier A to logistics partner B," "product data moves from logistics partner B to sales agent C," and "sales data moves from sales agent C to consumers."

[1576] Step 6:

[1577] The server analyzes the contractual arrangements between each entity, for example, identifying a "supply contract between supplier A and logistics partner B," a "transportation contract between logistics partner B and distributor C," and a "sales contract between distributor C and a consumer."

[1578] Step 7:

[1579] The server automatically generates a business model diagram based on the analysis results, which visually represents entities, their relationships, and data flows, and can be output in formats such as Google Slides.

[1580] Step 8:

[1581] The server generates a risk checklist and a list of outstanding issues to complement the business model diagram, thereby clarifying the risks and outstanding issues that users should consider when planning or proposing.

[1582] Step 9:

[1583] The server analyzes the user's input information using an emotion engine to recognize the user's emotional state, which may include positive, negative, or neutral emotions.

[1584] Step 10:

[1585] The server optimizes the content and structure of the generated business model diagram and risk checklist based on the user's emotional state recognized by the emotion engine. For example, if the user's emotion is positive, the provided output will include more encouraging information, while if the user's emotion is negative, the server will emphasize information that supports problem solving.

[1586] Step 11:

[1587] The server provides users with optimized business models and risk checklists, which can then be downloaded as Google Slides files for use in meetings and proposals.

[1588] As a concrete example, when a user inputs information for a proposed supply chain management system, he / she inputs "Supplier A provides raw materials, logistics partner B is responsible for transportation, and sales agent C sells the products to consumers" in step 1. The server processes steps 2 to 10 and finally provides an optimized business model diagram and risk checklist.

[1589] Example 2

[1590] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1591] In conventional systems, it takes a great deal of time and effort for users to create business model diagrams and generate risk checklists. Furthermore, because optimization is not performed taking into account the user's emotional state, it is difficult to obtain output that meets the user's needs. A new technology was needed to solve these issues.

[1592] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1593] In this invention, the server includes: means for acquiring information input by a user; means for analyzing the acquired information using natural language processing technology; means for automatically generating a business model diagram including entities, their relationships, and data flows based on the analyzed information; means for generating a risk checklist that complements the business model diagram; means for recognizing the emotional state of the user from the acquired information; means for optimizing the contents of the business model diagram and the risk checklist based on the recognized emotional state; and means for outputting the automatically generated business model diagram and risk checklist. This enables a user to simply input information, and the server to automatically generate a business model diagram and a risk checklist, and further enables an optimized output to be obtained based on the user's emotional state.

[1594] "User" means an individual or organization that utilizes the system to enter and verify information.

[1595] A "server" is a computing device that receives input information from a user, analyzes it, and generates and outputs various data.

[1596] "Natural language processing technology" is a technology that enables the analysis, understanding, and generation of human language.

[1597] An "entity" is an individual element or subject that appears in a business model.

[1598] A "relationship" indicates the interaction and division of roles between entities.

[1599] "Data flow" refers to how data or information flows between entities.

[1600] A "business model" is a visual representation of entities, their relationships, and data flows.

[1601] A "risk checklist" is a list of potential risks and unresolved issues in a business model.

[1602] "Emotional state" refers to the emotional state or tendency that can be read from the user's input information.

[1603] "Output optimization" refers to adjusting the content and structure of the information being output based on the user's emotional state.

[1604] This invention relates to a system that acquires input information from users, analyzes it, and automatically generates a business model diagram including the characters, their relationships, and data flows, and also provides a risk checklist. Furthermore, by integrating an emotion engine that recognizes the user's emotions, it has the function of optimizing output based on the user's emotions.

[1605] 1. Getting User Input

[1606] Users use their devices to input information into a web-based chat interface or voice input interface, built with HTML, CSS, and JavaScript, using the SpeechRecognition API for voice input. For example, they might input, "Supplier A provides the raw materials, logistics partner B handles the transportation, and sales agent C sells the products to consumers."

[1607] 2. Text Data Analysis

[1608] The server receives input data from users and analyzes the text using NLP (Natural Language Processing) tools. Libraries such as SpaCy and NLTK are used for this analysis. The server is built in Python and uses web frameworks such as Flask for processing.

[1609] 3. Entity Extraction

[1610] The server uses natural language processing technology to extract entities (e.g., suppliers, logistics partners, sales agents, consumers, etc.) from the input text. The entity extraction is performed using SpaCy's Named Entity Recognition (NER) function.

[1611] 4. Relationship Analysis

[1612] The server analyzes the relationships between the extracted entities using predefined business rules and logic, such as "Supplier supplies to logistics partner," "Logistics partner transports to distributor," and "Distributor sells to consumer."

[1613] 5. Data Flow Analysis

[1614] The server analyzes the data flow between entities, identifying data flows such as "Supplier to Logistics Partner," "Logistics Partner to Distributor," and "Distributor to Consumer."

[1615] 6. Identification of contract type

[1616] The server analyzes the contract types between entities using predefined contract templates and rules to identify contracts such as a "supply contract between a supplier and a logistics partner," a "transportation contract between a logistics partner and a distributor," or a "sales contract between a distributor and a consumer."

[1617] 7. Generate a Business Model

[1618] The server automatically generates a business model diagram based on the analysis results, using Graphviz or Google Slides API, which visually represents entities, their relationships, and data flows.

[1619] 8. Generate a risk checklist

[1620] The server generates a risk checklist and a list of outstanding items to complement the business model. The items in the risk checklist are predefined and cover the risks associated with the business model.

[1621] 9. Recognition of user emotions using an emotion engine

[1622] The server uses an emotion engine to recognize the emotional state of the user input, using a Sentiment Analysis library (e.g., VADER, TextBlob) to identify positive, negative, neutral, and other emotional states.

[1623] 10. Output optimization

[1624] The server optimizes the content and structure of the output based on the user's emotional state as recognized by the emotion engine: in a positive emotional state, encouraging messages and success stories are emphasized, while in a negative emotional state, information that helps solve problems is emphasized.

[1625] 11. Return to User

[1626] The server provides users with optimized business models and risk checklists, which can be downloaded as Google Slides files for use in meetings and proposals.

[1627] Prompt Sentence Examples

[1628] Generate a business model diagram and risk checklist for the following scenario: "Supplier A provides raw materials, logistics partner B handles transportation, and distributor C sells the goods to consumers."

[1629] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1630] Step 1:

[1631] A user uses their device to input information into a web-based chat interface or voice input interface, for example, "Supplier A provides the raw materials, logistics partner B handles the transportation, and sales agent C sells the goods to the consumer." This input is sent to the server as text data.

[1632] Input: Text information entered by the user

[1633] Output: Text data sent to the server

[1634] Step 2:

[1635] The server analyzes the received text data using natural language processing (NLP) tools such as SpaCy and NLTK. The server understands the context and meaning of the text data and performs syntactic analysis.

[1636] Input: Text data sent by the user

[1637] Output: Parsed text data (including tokenization and parsing results)

[1638] What happens: The server parses the sentence structure using SpaCy's .parser() method.

[1639] Step 3:

[1640] The server extracts entities from the parsed text data using SpaCy's Named Entity Recognition (NER) function, for example, to identify "Supplier A," "Logistics Partner B," "Distributor C," and "Consumer."

[1641] Input: Parsed text data

[1642] Output: A list of extracted entities

[1643] What happens: The server uses SpaCy's .ner() method to extract the specific entity.

[1644] Step 4:

[1645] The server analyzes the relationships between the extracted entities using predefined business rules and logic. For example, it identifies relationships such as "Supplier A supplies to Logistics Partner B," "Logistics Partner B transports to Distributor C," and "Distributor C sells to consumers."

[1646] Input: A list of extracted entities

[1647] Output: Relationship identification results

[1648] What it does: The server uses a Python rule-based algorithm to identify relationships between entities.

[1649] Step 5:

[1650] The server analyzes the data flow between entities, identifying data flows such as "Supplier A to Logistics Partner B," "Logistics Partner B to Distributor C," and "Distributor C to Consumer."

[1651] Input: Entities and their relationships

[1652] Output: Data flow identification results

[1653] Specific operation: The server executes a data flow analysis algorithm to identify the flow of data between entities.

[1654] Step 6:

[1655] The server analyzes the contract types between each entity using predefined contract templates and rules to identify "supply contract between supplier A and logistics partner B," "transportation contract between logistics partner B and distributor C," and "sales contract between distributor C and consumer."

[1656] Input: Entities and their relationships, data flow

[1657] Output: Contract type identification result

[1658] Specific operation: The server identifies the contract type based on the contract template.

[1659] Step 7:

[1660] The server automatically generates a business model based on the analysis results, using Graphviz and Google Slides APIs. The generated business model visually represents entities, their relationships, and data flows.

[1661] Input: Identification of entities, relationships, data flows, and contract types

[1662] Output: Auto-generated business model diagram (Google Slides format)

[1663] Specific operation: The server generates a business model using Graphviz or Google Slides API.

[1664] Step 8:

[1665] The server generates a risk checklist that complements the business model diagram, utilizing predefined risk items and checklists.

[1666] Input: Business Model

[1667] Output: Risk checklist and list of outstanding items

[1668] Specific operation: The server generates a risk checklist based on predefined risk items.

[1669] Step 9:

[1670] The server uses an emotion engine to recognize the emotional state of the user input, using a Sentiment Analysis library (e.g., VADER, TextBlob) to identify positive, negative, neutral, and other emotional states.

[1671] Input: User input information

[1672] Output: User's emotional state (positive, negative, neutral)

[1673] Specific behavior: The server uses the Sentiment Analysis library to identify the emotional state.

[1674] Step 10:

[1675] The server optimizes the content and structure of the output based on the user's emotional state as recognized by the emotion engine. In a positive emotional state, encouraging messages and success stories are emphasized, while in a negative emotional state, information that helps solve problems is emphasized.

[1676] Input: User's emotional state, business model, risk checklist

[1677] Output: Optimized business model, risk checklist

[1678] What it does: The server runs an algorithm to adjust output content based on emotional state.

[1679] Step 11:

[1680] The server provides users with optimized business models and risk checklists, and the generated output can be downloaded as a Google Slides file for use in meetings or to prepare proposals.

[1681] Inputs: Optimized business model, risk checklist

[1682] Output: Downloadable Google Slides file

[1683] Specific operation: The server provides the generated file to the user's device and sends a download link.

[1684] (Application example 2)

[1685] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1686] In the operation management of autonomous vehicles, there is a problem that it is difficult to grasp the vehicle operation plan and data flow effectively and quickly and to carry out appropriate risk management.In addition, it is difficult to provide optimal information according to the emotions and situation of the operation manager, which reduces the accuracy of decision-making, and it is necessary to solve this problem.

[1687] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1688] In this invention, the server includes means for acquiring information input by a user, means for analyzing the acquired information, means for automatically generating a business process model diagram including characters, their relationships, and data flows, and a risk checklist based on the analyzed information, means for outputting the automatically generated business process model diagram and risk checklist, means for extracting entities from the acquired information and analyzing relationships and data flows, means for generating a traffic control diagram and risk checklist and optimizing output through emotion recognition, and means for recognizing user emotions and providing optimized output. This enables operations managers to easily understand operation plans and risks and provide optimal information according to their emotional state at the time.

[1689] A "user" is a person who operates the system and provides input information.

[1690] "Information" refers to the content of reports and instructions processed by the system, such as data and instructions entered by a user.

[1691] "Analysis" refers to the processing and analysis of acquired information to identify relevant entities, relationships, and data flows.

[1692] An "entity" refers to an element with a specific role, such as a character or object identified within the system.

[1693] A "relationship" represents an interaction or connectivity between entities.

[1694] "Data flow" refers to the flow of data or information between entities.

[1695] A "business model diagram" is a diagram that visually represents entities, their relationships, and data flows.

[1696] A "risk checklist" is a list of risks and precautions related to the business model diagram.

[1697] "Emotion recognition" is the process of identifying a user's emotional state from input information, facial expressions, voice, etc.

[1698] "Optimization" refers to adjusting the content and format of output based on analyzed information and perceived emotional state.

[1699] A specific system for implementing this invention is intended for operation management of autonomous vehicles, and is realized as an application installed on a smartphone.

[1700] System Overview

[1701] Hardware and software used

[1702] Natural Language Processing (NLP): Uses the Google Cloud Natural Language API.

[1703] Emotion recognition engine: Uses Microsoft Azure Emotion API.

[1704] Data visualization: Using D3.js.

[1705] Frontend: Uses React Native.

[1706] Backend: Uses Node.js, Express.js, and MongoDB.

[1707] Explanation of program processing

[1708] 1. Getting User Input

[1709] Users can input operation plans via chat or voice input through a smartphone application.

[1710] For voice input, it converts it to a string using the Google Cloud Speech-to-Text API.

[1711] 2. Text Data Analysis

[1712] The server analyzes the input text data using the Google Cloud Natural Language API and extracts entities.

[1713] 3. Relationship and data flow analysis

[1714] The server analyzes the relationships between the extracted entities and identifies the data flow.

[1715] 4. Analysis of contract type

[1716] The server analyzes the contract between the entities and identifies the required information.

[1717] 5. Generation of Operation Control Chart

[1718] The server uses D3.js to generate a visual traffic control diagram.

[1719] 6. Generate a risk checklist

[1720] The server stores the risk factors in MongoDB and generates a risk checklist.

[1721] 7. Emotion recognition

[1722] The server analyzes the user's emotions using the Microsoft Azure Emotion API.

[1723] 8. Optimizing Output

[1724] The server adjusts the content and display method of the operation control chart and risk checklist based on the user's emotions.

[1725] 9. Return to User

[1726] The server returns the optimized operation control chart and risk checklist to the user using React Native.

[1727] Specific examples

[1728] Example of user input

[1729] A dispatcher opens a smartphone app and types, "Vehicle A will depart at 8:00 AM, deliver a package to distribution center B, and then head to distribution center C."

[1730] 1. Text Analysis

[1731] The servers "Vehicle A," "Distribution Center B," and "Distribution Center C" are extracted.

[1732] 2. Relationship and data flow analysis

[1733] The relationships between the extracted entities are analyzed as "Vehicle A delivers cargo to distribution center B" and "Vehicle A heads to distribution center C."

[1734] 3. Analysis of contract type

[1735] The server identifies the "delivery contract between vehicle A and distribution center B."

[1736] 4. Generate operation control charts and risk checklists

[1737] The server uses D3.js to generate operational management diagrams and creates risk checklists based on risk factors stored in MongoDB.

[1738] 5. Emotion recognition and output optimization

[1739] The server analyzes the emotional state, such as "positive" or "negative," and highlights information such as "What to do if distribution center B is congested" in the checklist.

[1740] Prompt Sentence Examples

[1741] 1. "Please enter your flight schedule."

[1742] 2. "Vehicle A departs at 8:00 AM, delivers a package to distribution center B, and then heads to distribution center C."

[1743] 3. "I want to know what to do if Distribution Center B is busy."

[1744] In this way, operation managers can easily understand operation plans and risks, and provide optimal information according to the emotional state of the driver at the time.

[1745] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1746] Step 1:

[1747] Getting User Input

[1748] Users launch the smartphone application and enter their trip plan using a chat interface or voice input. In the latter case, the device converts the speech into text using the Google Cloud Speech-to-Text API, resulting in a text version of the trip plan.

[1749] Step 2:

[1750] Text data analysis

[1751] The server receives the acquired text data and analyzes it using the Google Cloud Natural Language API. During the analysis process, entities (vehicle, distribution center, time, etc.) are extracted from the text. The input is the text data from the user, and the output is a list of extracted entities.

[1752] Step 3:

[1753] Relationship and data flow analysis

[1754] The server analyzes the relationships between the extracted entities and identifies the interactions and data flows between them. The analysis yields relationships such as "Vehicle A delivers packages to distribution center B." The input is a list of entities, and the output is information indicating the relationships and data flows.

[1755] Step 4:

[1756] Contract type analysis

[1757] The server identifies the contract type between each entity based on the relationship and entity information. A contract type such as "Delivery contract between vehicle A and distribution center B" can be obtained. The input is relationship and entity information, and the output is contract type information.

[1758] Step 5:

[1759] Generate operation control charts

[1760] The server uses D3.js to generate a visual control diagram, which visually represents entities, their relationships, and data flows. The inputs are entity, relationship, and data flow information, and the output is the control diagram.

[1761] Step 6:

[1762] Generate a risk checklist

[1763] The server retrieves risk factors related to the operation plan from MongoDB and generates a risk checklist. The risk factors are linked based on the operation control diagram. The input is the operation control diagram and the output is the risk checklist.

[1764] Step 7:

[1765] emotion recognition

[1766] The server uses the Microsoft Azure Emotion API to analyze the user's emotional state based on their input, facial expression, and voice. The analysis results in the user's emotional state (positive, negative, or neutral). The input is the user's facial expression and voice data, and the output is information about their emotional state.

[1767] Step 8:

[1768] Output optimization

[1769] The server adjusts the content and display method of the operation control chart and risk checklist based on the analyzed user's emotional state. For example, if the emotion is negative, it highlights cautions and risk avoidance measures. The inputs are the emotional state, operation control chart, and risk checklist, and the output is optimized output.

[1770] Step 9:

[1771] Return to user

[1772] The server generates an optimized operation control chart and risk checklist and returns them to the user's smartphone using React Native. The input is the optimized operation control chart and risk checklist, and the output is the information displayed on the user's smartphone.

[1773] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1774] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1775] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1776] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1777] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1778] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1779] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1780] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1781] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1782] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1783] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1784] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1785] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1786] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1787] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1788] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1789] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1790] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1791] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1792] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1793] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1794] The following is further disclosed regarding the above embodiment.

[1795] (Claim 1)

[1796] A means for obtaining information input by a user;

[1797] means for analyzing the acquired information;

[1798] A means for automatically generating a business model diagram including the characters, their relationships, and data flows, and a risk checklist based on the analyzed information;

[1799] a means for outputting the automatically generated business model diagram and risk checklist;

[1800] A system including:

[1801] (Claim 2)

[1802] 10. The system according to claim 1, wherein the acquired information is analyzed using natural language processing techniques.

[1803] (Claim 3)

[1804] 10. The system of claim 1, providing multi-modal outputs.

[1805] "Example 1"

[1806] (Claim 1)

[1807] A means for obtaining information input by a user;

[1808] means for analyzing the acquired information using natural language processing technology;

[1809] a means for automatically generating a business model diagram including entities, their relationships, and data flows, and a risk checklist based on the analyzed information;

[1810] a means for outputting the automatically generated business model diagram and risk checklist;

[1811] A system including:

[1812] (Claim 2)

[1813] The system according to claim 1, wherein a pre-trained relationship extraction model is used when analyzing the entities and their relationships.

[1814] (Claim 3)

[1815] The system according to claim 1, which outputs the business model diagram in Google Slides format.

[1816] "Application Example 1"

[1817] (Claim 1)

[1818] A means for obtaining information input by a user;

[1819] means for analyzing the acquired information;

[1820] A means for automatically generating a business model diagram including the characters, their relationships, and data flows, and a risk checklist based on the analyzed information;

[1821] a means for outputting the automatically generated business model diagram and risk checklist;

[1822] a means for generating a prompt sentence to be input to the generative AI model;

[1823] means for providing the business model diagram and risk checklist to a user via a smartphone;

[1824] A system including:

[1825] (Claim 2)

[1826] 10. The system according to claim 1, wherein the acquired information is analyzed using natural language processing techniques.

[1827] (Claim 3)

[1828] 10. The system of claim 1, providing multi-modal outputs.

[1829] "Example 2: Combining Emotion Engines"

[1830] (Claim 1)

[1831] A means for obtaining information input by a user;

[1832] means for analyzing the acquired information using natural language processing technology;

[1833] means for automatically generating a business model diagram including entities, their relationships, and data flows based on the analyzed information;

[1834] means for generating a risk checklist that complements the business model diagram;

[1835] means for recognizing an emotional state of a user from the acquired information;

[1836] means for optimizing the content of a business model and a risk checklist based on the recognized emotional state;

[1837] a means for outputting the automatically generated business model diagram and risk checklist;

[1838] A system including:

[1839] (Claim 2)

[1840] The system of claim 1, further comprising: identifying relationships and data flows between entities based on the analyzed information.

[1841] (Claim 3)

[1842] The system according to claim 1, wherein the business model diagram is output in Google Slides format.

[1843] "Application example 2 when combining emotion engines"

[1844] (Claim 1)

[1845] A means for obtaining information input by a user;

[1846] means for analyzing the acquired information;

[1847] A means for automatically generating a business model diagram including the characters and their relationships and data flow, and a risk checklist based on the analyzed information;

[1848] means for outputting the automatically generated business model diagram and risk checklist;

[1849] means for extracting entities from the acquired information and analyzing relationships and data flows;

[1850] A means to generate operational control charts and risk checklists and optimize output through emotion recognition;

[1851] means for recognizing user emotions and providing optimized output;

[1852] A system including:

[1853] (Claim 2)

[1854] 10. The system according to claim 1, wherein the acquired information is analyzed using natural language processing techniques.

[1855] (Claim 3)

[1856] 10. The system of claim 1, providing multi-modal outputs. [Explanation of symbols]

[1857] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for obtaining information input by a user; means for analyzing the acquired information; A means for automatically generating a business model diagram including the characters, their relationships, and data flows, and a risk checklist based on the analyzed information; a means for outputting the automatically generated business model diagram and risk checklist; A system including:

2. The system of claim 1 , wherein the acquired information is analyzed using natural language processing techniques.

3. 10. The system of claim 1, providing multi-modal outputs.

Images