system

Abstract

We provide the system. [Solution] The present invention relates to a system that centrally collects electronic files of business documents and division of responsibilities held by each department within an organization, performs text analysis and summarization using generative AI, automatically extracts and summarizes the business content, scope of responsibility, business flow, deliverables, and related departments of each department, and further analyzes the similarity and relationship of business content between departments and visualizes it in a graph structure. This allows for an intuitive understanding of overlapping tasks and the need for collaboration, thereby achieving improved business efficiency, cost reduction, faster information transmission, and optimized task requests.

Description

TECHNICAL FIELD

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

BACKGROUND ART

[0002] Patent Document 1 discloses a persona chatbot control method executed by at least one processor, the method comprising the steps of: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence associated with a description relating to a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

PRIOR ART DOCUMENTS

PATENT DOCUMENTS

[0003]

PATENT DOCUMENT 1

SUMMARY OF THE INVENTION

PROBLEMS TO BE SOLVED BY THE INVENTION

[0004] The problem that this invention aims to solve is that within an organization, the business documents and division of responsibilities held by each department are not sufficiently visible, making it difficult for other departments to understand the business content and scope of responsibilities of each department. Furthermore, when departments are located in different headquarters or divisions, the connections and overlaps in work between departments cannot be grasped, resulting in overlapping work, inefficient work requests, increased costs due to lack of coordination, and delays in information transmission. Traditionally, understanding the business content of each department required individually reviewing documents or directly contacting the person in charge, making it difficult to grasp the overall business structure and relationships of the organization. In particular, in large organizations spanning multiple headquarters and divisions, the problem of overlapping work content and the existence of similar tasks going unnoticed, leading to the normalization of wasteful work and inefficient work requests, has become apparent. In addition, when visualizing business content and analyzing relationships is done manually, it requires a great deal of time and effort to review and organize vast amounts of documents, making practical implementation difficult. Therefore, the problem that this invention aims to solve is to automatically collect and analyze business documents and work assignments from each department, use generative AI to summarize work content and analyze relationships, and intuitively and comprehensively visualize the connections and overlaps in work between departments, thereby improving overall organizational efficiency, reducing costs, accelerating information transmission, and optimizing work requests. [Means for solving the problem]

[0005] The means for solving the problems of the present invention is to configure a system comprising a business data collection unit, a text analysis unit, and a business relationship visualization unit. First, the business data collection unit centrally collects electronic files of business documents and job descriptions from multiple departments within the organization and stores them in storage. Next, the text analysis unit converts the stored electronic files into text data using optical character recognition and text extraction processing, and performs natural language processing using generative AI to extract the business content, scope of responsibility, characteristic keywords, etc. for each department, and further automatically generates explanatory text summarizing the business content of each department. As a result, the business content of each department is stored in the database in a concise and easy-to-understand form. Furthermore, the business relationship visualization unit vectorizes the business content data of each department extracted by the text analysis unit, performs similarity calculation and clustering using generative AI, and analyzes the overlap and relationships of business between departments. The analysis results are visualized as a graph structure, and users can search and view the work content of each department and its relationships with other departments on a web interface. This allows for an intuitive and comprehensive understanding of the overall organizational structure, connections between tasks, and areas of overlap, thereby enabling improved operational efficiency, cost reduction, and faster information dissemination. [Brief explanation of the drawing]

[0006] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0007] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0008] First, let's explain the terminology used in the following explanation.

[0009] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0010] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0011] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of the non-volatile storage device include a flash memory (SSD (Solid State Drive)), a magnetic disk (for example, a hard disk), or a magnetic tape and the like.

[0012] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of 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), or Bluetooth (registered trademark) and the like.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Further, in the present specification, when three or more matters are expressed in combination by "and / or", the same concept as that for "A and / or B" is applied.

[0014] [First Embodiment]

[0015] FIG. 1 illustrates an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 includes a server.

[0017] 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 the "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, RAM 30, and 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), and the like.

[0018] 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, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, camera 42, and communication I / F 44 are also connected to the bus 52.

[0019] 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 of an indicator (for example, a pen, a finger, or the like), thereby receiving user input via the contact of the indicator. The microphone 38B detects a user's voice, thereby receiving voice-based user input. A control unit 46A in the processor 46 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, a specific processing unit 290 acquires the data indicating the user input.

[0020] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0022] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0024] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0026] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0027] (Example 1)

[0028] The flow of a specific process in Example 1 will now be described. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0029] (Embodiments for carrying out the present invention)

[0030] Embodiments of the present invention will be described in more detail. The system of the present invention consists of a server and a terminal, with the server side implementing a business data collection unit, a text analysis unit, a business relationship visualization unit, a database management unit, and a learning / update management unit, and the terminal side implementing a user interface unit, a file upload unit, and a feedback input unit.

[0031] First, the Business Document Collection Department will provide a dedicated web interface accessible from each department's terminal, allowing them to upload electronic files of business documents and work assignments. For example, a sales representative could upload sales reports (Word files), customer lists (Excel files), and contract templates (PDF files), while a legal representative could upload contract review flows (PowerPoint files), compliance manuals (PDF files), and litigation records (Word files). Furthermore, an accounting representative could upload financial statements (Excel files), payment management sheets (Word files), and tax returns (PDF files), with a variety of file formats and contents expected depending on the department. Image files (JPEG, PNG, etc.) and scanned data will also be supported, allowing for the uploading of handwritten business flow diagrams and scanned paper documents, for example. Uploaded files will be automatically categorized and saved to the server's storage, and metadata such as department name, file type, upload date and time, and responsible person information will be recorded simultaneously.

[0032] Next, the text analysis unit operates on the server and processes the stored electronic files sequentially. For PDF and image files, an optical character recognition engine is used to convert them into text data, while for files such as Word, Excel, and PowerPoint, a dedicated text extraction module extracts the content. For example, from a PDF contract template, headings and body text for each clause are extracted; from an Excel customer list, cell information such as customer name, contact person, and transaction details are extracted; and from a PowerPoint business flow diagram, process names and explanatory texts are extracted. The extracted text data is input into a natural language processing engine powered by generative AI. The generative AI performs a combination of processes, such as text structure analysis, keyword extraction, part-of-speech analysis, contextual understanding, summary generation, and semantic clustering. From sales department documents, business tasks such as "new customer acquisition," "existing customer follow-up," "quotation creation," "contract signing," "sales meeting material creation," and "sales progress management" are extracted, while from legal department documents, tasks such as "contract review," "legal research," "litigation support," "internal regulations development," and "compliance training" are extracted. The generative AI summarizes the work of each department based on the extracted information, automatically generating explanatory text such as, "The sales department is responsible for a wide range of sales activities, including acquiring new customers, following up with existing customers, creating quotations, concluding contracts, preparing materials for sales meetings, and managing sales progress." Furthermore, it generates more detailed explanatory text, including the purpose of the work, deliverables, characteristics of the workflow, and the names of other related departments. For example, it can explain that, "The legal department is responsible for contract review, legal research, litigation support, development of internal regulations, and compliance training, and manages risks in cooperation with the sales and general affairs departments."

[0033] The generated summaries and explanatory texts of each department's work are stored as structured data by the database management unit on the server, along with attribute information such as department name, work content, scope of responsibility, keywords, workflow, deliverables, related departments, and links to original documents. For example, the "Quotation Creation" task of the sales department is associated with attributes such as "Sales Department," "Quotation Creation," "New Customer," "Existing Customer," "Quotation," "Sales Meeting," and "Contract Signing." This then serves as the basic data for the search and visualization processes described later.

[0034] The business relationship visualization unit operates on a server and vectorizes the business content data of each department extracted and summarized by the text analysis unit. The generative AI uses natural language processing technology to convert each business content into a numerical vector and calculates the similarity of business content by calculating the distance between vectors of similar business content, such as "new customer acquisition" and "new market research". Furthermore, the generative AI uses clustering and network analysis methods to analyze the overlap and relationships of business content between departments. For example, if the sales department and the marketing department have a high degree of similarity in areas such as "market research" and "customer analysis", it can be detected that the business content of both departments overlaps. Also, if the accounting department and the general affairs department have a high degree of relatedness in areas such as "payment management" and "expense reimbursement", it can be indicated that business collaboration is necessary.

[0035] The analysis results are visualized as a graph structure. Each node represents a department, and the edges between nodes indicate the similarity and strength of the relationship between their work. For example, nodes with high similarity are connected with thick lines and dark colors, while those with low relevance are connected with thin lines and light colors. Furthermore, the generative AI can dynamically change the size and color of the nodes according to the degree of overlap and strength of the relationship between their work. For example, departments with high overlap can be displayed with larger nodes, and departments with strong relationships can have their edges highlighted, enabling intuitive visualization.

[0036] On the terminal side, the user interface operates and communicates with the server via a web browser. Users can search by department name, job description, keywords, etc., and a list of relevant departments and related departments is displayed. For example, searching for "contract creation" will display departments responsible for that task, such as the sales department, legal department, and general affairs department, and users can also view summaries and detailed explanations of each department's work. In addition, on the graph visualization screen, when a user clicks on a specific department or job description, connections and overlaps between related departments are dynamically highlighted. For example, selecting the sales department highlights the connections between the sales department and related departments such as the marketing and accounting departments, allowing users to quickly grasp the overlaps and need for collaboration.

[0037] Furthermore, generative AI can continuously learn from user feedback and newly added business documents, improving the accuracy of its business content summaries and relevance analyses. For example, if a user enters a comment such as "This task actually involves collaboration with other departments," the generative AI can incorporate that information and reflect it in subsequent analyses and visualizations. Also, if a new department is added or business content changes, the generative AI can automatically analyze the latest information, keeping the overall business structure of the system constantly up-to-date.

[0038] As described above, in the embodiments of the present invention, the server centrally performs the collection of business data, text analysis, analysis of business relationships, and visualization, and by utilizing generative AI step by step, it becomes possible to automatically extract and summarize the business content of each department from a vast and diverse amount of business data, and to visualize the overlap and relationships of work between departments with high accuracy and in an intuitive manner. On the terminal side, an interface is provided that allows users to easily search, view, and visualize, enabling improved operational efficiency, cost reduction, faster information transmission, and optimization of work requests across the entire organization. For example, the system of the present invention can be used for various business improvement measures such as considering the consolidation of operations during organizational restructuring, reviewing work request flows, optimizing work distribution, strengthening inter-departmental collaboration, and reducing redundant work.

[0039] (System Configuration)

[0040] The system according to this embodiment comprises a business data collection unit, a text analysis unit, a business relevance visualization unit, a database management unit, a learning and update management unit, a user interface unit, a file upload unit, and a feedback input unit. The business data collection unit centrally receives electronic files in various formats, such as Word files, Excel files, PDF files, PowerPoint files, and image files, from terminals used by personnel in each department, including sales reports, customer lists, contract templates, legal compliance manuals, litigation records, financial statements, payment management sheets, tax returns, business flow diagrams, and scanned data of paper documents. It automatically classifies and saves these files to the server-side storage and adds metadata such as department name, file type, upload date and time, and personnel information. For example, it is conceivable that a sales department employee uploads sales meeting materials and sales progress management sheets, a legal department employee uploads internal regulations development materials and compliance training materials, and an accounting department employee uploads monthly financial statements and expense reports. The text analysis unit sequentially processes various electronic files stored by the business data collection unit. For PDF and image files, it uses an optical character recognition engine to convert them into text data. For files such as Word, Excel, and PowerPoint, it extracts the content using a dedicated text extraction module and inputs the extracted text data into the generative AI. The generative AI uses prompt statements such as, "Extract the business content, scope of responsibility, purpose, deliverables, frequently occurring keywords, and workflow from this document, and create a summary for each department," "Summarize the contents of this document clearly as a division of labor for each department," "List the business content of each department from this group of files, and organize the purpose and deliverables for each task," and "Extract tasks related to other departments from the business documents of this department, and group highly related tasks." The generative AI then executes a combination of processes, including text structure analysis, keyword extraction, part-of-speech analysis, contextual understanding, summary generation, and semantic clustering.For example, the AI ​​extracts business tasks such as "new customer acquisition," "existing customer follow-up," "quote creation," "contract signing," "sales meeting material creation," and "sales progress management" from the sales department's materials, "contract review," "legal research," "litigation support," "internal regulations development," and "compliance training" from the legal department's materials, and "invoice issuance," "payment management," "financial closing," "tax filing," and "expense reimbursement" from the accounting department's materials. Based on the extracted information, the generation AI summarizes the work of each department and automatically generates detailed explanatory text, such as "The sales department is responsible for a wide range of sales activities including new customer acquisition, existing customer follow-up, quotation creation, contract signing, sales meeting material creation, and sales progress management," "The legal department is responsible for contract review, legal research, litigation support, internal regulations development, and compliance training, and manages risks in cooperation with the sales and general affairs departments," and "The accounting department is responsible for a series of accounting tasks from invoice issuance to payment management, financial closing, tax filing, and expense reimbursement, and each task has different flows on a monthly, quarterly, and annual basis." The Business Relationship Visualization Department vectorizes the business content data of each department extracted and summarized by the Text Analysis Department, and uses generative AI and natural language processing technology to convert each business content into a numerical vector. For example, it calculates the similarity of business content by calculating the distance between vectors of similar business content such as "new customer acquisition" and "new market research." Furthermore, it uses clustering and network analysis methods to analyze the overlap and relationships of business content between departments. For example, if the Sales Department and the Marketing Department have a high degree of similarity in "market research" or "customer analysis," it detects that the business content of both departments overlaps. If the Accounting Department and the General Affairs Department have a high degree of relatedness in "payment management" or "expense reimbursement," it indicates that business collaboration is necessary. The analysis results are visualized as a graph structure, where nodes represent each department, and the edges between nodes indicate the similarity and strength of the relationship between business content. Nodes with high similarity are connected with thick lines and dark colors, while those with low relatedness are connected with thin lines and light colors. Departments with high overlap are displayed with larger nodes, and departments with strong relatedness have prominent edges, achieving intuitive visualization.The Database Management Department stores attribute information such as summaries and explanations of each department's work, department names, work content, scope of responsibility, keywords, workflows, deliverables, related departments, and links to original documents as structured data. For example, the "Quotation Creation" task in the Sales Department is associated with attributes such as "Sales Department," "Quotation Creation," "New Customers," "Existing Customers," "Quotation," "Sales Meeting," and "Contract Signing," while the "Contract Review" task in the Legal Department is associated with attributes such as "Legal Department," "Contract Review," "Contract," "Legal Research," "Sales Department," and "Risk Management." The Learning and Update Management Department continuously learns from user feedback and newly added business documents to improve the accuracy of summarizing work content and analyzing relevance using generative AI. For example, if a user enters a comment such as "This task is actually linked to another department," that information is incorporated and reflected in subsequent analyses and visualizations. It also automatically analyzes the latest information when new departments are added or work content changes, keeping the overall business structure of the system constantly up-to-date. The user interface unit operates on the terminal side, communicating with the server via a web browser. Users can search by department name, job description, keywords, etc., and a list of relevant departments and related departments is displayed. For example, searching for "contract creation" will display departments responsible for that task, such as the sales department, legal department, and general affairs department. Users can view summaries and detailed explanations of each department's work. In the graph structure visualization screen, clicking on a specific department or job description dynamically highlights connections and overlaps between related departments. Selecting the sales department highlights the connections between sales and related departments such as the marketing and accounting departments. The file upload unit handles file transmission from the terminal, enabling bulk uploads of multiple files per department, intuitive drag-and-drop operation, automatic classification by file type, and management of upload history. For example, the sales department can upload monthly sales reports in bulk, or the legal department can add new legal compliance documents. The feedback input section provides a function that allows users to input comments and suggestions for corrections regarding the analysis results of work content and relationships. For example, it can reflect information such as "This task is actually coordinated with the accounting department" or "The scope of responsibility for this task has changed" in the system.Specific examples of prompts to be fed into the generating AI include: "Based on the business documents of this department, extract the business content, objectives, deliverables, scope of responsibility, and related departments, and summarize them clearly," "List the business content of each department from this set of files, and organize the objectives and deliverables for each business," "Based on the content of this document, extract the business related to other departments, and group the highly related business," and "Calculate the similarity between the business content of this department and the business content of other departments, and visualize the need for duplication and collaboration." The system of this embodiment achieves visualization of the business content of the entire organization, detection of duplication and collaboration in business, business efficiency, cost reduction, faster information transmission, and optimization of business requests by having each of these parts work together.

[0041] (Implementation Steps)

[0042] Step 1: Collect and upload business documents Personnel in each department can upload various types of electronic files, such as sales reports, customer lists, contract templates, compliance manuals, litigation records, financial statements, payment management sheets, tax returns, business process diagrams, and scanned paper documents, using a dedicated web interface from their terminals. During upload, metadata such as department name, file type, upload date and time, and person in charge information are also entered and automatically categorized and saved to the server's storage. For example, the sales department might upload monthly sales meeting materials and sales progress reports in bulk, the legal department might add new compliance documents and litigation records, and the accounting department might upload monthly financial statements and expense reports.

[0043] Step 2: Text conversion and pre-processing of business documents For various electronic files stored on the server, PDF and image files are converted into text data using an optical character recognition engine, while files such as Word, Excel, and PowerPoint are extracted using a dedicated text extraction module. For example, headings and body text for each clause can be extracted from a PDF contract template, customer names and transaction details from an Excel customer list, and process names and explanatory text from a PowerPoint business process diagram.

[0044] Step 3: Extracting and summarizing business content using generation AI. The system inputs digitized data into a generation AI, extracts job descriptions, responsibilities, objectives, deliverables, frequently occurring keywords, and workflows, and creates summary sentences for each department. Specific examples of prompts include: "Extract job descriptions, responsibilities, objectives, deliverables, frequently occurring keywords, and workflows from this document and create summary sentences for each department," "Summarize the contents of this document clearly as a division of labor for each department," "List the department's job descriptions from this set of files and organize the objectives and deliverables for each job," and "Extract tasks related to other departments from this department's business documents and group highly related tasks." For example, it might extract tasks such as "new customer acquisition," "existing customer follow-up," "quotation creation," and "contract signing" from the sales department's documents, "contract review," "legal research," and "litigation support" from the legal department's documents, and "invoice issuance," "payment management," and "financial closing" from the accounting department's documents.

[0045] Step 4: Storing in the business content database The AI ​​generates and summarizes attribute information for each department, such as the work content, responsibilities, keywords, workflow, deliverables, related departments, and links to original documents, and stores this information as structured data in a database on the server. For example, the "quote creation" task in the sales department is associated with attributes such as "sales department," "quote creation," "new customer," "existing customer," "quote," "sales meeting," and "contract signing."

[0046] Step 5: Business relevance analysis and vectorization using generative AI The system uses AI to generate data on the work content of each department stored in a database, converts it into numerical vectors using natural language processing technology, calculates the similarity between work content, and analyzes overlaps and relationships between departments' work using clustering and network analysis techniques. Specific examples of prompts include: "Vectorize the work content of each department and calculate the similarity of the work content," "Calculate the similarity between the work content of this department and that of other departments, and visualize the need for overlap and collaboration," and "Group the work content according to the strength of overlap and relevance, and extract departments with high relevance." For example, if the sales department and the marketing department have a high similarity in "market research" and "customer analysis," it will detect that their work overlaps, and if the accounting department and the general affairs department have a high relevance in "payment management" and "expense reimbursement," it will indicate that collaboration is necessary.

[0047] Step 6: Visualization and display of business relevance graphs Based on the analysis results, a graph structure is generated where nodes represent departments and edges represent the similarity and strength of the relationship between their work content. Nodes with high similarity are connected with thicker lines and darker colors, departments with high overlap are displayed with larger nodes, and departments with strong relationships are highlighted with more prominent edges, enabling intuitive visualization. Users can click on specific departments or work content on the web interface to dynamically highlight connections and overlaps between related departments.

[0048] Step 7: User Search, Feedback, and Learning Users can search for department names, job descriptions, keywords, etc., via a web interface from their terminals. A list of relevant departments and related departments is displayed, and summaries and detailed explanations of each department's work are available. Furthermore, through the feedback input section, users can input comments and correction suggestions such as "This task actually involves collaboration with other departments" or "The scope of responsibility for this task has changed." The learning and update management department then incorporates this information into the generating AI, which is used for future analysis and visualization, keeping the overall business structure of the system constantly up-to-date.

[0049] (Specific use cases)

[0050] For example, consider a scenario in a large organization consisting of multiple headquarters or departments where each department uploads electronic files of business documents and work assignments that it creates and manages on a daily basis to the system of the present invention. The sales department uploads sales reports, customer lists, quotation templates, sales meeting materials, etc. The legal department uploads contract review flows, legal compliance manuals, litigation response records, internal regulations development materials, etc. The accounting department uploads financial statements, payment management sheets, tax returns, expense reports, etc. The general affairs department uploads personnel regulations, welfare materials, internal event operation manuals, equipment management ledgers, etc. These files include a variety of formats such as Word files, Excel files, PDF files, PowerPoint files, image files, and scanned data, and each file is assigned metadata such as department name, file type, upload date and time, and person in charge information.

[0051] On the server side, these files are converted into text data using optical character recognition and text extraction modules, and a generating AI extracts information such as work content, scope of responsibility, objectives, deliverables, frequently occurring keywords, and workflow. For example, from the sales department's documents, work tasks such as "new customer acquisition," "existing customer follow-up," "quotation creation," "contract signing," "sales meeting material creation," and "sales progress management" are extracted, while from the legal department's documents, tasks such as "contract review," "legal research," "litigation support," "internal regulations development," and "compliance training" are extracted. Based on this information, the generating AI summarizes the work content of each department and automatically generates detailed explanatory text such as, "The sales department is responsible for a wide range of sales activities including new customer acquisition, existing customer follow-up, quotation creation, contract signing, sales meeting material creation, and sales progress management," and "The legal department is responsible for contract review, legal research, litigation support, internal regulations development, and compliance training, and manages risks in cooperation with the sales and general affairs departments." Specific examples of prompts to be fed into the generating AI include: "Extract the job content, scope of responsibility, objectives, deliverables, frequently occurring keywords, and workflow from this document, and create a summary for each department," "List the job content of each department from this set of files, and organize the objectives and deliverables for each job," and "Extract the tasks related to other departments from the business documents of this department, and group the highly related tasks."

[0052] Attribute information such as the work content, scope of responsibility, keywords, workflow, deliverables, related departments, and links to original documents for each department, extracted and summarized by the generating AI, is stored as structured data in a database on the server. For example, the "quote creation" task of the sales department is associated with attributes such as "sales department," "quote creation," "new customer," "existing customer," "quote," "sales meeting," and "contract signing," while the "contract review" task of the legal department is associated with attributes such as "legal department," "contract review," "contract," "legal research," "sales department," and "risk management."

[0053] Next, the generating AI converts the business content data of each department stored in the database into numerical vectors using natural language processing technology and calculates the similarity between business content. For example, it calculates the distance between vectors of similar business content such as "new customer acquisition" and "new market research," and uses clustering and network analysis methods to analyze the overlap and relationships between departmental business content. Specific examples of prompts to be fed into the generating AI include: "Vectorize the business content of each department and calculate the similarity of the business content," "Calculate the similarity between the business content of this department and the business content of other departments, and visualize the overlap and need for collaboration," and "Group the business content according to the strength of overlap and relationship, and extract departments with high relevance."

[0054] The analysis results are visualized as a graph structure where nodes represent each department and edges represent the similarity or strength of the relationship between their work. For example, if the sales department and the marketing department have a high degree of similarity in "market research" or "customer analysis," it detects that the work of both departments overlaps. If the accounting department and the general affairs department have a high degree of relationship in "payment management" or "expense reimbursement," it indicates that collaboration between their work is necessary. High similarity is indicated by thick lines or dark colors connecting the nodes, departments with high overlap are displayed with larger nodes, and departments with strong relationships have prominent edges, achieving an intuitive visualization.

[0055] Users can search for department names, job descriptions, keywords, etc., via a web interface from their terminals. A list of relevant departments and related departments is displayed, and summaries and detailed explanations of each department's work are available. Furthermore, through the feedback input section, users can input comments and correction suggestions such as "This task actually involves collaboration with other departments" or "The scope of responsibility for this task has changed." The learning and update management department then incorporates this information into the generating AI, which is used for future analysis and visualization, ensuring that the overall business structure of the system is always up-to-date.

[0056] These use cases enable the visualization of operations across the entire organization, the identification of overlapping or overlapping tasks, improved operational efficiency, cost reduction, faster information dissemination, and optimization of work requests.

[0057] (Application Example 1) The flow of a specific process in Application Example 1 will be explained below. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] (Embodiments for carrying out the present invention)

[0059] Embodiments of the present invention will be described in more specific and detail. The system of the present invention is composed of multiple functional units, such as an urban management information collection unit, a business analysis unit, a business relationship visualization unit, a database management unit, a user interface unit, a feedback management unit, and a learning and update management unit, in order to collect, analyze, and visualize business information from various departments involved in urban management in a cross-sectional and automatic manner.

[0060] First, the Urban Management Information Collection Department will centrally receive a variety of electronic files from terminals used by personnel in all departments involved in urban management, including administrative departments, infrastructure management departments, traffic management departments, disaster prevention departments, education departments, medical departments, environmental management departments, welfare departments, urban planning departments, water and sewage departments, and energy management departments. These files will include business documents, operation manuals, departmental documents, field reports, plans, inspection records, disaster response manuals, resident response records, event management materials, equipment management ledgers, educational program materials, medical collaboration records, and environmental monitoring reports. For example, the traffic management department might upload signal control manuals, road maintenance plans, traffic congestion countermeasure reports, and emergency vehicle guidance procedures; the infrastructure management department might upload water and sewage inspection records, power supply plans, equipment maintenance manuals, and disaster recovery procedures; the education department might upload school management manuals, environmental education programs, and community collaboration event materials; and the medical department might upload emergency transport records, medical collaboration protocols, and infectious disease control manuals. A wide variety of business documents are expected from each department. The supported file formats are diverse, including Word files, Excel files, PDF files, PowerPoint files, image files, and scanned data. When files are uploaded, metadata such as department name, file type, creation date, and person in charge is automatically added, and the files are categorized and saved on the server's storage. For example, the water and sewage department uploads monthly inspection records as Excel files, the disaster response department uploads evacuation center operation manuals as PDFs, the environmental management department uploads air quality monitoring reports as Word files, and the education department uploads disaster prevention education programs as PowerPoint files.

[0061] Next, the Business Analysis Department sequentially processes various electronic files stored by the Urban Management Information Collection Department. PDF files and image files are converted into text data using an optical character recognition engine, while Word, Excel, and PowerPoint files have their contents extracted using a dedicated text extraction module. For example, various response procedures and contact systems are extracted from PDF disaster response manuals, cell information such as equipment name, inspection date, person in charge, and inspection results is extracted from Excel equipment management ledgers, and event name, date, operational structure, and cooperating departments are extracted from PowerPoint regional event materials. The extracted text data is input into a generative AI. The generative AI is given prompts such as, "Extract the work content, scope of responsibility, purpose, deliverables, frequently occurring keywords, work flow, and related departments from this document, and create a summary for each department," "List the work content for each department from this group of files, and organize the purpose and deliverables for each task," and "Extract tasks related to other departments from this department's work materials, and group highly related tasks." Generative AI extracts tasks such as "traffic signal control," "road maintenance," "traffic congestion countermeasures," and "emergency vehicle guidance" from documents in the traffic management department, "water and sewage inspection," "power supply management," "equipment maintenance," and "disaster recovery" from documents in the infrastructure management department, and "school management," "environmental education," "community event management," and "disaster prevention education" from documents in the education department. Furthermore, it automatically extracts the purpose, deliverables, workflow, and related departments for each task, and automatically generates summary sentences such as "traffic signal control is the responsibility of the traffic management department, and in emergencies, they cooperate with the disaster prevention and police departments" and "disaster recovery is led by the infrastructure management department, and they cooperate with the water and sewage departments and the energy management department." For example, emergency transport records from the medical department extract tasks such as "emergency transport," "patient information management," "medical institution coordination," and "disaster medical response," and resident response records from the welfare department extract tasks such as "elderly support," "disability welfare," "public assistance services," and "support for vulnerable people during disasters."

[0062] The generated summaries and extracted information are stored in databases for each department by the database management department. For example, attributes such as "Traffic Management Department," "Signal Control," "Road Maintenance," "Traffic Congestion Countermeasures," "Emergency Vehicle Guidance," "Disaster Prevention Department," and "Police Department" are linked to the data, which then serve as the basis for searching and visualization. For instance, the "Water Quality Testing" operation in the Water and Sewerage Department is assigned attributes such as "Water and Sewerage Department," "Water Quality Testing," "Regular Inspection," "Anomaly Response," "Environmental Management Department," and "Report Creation."

[0063] The Business Relationship Visualization Unit uses generative AI to vectorize the business content data of each department extracted and summarized by the Business Analysis Unit, and calculates the similarity and relationship between business content. For example, "Disaster Recovery" and "Emergency Vehicle Guidance" are determined to have a high degree of relationship, visualizing the need for strong cooperation between the Infrastructure Management Department, the Traffic Management Department, and the Disaster Prevention Department. Also, "Environmental Education" and "Regional Event Management" reveal overlap and cooperation between the Education Department and the Environmental Management Department. The generative AI is given prompts such as "Vectorize the business content of each department and calculate the similarity of business content," "Calculate the similarity between the business content of this department and the business content of other departments, and visualize the need for overlap and cooperation," and "Group according to the strength of overlap and relationship of business content, and extract departments with high relevance." For example, "Disaster Prevention Education" of the Education Department and "Evacuation Drills" of the Disaster Prevention Department are determined to have a high degree of relationship, and the cooperation between the two departments is visualized. "Infection Control" of the Medical Department and "Air Quality Monitoring" of the Environmental Management Department are also highlighted as tasks that require cooperation during a pandemic.

[0064] The analysis results are visualized as a graph structure, with nodes representing each department and edges indicating the relationships and overlaps of operations. For example, during disaster response, the disaster prevention, infrastructure management, traffic management, and medical departments are connected by thick lines, and in daily operations, the collaboration between the education and environmental management departments is immediately apparent. The user interface accepts access from terminals, allowing users to search by department name, work content, or keywords. A list of relevant departments and related departments is displayed, and summaries and detailed explanations of each department's work content can be viewed. For example, searching for "evacuation guidance during disasters" displays a list of the collaboration status of the traffic management, disaster prevention, welfare, and medical departments, as well as the division of roles among each department and past response examples. Furthermore, on the graph structure visualization screen, when a user clicks on a specific department or work content, the connections and overlaps between related departments are dynamically highlighted. For example, selecting the water and sewage department highlights the collaboration with the infrastructure management and environmental management departments regarding water quality management and disaster response.

[0065] The Feedback Management Department receives comments and correction suggestions from users and reflects information such as "This task now requires collaboration with the Energy Management Department" or "The scope of responsibility for this task has changed" in the system. The Learning and Update Management Department continuously trains the generative AI with this feedback and the addition of new materials, maintaining an up-to-date work structure that responds immediately to the current state of urban management and new challenges. For example, even if new departments or tasks are added when urban reorganization or new projects are launched, the system can automatically analyze the information and update the overall structure. For instance, if a Smart City Promotion Department is newly established and IoT infrastructure management and data integration tasks are added, the overlap and collaboration of tasks with related departments will be immediately visualized.

[0066] As described above, in the embodiments of the present invention, a vast amount of diverse business data related to urban management is automatically collected and analyzed, and generative AI is used to extract and summarize the business content and relationships of each department with high accuracy, making it possible to constantly visualize the overall business structure of the city, the status of cooperation between departments, and the duplication and optimal division of tasks. This enables the streamlining of urban management, the optimization of administrative services, the acceleration of disaster response, and the effective utilization of urban resources. For example, the system of the present invention can be used for a wide range of urban management challenges, such as reviewing disaster response plans for the entire city, considering the consolidation of operations between departments, optimizing the business request flow, strengthening cooperation between departments, reducing duplicate tasks, supporting the formulation of urban policies, improving resident services, promoting smart city measures, strengthening environmental measures, and enhancing cooperation between education, welfare, and medical care.

[0067] (System Configuration)

[0068] The system according to this embodiment includes a city management information collection unit, a business analysis unit, a business relationship visualization unit, a database management unit, a user interface unit, a feedback management unit, and a learning and update management unit. The Urban Management Information Collection Department has the function of centrally receiving electronic files such as business documents, operation manuals, departmental documents, field reports, plans, inspection records, disaster response manuals, resident response records, event management materials, equipment management ledgers, educational program materials, medical collaboration records, and environmental monitoring reports from terminals used by personnel in various departments within the city, including administrative departments, infrastructure management departments, traffic management departments, disaster prevention departments, education departments, medical departments, environmental management departments, welfare departments, urban planning departments, water and sewage departments, and energy management departments. For example, the traffic management department can upload signal control manuals, road maintenance plans, traffic congestion countermeasure reports, and emergency vehicle guidance procedures; the infrastructure management department can upload water and sewage inspection records, power supply plans, equipment maintenance manuals, and disaster recovery procedures; the education department can upload school management manuals, environmental education programs, and community collaboration event materials; and the medical department can upload emergency transport records, medical collaboration protocols, and infectious disease control manuals. The department accepts a variety of business documents from each department. The supported file formats are diverse, including Word files, Excel files, PDF files, PowerPoint files, image files, and scanned data. When files are uploaded, metadata such as department name, file type, creation date, and responsible person's name are automatically added, and the files are classified and saved to the server's storage.

[0069] The Business Analysis Department sequentially processes various electronic files stored by the Urban Management Information Collection Department. PDF and image files are converted into text data using an optical character recognition engine, while Word, Excel, and PowerPoint files have their contents extracted using a dedicated text extraction module. For example, various response procedures and contact systems are extracted from PDF disaster response manuals, cell information such as equipment names, inspection dates, responsible persons, and inspection results are extracted from Excel equipment management ledgers, and event names, dates, operational structures, and cooperating departments are extracted from PowerPoint regional event materials. The extracted text data is input into the generating AI, which provides prompts such as, "Extract the work content, scope of responsibility, purpose, deliverables, frequently occurring keywords, workflow, and related departments from this document, and create a summary for each department," "List the work content for each department from this group of files, and organize the purpose and deliverables for each task," and "Extract tasks related to other departments from this department's work materials, and group highly related tasks." The generating AI extracts tasks such as "traffic signal control," "road maintenance," "traffic congestion countermeasures," and "emergency vehicle guidance" from documents in the traffic management department, "water and sewage inspection," "power supply management," "equipment maintenance," and "disaster recovery" from documents in the infrastructure management department, "school management," "environmental education," "community event management," and "disaster prevention education" from documents in the education department, "emergency transport," "patient information management," "medical institution collaboration," and "disaster medical response" from emergency transport records in the medical department, and "elderly support," "disability welfare," "public assistance services," and "support for vulnerable people during disasters" from resident response records in the welfare department. Furthermore, it automatically extracts the purpose, deliverables, workflow, and related departments for each task, and automatically generates summary sentences such as "traffic signal control is the responsibility of the traffic management department, and in emergencies, it collaborates with the disaster prevention and police departments" and "disaster recovery is led by the infrastructure management department, and cooperates with the water and sewage departments and the energy management department."

[0070] The Business Relationship Visualization Department uses AI to vectorize the business content data of each department extracted and summarized by the Business Analysis Department, and calculates the similarity and relationship between business content. For example, it determines that "disaster recovery" and "emergency vehicle guidance" have a high degree of relationship, visualizing the need for strong cooperation between the infrastructure management department, the traffic management department, and the disaster prevention department. It also reveals overlap and cooperation between the education department and the environmental management department for "environmental education" and "community event management." The generating AI is given prompts such as "vectorize the business content of each department and calculate the similarity of the business content," "calculate the similarity between the business content of this department and the business content of other departments, and visualize the need for overlap and cooperation," and "group according to the strength of overlap and relationship of business content, and extract departments with high relevance." For example, "disaster prevention education" in the education department and "evacuation drills" in the disaster prevention department are determined to have a high degree of relationship, and the cooperation between the two departments is visualized. "Infection control" in the medical department and "air quality monitoring" in the environmental management department are also highlighted as tasks that require cooperation during a pandemic.

[0071] The Database Management Department structures and stores various data generated by the Business Analysis Department and the Business Relationship Visualization Department by department and by business function. Attributes such as "Traffic Management Department," "Signal Control," "Road Maintenance," "Traffic Congestion Countermeasures," "Emergency Vehicle Guidance," "Disaster Prevention Department," and "Police Department" are linked to these data, serving as the basis for searching and visualization. For example, the "Water Quality Testing" operation in the Water and Sewerage Department is assigned attributes such as "Water and Sewerage Department," "Water Quality Testing," "Regular Inspection," "Anomaly Response," "Environmental Management Department," and "Report Creation." The Database Management Department has a structure optimized for high-speed searching and extraction of this information.

[0072] The user interface accepts access from terminals, allowing users to search by department name, job description, keywords, etc. A list of relevant departments and related departments is displayed, and summaries and detailed explanations of each department's work are available. For example, searching for "evacuation guidance during disasters" will display a list of the collaboration status of the traffic management department, disaster prevention department, welfare department, and medical department, as well as the division of roles among each department and past response examples. In the graph visualization screen, when a user clicks on a specific department or job description, the connections and overlaps between related departments are dynamically highlighted. For example, selecting the water and sewage department will highlight the collaboration with the infrastructure management department and environmental management department regarding water quality management and disaster response.

[0073] The Feedback Management Department receives comments and modification suggestions from users and reflects information such as "This task now requires collaboration with the Energy Management Department" or "The scope of responsibility for this task has changed" in the system. For example, even if new departments or tasks are added during urban restructuring or the launch of a new project, the Feedback Management Department receives that information and reflects it throughout the entire system.

[0074] The Learning and Update Management Department continuously trains its AI when new data is added from the Feedback Management Department and the Urban Management Information Collection Department, maintaining an up-to-date operational structure that responds immediately to the current state of urban management and new challenges. For example, even if a Smart City Promotion Department is newly established and IoT infrastructure management and data linkage tasks are added, any overlap or coordination of tasks with related departments will be immediately visualized. The Learning and Update Management Department maintains the freshness of information throughout the entire system and responds flexibly to changes in the city.

[0075] Specific examples of prompts to be fed into the generating AI necessary for implementing the present invention include: "Extract the business content, scope of responsibility, objectives, deliverables, frequently occurring keywords, business flow, and related departments from this document, and create a summary for each department," "List the business content for each department from this set of files, and organize the objectives and deliverables for each business," "Extract the business related to other departments from the business documents of this department, and group the highly related business," "Vectorize the business content of each department and calculate the similarity of the business content," "Calculate the similarity between the business content of this department and the business content of other departments, and visualize the need for overlap and collaboration," and "Group according to the strength of overlap and relevance of the business content, and extract the departments that are most related."

[0076] Thus, the system according to this embodiment is configured to automatically collect and analyze a vast amount of diverse business data related to urban management, use generating AI to extract and summarize the business content and relationships of each department with high accuracy, and constantly visualize the overall business structure of the city, the status of cooperation between departments, and the duplication and optimal division of labor.

[0077] (Implementation Steps)

[0078] Step 1: Collect and upload business documents Personnel in various departments within the city, such as administrative, infrastructure management, traffic management, disaster prevention, education, healthcare, environmental management, welfare, urban planning, water and sewage, and energy management departments, can upload a variety of electronic files, including work documents, operation manuals, departmental documents, field reports, plans, inspection records, disaster response manuals, resident response records, event management materials, equipment management ledgers, educational program materials, medical collaboration records, and environmental monitoring reports, through a dedicated web interface. File formats are diverse, including Word, Excel, PDF, PowerPoint, image files, and scanned data. Metadata such as department name, file type, creation date, and person in charge is added during upload, and the files are categorized and stored on the server's storage.

[0079] Step 2: Text conversion and pre-processing of business documents For various electronic files stored on the server, PDF and image files are converted into text data using an optical character recognition engine, while files such as Word, Excel, and PowerPoint are extracted using a dedicated text extraction module. For example, various response procedures and contact information can be extracted from a PDF disaster response manual, cell information such as equipment name, inspection date, person in charge, and inspection results can be extracted from an Excel equipment management ledger, and event name, date, operational structure, and cooperating departments can be extracted from PowerPoint regional event materials.

[0080] Step 3: Extracting and summarizing business content using generation AI. The system inputs digitized data into a generating AI to extract information such as the work content, responsibilities, objectives, deliverables, frequently occurring keywords, workflows, and related departments for each department, and then creates a summary for each department. Specific examples of prompts to be fed into the generating AI include: "Extract work content, responsibilities, objectives, deliverables, frequently occurring keywords, workflows, and related departments from this document, and create a summary for each department," "List the work content for each department from this set of files, and organize the objectives and deliverables for each task," and "Extract tasks related to other departments from the work documents of this department, and group highly related tasks." For example, from the traffic management department's documents, tasks such as "signal control," "road maintenance," "traffic congestion countermeasures," and "emergency vehicle guidance" could be extracted; from the infrastructure management department's documents, tasks such as "water and sewage inspection," "power supply management," "equipment maintenance," and "disaster recovery" could be extracted; and from the education department's documents, tasks such as "school management," "environmental education," "community event management," and "disaster prevention education" could be extracted.

[0081] Step 4: Storing in the business content database The database management department stores attribute information such as the work content, scope of responsibility, keywords, workflow, deliverables, related departments, and links to original documents for each department, extracted and summarized by the generating AI, as structured data for each department. For example, the "water quality testing" work of the water and sewage department is assigned attributes such as "water and sewage department," "water quality testing," "periodic inspection," "anomaly response," "environmental management department," and "report creation."

[0082] Step 5: Business relevance analysis and vectorization using generative AI The AI ​​generates numerical vectors from the business content data of each department stored in the database using natural language processing technology. It then calculates the similarity and relationship between business content and analyzes the overlap and relationships between departmental business content using clustering and network analysis techniques. Specific examples of prompts to be fed into the AI ​​include: "Vectorize the business content of each department and calculate the similarity of the business content," "Calculate the similarity between the business content of this department and that of other departments, and visualize the need for overlap and collaboration," and "Group the business content according to the strength of overlap and relationship, and extract departments with high relevance."

[0083] Step 6: Visualization and display of business relevance graphs Based on the analysis results, a graph structure is generated where nodes represent departments and edges represent the similarity and strength of the relationship between business operations. Nodes with high similarity are connected with thicker lines and darker colors, departments with high overlap are displayed with larger nodes, and departments with strong relationships have prominent edges, enabling intuitive visualization. Users can click on specific departments or business operations on the web interface to dynamically highlight connections and overlaps between related departments.

[0084] Step 7: User Search, Feedback, and Learning Users can search for department names, job descriptions, keywords, etc., via a web interface from their terminals. A list of relevant departments and related departments is displayed, and summaries and detailed explanations of each department's work are available. Furthermore, through the Feedback Management Department, users can input comments and modification suggestions such as "This task now requires collaboration with the Energy Management Department" or "The scope of responsibility for this task has changed." The Learning and Update Management Department then incorporates this information into the generating AI, which is used for subsequent analysis and visualization, keeping the overall business structure of the system constantly up-to-date.

[0085] (Specific use cases)

[0086] For example, consider a scenario in urban management where administrative departments, traffic management departments, disaster prevention departments, infrastructure management departments, education departments, medical departments, environmental management departments, welfare departments, urban planning departments, water and sewage departments, and energy management departments upload their daily created and managed operational documents, operational manuals, departmental documents, field reports, plans, inspection records, disaster response manuals, resident response records, event management materials, equipment management ledgers, educational program materials, medical collaboration records, environmental monitoring reports, etc., to the system of the present invention. For example, the traffic management department uploads signal control manuals, road maintenance plans, traffic congestion countermeasure reports, and emergency vehicle guidance procedures; the infrastructure management department uploads water and sewage inspection records, power supply plans, equipment maintenance manuals, and disaster recovery procedures; the education department uploads school operation manuals, environmental education programs, and community collaboration event materials; the medical department uploads emergency transport records, medical collaboration protocols, and infectious disease control manuals; and the welfare department uploads records of elderly support work, disability welfare work, public assistance work, and disaster-vulnerable support records. The supported file formats are diverse, including Word files, Excel files, PDF files, PowerPoint files, image files, and scanned data. When uploading, metadata such as department name, file type, creation date, and responsible person's name are also attached.

[0087] On the server side, these files are converted into text data using optical character recognition and text extraction modules and input into the generating AI. The generating AI is given prompts such as, "Extract the work content, scope of responsibility, purpose, deliverables, frequently occurring keywords, workflow, and related departments from this document, and create a summary for each department," "List the work content for each department from this set of files, and organize the purpose and deliverables for each task," and "Extract tasks related to other departments from the work documents of this department, and group highly related tasks." For example, the generating AI extracts work tasks such as "signal control," "road maintenance," "traffic congestion countermeasures," and "emergency vehicle guidance" from documents of the traffic management department, extracts "water and sewage inspection," "power supply management," "equipment maintenance," and "disaster recovery" from documents of the infrastructure management department, extracts "school management," "environmental education," "community event management," and "disaster prevention education" from documents of the education department, extracts "emergency transport," "patient information management," "medical institution collaboration," and "disaster medical response" from emergency transport records of the medical department, and extracts "elderly support," "disability welfare," "public assistance work," and "support for vulnerable people during disasters" from resident response records of the welfare department. Furthermore, the system automatically extracts the purpose, deliverables, workflow, and related departments for each task, and automatically generates summary sentences such as, "Traffic signal control is the responsibility of the traffic management department, and in emergencies, they will cooperate with the disaster prevention and police departments," and "Disaster recovery will be led by the infrastructure management department, and they will cooperate with the water and sewage departments and the energy management department."

[0088] The generated summaries and extracted information are stored in databases for each department by the Database Management Department. For example, the "Water Quality Testing" task in the Water and Sewerage Department is assigned attributes such as "Water and Sewerage Department," "Water Quality Testing," "Regular Inspection," "Anomaly Response," "Environmental Management Department," and "Report Creation." The Business Relationship Visualization Department vectorizes the business content data of each department extracted and summarized by the Business Analysis Department using a generating AI, and calculates the similarity and relationship between business content. For example, it determines that "Disaster Recovery" and "Emergency Vehicle Guidance" have a high relationship, visualizing the need for strong cooperation between the Infrastructure Management Department, the Traffic Management Department, and the Disaster Prevention Department. It also becomes clear that there is overlap and cooperation between the Education Department and the Environmental Management Department regarding "Environmental Education" and "Regional Event Management." The generating AI is given prompts such as "Vectorize the business content of each department and calculate the similarity of the business content," "Calculate the similarity between the business content of this department and the business content of other departments, and visualize the need for overlap and cooperation," and "Group according to the strength of overlap and relationship of business content, and extract departments with high relevance."

[0089] The analysis results are visualized as a graph structure, with nodes representing each department and edges indicating the relationships and overlaps of operations. For example, during disaster response, the disaster prevention, infrastructure management, traffic management, and medical departments are connected by thick lines, and in daily operations, the collaboration between the education and environmental management departments is immediately apparent. The user interface accepts access from terminals, allowing users to search by department name, work content, or keywords. A list of relevant departments and related departments is displayed, and summaries and detailed explanations of each department's work content can be viewed. For example, searching for "evacuation guidance during disasters" displays a list of the collaboration status of the traffic management, disaster prevention, welfare, and medical departments, as well as the division of roles among each department and past response examples. Furthermore, on the graph structure visualization screen, when a user clicks on a specific department or work content, the connections and overlaps between related departments are dynamically highlighted. For example, selecting the water and sewage department highlights the collaboration with the infrastructure management and environmental management departments regarding water quality management and disaster response.

[0090] The Feedback Management Department receives comments and correction suggestions from users and reflects information such as "This task now requires collaboration with the Energy Management Department" or "The scope of responsibility for this task has changed" in the system. The Learning and Update Management Department continuously trains the generating AI with this feedback and the addition of new materials, maintaining an up-to-date work structure that responds immediately to the current state of urban management and new challenges. For example, if a Smart City Promotion Department is newly established and IoT infrastructure management and data integration tasks are added, any overlap or collaboration of tasks with related departments will be immediately visualized.

[0091] These use cases provide constant visibility into the overall operations of a city, the collaboration between departments, and the duplication and optimal allocation of tasks, leading to more efficient urban management, optimized administrative services, faster disaster response, and effective utilization of urban resources.

[0092] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0093] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0094] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0095] For example, the data collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart device 14 and processes it with the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.

[0096] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0097] [Second Embodiment]

[0098] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0099] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0100] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0101] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and communication interface 44 are also connected to the bus 52.

[0102] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0103] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0104] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0105] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0106] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0107] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0108] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the identification processing unit 290 using these models.

[0109] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is realized by the data processing device 12 and the smart glasses 214. 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".

[0110] (Example 1)

[0111] Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0112] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0113] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0114] Furthermore, the processing by the data processing system 10 described above is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0115] For example, the data collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart glasses 214 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0116] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0117] [Third Embodiment]

[0118] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0119] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0120] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0121] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, display 343, and communication interface 44 are also connected to the bus 52.

[0122] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0124] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0125] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0126] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0127] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0128] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0129] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the headset terminal 314. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0130] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0131] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0132] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0133] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] For example, the data collection unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the headset terminal 314 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 and display 343 of the headset terminal 314 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0135] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0136] [Fourth Embodiment]

[0137] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0138] As shown in Figure 7, the 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.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0140] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, controlled object 443, and communication interface 44 are also connected to the bus 52.

[0141] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0143] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0144] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0145] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0146] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0147] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0148] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0149] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the robot 414. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0150] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0151] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0152] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0153] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or external devices, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or external devices.

[0154] For example, the data collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the robot 414 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using a generation AI. For example, the serving unit is implemented by the speaker 240 and controlled object 443 of the robot 414 and the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0155] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0156] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0157] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0158] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0159] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0160] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0161] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0162] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0163] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0164] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0165] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0166] 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.

[0167] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0168] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0169] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0170] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0171] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0172] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0173] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0174] Furthermore, the following additional information is disclosed regarding the above explanation.

[0175] (Claim 1)

[0176] The system comprises an urban management information collection unit, a business analysis unit, and a business relationship visualization unit. The urban management information collection unit centrally collects various electronic files from multiple departments within the city, such as administrative departments, infrastructure management departments, traffic management departments, disaster prevention departments, education departments, medical departments, environmental management departments, welfare departments, urban planning departments, water and sewage departments, and energy management departments. These files include business documents, operation manuals, departmental documents, field reports, plans, inspection records, disaster response manuals, resident response records, event management materials, equipment management ledgers, educational program materials, medical collaboration records, and environmental monitoring reports. The system has the function of adding metadata such as department name, file type, creation date, and person in charge, and storing them in storage on the server. The business analysis unit is based on the urban management information collection unit. The system features the following functions: it converts saved electronic files into text data using optical character recognition and text extraction processing; uses generative AI to extract the work content, scope of responsibility, objectives, deliverables, frequently occurring keywords, workflow, and related departments for each department; automatically generates explanatory text summarizing the work content of each department and stores it in a database for each department; the work relationship visualization unit vectorizes the work content data of each department extracted by the aforementioned work analysis unit using generative AI, performs similarity calculation and clustering to analyze the overlap and need for collaboration in work content; visualizes the analysis results as a graph structure; and enables city employees and administrators to search, view, and analyze the work content of each department and its relationships with other departments via a web interface. (Claim 2)

[0177] The system according to claim 1, wherein the business analysis unit automatically organizes the business content, scope of responsibility, purpose, deliverables, frequently occurring keywords, business flow, and related departments extracted from the business documents of each department using a generative AI, and further stores the summarized results in a database, so that when a user performs various searches by department name, business content, keywords, business flow, deliverables, and related departments, the relevant departments and related departments are displayed in a list, and a summary and detailed explanation of the business content of each department can be viewed. (Claim 3)

[0178] The system according to claim 1, wherein the business relationship visualization unit uses a generative AI to vectorize the business content data of each department and calculate similarity, visualizes the data by changing the thickness and color of the edges between nodes in the graph structure according to the overlap and strength of the relationships between the business content, and further enables the system to dynamically highlight connections and overlaps between related departments when a user specifies specific business content or keywords on the web interface. [Explanation of symbols]

[0179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A system comprising a business data collection unit, a text analysis unit, and a business relationship visualization unit, wherein the business data collection unit has the function of collecting electronic files of business data and division of duties from multiple departments and storing them centrally; the text analysis unit has the function of converting the electronic files stored by the business data collection unit into text data using optical character recognition and text extraction processing, extracting the business content, scope of responsibility, and characteristic keywords for each department using generative AI and natural language processing, and further automatically generating explanatory text summarizing the business content of each department; and the business relationship visualization unit vectorizes the business content data of each department extracted by the text analysis unit and performs similarity calculations, analyzes the overlap and relationships of business between departments using generative AI, visualizes the analysis results as a graph structure, and enables users to search and view the business content of each department and its relationships with other departments on a web interface.

2. The system according to claim 1, wherein when the text analysis unit uses a generative AI to summarize the business content extracted from the business documents of each department, it automatically organizes information such as the purpose of the work, deliverables, scope of responsibility, frequently occurring keywords, and business flow, which differ for each department, and further stores the summary results in a database so that when a user searches by department name, business content, or keywords, the relevant departments and related departments are displayed in a list.

3. The system according to claim 1, wherein the business relationship visualization unit uses a generative AI to vectorize the business content data of each department and calculate similarity, visualizes the data by changing the thickness and color of the edges between nodes in the graph structure according to the overlap and strength of the relationships between the business content, and further enables the system to dynamically highlight connections and overlaps between related departments when a user specifies specific business content or keywords on the web interface.

Images