System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting use cases from each company in a company group; means for storing the collected use cases in a database and performing tagging and categorization; means for scoring the use cases quarterly based on evaluation criteria and creating a ranking; means for preparing an event based on the evaluation results and presenting superior use cases; and means for preferentially displaying superior use cases in the database after the event ends.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While the use of generative AI models is increasing within corporate groups, examples of use cases from each company are not being effectively shared, resulting in delays in improving productivity and promoting innovation across the group. This problem arises from insufficient information collection and evaluation. Furthermore, excellent use cases are not made visible, making it difficult for other companies to use them as reference. Furthermore, the lack of a mechanism for incorporating user feedback into system improvements hampers the continuous evolution of the system. [Means for solving the problem]

[0005] To solve this problem, we provide a system that includes the following means: a means for collecting use cases from each company in a corporate group; a means for storing the collected use cases in a database and tagging and categorizing them; a means for scoring and ranking the use cases based on evaluation criteria every quarter; a means for preparing events based on the evaluation results and presenting outstanding use cases; and a means for displaying outstanding use cases preferentially in the database after the event. Furthermore, the system also includes a means for other companies to search and view the company's use cases through a shared portal, and a means for aggregating user feedback and considering and implementing system improvements. This enables effective sharing and evaluation of generative AI model usage, which is expected to promote productivity and innovation throughout the corporate group.

[0006] A "corporate group" is an organization consisting of a common parent company or multiple affiliated companies.

[0007] "Use cases" are detailed descriptions of specific outcomes or projects that companies have achieved using generative AI models.

[0008] "Database" means a centralized storage system for efficiently storing, retrieving, and managing use cases and other information.

[0009] "Tagging" is the process of attaching relevant keywords or identifiers to data so that it can be efficiently classified and searched.

[0010] "Categorization" is a technique for classifying data based on specific themes or types to make it easier to manage.

[0011] "Scoring" is the process of assigning a numerical score to a use case according to evaluation criteria.

[0012] "Ranking" refers to ranking use cases based on the results of scoring.

[0013] "Evaluation criteria" are standards set to objectively evaluate use cases (for example, "reduction of work time," "increased profits," "uniqueness of use," etc.).

[0014] An "event" is a gathering or meeting to present evaluated use cases and share knowledge within a group.

[0015] A "presentation" is a formalized presentation that details the evaluated use case and communicates the information to other participants.

[0016] The "Sharing Portal" is an online platform for sharing, searching, and viewing use cases and information within a corporate group.

[0017] "Feedback" refers to information such as opinions, improvement suggestions, and evaluations provided by users.

[0018] "System improvement" is the process of improving an existing system based on collected feedback to make it function more effectively.

[0019] "Priority display" refers to placing certain data or information in a way that makes it more prominent than other data. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0024] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0025] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0041] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. This system allows each company to collect, evaluate, and share use cases that utilize generative AI models, encouraging other companies to adopt similar methods.

[0042] System Overview

[0043] The system consists of the following main components:

[0044] 1. Data Collection Portal

[0045] 2. Database Management System

[0046] 3. Shared Portal

[0047] 4. Rating and Ranking System

[0048] 5. Event Management System

[0049] Data Collection Portal

[0050] Users (personnel at each company) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[0051] Database Management Systems

[0052] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[0053] Shared Portal

[0054] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[0055] Rating and Ranking System

[0056] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[0057] Event Management System

[0058] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[0059] Specific examples

[0060] For example, let's say Company A used a generative AI model to automate customer service inquiries, resulting in an average 30% reduction in inquiry response time and an annual cost reduction of 300,000 yen. The user (company A's representative) accesses the data collection portal, enters the case title "Customer Service Automation," a detailed description, and the results, and presses the submit button. The server saves this information in a database and assigns the tags "Customer Service" and "Cost Reduction."

[0061] Later, when a user at Company B searches for "customer service" cases on the shared portal, the case study from Company A appears and the user can view the details. Company B uses this as a reference to consider similar improvement measures at their own company.

[0062] If this case receives high praise at a quarterly event, the server will prepare materials for the event and a representative from Company A will give a presentation. Other companies will learn from the content and apply it to their own operations.

[0063] This will promote the effective use of generative AI models across the entire corporate group, resulting in improved business efficiency and productivity.

[0064] The processing flow will be explained below.

[0065] Specific processing flow of the program

[0066] (Data Collection Portal Processing)

[0067] Step 1:

[0068] The user accesses the data collection portal website.

[0069] Step 2:

[0070] The user enters authentication information (user ID and password) on the login screen and clicks the login button.

[0071] Step 3:

[0072] The server receives the entered authentication information and authenticates the user. If authentication is successful, the case registration form is displayed.

[0073] Step 4:

[0074] The user enters the case title, details, and results (such as reduced work time or increased profits) in the case registration form and presses the submit button.

[0075] Step 5:

[0076] The terminal transmits the input case data to the server.

[0077] Step 6:

[0078] The server stores the received case data in a database and automatically tags and categorizes them.

[0079] (Shared Portal Processing)

[0080] Step 7:

[0081] The user accesses the shared portal and proceeds to the case search screen.

[0082] Step 8:

[0083] The user enters search criteria (keywords and tags) and presses the search button.

[0084] Step 9:

[0085] The terminal transmits the user's search conditions to the server.

[0086] Step 10:

[0087] The server extracts cases that match the search criteria from the database and generates a list of related cases.

[0088] Step 11:

[0089] The server transmits the generated case list to the user's terminal and displays the search results.

[0090] Step 12:

[0091] Users can click on a case that interests them from the search results to access the details page and view more information.

[0092] Step 13:

[0093] The server records user access logs and accumulates data for analyzing usage trends.

[0094] (Rating and ranking system processing)

[0095] Step 14:

[0096] The server extracts new use cases from the database every quarter.

[0097] Step 15:

[0098] The server scores the extracted cases based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.).

[0099] Step 16:

[0100] The server creates a ranking based on the scoring results.

[0101] Step 17:

[0102] The server prepares the top case studies, along with the ranking results, as presentation materials for the event.

[0103] Step 18:

[0104] The server notifies the event schedule and a list of participating companies.

[0105] (Event management system processing)

[0106] Step 19:

[0107] The user follows the notified event date and participates in the event online or offline.

[0108] Step 20:

[0109] The server will give a presentation based on the top-ranked cases, announcing details of each case and its evaluation points.

[0110] Step 21:

[0111] Users will study the case studies presented at the event and take notes on points that can be applied to their own company's operations.

[0112] Step 22:

[0113] After the event, the server registers the awarded cases in a database as a priority display, and makes them accessible to all users through a shared portal.

[0114] (Handling feedback and system improvements)

[0115] Step 23:

[0116] Users can submit feedback and suggestions for improvement while using the system through a feedback form.

[0117] Step 24:

[0118] The server aggregates the feedback and improvement suggestions received and notifies the administrator.

[0119] Step 25:

[0120] The server implements system improvement measures based on instructions from the administrator and updates the system version.

[0121] This specific processing flow enables efficient collection, evaluation, and sharing of use cases of generative AI models within a corporate group, thereby improving overall productivity and promoting innovation.

[0122] Example 1

[0123] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0124] Conventional information sharing systems within corporate groups lack a consistent management system for effectively collecting, evaluating, and sharing examples of how individual companies have utilized generative AI models. This has made it difficult to improve productivity and promote innovation across the entire company. Furthermore, there have been challenges in efficiently searching for use cases, ensuring objectivity in evaluation, and ensuring optimal sharing methods.

[0125] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0126] In this invention, the server includes means for performing user authentication using authentication information, means for collecting use cases from each company in the corporate group, means for storing the collected use cases in a database and tagging and categorizing them using an NLP model, means for allowing other companies to search and view the use cases through a shared portal, means for scoring the use cases based on evaluation criteria using a machine learning algorithm every quarter and creating rankings, means for preparing an event based on the evaluation results and presenting excellent use cases, and means for preferentially displaying excellent use cases in the database after the event. This enables efficient and effective collection, evaluation, and sharing of use cases of generative AI models within the corporate group, thereby improving productivity and promoting innovation.

[0127] "Authentication Information" means a user ID, password, or other means of identification used to verify a user's identity.

[0128] "User authentication" is the process of using authentication information to verify a user's identity and grant them access to a system.

[0129] "Corporate group" refers to the entire group formed by the collaboration of multiple companies.

[0130] "Use cases" are specific results and practical reports obtained by each company using generative AI models.

[0131] A "database" is a computer system that systematically stores and manages collected information.

[0132] An "NLP model" is a machine learning model that uses natural language processing technology to analyze text data and extract meanings and categories.

[0133] "Tagging" is the process of assigning relevant keywords and labels to data to make it easier to search and classify.

[0134] "Categorization" is the process of classifying data into specific categories or groups.

[0135] A "shared portal" is a web-based interface that multiple users can access to search and view information.

[0136] A "machine learning algorithm" is a computational method that automatically learns from data and makes predictions and classifications.

[0137] "Scoring" is the process of assigning a score to data or cases based on specific evaluation criteria.

[0138] "Ranking" refers to the ranking of data or cases based on the evaluated scores.

[0139] An "event" is a gathering such as a presentation or seminar that is held on a specific date and time.

[0140] A "presentation" is the act of explaining and presenting information and examples to an audience.

[0141] "Feedback" refers to ratings, opinions, and comments provided by users.

[0142] An "access log" is data that keeps a record of users accessing a system.

[0143] "Usage trends" refers to patterns and tendencies in how users use the system.

[0144] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. This system allows each company to collect, evaluate, and share use cases that utilize generative AI models, encouraging other companies to adopt similar methods.

[0145] The system consists of the following main components: data collection portal, database management system, sharing portal, evaluation and ranking system, and event management system.

[0146] Data Collection Portal

[0147] Users enter use cases that utilize generative AI models through a data collection portal. User authentication is performed using authentication information (user ID and password), and only authenticated users can access the portal. The input information includes the case title, details, and results obtained.

[0148] As a specific example, a person in charge at Company A will enter details of a case study titled "Customer Service Automation" in which they reduced inquiry response time by an average of 30%, achieving annual cost savings of 300,000 yen, and then press the send button.

[0149] Database Management Systems

[0150] The server stores the received use cases in a database, typically a relational database such as MySQL or PostgreSQL, and uses an NLP model to analyze the text and automatically tag and categorize it into categories such as "customer service" or "cost reduction."

[0151] Specifically, the server invokes the NLP model, analyzes the input case content, assigns appropriate tags, and stores the tagged data in a database.

[0152] Shared Portal

[0153] Users can access the shared portal and search for and view use cases from other companies. The server uses a search engine such as ElasticSearch to list and display relevant cases based on the user's search criteria. It also has the ability to record user access logs and analyze usage trends.

[0154] As a specific example, when a user from Company B searches for cases related to "customer service," cases from Company A are displayed.

[0155] Rating and Ranking System

[0156] Every quarter, the server extracts new use cases from the database and scores them using a machine learning algorithm based on set evaluation criteria, such as "reduction of work time," "increased profits," and "uniqueness of use." A ranking is created based on the scoring results, and the best cases are selected.

[0157] Specifically, the server extracts cases from the database and runs a scoring algorithm to generate a ranking.

[0158] Event Management System

[0159] The server will then prepare an event based on the evaluation results. Highly rated cases will be presented at the event, and participating companies will be able to participate remotely. The event will be held using online conferencing tools such as Zoom and Microsoft Teams. Outstanding cases will be prioritized in the database.

[0160] As a concrete example, best practices are presented at quarterly events, and other companies can learn from them and use them to improve their own companies.

[0161] Example prompt

[0162] Please provide the case study title, details, and results of your business operations using generative AI models.

[0163] These components and specific processing steps will promote the effective use of generative AI models across the corporate group, thereby achieving improved operational efficiency and productivity.

[0164] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0165] Step 1: User authentication

[0166] Input: User ID and password

[0167] Output: Authentication result (success or failure)

[0168] Specific behavior:

[0169] A user accesses the data collection portal and enters their user ID and password on the login page. The server sends the entered authentication information to the LDAP server for authentication. The LDAP server returns the authentication result, and if the server is successful, the user can proceed to the next step.

[0170] Step 2: Enter and submit your use case

[0171] Input: Case title, details, results

[0172] Output: Submitted use case

[0173] Specific behavior:

[0174] After authenticating, the user enters the use case title, details, and results obtained in the data collection portal, including specific numerical data (e.g., man-hour reduction percentage, cost reduction amount, etc.). By pressing the submit button, the data is sent to the server.

[0175] Step 3: Saving to the database

[0176] Input: Use case data

[0177] Output: Saved database records

[0178] Specific behavior:

[0179] The server receives the submitted use case and stores it in a relational database (e.g. MySQL or PostgreSQL), mapping the data to the appropriate tables and executing INSERT statements to store it.

[0180] Step 4: Tagging and categorizing the cases

[0181] Input: Saved database record

[0182] Output: Tagged and categorized data

[0183] Specific behavior:

[0184] The server inputs the stored data into an NLP model, analyzes the text, and automatically assigns tags such as "customer service" or "cost reduction" based on the analysis results, updating the record in the database.

[0185] Step 5: Search for cases in the shared portal

[0186] Input: Search keyword

[0187] Output: A list of search results

[0188] Specific behavior:

[0189] A user accesses the shared portal and enters a keyword (e.g., "customer service") into the search box. The server uses a search engine such as ElasticSearch to generate a search query based on the keyword and retrieves relevant cases from the database.

[0190] Step 6: Viewing search results

[0191] Input: list of search results

[0192] Output: The search results page that is displayed to the user

[0193] Specific behavior:

[0194] The server renders the search results retrieved from the database in HTML format, using an HTML template engine (e.g. Thymeleaf or Handlebars) to generate the search results page and send it back to the user's browser for display.

[0195] Step 7: Conduct evaluation and ranking

[0196] Input: Use cases in the database

[0197] Output: Evaluation and ranking results

[0198] Specific behavior:

[0199] The server extracts cases to be evaluated from the database every quarter. It runs a machine learning algorithm to score each case based on the set evaluation criteria (e.g., "reduction of work time," "increase in profits," "uniqueness of use," etc.). It generates a ranking based on the scoring results and stores it in the database.

[0200] Step 8: Prepare and execute the event

[0201] Input: Rating and ranking results

[0202] Output: Event materials and presentations

[0203] Specific behavior:

[0204] The server prepares event materials based on the evaluation results. The materials are generated in PDF or slide format and presented on the day of the event using online conferencing tools such as Zoom or Microsoft Teams. Outstanding cases are prioritized in the database, allowing other companies to learn from them.

[0205] These steps will promote the effective use of generative AI models across the corporate group, resulting in improved operational efficiency and productivity.

[0206] (Application example 1)

[0207] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0208] In conventional systems, there was no adequate method for effectively collecting, sharing, evaluating, and utilizing use cases of generative AI models within a corporate group. As a result, it was difficult to maximize the benefits of productivity improvement and cost reduction. Furthermore, improving task management and work efficiency was a key issue, particularly in logistics centers, and an effective solution was needed.

[0209] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0210] In this invention, the server includes: means for collecting use cases from each company in the corporate group; means for storing the collected use cases in a database and tagging and categorizing them; means for scoring the use cases based on evaluation criteria every quarter and creating rankings; means for preparing an event based on the evaluation results and presenting outstanding use cases; means for preferentially displaying outstanding use cases in the database after the event; means for including an AI assistant application for smart glasses that can be used by workers in the logistics center; means for managing tasks using voice recognition and presenting work instructions in real time; and means for monitoring task progress and presenting the next task. This enables effective use of generative AI models within the corporate group and significant improvement in work efficiency at the logistics center.

[0211] 1. A "corporate group" refers to multiple companies linked together under common capital and management policies.

[0212] 2. "Use Case" refers to information showing specific use cases and results of applying a generative AI model to business activities.

[0213] 3. "Database" refers to an information system that systematically stores and manages collected use cases and other related data.

[0214] 4. "Tagging" refers to the practice of assigning specific keywords or identifiers to data to make it easier to search for later.

[0215] 5. "Categorization" refers to the method of classifying collected data into specific categories.

[0216] 6. "Evaluation Criteria" refers to the criteria or measures used to evaluate a Use Case.

[0217] 7. "Scoring" refers to the process of assigning a score to a use case based on evaluation criteria.

[0218] 8. "Ranking" refers to the ranking of use cases based on the scoring results.

[0219] 9. "Event" means an event or gathering to announce evaluation results and present successful use cases.

[0220] 10. "AI assistant application" refers to application software that uses artificial intelligence technology to assist users in their work.

[0221] 11. "Smart glasses" refers to a wearable device in the form of glasses with built-in displays and sensors.

[0222] 12. "Speech recognition" refers to the technology that analyzes human speech and recognizes it as text or commands.

[0223] 13. "Task management" refers to the method of listing the tasks required to achieve a specific goal and tracking their progress.

[0224] 14. "Real-time" refers to immediate processing or response without delay.

[0225] 15. "Work Instructions" means the specific instructions required to complete a particular task.

[0226] 16. “Progress management” refers to the process of monitoring the progress of work and making adjustments as needed.

[0227] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. The main purpose of this system is to improve work efficiency at logistics centers.

[0228] System Overview

[0229] The system consists of the following main components:

[0230] 1. Data Collection Portal

[0231] 2. Database Management System

[0232] 3. Shared Portal

[0233] 4. Rating and Ranking System

[0234] 5. Event Management System

[0235] 6. AI Assistant Application for Smart Glasses

[0236] Data Collection Portal

[0237] Company personnel (users) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[0238] Database Management Systems

[0239] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[0240] Shared Portal

[0241] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[0242] Rating and Ranking System

[0243] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[0244] Event Management System

[0245] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[0246] AI assistant application for smart glasses

[0247] This application allows workers in a logistics center to use smart glasses to manage tasks using generative AI models. Smart glasses are wearable devices with built-in displays and sensors. The application provides the following features:

[0248] 1. Real-time task display: The smart glasses display the worker's task list and work procedures in real time.

[0249] 2. Speech Recognition and Instructions: The next work task and instructions can be received through the worker's voice input. The speech recognition system uses the speech_recognition library.

[0250] 3. Task progress management: Register completed tasks and get real-time updates on progress.

[0251] 4. Optimal route suggestion: Optimizes routes within the warehouse to help efficiently pick up and deliver goods.

[0252] Hardware and software used

[0253] Hardware: Smart glasses, microphone

[0254] Software: Python, speech_recognition library, pyttsx3 library

[0255] Specific examples

[0256] For example, if a worker at a logistics center wears smart glasses and says, "Tell me what my next task is," the AI ​​assistant application will give instructions such as, "Move pallet A." Once the worker has completed the task, they can say, "This task is complete," and receive instructions for the next task.

[0257] Prompt Sentence Examples

[0258] "Tell me the next task"

[0259] Complete this task

[0260] "Show more tasks"

[0261] This will significantly improve the work efficiency of the logistics center and promote the effective use of generative AI models across the corporate group.

[0262] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0263] Step 1:

[0264] The user wears the smart glasses and gives instructions via voice input such as "Tell me the next task." At this time, the voice input is captured using a microphone. The input voice data is converted into text data by the voice recognition system (speech_recognition library) in the smart glasses.

[0265] Step 2:

[0266] The smart glasses receive the text data generated by the voice recognition system and send it to the backend server to present the next task to the user. The backend server selects the next task from the current task list and returns it to the smart glasses as text data. At this time, it queries the task management database for information on related tasks and selects the appropriate task.

[0267] Step 3:

[0268] The smart glasses display the next task text data received from the backend server and also provide audio instructions using the pyttsx3 library, giving the user both visual and audible confirmation of what they need to do next.

[0269] Step 4:

[0270] After completing the task, the user again speaks "I've completed this task." The microphone again captures the voice data, which is then converted into text data by the speech recognition system.

[0271] Step 5:

[0272] The smart glasses send the task completion text data generated by the voice recognition system to the backend server, which updates the task management database to record that the current task has been completed, and prepares to select a new task from the next task list and provide it to the user.

[0273] Step 6:

[0274] The smart glasses receive new task information from the backend server and present it to the user visually and audibly, updating the next task in real time and helping the user work efficiently.

[0275] Through these steps, workers within the logistics center can complete tasks efficiently and quickly, improving overall work efficiency.

[0276] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0277] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. In particular, the system aims to improve the quality of feedback and maximize the effectiveness of events by combining an emotion engine that recognizes user emotions.

[0278] System Overview

[0279] The system consists of the following main components:

[0280] 1. Data Collection Portal

[0281] 2. Database Management System

[0282] 3. Shared Portal

[0283] 4. Rating and Ranking System

[0284] 5. Event Management System

[0285] 6. Emotion Engine

[0286] Data Collection Portal

[0287] Users (personnel at each company) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[0288] Database Management Systems

[0289] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[0290] Shared Portal

[0291] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[0292] Rating and Ranking System

[0293] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[0294] Event Management System

[0295] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[0296] Emotion Engine

[0297] The emotion engine is a component that recognizes and analyzes user emotions in real time. Specifically, it analyzes emotions contained in feedback and comments and categorizes them into emotional states such as positive, negative, and neutral.

[0298] Specific processing explanation

[0299] The processing of the data collection portal and database management system from step 1 to step 6 has been described above.

[0300] The shared portal processing from step 7 to step 13 is performed in a similar manner.

[0301] The evaluation and ranking system processes from step 14 to step 18 are carried out in the same manner.

[0302] Further processing by the emotion engine:

[0303] Step 19:

[0304] Users can enter their thoughts and suggestions for improvement through a feedback form.

[0305] Step 20:

[0306] The terminal transmits the user's input data to the emotion engine.

[0307] Step 21:

[0308] The emotion engine analyzes the input data and classifies the emotional state as positive, negative, or neutral.

[0309] Step 22:

[0310] The server stores the analysis results in a database and categorizes the feedback based on the emotional state.

[0311] Real-time sentiment analysis during the event:

[0312] Step 23:

[0313] Users view presentations delivered in real time during the event.

[0314] Step 24:

[0315] The emotion engine collects and analyzes real-time user emotion data to evaluate how the presentation content is perceived by the user.

[0316] Step 25:

[0317] The server dynamically adjusts the presentation content based on data from the emotion engine, providing information to keep the user engaged.

[0318] Specific examples

[0319] For example, let's say Company A used a generative AI model to automate customer service inquiries, resulting in an average 30% reduction in inquiry response time and an annual cost reduction of 300,000 yen. The user (company A's representative) accesses the data collection portal, enters the case title "Customer Service Automation," a detailed description, and the results, and presses the submit button. The server saves this information in a database and assigns the tags "Customer Service" and "Cost Reduction."

[0320] Later, when a user at Company B searches for "customer service" cases on the shared portal, the case study from Company A appears and the user can view the details. Company B uses this as a reference to consider similar improvement measures at their own company.

[0321] If this case receives high praise at a quarterly event, the server will prepare materials for the event and a representative from Company A will give a presentation. Other companies will learn from the content and apply it to their own operations.

[0322] Furthermore, the emotion engine analyzes user reactions during the event, and if there are many positive reactions, it dynamically adjusts the presentation content to emphasize those points, maximizing the effectiveness of the presentation and increasing participant understanding and interest.

[0323] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and improved productivity, but also improving the quality of feedback by utilizing user emotional data.

[0324] The processing flow will be explained below.

[0325] Specific processing flow of the program

[0326] (Data Collection Portal Processing)

[0327] Step 1:

[0328] The user accesses the data collection portal website.

[0329] Step 2:

[0330] The user enters authentication information (user ID and password) on the login screen and clicks the login button.

[0331] Step 3:

[0332] The server receives the entered authentication information and authenticates the user. If authentication is successful, the case registration form is displayed.

[0333] Step 4:

[0334] The user enters the case title, details, and results (such as reduced work time or increased profits) in the case registration form and presses the submit button.

[0335] Step 5:

[0336] The terminal transmits the input case data to the server.

[0337] Step 6:

[0338] The server stores the received case data in a database, automatically tagging it with categories such as "customer service" and "cost reduction."

[0339] (Shared Portal Processing)

[0340] Step 7:

[0341] The user accesses the shared portal and proceeds to the case search screen.

[0342] Step 8:

[0343] The user enters search criteria (keywords and tags) and presses the search button.

[0344] Step 9:

[0345] The terminal transmits the user's search conditions to the server.

[0346] Step 10:

[0347] The server extracts cases that match the search criteria from the database and generates a list of related cases.

[0348] Step 11:

[0349] The server transmits the generated case list to the user's terminal and displays the search results.

[0350] Step 12:

[0351] Users can click on a case that interests them from the search results to access the details page and view more information.

[0352] Step 13:

[0353] The server records user access logs and accumulates data for analyzing usage trends.

[0354] (Rating and ranking system processing)

[0355] Step 14:

[0356] The server extracts new use cases from the database every quarter.

[0357] Step 15:

[0358] The server scores the extracted cases based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.).

[0359] Step 16:

[0360] The server creates a ranking based on the scoring results.

[0361] Step 17:

[0362] The server prepares the top case studies, along with the ranking results, as presentation materials for the event.

[0363] Step 18:

[0364] The server notifies the event schedule and a list of participating companies.

[0365] (Event management system processing)

[0366] Step 19:

[0367] The user follows the notified event date and participates in the event online or offline.

[0368] Step 20:

[0369] The server will give a presentation based on the top-ranked cases, announcing details of each case and its evaluation points.

[0370] Step 21:

[0371] Users will study the case studies presented at the event and take notes on points that can be applied to their own company's operations.

[0372] Step 22:

[0373] After the event, the server registers the awarded cases in a database as a priority display, and makes them accessible to all users through a shared portal.

[0374] (Handling feedback and system improvements)

[0375] Step 23:

[0376] Users can submit feedback and suggestions for improvement while using the system through a feedback form.

[0377] Step 24:

[0378] The server aggregates the feedback and improvement suggestions received and notifies the administrator.

[0379] Step 25:

[0380] The server implements system improvement measures based on instructions from the administrator and updates the system version.

[0381] (Processed by emotion engine)

[0382] Step 26:

[0383] Users can enter their thoughts and suggestions for improvement through a feedback form.

[0384] Step 27:

[0385] The terminal transmits the user's input data to the emotion engine.

[0386] Step 28:

[0387] The emotion engine analyzes the input data and classifies the emotional state as positive, negative, or neutral.

[0388] Step 29:

[0389] The server stores the analysis results in a database and categorizes the feedback based on the emotional state.

[0390] (Real-time sentiment analysis during the event)

[0391] Step 30:

[0392] Users view presentations delivered in real time during the event.

[0393] Step 31:

[0394] The emotion engine collects and analyzes real-time user emotion data to evaluate how the presentation content is perceived by the user.

[0395] Step 32:

[0396] The server dynamically adjusts the presentation content based on data from the emotion engine, providing information to keep the user engaged.

[0397] This specific process flow allows companies to efficiently collect, evaluate, and share use cases of generative AI models within their group, improving overall productivity and promoting innovation. Furthermore, the introduction of an emotion engine improves the quality of feedback and maximizes the effectiveness of events.

[0398] Example 2

[0399] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0400] To effectively utilize generative AI models within a corporate group and promote productivity and innovation within each company, effective sharing and evaluation of use cases is necessary. However, with conventional systems, collecting, tagging, and categorizing use cases is done manually, which is time-consuming and labor-intensive. Another issue is that user feedback is not collected and analyzed sufficiently, which hinders the quality of the feedback. Furthermore, it is difficult to analyze user reactions in real time during an event and dynamically adjust presentation content.

[0401] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting use cases from each company in a corporate group, means for saving the collected use cases in a database and tagging and categorizing them, means for scoring the use cases based on evaluation criteria every quarter and creating rankings, means for preparing an event based on the evaluation results and presenting excellent use cases, means for preferentially displaying excellent use cases in the database after the event, means for collecting feedback from users and classifying the feedback as positive, negative, or neutral using an emotion analysis engine, and means for analyzing user emotion data in real time during the event and dynamically adjusting the content of the presentation. This enables effective collection and sharing of use cases, improves the quality of user feedback, and enables real-time presentation adjustments.

[0402] A "corporate group" is an organization formed by multiple companies working together to pursue common goals and interests.

[0403] "Use cases" are the results of specific applications or projects in which companies have used generative AI models, as well as the information gained in the process.

[0404] A "database" is a recording medium that systematically stores collected use cases and feedback, allowing for efficient search and management.

[0405] "Tagging" is a method of categorizing use cases and data with specific categories or keywords to make them easier to search and view.

[0406] "Categorization" is a method of classifying and structuring collected data according to specific criteria.

[0407] "Scoring" is the process of numerically evaluating use cases based on evaluation criteria and creating a ranking.

[0408] "Evaluation criteria" are indicators or rules established to judge the value or usefulness of a use case.

[0409] A "ranking" is a list of multiple use cases ordered based on evaluation criteria.

[0410] A "presentation" is a presentation format for introducing evaluated use cases to other companies and sharing knowledge.

[0411] "Portal" means a website or application that users within a corporate group can access to collect, view, and share information.

[0412] "Feedback" is data that expresses users' feelings, suggestions, and opinions about use cases and systems.

[0413] An "emotion analysis engine" is software or algorithms that analyze user feedback and real-time data and classify the emotions contained in that content as positive, negative, or neutral.

[0414] "Real-time analytics" is the process of analyzing data and obtaining results immediately as the data is generated.

[0415] "Dynamic adjustment" is the means by which presentations and system behavior can be instantly changed and adapted based on real-time analysis results.

[0416] MODE FOR CARRYING OUT THE INVENTION

[0417] This invention is a system that uses a generative AI model to effectively collect, evaluate, and share case studies within a corporate group, thereby improving productivity and promoting innovation across the entire company. In particular, by combining it with an emotion analysis engine that analyzes user emotions in real time, we aim to improve the quality of feedback and maximize the effectiveness of events.

[0418] Data Collection Portal

[0419] Users enter use cases that utilize generative AI models through a data collection portal. The data collection portal has fields for the case title, details, and results obtained (e.g., reduced work time, increased profits), and users enter these and press the submit button. The data collection portal has an authentication function, and only authenticated users can access it. A common ID and password are used for authentication.

[0420] Database Management Systems

[0421] The server receives the use cases submitted by users and stores them in a database. At this time, text analysis algorithms are used to automatically tag and categorize the cases based on their content, making them easier to search for later. The database management system can be a relational database management system (RDBMS), such as MySQL or PostgreSQL.

[0422] Shared Portal

[0423] Users can access the shared portal and search for and view use cases registered by other companies. Users search for specific keywords or categories, and the server executes a search within the database and displays a list of relevant use cases to the user. The shared portal is built as a web application that can be accessed from a web browser.

[0424] Rating and Ranking System

[0425] Every quarter, the server scores new use cases based on evaluation criteria, such as "time saved," "profit increase," and "uniqueness of use," and creates a ranking. The scoring uses machine learning algorithms to ensure fair and consistent evaluations.

[0426] Event Management System

[0427] The server prepares events based on the quarterly evaluation results. At the events, highly rated use cases are presented, allowing other companies to learn from them. During the events, real-time user feedback is collected and analyzed by a sentiment analysis engine. After the events, outstanding use cases are prioritized in the database.

[0428] Sentiment Analysis Engine

[0429] A sentiment analysis engine collects user-provided feedback and real-time comments and uses natural language processing (NLP) techniques to classify them into positive, negative, or neutral sentiment. A sentiment analysis engine can use machine learning models built in Python (e.g., TensorFlow or PyTorch), for example.

[0430] Specific operation example

[0431] For example, consider a case where Company A used a generative AI model to automate customer service, reducing inquiry response times by 30% and saving 300,000 yen per year. A user enters this case into the data collection portal, enters the title "Customer Service Automation," a detailed description, and the results, and presses the submit button.

[0432] The server receives the information and stores it in a database, automatically tagging it with "customer service" and "cost reduction." Later, when a user from Company B searches for cases related to "customer service" on the shared portal, Company A's cases will be listed and the user can view their details.

[0433] This case study was highly rated and was presented at the event. During the presentation, a sentiment analysis engine analyzed user reactions in real time, and if there were a lot of positive reactions, the content of the presentation was dynamically adjusted to emphasize those parts, maintaining the participants' interest and deepening their understanding.

[0434] Prompt Sentence Examples

[0435] "Please give us a specific example of how a generative AI model has been used to improve business processes."

[0436] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and productivity improvements, but also improving the quality of feedback.

[0437] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0438] Step 1:

[0439] The user accesses the data collection portal and enters authentication information (ID and password). The entered authentication information is sent to the server by the terminal. The server checks the authentication information against the database, and if authentication is successful, displays a data input form to the user. As a result, the user can access the data input form.

[0440] Step 2:

[0441] The user enters a use case for the generative AI model into a data entry form and presses the submit button. The input data includes the case title, details, and outcomes (e.g., reduced work time, increased profits). The device then sends this data to the server. The server stores the received data in a database and applies text analysis algorithms to automatically assign tags such as "customer service" or "cost reduction." This makes the stored data easier to search later.

[0442] Step 3:

[0443] A user accesses the shared portal and searches for use cases using a specific keyword (e.g., "customer service"). The device sends the search query to the server, which performs a search in the database and lists relevant use cases. As a result, the device displays the search results sent from the server to the user. The user can view the displayed use cases and check detailed information.

[0444] Step 4:

[0445] The server extracts new use cases from the database every quarter. It scores the extracted data based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use") using a machine learning algorithm. Based on the scoring results, the server creates a ranking, which allows the best use cases to be identified.

[0446] Step 5:

[0447] The server will use the quarterly evaluation results to prepare the schedule and content for the next event. At the event, materials will be created and presenters will be selected so that the most highly rated use cases will be presented. A function to collect feedback in real time will be provided during the event. Event materials and a feedback function will be provided.

[0448] Step 6:

[0449] Users attend the event and watch the presentations provided. A form is provided to collect feedback from users in real time during the event. Users enter their impressions and suggestions for improvement in the feedback form and press the submit button. The device then sends the feedback data to the server.

[0450] Step 7:

[0451] The server sends the received feedback data to the sentiment analysis engine, which analyzes the feedback data and classifies it into positive, negative, or neutral sentiment. The analysis results are sent to the server, which stores them in a database. This allows the system to consider improvements based on the content of the feedback.

[0452] Step 8:

[0453] Users watch presentations in real time during an event. The sentiment analysis engine collects and analyzes users' real-time emotional data to evaluate how the presentation content is perceived by the users. The server receives the data from the sentiment analysis engine and dynamically adjusts the content of the presentation, thereby maintaining user interest and providing a better presentation.

[0454] (Application example 2)

[0455] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0456] In systems that effectively utilize generative AI models within corporate groups to improve productivity and promote innovation across the entire company, there is a need for a mechanism that can recognize user emotions in real time and reflect them in high-quality feedback and work instructions.If this requirement is not met, it is difficult to maximize the quality of feedback and the effectiveness of events, and there is also the problem of not being able to improve the efficiency of factory work.

[0457] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0458] In this invention, the server includes: means for collecting use cases from each company in the corporate group; means for storing the collected use cases in a database and tagging and categorizing them; means for scoring the use cases based on evaluation criteria every quarter and creating rankings; means for preparing events based on the evaluation results and presenting outstanding use cases; means for displaying outstanding use cases in a prioritized manner in the database after the event; means for analyzing operator emotion data in real time and providing work instructions and feedback; and means for dynamically adjusting presentation content based on the emotion data. This enables the effective use of generative AI models across the entire corporate group, improving business efficiency and productivity. Furthermore, the quality of feedback can be improved by utilizing user emotion data, maximizing the effectiveness of events.

[0459] A "corporate group" is a group of multiple companies that share common goals and interests, and among which there are cooperative and business relationships.

[0460] A "use case" refers to a real-world application or outcome that utilizes a generative AI model in a specific setting or situation.

[0461] A "database" is a system for systematically and efficiently storing and managing use cases and other related information.

[0462] "Tagging" refers to the act of assigning labels to information in a database that indicate specific attributes or categories.

[0463] "Categorization" is a method of classifying information in a database based on certain commonalities.

[0464] "Scoring" is a method of assigning points to each use case based on specific evaluation criteria to determine its merits or demerits.

[0465] "Ranking" refers to ranking use cases based on the scoring results.

[0466] "Event" refers to a gathering or presentation held within a corporate group for the purpose of sharing evaluation results and use cases.

[0467] "Emotion data" is information that indicates an emotional state analyzed from user input and feedback.

[0468] "Presentation" refers to the act of explaining and announcing information about use cases and evaluation results verbally and visually to other companies and stakeholders.

[0469] "Real-time" refers to a time frame in which analysis and processing occur almost immediately.

[0470] The "emotion engine" is a system that analyzes the user's emotional data and classifies and evaluates their emotional state.

[0471] This invention is a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. In particular, it aims to maximize the effectiveness of events by combining it with an emotion engine that recognizes user emotions in real time to improve the quality of feedback and work instructions.

[0472] System configuration

[0473] The system consists of the following main components:

[0474] 1. Data Collection Portal

[0475] 2. Database Management System

[0476] 3. Shared Portal

[0477] 4. Rating and Ranking System

[0478] 5. Event Management System

[0479] 6. Emotion Engine

[0480] Data Collection Portal

[0481] Users enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduction in work time or increased profits) and submit the data. The portal has an authentication function, and only authenticated users can access it.

[0482] Database Management Systems

[0483] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[0484] Shared Portal

[0485] Users can access the shared portal and search for and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[0486] Rating and Ranking System

[0487] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). Rankings are created based on the scoring results, and outstanding cases are selected.

[0488] Event Management System

[0489] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[0490] Emotion Engine

[0491] The emotion engine is a component that recognizes and analyzes user emotions in real time. Specifically, it analyzes emotions contained in feedback and comments and categorizes them into emotional states such as positive, negative, and neutral.

[0492] Specific use cases

[0493] For example, a user operating a factory robot can enter a case study of "improving robot operation speed" through a data collection portal, providing a title, details, and results (e.g., a 90% efficiency improvement), and submit the study. The server stores this information in a database and automatically assigns tags such as "efficiency improvement" and "cost reduction."

[0494] When users at other factories search for "efficiency improvement" cases on the shared portal, this case will appear and they can view the details. If this case receives high praise at a quarterly event, event materials will be prepared. Users can give presentations that other companies can use as reference.

[0495] Furthermore, during the event, the emotion engine analyzes users' real-time reactions, and if there are a lot of positive reactions, the presentation content is dynamically adjusted to emphasize those points, maximizing the effectiveness of the presentation and increasing participant understanding and interest.

[0496] Prompt Sentence Examples

[0497] An example prompt for a generative AI model is:

[0498] Based on the feedback analysis of the robot's work, create a presentation to improve work efficiency. Highlight the positive feedback points and propose improvements for the negative feedback.

[0499] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and improved productivity, but also improving the quality of feedback by utilizing user emotional data.

[0500] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0501] Step 1:

[0502] Users access a data collection portal and input use cases that utilize generative AI models, including the case title, details, and results achieved (e.g., time saved or increased profits). This input data is then sent to the data collection portal.

[0503] Step 2:

[0504] The device receives the use case data sent by the user and sends it to the server. The server receives this data and stores it in a database. When storing it, it automatically tags and categorizes the cases based on their characteristics, such as "customer service" or "cost reduction." This tagging and categorization makes it easier to search the data.

[0505] Step 3:

[0506] Users access the shared portal to search and browse use cases in the database. When users enter search criteria, the server lists relevant use cases based on tagging and categories and displays them to the user, allowing users to quickly access the information they need.

[0507] Step 4:

[0508] The server extracts new use cases from the database every quarter. It scores each case based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.). It then assigns points to each evaluation criterion and calculates an overall score.

[0509] Step 5:

[0510] The server creates a ranking of the use cases based on the scoring results. Use cases with high scores are placed at the top of the list, and those with low scores are placed at the bottom. The ranking results are used to prepare for the event.

[0511] Step 6:

[0512] The server prepares an event based on the evaluation results. The highly evaluated cases are prepared to be presented at the event. At this time, the outstanding use cases are given special recognition and are prioritized in the database.

[0513] Step 7:

[0514] During the event, users will watch presentations delivered in real time, including top use cases.

[0515] Step 8:

[0516] The emotion engine analyzes user emotion data collected from devices during the event in real time. Input data includes user comments and feedback. The emotion engine analyzes this data and classifies it into positive, negative, or neutral emotional states.

[0517] Step 9:

[0518] The server receives the analysis results and dynamically adjusts the presentation content based on them. For example, if there are a lot of positive reactions, it will emphasize the success points, and if there are a lot of negative reactions, it will add improvement measures. This will help maintain and improve the understanding and interest of event participants.

[0519] Step 10:

[0520] After the event, the server will prioritize the best use cases in the database and encourage information sharing among participating companies, allowing other companies to learn from the best use cases and consider ways to use them in their own companies.

[0521] This series of processes promotes the effective use of generative AI models across the entire corporate group, improving business efficiency and productivity. Furthermore, by utilizing user emotion data, the quality of feedback is improved and the effectiveness of events is maximized.

[0522] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0523] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0524] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0525] [Second embodiment]

[0526] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0527] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0528] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0529] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0530] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0531] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0532] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0533] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0534] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0535] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0536] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0537] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0538] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. This system allows each company to collect, evaluate, and share use cases that utilize generative AI models, encouraging other companies to adopt similar methods.

[0539] System Overview

[0540] The system consists of the following main components:

[0541] 1. Data Collection Portal

[0542] 2. Database Management System

[0543] 3. Shared Portal

[0544] 4. Rating and Ranking System

[0545] 5. Event Management System

[0546] Data Collection Portal

[0547] Users (personnel at each company) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[0548] Database Management Systems

[0549] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[0550] Shared Portal

[0551] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[0552] Rating and Ranking System

[0553] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[0554] Event Management System

[0555] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[0556] Specific examples

[0557] For example, let's say Company A used a generative AI model to automate customer service inquiries, resulting in an average 30% reduction in inquiry response time and an annual cost reduction of 300,000 yen. The user (company A's representative) accesses the data collection portal, enters the case title "Customer Service Automation," a detailed description, and the results, and presses the submit button. The server saves this information in a database and assigns the tags "Customer Service" and "Cost Reduction."

[0558] Later, when a user at Company B searches for "customer service" cases on the shared portal, the case study from Company A appears and the user can view the details. Company B uses this as a reference to consider similar improvement measures at their own company.

[0559] If this case receives high praise at a quarterly event, the server will prepare materials for the event and a representative from Company A will give a presentation. Other companies will learn from the content and apply it to their own operations.

[0560] This will promote the effective use of generative AI models across the entire corporate group, resulting in improved business efficiency and productivity.

[0561] The processing flow will be explained below.

[0562] Specific processing flow of the program

[0563] (Data Collection Portal Processing)

[0564] Step 1:

[0565] The user accesses the data collection portal website.

[0566] Step 2:

[0567] The user enters authentication information (user ID and password) on the login screen and clicks the login button.

[0568] Step 3:

[0569] The server receives the entered authentication information and authenticates the user. If authentication is successful, the case registration form is displayed.

[0570] Step 4:

[0571] The user enters the case title, details, and results (such as reduced work time or increased profits) in the case registration form and presses the submit button.

[0572] Step 5:

[0573] The terminal transmits the input case data to the server.

[0574] Step 6:

[0575] The server stores the received case data in a database and automatically tags and categorizes them.

[0576] (Shared Portal Processing)

[0577] Step 7:

[0578] The user accesses the shared portal and proceeds to the case search screen.

[0579] Step 8:

[0580] The user enters search criteria (keywords and tags) and presses the search button.

[0581] Step 9:

[0582] The terminal transmits the user's search conditions to the server.

[0583] Step 10:

[0584] The server extracts cases that match the search criteria from the database and generates a list of related cases.

[0585] Step 11:

[0586] The server transmits the generated case list to the user's terminal and displays the search results.

[0587] Step 12:

[0588] Users can click on a case that interests them from the search results to access the details page and view more information.

[0589] Step 13:

[0590] The server records user access logs and accumulates data for analyzing usage trends.

[0591] (Rating and ranking system processing)

[0592] Step 14:

[0593] The server extracts new use cases from the database every quarter.

[0594] Step 15:

[0595] The server scores the extracted cases based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.).

[0596] Step 16:

[0597] The server creates a ranking based on the scoring results.

[0598] Step 17:

[0599] The server prepares the top case studies, along with the ranking results, as presentation materials for the event.

[0600] Step 18:

[0601] The server notifies the event schedule and a list of participating companies.

[0602] (Event management system processing)

[0603] Step 19:

[0604] The user follows the notified event date and participates in the event online or offline.

[0605] Step 20:

[0606] The server will give a presentation based on the top-ranked cases, announcing details of each case and its evaluation points.

[0607] Step 21:

[0608] Users will study the case studies presented at the event and take notes on points that can be applied to their own company's operations.

[0609] Step 22:

[0610] After the event, the server registers the awarded cases in a database as a priority display, and makes them accessible to all users through a shared portal.

[0611] (Handling feedback and system improvements)

[0612] Step 23:

[0613] Users can submit feedback and suggestions for improvement while using the system through a feedback form.

[0614] Step 24:

[0615] The server aggregates the feedback and improvement suggestions received and notifies the administrator.

[0616] Step 25:

[0617] The server implements system improvement measures based on instructions from the administrator and updates the system version.

[0618] This specific processing flow enables efficient collection, evaluation, and sharing of use cases of generative AI models within a corporate group, thereby improving overall productivity and promoting innovation.

[0619] Example 1

[0620] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0621] Conventional information sharing systems within corporate groups lack a consistent management system for effectively collecting, evaluating, and sharing examples of how individual companies have utilized generative AI models. This has made it difficult to improve productivity and promote innovation across the entire company. Furthermore, there have been challenges in efficiently searching for use cases, ensuring objectivity in evaluation, and ensuring optimal sharing methods.

[0622] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0623] In this invention, the server includes means for performing user authentication using authentication information, means for collecting use cases from each company in the corporate group, means for storing the collected use cases in a database and tagging and categorizing them using an NLP model, means for allowing other companies to search and view the use cases through a shared portal, means for scoring the use cases based on evaluation criteria using a machine learning algorithm every quarter and creating rankings, means for preparing an event based on the evaluation results and presenting excellent use cases, and means for preferentially displaying excellent use cases in the database after the event. This enables efficient and effective collection, evaluation, and sharing of use cases of generative AI models within the corporate group, thereby improving productivity and promoting innovation.

[0624] "Authentication Information" means a user ID, password, or other means of identification used to verify a user's identity.

[0625] "User authentication" is the process of using authentication information to verify a user's identity and grant them access to a system.

[0626] "Corporate group" refers to the entire group formed by the collaboration of multiple companies.

[0627] "Use cases" are specific results and practical reports obtained by each company using generative AI models.

[0628] A "database" is a computer system that systematically stores and manages collected information.

[0629] An "NLP model" is a machine learning model that uses natural language processing technology to analyze text data and extract meanings and categories.

[0630] "Tagging" is the process of assigning relevant keywords and labels to data to make it easier to search and classify.

[0631] "Categorization" is the process of classifying data into specific categories or groups.

[0632] A "shared portal" is a web-based interface that multiple users can access to search and view information.

[0633] A "machine learning algorithm" is a computational method that automatically learns from data and makes predictions and classifications.

[0634] "Scoring" is the process of assigning a score to data or cases based on specific evaluation criteria.

[0635] "Ranking" refers to the ranking of data or cases based on the evaluated scores.

[0636] An "event" is a gathering such as a presentation or seminar that is held on a specific date and time.

[0637] A "presentation" is the act of explaining and presenting information and examples to an audience.

[0638] "Feedback" refers to ratings, opinions, and comments provided by users.

[0639] An "access log" is data that keeps a record of users accessing a system.

[0640] "Usage trends" refers to patterns and tendencies in how users use the system.

[0641] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. This system allows each company to collect, evaluate, and share use cases that utilize generative AI models, encouraging other companies to adopt similar methods.

[0642] The system consists of the following main components: data collection portal, database management system, sharing portal, evaluation and ranking system, and event management system.

[0643] Data Collection Portal

[0644] Users enter use cases that utilize generative AI models through a data collection portal. User authentication is performed using authentication information (user ID and password), and only authenticated users can access the portal. The input information includes the case title, details, and results obtained.

[0645] As a specific example, a person in charge at Company A will enter details of a case study titled "Customer Service Automation" in which they reduced inquiry response time by an average of 30%, achieving annual cost savings of 300,000 yen, and then press the send button.

[0646] Database Management Systems

[0647] The server stores the received use cases in a database, typically a relational database such as MySQL or PostgreSQL, and uses an NLP model to analyze the text and automatically tag and categorize it into categories such as "customer service" or "cost reduction."

[0648] Specifically, the server invokes the NLP model, analyzes the input case content, assigns appropriate tags, and stores the tagged data in a database.

[0649] Shared Portal

[0650] Users can access the shared portal and search for and view use cases from other companies. The server uses a search engine such as ElasticSearch to list and display relevant cases based on the user's search criteria. It also has the ability to record user access logs and analyze usage trends.

[0651] As a specific example, when a user from Company B searches for cases related to "customer service," cases from Company A are displayed.

[0652] Rating and Ranking System

[0653] Every quarter, the server extracts new use cases from the database and scores them using a machine learning algorithm based on set evaluation criteria, such as "reduction of work time," "increased profits," and "uniqueness of use." A ranking is created based on the scoring results, and the best cases are selected.

[0654] Specifically, the server extracts cases from the database and runs a scoring algorithm to generate a ranking.

[0655] Event Management System

[0656] The server will then prepare an event based on the evaluation results. Highly rated cases will be presented at the event, and participating companies will be able to participate remotely. The event will be held using online conferencing tools such as Zoom and Microsoft Teams. Outstanding cases will be prioritized in the database.

[0657] As a concrete example, best practices are presented at quarterly events, and other companies can learn from them and use them to improve their own companies.

[0658] Example prompt

[0659] Please provide the case study title, details, and results of your business operations using generative AI models.

[0660] These components and specific processing steps will promote the effective use of generative AI models across the corporate group, thereby achieving improved operational efficiency and productivity.

[0661] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0662] Step 1: User authentication

[0663] Input: User ID and password

[0664] Output: Authentication result (success or failure)

[0665] Specific behavior:

[0666] A user accesses the data collection portal and enters their user ID and password on the login page. The server sends the entered authentication information to the LDAP server for authentication. The LDAP server returns the authentication result, and if the server is successful, the user can proceed to the next step.

[0667] Step 2: Enter and submit your use case

[0668] Input: Case title, details, results

[0669] Output: Submitted use case

[0670] Specific behavior:

[0671] After authenticating, the user enters the use case title, details, and results obtained in the data collection portal, including specific numerical data (e.g., man-hour reduction percentage, cost reduction amount, etc.). By pressing the submit button, the data is sent to the server.

[0672] Step 3: Saving to the database

[0673] Input: Use case data

[0674] Output: Saved database records

[0675] Specific behavior:

[0676] The server receives the submitted use case and stores it in a relational database (e.g. MySQL or PostgreSQL), mapping the data to the appropriate tables and executing INSERT statements to store it.

[0677] Step 4: Tagging and categorizing the cases

[0678] Input: Saved database record

[0679] Output: Tagged and categorized data

[0680] Specific behavior:

[0681] The server inputs the stored data into an NLP model, analyzes the text, and automatically assigns tags such as "customer service" or "cost reduction" based on the analysis results, updating the record in the database.

[0682] Step 5: Search for cases in the shared portal

[0683] Input: Search keyword

[0684] Output: A list of search results

[0685] Specific behavior:

[0686] A user accesses the shared portal and enters a keyword (e.g., "customer service") into the search box. The server uses a search engine such as ElasticSearch to generate a search query based on the keyword and retrieves relevant cases from the database.

[0687] Step 6: Viewing search results

[0688] Input: list of search results

[0689] Output: The search results page that is displayed to the user

[0690] Specific behavior:

[0691] The server renders the search results retrieved from the database in HTML format, using an HTML template engine (e.g. Thymeleaf or Handlebars) to generate the search results page and send it back to the user's browser for display.

[0692] Step 7: Conduct evaluation and ranking

[0693] Input: Use cases in the database

[0694] Output: Evaluation and ranking results

[0695] Specific behavior:

[0696] The server extracts cases to be evaluated from the database every quarter. It runs a machine learning algorithm to score each case based on the set evaluation criteria (e.g., "reduction of work time," "increase in profits," "uniqueness of use," etc.). It generates a ranking based on the scoring results and stores it in the database.

[0697] Step 8: Prepare and execute the event

[0698] Input: Rating and ranking results

[0699] Output: Event materials and presentations

[0700] Specific behavior:

[0701] The server prepares event materials based on the evaluation results. The materials are generated in PDF or slide format and presented on the day of the event using online conferencing tools such as Zoom or Microsoft Teams. Outstanding cases are prioritized in the database, allowing other companies to learn from them.

[0702] These steps will promote the effective use of generative AI models across the corporate group, resulting in improved operational efficiency and productivity.

[0703] (Application example 1)

[0704] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0705] In conventional systems, there was no adequate method for effectively collecting, sharing, evaluating, and utilizing use cases of generative AI models within a corporate group. As a result, it was difficult to maximize the benefits of productivity improvement and cost reduction. Furthermore, improving task management and work efficiency was a key issue, particularly in logistics centers, and an effective solution was needed.

[0706] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0707] In this invention, the server includes: means for collecting use cases from each company in the corporate group; means for storing the collected use cases in a database and tagging and categorizing them; means for scoring the use cases based on evaluation criteria every quarter and creating rankings; means for preparing an event based on the evaluation results and presenting outstanding use cases; means for preferentially displaying outstanding use cases in the database after the event; means for including an AI assistant application for smart glasses that can be used by workers in the logistics center; means for managing tasks using voice recognition and presenting work instructions in real time; and means for monitoring task progress and presenting the next task. This enables effective use of generative AI models within the corporate group and significant improvement in work efficiency at the logistics center.

[0708] 1. A "corporate group" refers to multiple companies linked together under common capital and management policies.

[0709] 2. "Use Case" refers to information showing specific use cases and results of applying a generative AI model to business activities.

[0710] 3. "Database" refers to an information system that systematically stores and manages collected use cases and other related data.

[0711] 4. "Tagging" refers to the practice of assigning specific keywords or identifiers to data to make it easier to search for later.

[0712] 5. "Categorization" refers to the method of classifying collected data into specific categories.

[0713] 6. "Evaluation Criteria" refers to the criteria or measures used to evaluate a Use Case.

[0714] 7. "Scoring" refers to the process of assigning a score to a use case based on evaluation criteria.

[0715] 8. "Ranking" refers to the ranking of use cases based on the scoring results.

[0716] 9. "Event" means an event or gathering to announce evaluation results and present successful use cases.

[0717] 10. "AI assistant application" refers to application software that uses artificial intelligence technology to assist users in their work.

[0718] 11. "Smart glasses" refers to a wearable device in the form of glasses with built-in displays and sensors.

[0719] 12. "Speech recognition" refers to the technology that analyzes human speech and recognizes it as text or commands.

[0720] 13. "Task management" refers to the method of listing the tasks required to achieve a specific goal and tracking their progress.

[0721] 14. "Real-time" refers to immediate processing or response without delay.

[0722] 15. "Work Instructions" means the specific instructions required to complete a particular task.

[0723] 16. “Progress management” refers to the process of monitoring the progress of work and making adjustments as needed.

[0724] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. The main purpose of this system is to improve work efficiency at logistics centers.

[0725] System Overview

[0726] The system consists of the following main components:

[0727] 1. Data Collection Portal

[0728] 2. Database Management System

[0729] 3. Shared Portal

[0730] 4. Rating and Ranking System

[0731] 5. Event Management System

[0732] 6. AI Assistant Application for Smart Glasses

[0733] Data Collection Portal

[0734] Company personnel (users) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[0735] Database Management Systems

[0736] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[0737] Shared Portal

[0738] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[0739] Rating and Ranking System

[0740] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[0741] Event Management System

[0742] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[0743] AI assistant application for smart glasses

[0744] This application allows workers in a logistics center to use smart glasses to manage tasks using generative AI models. Smart glasses are wearable devices with built-in displays and sensors. The application provides the following features:

[0745] 1. Real-time task display: The smart glasses display the worker's task list and work procedures in real time.

[0746] 2. Speech Recognition and Instructions: The next work task and instructions can be received through the worker's voice input. The speech recognition system uses the speech_recognition library.

[0747] 3. Task progress management: Register completed tasks and get real-time updates on progress.

[0748] 4. Optimal route suggestion: Optimizes routes within the warehouse to help efficiently pick up and deliver goods.

[0749] Hardware and software used

[0750] Hardware: Smart glasses, microphone

[0751] Software: Python, speech_recognition library, pyttsx3 library

[0752] Specific examples

[0753] For example, if a worker at a logistics center wears smart glasses and says, "Tell me what my next task is," the AI ​​assistant application will give instructions such as, "Move pallet A." Once the worker has completed the task, they can say, "This task is complete," and receive instructions for the next task.

[0754] Prompt Sentence Examples

[0755] "Tell me the next task"

[0756] Complete this task

[0757] "Show more tasks"

[0758] This will significantly improve the work efficiency of the logistics center and promote the effective use of generative AI models across the corporate group.

[0759] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0760] Step 1:

[0761] The user wears the smart glasses and gives instructions via voice input such as "Tell me the next task." At this time, the voice input is captured using a microphone. The input voice data is converted into text data by the voice recognition system (speech_recognition library) in the smart glasses.

[0762] Step 2:

[0763] The smart glasses receive the text data generated by the voice recognition system and send it to the backend server to present the next task to the user. The backend server selects the next task from the current task list and returns it to the smart glasses as text data. At this time, it queries the task management database for information on related tasks and selects the appropriate task.

[0764] Step 3:

[0765] The smart glasses display the next task text data received from the backend server and also provide audio instructions using the pyttsx3 library, giving the user both visual and audible confirmation of what they need to do next.

[0766] Step 4:

[0767] After completing the task, the user again speaks "I've completed this task." The microphone again captures the voice data, which is then converted into text data by the speech recognition system.

[0768] Step 5:

[0769] The smart glasses send the task completion text data generated by the voice recognition system to the backend server, which updates the task management database to record that the current task has been completed, and prepares to select a new task from the next task list and provide it to the user.

[0770] Step 6:

[0771] The smart glasses receive new task information from the backend server and present it to the user visually and audibly, updating the next task in real time and helping the user work efficiently.

[0772] Through these steps, workers within the logistics center can complete tasks efficiently and quickly, improving overall work efficiency.

[0773] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0774] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. In particular, the system aims to improve the quality of feedback and maximize the effectiveness of events by combining an emotion engine that recognizes user emotions.

[0775] System Overview

[0776] The system consists of the following main components:

[0777] 1. Data Collection Portal

[0778] 2. Database Management System

[0779] 3. Shared Portal

[0780] 4. Rating and Ranking System

[0781] 5. Event Management System

[0782] 6. Emotion Engine

[0783] Data Collection Portal

[0784] Users (personnel at each company) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[0785] Database Management Systems

[0786] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[0787] Shared Portal

[0788] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[0789] Rating and Ranking System

[0790] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[0791] Event Management System

[0792] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[0793] Emotion Engine

[0794] The emotion engine is a component that recognizes and analyzes user emotions in real time. Specifically, it analyzes emotions contained in feedback and comments and categorizes them into emotional states such as positive, negative, and neutral.

[0795] Specific processing explanation

[0796] The processing of the data collection portal and database management system from step 1 to step 6 has been described above.

[0797] The shared portal processing from step 7 to step 13 is performed in a similar manner.

[0798] The evaluation and ranking system processes from step 14 to step 18 are carried out in the same manner.

[0799] Further processing by the emotion engine:

[0800] Step 19:

[0801] Users can enter their thoughts and suggestions for improvement through a feedback form.

[0802] Step 20:

[0803] The terminal transmits the user's input data to the emotion engine.

[0804] Step 21:

[0805] The emotion engine analyzes the input data and classifies the emotional state as positive, negative, or neutral.

[0806] Step 22:

[0807] The server stores the analysis results in a database and categorizes the feedback based on the emotional state.

[0808] Real-time sentiment analysis during the event:

[0809] Step 23:

[0810] Users view presentations delivered in real time during the event.

[0811] Step 24:

[0812] The emotion engine collects and analyzes real-time user emotion data to evaluate how the presentation content is perceived by the user.

[0813] Step 25:

[0814] The server dynamically adjusts the presentation content based on data from the emotion engine, providing information to keep the user engaged.

[0815] Specific examples

[0816] For example, let's say Company A used a generative AI model to automate customer service inquiries, resulting in an average 30% reduction in inquiry response time and an annual cost reduction of 300,000 yen. The user (company A's representative) accesses the data collection portal, enters the case title "Customer Service Automation," a detailed description, and the results, and presses the submit button. The server saves this information in a database and assigns the tags "Customer Service" and "Cost Reduction."

[0817] Later, when a user at Company B searches for "customer service" cases on the shared portal, the case study from Company A appears and the user can view the details. Company B uses this as a reference to consider similar improvement measures at their own company.

[0818] If this case receives high praise at a quarterly event, the server will prepare materials for the event and a representative from Company A will give a presentation. Other companies will learn from the content and apply it to their own operations.

[0819] Furthermore, the emotion engine analyzes user reactions during the event, and if there are many positive reactions, it dynamically adjusts the presentation content to emphasize those points, maximizing the effectiveness of the presentation and increasing participant understanding and interest.

[0820] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and improved productivity, but also improving the quality of feedback by utilizing user emotional data.

[0821] The processing flow will be explained below.

[0822] Specific processing flow of the program

[0823] (Data Collection Portal Processing)

[0824] Step 1:

[0825] The user accesses the data collection portal website.

[0826] Step 2:

[0827] The user enters authentication information (user ID and password) on the login screen and clicks the login button.

[0828] Step 3:

[0829] The server receives the entered authentication information and authenticates the user. If authentication is successful, the case registration form is displayed.

[0830] Step 4:

[0831] The user enters the case title, details, and results (such as reduced work time or increased profits) in the case registration form and presses the submit button.

[0832] Step 5:

[0833] The terminal transmits the input case data to the server.

[0834] Step 6:

[0835] The server stores the received case data in a database, automatically tagging it with categories such as "customer service" and "cost reduction."

[0836] (Shared Portal Processing)

[0837] Step 7:

[0838] The user accesses the shared portal and proceeds to the case search screen.

[0839] Step 8:

[0840] The user enters search criteria (keywords and tags) and presses the search button.

[0841] Step 9:

[0842] The terminal transmits the user's search conditions to the server.

[0843] Step 10:

[0844] The server extracts cases that match the search criteria from the database and generates a list of related cases.

[0845] Step 11:

[0846] The server transmits the generated case list to the user's terminal and displays the search results.

[0847] Step 12:

[0848] Users can click on a case that interests them from the search results to access the details page and view more information.

[0849] Step 13:

[0850] The server records user access logs and accumulates data for analyzing usage trends.

[0851] (Rating and ranking system processing)

[0852] Step 14:

[0853] The server extracts new use cases from the database every quarter.

[0854] Step 15:

[0855] The server scores the extracted cases based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.).

[0856] Step 16:

[0857] The server creates a ranking based on the scoring results.

[0858] Step 17:

[0859] The server prepares the top case studies, along with the ranking results, as presentation materials for the event.

[0860] Step 18:

[0861] The server notifies the event schedule and a list of participating companies.

[0862] (Event management system processing)

[0863] Step 19:

[0864] The user follows the notified event date and participates in the event online or offline.

[0865] Step 20:

[0866] The server will give a presentation based on the top-ranked cases, announcing details of each case and its evaluation points.

[0867] Step 21:

[0868] Users will study the case studies presented at the event and take notes on points that can be applied to their own company's operations.

[0869] Step 22:

[0870] After the event, the server registers the awarded cases in a database as a priority display, and makes them accessible to all users through a shared portal.

[0871] (Handling feedback and system improvements)

[0872] Step 23:

[0873] Users can submit feedback and suggestions for improvement while using the system through a feedback form.

[0874] Step 24:

[0875] The server aggregates the feedback and improvement suggestions received and notifies the administrator.

[0876] Step 25:

[0877] The server implements system improvement measures based on instructions from the administrator and updates the system version.

[0878] (Processed by emotion engine)

[0879] Step 26:

[0880] Users can enter their thoughts and suggestions for improvement through a feedback form.

[0881] Step 27:

[0882] The terminal transmits the user's input data to the emotion engine.

[0883] Step 28:

[0884] The emotion engine analyzes the input data and classifies the emotional state as positive, negative, or neutral.

[0885] Step 29:

[0886] The server stores the analysis results in a database and categorizes the feedback based on the emotional state.

[0887] (Real-time sentiment analysis during the event)

[0888] Step 30:

[0889] Users view presentations delivered in real time during the event.

[0890] Step 31:

[0891] The emotion engine collects and analyzes real-time user emotion data to evaluate how the presentation content is perceived by the user.

[0892] Step 32:

[0893] The server dynamically adjusts the presentation content based on data from the emotion engine, providing information to keep the user engaged.

[0894] This specific process flow allows companies to efficiently collect, evaluate, and share use cases of generative AI models within their group, improving overall productivity and promoting innovation. Furthermore, the introduction of an emotion engine improves the quality of feedback and maximizes the effectiveness of events.

[0895] Example 2

[0896] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0897] To effectively utilize generative AI models within a corporate group and promote productivity and innovation within each company, effective sharing and evaluation of use cases is necessary. However, with conventional systems, collecting, tagging, and categorizing use cases is done manually, which is time-consuming and labor-intensive. Another issue is that user feedback is not collected and analyzed sufficiently, which hinders the quality of the feedback. Furthermore, it is difficult to analyze user reactions in real time during an event and dynamically adjust presentation content.

[0898] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting use cases from each company in a corporate group, means for saving the collected use cases in a database and tagging and categorizing them, means for scoring the use cases based on evaluation criteria every quarter and creating rankings, means for preparing an event based on the evaluation results and presenting excellent use cases, means for preferentially displaying excellent use cases in the database after the event, means for collecting feedback from users and classifying the feedback as positive, negative, or neutral using an emotion analysis engine, and means for analyzing user emotion data in real time during the event and dynamically adjusting the content of the presentation. This enables effective collection and sharing of use cases, improves the quality of user feedback, and enables real-time presentation adjustments.

[0899] A "corporate group" is an organization formed by multiple companies working together to pursue common goals and interests.

[0900] "Use cases" are the results of specific applications or projects in which companies have used generative AI models, as well as the information gained in the process.

[0901] A "database" is a recording medium that systematically stores collected use cases and feedback, allowing for efficient search and management.

[0902] "Tagging" is a method of categorizing use cases and data with specific categories or keywords to make them easier to search and view.

[0903] "Categorization" is a method of classifying and structuring collected data according to specific criteria.

[0904] "Scoring" is the process of numerically evaluating use cases based on evaluation criteria and creating a ranking.

[0905] "Evaluation criteria" are indicators or rules established to judge the value or usefulness of a use case.

[0906] A "ranking" is a list of multiple use cases ordered based on evaluation criteria.

[0907] A "presentation" is a presentation format for introducing evaluated use cases to other companies and sharing knowledge.

[0908] "Portal" means a website or application that users within a corporate group can access to collect, view, and share information.

[0909] "Feedback" is data that expresses users' feelings, suggestions, and opinions about use cases and systems.

[0910] An "emotion analysis engine" is software or algorithms that analyze user feedback and real-time data and classify the emotions contained in that content as positive, negative, or neutral.

[0911] "Real-time analytics" is the process of analyzing data and obtaining results immediately as the data is generated.

[0912] "Dynamic adjustment" is the means by which presentations and system behavior can be instantly changed and adapted based on real-time analysis results.

[0913] MODE FOR CARRYING OUT THE INVENTION

[0914] This invention is a system that uses a generative AI model to effectively collect, evaluate, and share case studies within a corporate group, thereby improving productivity and promoting innovation across the entire company. In particular, by combining it with an emotion analysis engine that analyzes user emotions in real time, we aim to improve the quality of feedback and maximize the effectiveness of events.

[0915] Data Collection Portal

[0916] Users enter use cases that utilize generative AI models through a data collection portal. The data collection portal has fields for the case title, details, and results obtained (e.g., reduced work time, increased profits), and users enter these and press the submit button. The data collection portal has an authentication function, and only authenticated users can access it. A common ID and password are used for authentication.

[0917] Database Management Systems

[0918] The server receives the use cases submitted by users and stores them in a database. At this time, text analysis algorithms are used to automatically tag and categorize the cases based on their content, making them easier to search for later. The database management system can be a relational database management system (RDBMS), such as MySQL or PostgreSQL.

[0919] Shared Portal

[0920] Users can access the shared portal and search for and view use cases registered by other companies. Users search for specific keywords or categories, and the server executes a search within the database and displays a list of relevant use cases to the user. The shared portal is built as a web application that can be accessed from a web browser.

[0921] Rating and Ranking System

[0922] Every quarter, the server scores new use cases based on evaluation criteria, such as "time saved," "profit increase," and "uniqueness of use," and creates a ranking. The scoring uses machine learning algorithms to ensure fair and consistent evaluations.

[0923] Event Management System

[0924] The server prepares events based on the quarterly evaluation results. At the events, highly rated use cases are presented, allowing other companies to learn from them. During the events, real-time user feedback is collected and analyzed by a sentiment analysis engine. After the events, outstanding use cases are prioritized in the database.

[0925] Sentiment Analysis Engine

[0926] A sentiment analysis engine collects user-provided feedback and real-time comments and uses natural language processing (NLP) techniques to classify them into positive, negative, or neutral sentiment. A sentiment analysis engine can use machine learning models built in Python (e.g., TensorFlow or PyTorch), for example.

[0927] Specific operation example

[0928] For example, consider a case where Company A used a generative AI model to automate customer service, reducing inquiry response times by 30% and saving 300,000 yen per year. A user enters this case into the data collection portal, enters the title "Customer Service Automation," a detailed description, and the results, and presses the submit button.

[0929] The server receives the information and stores it in a database, automatically tagging it with "customer service" and "cost reduction." Later, when a user from Company B searches for cases related to "customer service" on the shared portal, Company A's cases will be listed and the user can view their details.

[0930] This case study was highly rated and was presented at the event. During the presentation, a sentiment analysis engine analyzed user reactions in real time, and if there were a lot of positive reactions, the content of the presentation was dynamically adjusted to emphasize those parts, maintaining the participants' interest and deepening their understanding.

[0931] Prompt Sentence Examples

[0932] "Please give us a specific example of how a generative AI model has been used to improve business processes."

[0933] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and productivity improvements, but also improving the quality of feedback.

[0934] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0935] Step 1:

[0936] The user accesses the data collection portal and enters authentication information (ID and password). The entered authentication information is sent to the server by the terminal. The server checks the authentication information against the database, and if authentication is successful, displays a data input form to the user. As a result, the user can access the data input form.

[0937] Step 2:

[0938] The user enters a use case for the generative AI model into a data entry form and presses the submit button. The input data includes the case title, details, and outcomes (e.g., reduced work time, increased profits). The device then sends this data to the server. The server stores the received data in a database and applies text analysis algorithms to automatically assign tags such as "customer service" or "cost reduction." This makes the stored data easier to search later.

[0939] Step 3:

[0940] A user accesses the shared portal and searches for use cases using a specific keyword (e.g., "customer service"). The device sends the search query to the server, which performs a search in the database and lists relevant use cases. As a result, the device displays the search results sent from the server to the user. The user can view the displayed use cases and check detailed information.

[0941] Step 4:

[0942] The server extracts new use cases from the database every quarter. It scores the extracted data based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use") using a machine learning algorithm. Based on the scoring results, the server creates a ranking, which allows the best use cases to be identified.

[0943] Step 5:

[0944] The server will use the quarterly evaluation results to prepare the schedule and content for the next event. At the event, materials will be created and presenters will be selected so that the most highly rated use cases will be presented. A function to collect feedback in real time will be provided during the event. Event materials and a feedback function will be provided.

[0945] Step 6:

[0946] Users attend the event and watch the presentations provided. A form is provided to collect feedback from users in real time during the event. Users enter their impressions and suggestions for improvement in the feedback form and press the submit button. The device then sends the feedback data to the server.

[0947] Step 7:

[0948] The server sends the received feedback data to the sentiment analysis engine, which analyzes the feedback data and classifies it into positive, negative, or neutral sentiment. The analysis results are sent to the server, which stores them in a database. This allows the system to consider improvements based on the content of the feedback.

[0949] Step 8:

[0950] Users watch presentations in real time during an event. The sentiment analysis engine collects and analyzes users' real-time emotional data to evaluate how the presentation content is perceived by the users. The server receives the data from the sentiment analysis engine and dynamically adjusts the content of the presentation, thereby maintaining user interest and providing a better presentation.

[0951] (Application example 2)

[0952] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0953] In systems that effectively utilize generative AI models within corporate groups to improve productivity and promote innovation across the entire company, there is a need for a mechanism that can recognize user emotions in real time and reflect them in high-quality feedback and work instructions.If this requirement is not met, it is difficult to maximize the quality of feedback and the effectiveness of events, and there is also the problem of not being able to improve the efficiency of factory work.

[0954] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0955] In this invention, the server includes: means for collecting use cases from each company in the corporate group; means for storing the collected use cases in a database and tagging and categorizing them; means for scoring the use cases based on evaluation criteria every quarter and creating rankings; means for preparing events based on the evaluation results and presenting outstanding use cases; means for displaying outstanding use cases in a prioritized manner in the database after the event; means for analyzing operator emotion data in real time and providing work instructions and feedback; and means for dynamically adjusting presentation content based on the emotion data. This enables the effective use of generative AI models across the entire corporate group, improving business efficiency and productivity. Furthermore, the quality of feedback can be improved by utilizing user emotion data, maximizing the effectiveness of events.

[0956] A "corporate group" is a group of multiple companies that share common goals and interests, and among which there are cooperative and business relationships.

[0957] A "use case" refers to a real-world application or outcome that utilizes a generative AI model in a specific setting or situation.

[0958] A "database" is a system for systematically and efficiently storing and managing use cases and other related information.

[0959] "Tagging" refers to the act of assigning labels to information in a database that indicate specific attributes or categories.

[0960] "Categorization" is a method of classifying information in a database based on certain commonalities.

[0961] "Scoring" is a method of assigning points to each use case based on specific evaluation criteria to determine its merits or demerits.

[0962] "Ranking" refers to ranking use cases based on the scoring results.

[0963] "Event" refers to a gathering or presentation held within a corporate group for the purpose of sharing evaluation results and use cases.

[0964] "Emotion data" is information that indicates an emotional state analyzed from user input and feedback.

[0965] "Presentation" refers to the act of explaining and announcing information about use cases and evaluation results verbally and visually to other companies and stakeholders.

[0966] "Real-time" refers to a time frame in which analysis and processing occur almost immediately.

[0967] The "emotion engine" is a system that analyzes the user's emotional data and classifies and evaluates their emotional state.

[0968] This invention is a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. In particular, it aims to maximize the effectiveness of events by combining it with an emotion engine that recognizes user emotions in real time to improve the quality of feedback and work instructions.

[0969] System configuration

[0970] The system consists of the following main components:

[0971] 1. Data Collection Portal

[0972] 2. Database Management System

[0973] 3. Shared Portal

[0974] 4. Rating and Ranking System

[0975] 5. Event Management System

[0976] 6. Emotion Engine

[0977] Data Collection Portal

[0978] Users enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduction in work time or increased profits) and submit the data. The portal has an authentication function, and only authenticated users can access it.

[0979] Database Management Systems

[0980] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[0981] Shared Portal

[0982] Users can access the shared portal and search for and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[0983] Rating and Ranking System

[0984] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). Rankings are created based on the scoring results, and outstanding cases are selected.

[0985] Event Management System

[0986] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[0987] Emotion Engine

[0988] The emotion engine is a component that recognizes and analyzes user emotions in real time. Specifically, it analyzes emotions contained in feedback and comments and categorizes them into emotional states such as positive, negative, and neutral.

[0989] Specific use cases

[0990] For example, a user operating a factory robot can enter a case study of "improving robot operation speed" through a data collection portal, providing a title, details, and results (e.g., a 90% efficiency improvement), and submit the study. The server stores this information in a database and automatically assigns tags such as "efficiency improvement" and "cost reduction."

[0991] When users at other factories search for "efficiency improvement" cases on the shared portal, this case will appear and they can view the details. If this case receives high praise at a quarterly event, event materials will be prepared. Users can give presentations that other companies can use as reference.

[0992] Furthermore, during the event, the emotion engine analyzes users' real-time reactions, and if there are a lot of positive reactions, the presentation content is dynamically adjusted to emphasize those points, maximizing the effectiveness of the presentation and increasing participant understanding and interest.

[0993] Prompt Sentence Examples

[0994] An example prompt for a generative AI model is:

[0995] Based on the feedback analysis of the robot's work, create a presentation to improve work efficiency. Highlight the positive feedback points and propose improvements for the negative feedback.

[0996] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and improved productivity, but also improving the quality of feedback by utilizing user emotional data.

[0997] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0998] Step 1:

[0999] Users access a data collection portal and input use cases that utilize generative AI models, including the case title, details, and results achieved (e.g., time saved or increased profits). This input data is then sent to the data collection portal.

[1000] Step 2:

[1001] The device receives the use case data sent by the user and sends it to the server. The server receives this data and stores it in a database. When storing it, it automatically tags and categorizes the cases based on their characteristics, such as "customer service" or "cost reduction." This tagging and categorization makes it easier to search the data.

[1002] Step 3:

[1003] Users access the shared portal to search and browse use cases in the database. When users enter search criteria, the server lists relevant use cases based on tagging and categories and displays them to the user, allowing users to quickly access the information they need.

[1004] Step 4:

[1005] The server extracts new use cases from the database every quarter. It scores each case based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.). It then assigns points to each evaluation criterion and calculates an overall score.

[1006] Step 5:

[1007] The server creates a ranking of the use cases based on the scoring results. Use cases with high scores are placed at the top of the list, and those with low scores are placed at the bottom. The ranking results are used to prepare for the event.

[1008] Step 6:

[1009] The server prepares an event based on the evaluation results. The highly evaluated cases are prepared to be presented at the event. At this time, the outstanding use cases are given special recognition and are prioritized in the database.

[1010] Step 7:

[1011] During the event, users will watch presentations delivered in real time, including top use cases.

[1012] Step 8:

[1013] The emotion engine analyzes user emotion data collected from devices during the event in real time. Input data includes user comments and feedback. The emotion engine analyzes this data and classifies it into positive, negative, or neutral emotional states.

[1014] Step 9:

[1015] The server receives the analysis results and dynamically adjusts the presentation content based on them. For example, if there are a lot of positive reactions, it will emphasize the success points, and if there are a lot of negative reactions, it will add improvement measures. This will help maintain and improve the understanding and interest of event participants.

[1016] Step 10:

[1017] After the event, the server will prioritize the best use cases in the database and encourage information sharing among participating companies, allowing other companies to learn from the best use cases and consider ways to use them in their own companies.

[1018] This series of processes promotes the effective use of generative AI models across the entire corporate group, improving business efficiency and productivity. Furthermore, by utilizing user emotion data, the quality of feedback is improved and the effectiveness of events is maximized.

[1019] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1020] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1021] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1022] [Third embodiment]

[1023] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1024] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1026] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1027] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1028] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1030] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1031] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1033] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1034] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1035] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. This system allows each company to collect, evaluate, and share use cases that utilize generative AI models, encouraging other companies to adopt similar methods.

[1036] System Overview

[1037] The system consists of the following main components:

[1038] 1. Data Collection Portal

[1039] 2. Database Management System

[1040] 3. Shared Portal

[1041] 4. Rating and Ranking System

[1042] 5. Event Management System

[1043] Data Collection Portal

[1044] Users (personnel at each company) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[1045] Database Management Systems

[1046] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[1047] Shared Portal

[1048] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[1049] Rating and Ranking System

[1050] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[1051] Event Management System

[1052] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[1053] Specific examples

[1054] For example, let's say Company A used a generative AI model to automate customer service inquiries, resulting in an average 30% reduction in inquiry response time and an annual cost reduction of 300,000 yen. The user (company A's representative) accesses the data collection portal, enters the case title "Customer Service Automation," a detailed description, and the results, and presses the submit button. The server saves this information in a database and assigns the tags "Customer Service" and "Cost Reduction."

[1055] Later, when a user at Company B searches for "customer service" cases on the shared portal, the case study from Company A appears and the user can view the details. Company B uses this as a reference to consider similar improvement measures at their own company.

[1056] If this case receives high praise at a quarterly event, the server will prepare materials for the event and a representative from Company A will give a presentation. Other companies will learn from the content and apply it to their own operations.

[1057] This will promote the effective use of generative AI models across the entire corporate group, resulting in improved business efficiency and productivity.

[1058] The processing flow will be explained below.

[1059] Specific processing flow of the program

[1060] (Data Collection Portal Processing)

[1061] Step 1:

[1062] The user accesses the data collection portal website.

[1063] Step 2:

[1064] The user enters authentication information (user ID and password) on the login screen and clicks the login button.

[1065] Step 3:

[1066] The server receives the entered authentication information and authenticates the user. If authentication is successful, the case registration form is displayed.

[1067] Step 4:

[1068] The user enters the case title, details, and results (such as reduced work time or increased profits) in the case registration form and presses the submit button.

[1069] Step 5:

[1070] The terminal transmits the input case data to the server.

[1071] Step 6:

[1072] The server stores the received case data in a database and automatically tags and categorizes them.

[1073] (Shared Portal Processing)

[1074] Step 7:

[1075] The user accesses the shared portal and proceeds to the case search screen.

[1076] Step 8:

[1077] The user enters search criteria (keywords and tags) and presses the search button.

[1078] Step 9:

[1079] The terminal transmits the user's search conditions to the server.

[1080] Step 10:

[1081] The server extracts cases that match the search criteria from the database and generates a list of related cases.

[1082] Step 11:

[1083] The server transmits the generated case list to the user's terminal and displays the search results.

[1084] Step 12:

[1085] Users can click on a case that interests them from the search results to access the details page and view more information.

[1086] Step 13:

[1087] The server records user access logs and accumulates data for analyzing usage trends.

[1088] (Rating and ranking system processing)

[1089] Step 14:

[1090] The server extracts new use cases from the database every quarter.

[1091] Step 15:

[1092] The server scores the extracted cases based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.).

[1093] Step 16:

[1094] The server creates a ranking based on the scoring results.

[1095] Step 17:

[1096] The server prepares the top case studies, along with the ranking results, as presentation materials for the event.

[1097] Step 18:

[1098] The server notifies the event schedule and a list of participating companies.

[1099] (Event management system processing)

[1100] Step 19:

[1101] The user follows the notified event date and participates in the event online or offline.

[1102] Step 20:

[1103] The server will give a presentation based on the top-ranked cases, announcing details of each case and its evaluation points.

[1104] Step 21:

[1105] Users will study the case studies presented at the event and take notes on points that can be applied to their own company's operations.

[1106] Step 22:

[1107] After the event, the server registers the awarded cases in a database as a priority display, and makes them accessible to all users through a shared portal.

[1108] (Handling feedback and system improvements)

[1109] Step 23:

[1110] Users can submit feedback and suggestions for improvement while using the system through a feedback form.

[1111] Step 24:

[1112] The server aggregates the feedback and improvement suggestions received and notifies the administrator.

[1113] Step 25:

[1114] The server implements system improvement measures based on instructions from the administrator and updates the system version.

[1115] This specific processing flow enables efficient collection, evaluation, and sharing of use cases of generative AI models within a corporate group, thereby improving overall productivity and promoting innovation.

[1116] Example 1

[1117] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1118] Conventional information sharing systems within corporate groups lack a consistent management system for effectively collecting, evaluating, and sharing examples of how individual companies have utilized generative AI models. This has made it difficult to improve productivity and promote innovation across the entire company. Furthermore, there have been challenges in efficiently searching for use cases, ensuring objectivity in evaluation, and ensuring optimal sharing methods.

[1119] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1120] In this invention, the server includes means for performing user authentication using authentication information, means for collecting use cases from each company in the corporate group, means for storing the collected use cases in a database and tagging and categorizing them using an NLP model, means for allowing other companies to search and view the use cases through a shared portal, means for scoring the use cases based on evaluation criteria using a machine learning algorithm every quarter and creating rankings, means for preparing an event based on the evaluation results and presenting excellent use cases, and means for preferentially displaying excellent use cases in the database after the event. This enables efficient and effective collection, evaluation, and sharing of use cases of generative AI models within the corporate group, thereby improving productivity and promoting innovation.

[1121] "Authentication Information" means a user ID, password, or other means of identification used to verify a user's identity.

[1122] "User authentication" is the process of using authentication information to verify a user's identity and grant them access to a system.

[1123] "Corporate group" refers to the entire group formed by the collaboration of multiple companies.

[1124] "Use cases" are specific results and practical reports obtained by each company using generative AI models.

[1125] A "database" is a computer system that systematically stores and manages collected information.

[1126] An "NLP model" is a machine learning model that uses natural language processing technology to analyze text data and extract meanings and categories.

[1127] "Tagging" is the process of assigning relevant keywords and labels to data to make it easier to search and classify.

[1128] "Categorization" is the process of classifying data into specific categories or groups.

[1129] A "shared portal" is a web-based interface that multiple users can access to search and view information.

[1130] A "machine learning algorithm" is a computational method that automatically learns from data and makes predictions and classifications.

[1131] "Scoring" is the process of assigning a score to data or cases based on specific evaluation criteria.

[1132] "Ranking" refers to the ranking of data or cases based on the evaluated scores.

[1133] An "event" is a gathering such as a presentation or seminar that is held on a specific date and time.

[1134] A "presentation" is the act of explaining and presenting information and examples to an audience.

[1135] "Feedback" refers to ratings, opinions, and comments provided by users.

[1136] An "access log" is data that keeps a record of users accessing a system.

[1137] "Usage trends" refers to patterns and tendencies in how users use the system.

[1138] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. This system allows each company to collect, evaluate, and share use cases that utilize generative AI models, encouraging other companies to adopt similar methods.

[1139] The system consists of the following main components: data collection portal, database management system, sharing portal, evaluation and ranking system, and event management system.

[1140] Data Collection Portal

[1141] Users enter use cases that utilize generative AI models through a data collection portal. User authentication is performed using authentication information (user ID and password), and only authenticated users can access the portal. The input information includes the case title, details, and results obtained.

[1142] As a specific example, a person in charge at Company A will enter details of a case study titled "Customer Service Automation" in which they reduced inquiry response time by an average of 30%, achieving annual cost savings of 300,000 yen, and then press the send button.

[1143] Database Management Systems

[1144] The server stores the received use cases in a database, typically a relational database such as MySQL or PostgreSQL, and uses an NLP model to analyze the text and automatically tag and categorize it into categories such as "customer service" or "cost reduction."

[1145] Specifically, the server invokes the NLP model, analyzes the input case content, assigns appropriate tags, and stores the tagged data in a database.

[1146] Shared Portal

[1147] Users can access the shared portal and search for and view use cases from other companies. The server uses a search engine such as ElasticSearch to list and display relevant cases based on the user's search criteria. It also has the ability to record user access logs and analyze usage trends.

[1148] As a specific example, when a user from Company B searches for cases related to "customer service," cases from Company A are displayed.

[1149] Rating and Ranking System

[1150] Every quarter, the server extracts new use cases from the database and scores them using a machine learning algorithm based on set evaluation criteria, such as "reduction of work time," "increased profits," and "uniqueness of use." A ranking is created based on the scoring results, and the best cases are selected.

[1151] Specifically, the server extracts cases from the database and runs a scoring algorithm to generate a ranking.

[1152] Event Management System

[1153] The server will then prepare an event based on the evaluation results. Highly rated cases will be presented at the event, and participating companies will be able to participate remotely. The event will be held using online conferencing tools such as Zoom and Microsoft Teams. Outstanding cases will be prioritized in the database.

[1154] As a concrete example, best practices are presented at quarterly events, and other companies can learn from them and use them to improve their own companies.

[1155] Example prompt

[1156] Please provide the case study title, details, and results of your business operations using generative AI models.

[1157] These components and specific processing steps will promote the effective use of generative AI models across the corporate group, thereby achieving improved operational efficiency and productivity.

[1158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1159] Step 1: User authentication

[1160] Input: User ID and password

[1161] Output: Authentication result (success or failure)

[1162] Specific behavior:

[1163] A user accesses the data collection portal and enters their user ID and password on the login page. The server sends the entered authentication information to the LDAP server for authentication. The LDAP server returns the authentication result, and if the server is successful, the user can proceed to the next step.

[1164] Step 2: Enter and submit your use case

[1165] Input: Case title, details, results

[1166] Output: Submitted use case

[1167] Specific behavior:

[1168] After authenticating, the user enters the use case title, details, and results obtained in the data collection portal, including specific numerical data (e.g., man-hour reduction percentage, cost reduction amount, etc.). By pressing the submit button, the data is sent to the server.

[1169] Step 3: Saving to the database

[1170] Input: Use case data

[1171] Output: Saved database records

[1172] Specific behavior:

[1173] The server receives the submitted use case and stores it in a relational database (e.g. MySQL or PostgreSQL), mapping the data to the appropriate tables and executing INSERT statements to store it.

[1174] Step 4: Tagging and categorizing the cases

[1175] Input: Saved database record

[1176] Output: Tagged and categorized data

[1177] Specific behavior:

[1178] The server inputs the stored data into an NLP model, analyzes the text, and automatically assigns tags such as "customer service" or "cost reduction" based on the analysis results, updating the record in the database.

[1179] Step 5: Search for cases in the shared portal

[1180] Input: Search keyword

[1181] Output: A list of search results

[1182] Specific behavior:

[1183] A user accesses the shared portal and enters a keyword (e.g., "customer service") into the search box. The server uses a search engine such as ElasticSearch to generate a search query based on the keyword and retrieves relevant cases from the database.

[1184] Step 6: Viewing search results

[1185] Input: list of search results

[1186] Output: The search results page that is displayed to the user

[1187] Specific behavior:

[1188] The server renders the search results retrieved from the database in HTML format, using an HTML template engine (e.g. Thymeleaf or Handlebars) to generate the search results page and send it back to the user's browser for display.

[1189] Step 7: Conduct evaluation and ranking

[1190] Input: Use cases in the database

[1191] Output: Evaluation and ranking results

[1192] Specific behavior:

[1193] The server extracts cases to be evaluated from the database every quarter. It runs a machine learning algorithm to score each case based on the set evaluation criteria (e.g., "reduction of work time," "increase in profits," "uniqueness of use," etc.). It generates a ranking based on the scoring results and stores it in the database.

[1194] Step 8: Prepare and execute the event

[1195] Input: Rating and ranking results

[1196] Output: Event materials and presentations

[1197] Specific behavior:

[1198] The server prepares event materials based on the evaluation results. The materials are generated in PDF or slide format and presented on the day of the event using online conferencing tools such as Zoom or Microsoft Teams. Outstanding cases are prioritized in the database, allowing other companies to learn from them.

[1199] These steps will promote the effective use of generative AI models across the corporate group, resulting in improved operational efficiency and productivity.

[1200] (Application example 1)

[1201] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1202] In conventional systems, there was no adequate method for effectively collecting, sharing, evaluating, and utilizing use cases of generative AI models within a corporate group. As a result, it was difficult to maximize the benefits of productivity improvement and cost reduction. Furthermore, improving task management and work efficiency was a key issue, particularly in logistics centers, and an effective solution was needed.

[1203] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1204] In this invention, the server includes: means for collecting use cases from each company in the corporate group; means for storing the collected use cases in a database and tagging and categorizing them; means for scoring the use cases based on evaluation criteria every quarter and creating rankings; means for preparing an event based on the evaluation results and presenting outstanding use cases; means for preferentially displaying outstanding use cases in the database after the event; means for including an AI assistant application for smart glasses that can be used by workers in the logistics center; means for managing tasks using voice recognition and presenting work instructions in real time; and means for monitoring task progress and presenting the next task. This enables effective use of generative AI models within the corporate group and significant improvement in work efficiency at the logistics center.

[1205] 1. A "corporate group" refers to multiple companies linked together under common capital and management policies.

[1206] 2. "Use Case" refers to information showing specific use cases and results of applying a generative AI model to business activities.

[1207] 3. "Database" refers to an information system that systematically stores and manages collected use cases and other related data.

[1208] 4. "Tagging" refers to the practice of assigning specific keywords or identifiers to data to make it easier to search for later.

[1209] 5. "Categorization" refers to the method of classifying collected data into specific categories.

[1210] 6. "Evaluation Criteria" refers to the criteria or measures used to evaluate a Use Case.

[1211] 7. "Scoring" refers to the process of assigning a score to a use case based on evaluation criteria.

[1212] 8. "Ranking" refers to the ranking of use cases based on the scoring results.

[1213] 9. "Event" means an event or gathering to announce evaluation results and present successful use cases.

[1214] 10. "AI assistant application" refers to application software that uses artificial intelligence technology to assist users in their work.

[1215] 11. "Smart glasses" refers to a wearable device in the form of glasses with built-in displays and sensors.

[1216] 12. "Speech recognition" refers to the technology that analyzes human speech and recognizes it as text or commands.

[1217] 13. "Task management" refers to the method of listing the tasks required to achieve a specific goal and tracking their progress.

[1218] 14. "Real-time" refers to immediate processing or response without delay.

[1219] 15. "Work Instructions" means the specific instructions required to complete a particular task.

[1220] 16. “Progress management” refers to the process of monitoring the progress of work and making adjustments as needed.

[1221] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. The main purpose of this system is to improve work efficiency at logistics centers.

[1222] System Overview

[1223] The system consists of the following main components:

[1224] 1. Data Collection Portal

[1225] 2. Database Management System

[1226] 3. Shared Portal

[1227] 4. Rating and Ranking System

[1228] 5. Event Management System

[1229] 6. AI Assistant Application for Smart Glasses

[1230] Data Collection Portal

[1231] Company personnel (users) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[1232] Database Management Systems

[1233] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[1234] Shared Portal

[1235] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[1236] Rating and Ranking System

[1237] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[1238] Event Management System

[1239] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[1240] AI assistant application for smart glasses

[1241] This application allows workers in a logistics center to use smart glasses to manage tasks using generative AI models. Smart glasses are wearable devices with built-in displays and sensors. The application provides the following features:

[1242] 1. Real-time task display: The smart glasses display the worker's task list and work procedures in real time.

[1243] 2. Speech Recognition and Instructions: The next work task and instructions can be received through the worker's voice input. The speech recognition system uses the speech_recognition library.

[1244] 3. Task progress management: Register completed tasks and get real-time updates on progress.

[1245] 4. Optimal route suggestion: Optimizes routes within the warehouse to help efficiently pick up and deliver goods.

[1246] Hardware and software used

[1247] Hardware: Smart glasses, microphone

[1248] Software: Python, speech_recognition library, pyttsx3 library

[1249] Specific examples

[1250] For example, if a worker at a logistics center wears smart glasses and says, "Tell me what my next task is," the AI ​​assistant application will give instructions such as, "Move pallet A." Once the worker has completed the task, they can say, "This task is complete," and receive instructions for the next task.

[1251] Prompt Sentence Examples

[1252] "Tell me the next task"

[1253] Complete this task

[1254] "Show more tasks"

[1255] This will significantly improve the work efficiency of the logistics center and promote the effective use of generative AI models across the corporate group.

[1256] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1257] Step 1:

[1258] The user wears the smart glasses and gives instructions via voice input such as "Tell me the next task." At this time, the voice input is captured using a microphone. The input voice data is converted into text data by the voice recognition system (speech_recognition library) in the smart glasses.

[1259] Step 2:

[1260] The smart glasses receive the text data generated by the voice recognition system and send it to the backend server to present the next task to the user. The backend server selects the next task from the current task list and returns it to the smart glasses as text data. At this time, it queries the task management database for information on related tasks and selects the appropriate task.

[1261] Step 3:

[1262] The smart glasses display the next task text data received from the backend server and also provide audio instructions using the pyttsx3 library, giving the user both visual and audible confirmation of what they need to do next.

[1263] Step 4:

[1264] After completing the task, the user again speaks "I've completed this task." The microphone again captures the voice data, which is then converted into text data by the speech recognition system.

[1265] Step 5:

[1266] The smart glasses send the task completion text data generated by the voice recognition system to the backend server, which updates the task management database to record that the current task has been completed, and prepares to select a new task from the next task list and provide it to the user.

[1267] Step 6:

[1268] The smart glasses receive new task information from the backend server and present it to the user visually and audibly, updating the next task in real time and helping the user work efficiently.

[1269] Through these steps, workers within the logistics center can complete tasks efficiently and quickly, improving overall work efficiency.

[1270] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1271] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. In particular, the system aims to improve the quality of feedback and maximize the effectiveness of events by combining an emotion engine that recognizes user emotions.

[1272] System Overview

[1273] The system consists of the following main components:

[1274] 1. Data Collection Portal

[1275] 2. Database Management System

[1276] 3. Shared Portal

[1277] 4. Rating and Ranking System

[1278] 5. Event Management System

[1279] 6. Emotion Engine

[1280] Data Collection Portal

[1281] Users (personnel at each company) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[1282] Database Management Systems

[1283] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[1284] Shared Portal

[1285] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[1286] Rating and Ranking System

[1287] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[1288] Event Management System

[1289] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[1290] Emotion Engine

[1291] The emotion engine is a component that recognizes and analyzes user emotions in real time. Specifically, it analyzes emotions contained in feedback and comments and categorizes them into emotional states such as positive, negative, and neutral.

[1292] Specific processing explanation

[1293] The processing of the data collection portal and database management system from step 1 to step 6 has been described above.

[1294] The shared portal processing from step 7 to step 13 is performed in a similar manner.

[1295] The evaluation and ranking system processes from step 14 to step 18 are carried out in the same manner.

[1296] Further processing by the emotion engine:

[1297] Step 19:

[1298] Users can enter their thoughts and suggestions for improvement through a feedback form.

[1299] Step 20:

[1300] The terminal transmits the user's input data to the emotion engine.

[1301] Step 21:

[1302] The emotion engine analyzes the input data and classifies the emotional state as positive, negative, or neutral.

[1303] Step 22:

[1304] The server stores the analysis results in a database and categorizes the feedback based on the emotional state.

[1305] Real-time sentiment analysis during the event:

[1306] Step 23:

[1307] Users view presentations delivered in real time during the event.

[1308] Step 24:

[1309] The emotion engine collects and analyzes real-time user emotion data to evaluate how the presentation content is perceived by the user.

[1310] Step 25:

[1311] The server dynamically adjusts the presentation content based on data from the emotion engine, providing information to keep the user engaged.

[1312] Specific examples

[1313] For example, let's say Company A used a generative AI model to automate customer service inquiries, resulting in an average 30% reduction in inquiry response time and an annual cost reduction of 300,000 yen. The user (company A's representative) accesses the data collection portal, enters the case title "Customer Service Automation," a detailed description, and the results, and presses the submit button. The server saves this information in a database and assigns the tags "Customer Service" and "Cost Reduction."

[1314] Later, when a user at Company B searches for "customer service" cases on the shared portal, the case study from Company A appears and the user can view the details. Company B uses this as a reference to consider similar improvement measures at their own company.

[1315] If this case receives high praise at a quarterly event, the server will prepare materials for the event and a representative from Company A will give a presentation. Other companies will learn from the content and apply it to their own operations.

[1316] Furthermore, the emotion engine analyzes user reactions during the event, and if there are many positive reactions, it dynamically adjusts the presentation content to emphasize those points, maximizing the effectiveness of the presentation and increasing participant understanding and interest.

[1317] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and improved productivity, but also improving the quality of feedback by utilizing user emotional data.

[1318] The processing flow will be explained below.

[1319] Specific processing flow of the program

[1320] (Data Collection Portal Processing)

[1321] Step 1:

[1322] The user accesses the data collection portal website.

[1323] Step 2:

[1324] The user enters authentication information (user ID and password) on the login screen and clicks the login button.

[1325] Step 3:

[1326] The server receives the entered authentication information and authenticates the user. If authentication is successful, the case registration form is displayed.

[1327] Step 4:

[1328] The user enters the case title, details, and results (such as reduced work time or increased profits) in the case registration form and presses the submit button.

[1329] Step 5:

[1330] The terminal transmits the input case data to the server.

[1331] Step 6:

[1332] The server stores the received case data in a database, automatically tagging it with categories such as "customer service" and "cost reduction."

[1333] (Shared Portal Processing)

[1334] Step 7:

[1335] The user accesses the shared portal and proceeds to the case search screen.

[1336] Step 8:

[1337] The user enters search criteria (keywords and tags) and presses the search button.

[1338] Step 9:

[1339] The terminal transmits the user's search conditions to the server.

[1340] Step 10:

[1341] The server extracts cases that match the search criteria from the database and generates a list of related cases.

[1342] Step 11:

[1343] The server transmits the generated case list to the user's terminal and displays the search results.

[1344] Step 12:

[1345] Users can click on a case that interests them from the search results to access the details page and view more information.

[1346] Step 13:

[1347] The server records user access logs and accumulates data for analyzing usage trends.

[1348] (Rating and ranking system processing)

[1349] Step 14:

[1350] The server extracts new use cases from the database every quarter.

[1351] Step 15:

[1352] The server scores the extracted cases based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.).

[1353] Step 16:

[1354] The server creates a ranking based on the scoring results.

[1355] Step 17:

[1356] The server prepares the top case studies, along with the ranking results, as presentation materials for the event.

[1357] Step 18:

[1358] The server notifies the event schedule and a list of participating companies.

[1359] (Event management system processing)

[1360] Step 19:

[1361] The user follows the notified event date and participates in the event online or offline.

[1362] Step 20:

[1363] The server will give a presentation based on the top-ranked cases, announcing details of each case and its evaluation points.

[1364] Step 21:

[1365] Users will study the case studies presented at the event and take notes on points that can be applied to their own company's operations.

[1366] Step 22:

[1367] After the event, the server registers the awarded cases in a database as a priority display, and makes them accessible to all users through a shared portal.

[1368] (Handling feedback and system improvements)

[1369] Step 23:

[1370] Users can submit feedback and suggestions for improvement while using the system through a feedback form.

[1371] Step 24:

[1372] The server aggregates the feedback and improvement suggestions received and notifies the administrator.

[1373] Step 25:

[1374] The server implements system improvement measures based on instructions from the administrator and updates the system version.

[1375] (Processed by emotion engine)

[1376] Step 26:

[1377] Users can enter their thoughts and suggestions for improvement through a feedback form.

[1378] Step 27:

[1379] The terminal transmits the user's input data to the emotion engine.

[1380] Step 28:

[1381] The emotion engine analyzes the input data and classifies the emotional state as positive, negative, or neutral.

[1382] Step 29:

[1383] The server stores the analysis results in a database and categorizes the feedback based on the emotional state.

[1384] (Real-time sentiment analysis during the event)

[1385] Step 30:

[1386] Users view presentations delivered in real time during the event.

[1387] Step 31:

[1388] The emotion engine collects and analyzes real-time user emotion data to evaluate how the presentation content is perceived by the user.

[1389] Step 32:

[1390] The server dynamically adjusts the presentation content based on data from the emotion engine, providing information to keep the user engaged.

[1391] This specific process flow allows companies to efficiently collect, evaluate, and share use cases of generative AI models within their group, improving overall productivity and promoting innovation. Furthermore, the introduction of an emotion engine improves the quality of feedback and maximizes the effectiveness of events.

[1392] Example 2

[1393] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1394] To effectively utilize generative AI models within a corporate group and promote productivity and innovation within each company, effective sharing and evaluation of use cases is necessary. However, with conventional systems, collecting, tagging, and categorizing use cases is done manually, which is time-consuming and labor-intensive. Another issue is that user feedback is not collected and analyzed sufficiently, which hinders the quality of the feedback. Furthermore, it is difficult to analyze user reactions in real time during an event and dynamically adjust presentation content.

[1395] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting use cases from each company in a corporate group, means for saving the collected use cases in a database and tagging and categorizing them, means for scoring the use cases based on evaluation criteria every quarter and creating rankings, means for preparing an event based on the evaluation results and presenting excellent use cases, means for preferentially displaying excellent use cases in the database after the event, means for collecting feedback from users and classifying the feedback as positive, negative, or neutral using an emotion analysis engine, and means for analyzing user emotion data in real time during the event and dynamically adjusting the content of the presentation. This enables effective collection and sharing of use cases, improves the quality of user feedback, and enables real-time presentation adjustments.

[1396] A "corporate group" is an organization formed by multiple companies working together to pursue common goals and interests.

[1397] "Use cases" are the results of specific applications or projects in which companies have used generative AI models, as well as the information gained in the process.

[1398] A "database" is a recording medium that systematically stores collected use cases and feedback, allowing for efficient search and management.

[1399] "Tagging" is a method of categorizing use cases and data with specific categories or keywords to make them easier to search and view.

[1400] "Categorization" is a method of classifying and structuring collected data according to specific criteria.

[1401] "Scoring" is the process of numerically evaluating use cases based on evaluation criteria and creating a ranking.

[1402] "Evaluation criteria" are indicators or rules established to judge the value or usefulness of a use case.

[1403] A "ranking" is a list of multiple use cases ordered based on evaluation criteria.

[1404] A "presentation" is a presentation format for introducing evaluated use cases to other companies and sharing knowledge.

[1405] "Portal" means a website or application that users within a corporate group can access to collect, view, and share information.

[1406] "Feedback" is data that expresses users' feelings, suggestions, and opinions about use cases and systems.

[1407] An "emotion analysis engine" is software or algorithms that analyze user feedback and real-time data and classify the emotions contained in that content as positive, negative, or neutral.

[1408] "Real-time analytics" is the process of analyzing data and obtaining results immediately as the data is generated.

[1409] "Dynamic adjustment" is the means by which presentations and system behavior can be instantly changed and adapted based on real-time analysis results.

[1410] MODE FOR CARRYING OUT THE INVENTION

[1411] This invention is a system that uses a generative AI model to effectively collect, evaluate, and share case studies within a corporate group, thereby improving productivity and promoting innovation across the entire company. In particular, by combining it with an emotion analysis engine that analyzes user emotions in real time, we aim to improve the quality of feedback and maximize the effectiveness of events.

[1412] Data Collection Portal

[1413] Users enter use cases that utilize generative AI models through a data collection portal. The data collection portal has fields for the case title, details, and results obtained (e.g., reduced work time, increased profits), and users enter these and press the submit button. The data collection portal has an authentication function, and only authenticated users can access it. A common ID and password are used for authentication.

[1414] Database Management Systems

[1415] The server receives the use cases submitted by users and stores them in a database. At this time, text analysis algorithms are used to automatically tag and categorize the cases based on their content, making them easier to search for later. The database management system can be a relational database management system (RDBMS), such as MySQL or PostgreSQL.

[1416] Shared Portal

[1417] Users can access the shared portal and search for and view use cases registered by other companies. Users search for specific keywords or categories, and the server executes a search within the database and displays a list of relevant use cases to the user. The shared portal is built as a web application that can be accessed from a web browser.

[1418] Rating and Ranking System

[1419] Every quarter, the server scores new use cases based on evaluation criteria, such as "time saved," "profit increase," and "uniqueness of use," and creates a ranking. The scoring uses machine learning algorithms to ensure fair and consistent evaluations.

[1420] Event Management System

[1421] The server prepares events based on the quarterly evaluation results. At the events, highly rated use cases are presented, allowing other companies to learn from them. During the events, real-time user feedback is collected and analyzed by a sentiment analysis engine. After the events, outstanding use cases are prioritized in the database.

[1422] Sentiment Analysis Engine

[1423] A sentiment analysis engine collects user-provided feedback and real-time comments and uses natural language processing (NLP) techniques to classify them into positive, negative, or neutral sentiment. A sentiment analysis engine can use machine learning models built in Python (e.g., TensorFlow or PyTorch), for example.

[1424] Specific operation example

[1425] For example, consider a case where Company A used a generative AI model to automate customer service, reducing inquiry response times by 30% and saving 300,000 yen per year. A user enters this case into the data collection portal, enters the title "Customer Service Automation," a detailed description, and the results, and presses the submit button.

[1426] The server receives the information and stores it in a database, automatically tagging it with "customer service" and "cost reduction." Later, when a user from Company B searches for cases related to "customer service" on the shared portal, Company A's cases will be listed and the user can view their details.

[1427] This case study was highly rated and was presented at the event. During the presentation, a sentiment analysis engine analyzed user reactions in real time, and if there were a lot of positive reactions, the content of the presentation was dynamically adjusted to emphasize those parts, maintaining the participants' interest and deepening their understanding.

[1428] Prompt Sentence Examples

[1429] "Please give us a specific example of how a generative AI model has been used to improve business processes."

[1430] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and productivity improvements, but also improving the quality of feedback.

[1431] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1432] Step 1:

[1433] The user accesses the data collection portal and enters authentication information (ID and password). The entered authentication information is sent to the server by the terminal. The server checks the authentication information against the database, and if authentication is successful, displays a data input form to the user. As a result, the user can access the data input form.

[1434] Step 2:

[1435] The user enters a use case for the generative AI model into a data entry form and presses the submit button. The input data includes the case title, details, and outcomes (e.g., reduced work time, increased profits). The device then sends this data to the server. The server stores the received data in a database and applies text analysis algorithms to automatically assign tags such as "customer service" or "cost reduction." This makes the stored data easier to search later.

[1436] Step 3:

[1437] A user accesses the shared portal and searches for use cases using a specific keyword (e.g., "customer service"). The device sends the search query to the server, which performs a search in the database and lists relevant use cases. As a result, the device displays the search results sent from the server to the user. The user can view the displayed use cases and check detailed information.

[1438] Step 4:

[1439] The server extracts new use cases from the database every quarter. It scores the extracted data based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use") using a machine learning algorithm. Based on the scoring results, the server creates a ranking, which allows the best use cases to be identified.

[1440] Step 5:

[1441] The server will use the quarterly evaluation results to prepare the schedule and content for the next event. At the event, materials will be created and presenters will be selected so that the most highly rated use cases will be presented. A function to collect feedback in real time will be provided during the event. Event materials and a feedback function will be provided.

[1442] Step 6:

[1443] Users attend the event and watch the presentations provided. A form is provided to collect feedback from users in real time during the event. Users enter their impressions and suggestions for improvement in the feedback form and press the submit button. The device then sends the feedback data to the server.

[1444] Step 7:

[1445] The server sends the received feedback data to the sentiment analysis engine, which analyzes the feedback data and classifies it into positive, negative, or neutral sentiment. The analysis results are sent to the server, which stores them in a database. This allows the system to consider improvements based on the content of the feedback.

[1446] Step 8:

[1447] Users watch presentations in real time during an event. The sentiment analysis engine collects and analyzes users' real-time emotional data to evaluate how the presentation content is perceived by the users. The server receives the data from the sentiment analysis engine and dynamically adjusts the content of the presentation, thereby maintaining user interest and providing a better presentation.

[1448] (Application example 2)

[1449] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1450] In systems that effectively utilize generative AI models within corporate groups to improve productivity and promote innovation across the entire company, there is a need for a mechanism that can recognize user emotions in real time and reflect them in high-quality feedback and work instructions.If this requirement is not met, it is difficult to maximize the quality of feedback and the effectiveness of events, and there is also the problem of not being able to improve the efficiency of factory work.

[1451] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1452] In this invention, the server includes: means for collecting use cases from each company in the corporate group; means for storing the collected use cases in a database and tagging and categorizing them; means for scoring the use cases based on evaluation criteria every quarter and creating rankings; means for preparing events based on the evaluation results and presenting outstanding use cases; means for displaying outstanding use cases in a prioritized manner in the database after the event; means for analyzing operator emotion data in real time and providing work instructions and feedback; and means for dynamically adjusting presentation content based on the emotion data. This enables the effective use of generative AI models across the entire corporate group, improving business efficiency and productivity. Furthermore, the quality of feedback can be improved by utilizing user emotion data, maximizing the effectiveness of events.

[1453] A "corporate group" is a group of multiple companies that share common goals and interests, and among which there are cooperative and business relationships.

[1454] A "use case" refers to a real-world application or outcome that utilizes a generative AI model in a specific setting or situation.

[1455] A "database" is a system for systematically and efficiently storing and managing use cases and other related information.

[1456] "Tagging" refers to the act of assigning labels to information in a database that indicate specific attributes or categories.

[1457] "Categorization" is a method of classifying information in a database based on certain commonalities.

[1458] "Scoring" is a method of assigning points to each use case based on specific evaluation criteria to determine its merits or demerits.

[1459] "Ranking" refers to ranking use cases based on the scoring results.

[1460] "Event" refers to a gathering or presentation held within a corporate group for the purpose of sharing evaluation results and use cases.

[1461] "Emotion data" is information that indicates an emotional state analyzed from user input and feedback.

[1462] "Presentation" refers to the act of explaining and announcing information about use cases and evaluation results verbally and visually to other companies and stakeholders.

[1463] "Real-time" refers to a time frame in which analysis and processing occur almost immediately.

[1464] The "emotion engine" is a system that analyzes the user's emotional data and classifies and evaluates their emotional state.

[1465] This invention is a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. In particular, it aims to maximize the effectiveness of events by combining it with an emotion engine that recognizes user emotions in real time to improve the quality of feedback and work instructions.

[1466] System configuration

[1467] The system consists of the following main components:

[1468] 1. Data Collection Portal

[1469] 2. Database Management System

[1470] 3. Shared Portal

[1471] 4. Rating and Ranking System

[1472] 5. Event Management System

[1473] 6. Emotion Engine

[1474] Data Collection Portal

[1475] Users enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduction in work time or increased profits) and submit the data. The portal has an authentication function, and only authenticated users can access it.

[1476] Database Management Systems

[1477] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[1478] Shared Portal

[1479] Users can access the shared portal and search for and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[1480] Rating and Ranking System

[1481] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). Rankings are created based on the scoring results, and outstanding cases are selected.

[1482] Event Management System

[1483] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[1484] Emotion Engine

[1485] The emotion engine is a component that recognizes and analyzes user emotions in real time. Specifically, it analyzes emotions contained in feedback and comments and categorizes them into emotional states such as positive, negative, and neutral.

[1486] Specific use cases

[1487] For example, a user operating a factory robot can enter a case study of "improving robot operation speed" through a data collection portal, providing a title, details, and results (e.g., a 90% efficiency improvement), and submit the study. The server stores this information in a database and automatically assigns tags such as "efficiency improvement" and "cost reduction."

[1488] When users at other factories search for "efficiency improvement" cases on the shared portal, this case will appear and they can view the details. If this case receives high praise at a quarterly event, event materials will be prepared. Users can give presentations that other companies can use as reference.

[1489] Furthermore, during the event, the emotion engine analyzes users' real-time reactions, and if there are a lot of positive reactions, the presentation content is dynamically adjusted to emphasize those points, maximizing the effectiveness of the presentation and increasing participant understanding and interest.

[1490] Prompt Sentence Examples

[1491] An example prompt for a generative AI model is:

[1492] Based on the feedback analysis of the robot's work, create a presentation to improve work efficiency. Highlight the positive feedback points and propose improvements for the negative feedback.

[1493] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and improved productivity, but also improving the quality of feedback by utilizing user emotional data.

[1494] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1495] Step 1:

[1496] Users access a data collection portal and input use cases that utilize generative AI models, including the case title, details, and results achieved (e.g., time saved or increased profits). This input data is then sent to the data collection portal.

[1497] Step 2:

[1498] The device receives the use case data sent by the user and sends it to the server. The server receives this data and stores it in a database. When storing it, it automatically tags and categorizes the cases based on their characteristics, such as "customer service" or "cost reduction." This tagging and categorization makes it easier to search the data.

[1499] Step 3:

[1500] Users access the shared portal to search and browse use cases in the database. When users enter search criteria, the server lists relevant use cases based on tagging and categories and displays them to the user, allowing users to quickly access the information they need.

[1501] Step 4:

[1502] The server extracts new use cases from the database every quarter. It scores each case based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.). It then assigns points to each evaluation criterion and calculates an overall score.

[1503] Step 5:

[1504] The server creates a ranking of the use cases based on the scoring results. Use cases with high scores are placed at the top of the list, and those with low scores are placed at the bottom. The ranking results are used to prepare for the event.

[1505] Step 6:

[1506] The server prepares an event based on the evaluation results. The highly evaluated cases are prepared to be presented at the event. At this time, the outstanding use cases are given special recognition and are prioritized in the database.

[1507] Step 7:

[1508] During the event, users will watch presentations delivered in real time, including top use cases.

[1509] Step 8:

[1510] The emotion engine analyzes user emotion data collected from devices during the event in real time. Input data includes user comments and feedback. The emotion engine analyzes this data and classifies it into positive, negative, or neutral emotional states.

[1511] Step 9:

[1512] The server receives the analysis results and dynamically adjusts the presentation content based on them. For example, if there are a lot of positive reactions, it will emphasize the success points, and if there are a lot of negative reactions, it will add improvement measures. This will help maintain and improve the understanding and interest of event participants.

[1513] Step 10:

[1514] After the event, the server will prioritize the best use cases in the database and encourage information sharing among participating companies, allowing other companies to learn from the best use cases and consider ways to use them in their own companies.

[1515] This series of processes promotes the effective use of generative AI models across the entire corporate group, improving business efficiency and productivity. Furthermore, by utilizing user emotion data, the quality of feedback is improved and the effectiveness of events is maximized.

[1516] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1517] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1518] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1519] [Fourth embodiment]

[1520] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1521] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1522] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1523] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1524] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1525] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1526] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1527] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1528] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1529] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1530] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1531] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1532] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1533] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. This system allows each company to collect, evaluate, and share use cases that utilize generative AI models, encouraging other companies to adopt similar methods.

[1534] System Overview

[1535] The system consists of the following main components:

[1536] 1. Data Collection Portal

[1537] 2. Database Management System

[1538] 3. Shared Portal

[1539] 4. Rating and Ranking System

[1540] 5. Event Management System

[1541] Data Collection Portal

[1542] Users (personnel at each company) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[1543] Database Management Systems

[1544] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[1545] Shared Portal

[1546] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[1547] Rating and Ranking System

[1548] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[1549] Event Management System

[1550] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[1551] Specific examples

[1552] For example, let's say Company A used a generative AI model to automate customer service inquiries, resulting in an average 30% reduction in inquiry response time and an annual cost reduction of 300,000 yen. The user (company A's representative) accesses the data collection portal, enters the case title "Customer Service Automation," a detailed description, and the results, and presses the submit button. The server saves this information in a database and assigns the tags "Customer Service" and "Cost Reduction."

[1553] Later, when a user at Company B searches for "customer service" cases on the shared portal, the case study from Company A appears and the user can view the details. Company B uses this as a reference to consider similar improvement measures at their own company.

[1554] If this case receives high praise at a quarterly event, the server will prepare materials for the event and a representative from Company A will give a presentation. Other companies will learn from the content and apply it to their own operations.

[1555] This will promote the effective use of generative AI models across the entire corporate group, resulting in improved business efficiency and productivity.

[1556] The processing flow will be explained below.

[1557] Specific processing flow of the program

[1558] (Data Collection Portal Processing)

[1559] Step 1:

[1560] The user accesses the data collection portal website.

[1561] Step 2:

[1562] The user enters authentication information (user ID and password) on the login screen and clicks the login button.

[1563] Step 3:

[1564] The server receives the entered authentication information and authenticates the user. If authentication is successful, the case registration form is displayed.

[1565] Step 4:

[1566] The user enters the case title, details, and results (such as reduced work time or increased profits) in the case registration form and presses the submit button.

[1567] Step 5:

[1568] The terminal transmits the input case data to the server.

[1569] Step 6:

[1570] The server stores the received case data in a database and automatically tags and categorizes them.

[1571] (Shared Portal Processing)

[1572] Step 7:

[1573] The user accesses the shared portal and proceeds to the case search screen.

[1574] Step 8:

[1575] The user enters search criteria (keywords and tags) and presses the search button.

[1576] Step 9:

[1577] The terminal transmits the user's search conditions to the server.

[1578] Step 10:

[1579] The server extracts cases that match the search criteria from the database and generates a list of related cases.

[1580] Step 11:

[1581] The server transmits the generated case list to the user's terminal and displays the search results.

[1582] Step 12:

[1583] Users can click on a case that interests them from the search results to access the details page and view more information.

[1584] Step 13:

[1585] The server records user access logs and accumulates data for analyzing usage trends.

[1586] (Rating and ranking system processing)

[1587] Step 14:

[1588] The server extracts new use cases from the database every quarter.

[1589] Step 15:

[1590] The server scores the extracted cases based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.).

[1591] Step 16:

[1592] The server creates a ranking based on the scoring results.

[1593] Step 17:

[1594] The server prepares the top case studies, along with the ranking results, as presentation materials for the event.

[1595] Step 18:

[1596] The server notifies the event schedule and a list of participating companies.

[1597] (Event management system processing)

[1598] Step 19:

[1599] The user follows the notified event date and participates in the event online or offline.

[1600] Step 20:

[1601] The server will give a presentation based on the top-ranked cases, announcing details of each case and its evaluation points.

[1602] Step 21:

[1603] Users will study the case studies presented at the event and take notes on points that can be applied to their own company's operations.

[1604] Step 22:

[1605] After the event, the server registers the awarded cases in a database as a priority display, and makes them accessible to all users through a shared portal.

[1606] (Handling feedback and system improvements)

[1607] Step 23:

[1608] Users can submit feedback and suggestions for improvement while using the system through a feedback form.

[1609] Step 24:

[1610] The server aggregates the feedback and improvement suggestions received and notifies the administrator.

[1611] Step 25:

[1612] The server implements system improvement measures based on instructions from the administrator and updates the system version.

[1613] This specific processing flow enables efficient collection, evaluation, and sharing of use cases of generative AI models within a corporate group, thereby improving overall productivity and promoting innovation.

[1614] Example 1

[1615] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1616] Conventional information sharing systems within corporate groups lack a consistent management system for effectively collecting, evaluating, and sharing examples of how individual companies have utilized generative AI models. This has made it difficult to improve productivity and promote innovation across the entire company. Furthermore, there have been challenges in efficiently searching for use cases, ensuring objectivity in evaluation, and ensuring optimal sharing methods.

[1617] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1618] In this invention, the server includes means for performing user authentication using authentication information, means for collecting use cases from each company in the corporate group, means for storing the collected use cases in a database and tagging and categorizing them using an NLP model, means for allowing other companies to search and view the use cases through a shared portal, means for scoring the use cases based on evaluation criteria using a machine learning algorithm every quarter and creating rankings, means for preparing an event based on the evaluation results and presenting excellent use cases, and means for preferentially displaying excellent use cases in the database after the event. This enables efficient and effective collection, evaluation, and sharing of use cases of generative AI models within the corporate group, thereby improving productivity and promoting innovation.

[1619] "Authentication Information" means a user ID, password, or other means of identification used to verify a user's identity.

[1620] "User authentication" is the process of using authentication information to verify a user's identity and grant them access to a system.

[1621] "Corporate group" refers to the entire group formed by the collaboration of multiple companies.

[1622] "Use cases" are specific results and practical reports obtained by each company using generative AI models.

[1623] A "database" is a computer system that systematically stores and manages collected information.

[1624] An "NLP model" is a machine learning model that uses natural language processing technology to analyze text data and extract meanings and categories.

[1625] "Tagging" is the process of assigning relevant keywords and labels to data to make it easier to search and classify.

[1626] "Categorization" is the process of classifying data into specific categories or groups.

[1627] A "shared portal" is a web-based interface that multiple users can access to search and view information.

[1628] A "machine learning algorithm" is a computational method that automatically learns from data and makes predictions and classifications.

[1629] "Scoring" is the process of assigning a score to data or cases based on specific evaluation criteria.

[1630] "Ranking" refers to the ranking of data or cases based on the evaluated scores.

[1631] An "event" is a gathering such as a presentation or seminar that is held on a specific date and time.

[1632] A "presentation" is the act of explaining and presenting information and examples to an audience.

[1633] "Feedback" refers to ratings, opinions, and comments provided by users.

[1634] An "access log" is data that keeps a record of users accessing a system.

[1635] "Usage trends" refers to patterns and tendencies in how users use the system.

[1636] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. This system allows each company to collect, evaluate, and share use cases that utilize generative AI models, encouraging other companies to adopt similar methods.

[1637] The system consists of the following main components: data collection portal, database management system, sharing portal, evaluation and ranking system, and event management system.

[1638] Data Collection Portal

[1639] Users enter use cases that utilize generative AI models through a data collection portal. User authentication is performed using authentication information (user ID and password), and only authenticated users can access the portal. The input information includes the case title, details, and results obtained.

[1640] As a specific example, a person in charge at Company A will enter details of a case study titled "Customer Service Automation" in which they reduced inquiry response time by an average of 30%, achieving annual cost savings of 300,000 yen, and then press the send button.

[1641] Database Management Systems

[1642] The server stores the received use cases in a database, typically a relational database such as MySQL or PostgreSQL, and uses an NLP model to analyze the text and automatically tag and categorize it into categories such as "customer service" or "cost reduction."

[1643] Specifically, the server invokes the NLP model, analyzes the input case content, assigns appropriate tags, and stores the tagged data in a database.

[1644] Shared Portal

[1645] Users can access the shared portal and search for and view use cases from other companies. The server uses a search engine such as ElasticSearch to list and display relevant cases based on the user's search criteria. It also has the ability to record user access logs and analyze usage trends.

[1646] As a specific example, when a user from Company B searches for cases related to "customer service," cases from Company A are displayed.

[1647] Rating and Ranking System

[1648] Every quarter, the server extracts new use cases from the database and scores them using a machine learning algorithm based on set evaluation criteria, such as "reduction of work time," "increased profits," and "uniqueness of use." A ranking is created based on the scoring results, and the best cases are selected.

[1649] Specifically, the server extracts cases from the database and runs a scoring algorithm to generate a ranking.

[1650] Event Management System

[1651] The server will then prepare an event based on the evaluation results. Highly rated cases will be presented at the event, and participating companies will be able to participate remotely. The event will be held using online conferencing tools such as Zoom and Microsoft Teams. Outstanding cases will be prioritized in the database.

[1652] As a concrete example, best practices are presented at quarterly events, and other companies can learn from them and use them to improve their own companies.

[1653] Example prompt

[1654] Please provide the case study title, details, and results of your business operations using generative AI models.

[1655] These components and specific processing steps will promote the effective use of generative AI models across the corporate group, thereby achieving improved operational efficiency and productivity.

[1656] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1657] Step 1: User authentication

[1658] Input: User ID and password

[1659] Output: Authentication result (success or failure)

[1660] Specific behavior:

[1661] A user accesses the data collection portal and enters their user ID and password on the login page. The server sends the entered authentication information to the LDAP server for authentication. The LDAP server returns the authentication result, and if the server is successful, the user can proceed to the next step.

[1662] Step 2: Enter and submit your use case

[1663] Input: Case title, details, results

[1664] Output: Submitted use case

[1665] Specific behavior:

[1666] After authenticating, the user enters the use case title, details, and results obtained in the data collection portal, including specific numerical data (e.g., man-hour reduction percentage, cost reduction amount, etc.). By pressing the submit button, the data is sent to the server.

[1667] Step 3: Saving to the database

[1668] Input: Use case data

[1669] Output: Saved database records

[1670] Specific behavior:

[1671] The server receives the submitted use case and stores it in a relational database (e.g. MySQL or PostgreSQL), mapping the data to the appropriate tables and executing INSERT statements to store it.

[1672] Step 4: Tagging and categorizing the cases

[1673] Input: Saved database record

[1674] Output: Tagged and categorized data

[1675] Specific behavior:

[1676] The server inputs the stored data into an NLP model, analyzes the text, and automatically assigns tags such as "customer service" or "cost reduction" based on the analysis results, updating the record in the database.

[1677] Step 5: Search for cases in the shared portal

[1678] Input: Search keyword

[1679] Output: A list of search results

[1680] Specific behavior:

[1681] A user accesses the shared portal and enters a keyword (e.g., "customer service") into the search box. The server uses a search engine such as ElasticSearch to generate a search query based on the keyword and retrieves relevant cases from the database.

[1682] Step 6: Viewing search results

[1683] Input: list of search results

[1684] Output: The search results page that is displayed to the user

[1685] Specific behavior:

[1686] The server renders the search results retrieved from the database in HTML format, using an HTML template engine (e.g. Thymeleaf or Handlebars) to generate the search results page and send it back to the user's browser for display.

[1687] Step 7: Conduct evaluation and ranking

[1688] Input: Use cases in the database

[1689] Output: Evaluation and ranking results

[1690] Specific behavior:

[1691] The server extracts cases to be evaluated from the database every quarter. It runs a machine learning algorithm to score each case based on the set evaluation criteria (e.g., "reduction of work time," "increase in profits," "uniqueness of use," etc.). It generates a ranking based on the scoring results and stores it in the database.

[1692] Step 8: Prepare and execute the event

[1693] Input: Rating and ranking results

[1694] Output: Event materials and presentations

[1695] Specific behavior:

[1696] The server prepares event materials based on the evaluation results. The materials are generated in PDF or slide format and presented on the day of the event using online conferencing tools such as Zoom or Microsoft Teams. Outstanding cases are prioritized in the database, allowing other companies to learn from them.

[1697] These steps will promote the effective use of generative AI models across the corporate group, resulting in improved operational efficiency and productivity.

[1698] (Application example 1)

[1699] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1700] In conventional systems, there was no adequate method for effectively collecting, sharing, evaluating, and utilizing use cases of generative AI models within a corporate group. As a result, it was difficult to maximize the benefits of productivity improvement and cost reduction. Furthermore, improving task management and work efficiency was a key issue, particularly in logistics centers, and an effective solution was needed.

[1701] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1702] In this invention, the server includes: means for collecting use cases from each company in the corporate group; means for storing the collected use cases in a database and tagging and categorizing them; means for scoring the use cases based on evaluation criteria every quarter and creating rankings; means for preparing an event based on the evaluation results and presenting outstanding use cases; means for preferentially displaying outstanding use cases in the database after the event; means for including an AI assistant application for smart glasses that can be used by workers in the logistics center; means for managing tasks using voice recognition and presenting work instructions in real time; and means for monitoring task progress and presenting the next task. This enables effective use of generative AI models within the corporate group and significant improvement in work efficiency at the logistics center.

[1703] 1. A "corporate group" refers to multiple companies linked together under common capital and management policies.

[1704] 2. "Use Case" refers to information showing specific use cases and results of applying a generative AI model to business activities.

[1705] 3. "Database" refers to an information system that systematically stores and manages collected use cases and other related data.

[1706] 4. "Tagging" refers to the practice of assigning specific keywords or identifiers to data to make it easier to search for later.

[1707] 5. "Categorization" refers to the method of classifying collected data into specific categories.

[1708] 6. "Evaluation Criteria" refers to the criteria or measures used to evaluate a Use Case.

[1709] 7. "Scoring" refers to the process of assigning a score to a use case based on evaluation criteria.

[1710] 8. "Ranking" refers to the ranking of use cases based on the scoring results.

[1711] 9. "Event" means an event or gathering to announce evaluation results and present successful use cases.

[1712] 10. "AI assistant application" refers to application software that uses artificial intelligence technology to assist users in their work.

[1713] 11. "Smart glasses" refers to a wearable device in the form of glasses with built-in displays and sensors.

[1714] 12. "Speech recognition" refers to the technology that analyzes human speech and recognizes it as text or commands.

[1715] 13. "Task management" refers to the method of listing the tasks required to achieve a specific goal and tracking their progress.

[1716] 14. "Real-time" refers to immediate processing or response without delay.

[1717] 15. "Work Instructions" means the specific instructions required to complete a particular task.

[1718] 16. “Progress management” refers to the process of monitoring the progress of work and making adjustments as needed.

[1719] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. The main purpose of this system is to improve work efficiency at logistics centers.

[1720] System Overview

[1721] The system consists of the following main components:

[1722] 1. Data Collection Portal

[1723] 2. Database Management System

[1724] 3. Shared Portal

[1725] 4. Rating and Ranking System

[1726] 5. Event Management System

[1727] 6. AI Assistant Application for Smart Glasses

[1728] Data Collection Portal

[1729] Company personnel (users) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[1730] Database Management Systems

[1731] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[1732] Shared Portal

[1733] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[1734] Rating and Ranking System

[1735] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[1736] Event Management System

[1737] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[1738] AI assistant application for smart glasses

[1739] This application allows workers in a logistics center to use smart glasses to manage tasks using generative AI models. Smart glasses are wearable devices with built-in displays and sensors. The application provides the following features:

[1740] 1. Real-time task display: The smart glasses display the worker's task list and work procedures in real time.

[1741] 2. Speech Recognition and Instructions: The next work task and instructions can be received through the worker's voice input. The speech recognition system uses the speech_recognition library.

[1742] 3. Task progress management: Register completed tasks and get real-time updates on progress.

[1743] 4. Optimal route suggestion: Optimizes routes within the warehouse to help efficiently pick up and deliver goods.

[1744] Hardware and software used

[1745] Hardware: Smart glasses, microphone

[1746] Software: Python, speech_recognition library, pyttsx3 library

[1747] Specific examples

[1748] For example, if a worker at a logistics center wears smart glasses and says, "Tell me what my next task is," the AI ​​assistant application will give instructions such as, "Move pallet A." Once the worker has completed the task, they can say, "This task is complete," and receive instructions for the next task.

[1749] Prompt Sentence Examples

[1750] "Tell me the next task"

[1751] Complete this task

[1752] "Show more tasks"

[1753] This will significantly improve the work efficiency of the logistics center and promote the effective use of generative AI models across the corporate group.

[1754] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1755] Step 1:

[1756] The user wears the smart glasses and gives instructions via voice input such as "Tell me the next task." At this time, the voice input is captured using a microphone. The input voice data is converted into text data by the voice recognition system (speech_recognition library) in the smart glasses.

[1757] Step 2:

[1758] The smart glasses receive the text data generated by the voice recognition system and send it to the backend server to present the next task to the user. The backend server selects the next task from the current task list and returns it to the smart glasses as text data. At this time, it queries the task management database for information on related tasks and selects the appropriate task.

[1759] Step 3:

[1760] The smart glasses display the next task text data received from the backend server and also provide audio instructions using the pyttsx3 library, giving the user both visual and audible confirmation of what they need to do next.

[1761] Step 4:

[1762] After completing the task, the user again speaks "I've completed this task." The microphone again captures the voice data, which is then converted into text data by the speech recognition system.

[1763] Step 5:

[1764] The smart glasses send the task completion text data generated by the voice recognition system to the backend server, which updates the task management database to record that the current task has been completed, and prepares to select a new task from the next task list and provide it to the user.

[1765] Step 6:

[1766] The smart glasses receive new task information from the backend server and present it to the user visually and audibly, updating the next task in real time and helping the user work efficiently.

[1767] Through these steps, workers within the logistics center can complete tasks efficiently and quickly, improving overall work efficiency.

[1768] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1769] This invention relates to a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. In particular, the system aims to improve the quality of feedback and maximize the effectiveness of events by combining an emotion engine that recognizes user emotions.

[1770] System Overview

[1771] The system consists of the following main components:

[1772] 1. Data Collection Portal

[1773] 2. Database Management System

[1774] 3. Shared Portal

[1775] 4. Rating and Ranking System

[1776] 5. Event Management System

[1777] 6. Emotion Engine

[1778] Data Collection Portal

[1779] Users (personnel at each company) enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduced work time or increased profits) and submit the case. The portal has an authentication function, and only authenticated users can access it.

[1780] Database Management Systems

[1781] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[1782] Shared Portal

[1783] Users can access the shared portal and search and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[1784] Rating and Ranking System

[1785] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). A ranking is created based on the scoring results, and the best cases are selected.

[1786] Event Management System

[1787] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[1788] Emotion Engine

[1789] The emotion engine is a component that recognizes and analyzes user emotions in real time. Specifically, it analyzes emotions contained in feedback and comments and categorizes them into emotional states such as positive, negative, and neutral.

[1790] Specific processing explanation

[1791] The processing of the data collection portal and database management system from step 1 to step 6 has been described above.

[1792] The shared portal processing from step 7 to step 13 is performed in a similar manner.

[1793] The evaluation and ranking system processes from step 14 to step 18 are carried out in the same manner.

[1794] Further processing by the emotion engine:

[1795] Step 19:

[1796] Users can enter their thoughts and suggestions for improvement through a feedback form.

[1797] Step 20:

[1798] The terminal transmits the user's input data to the emotion engine.

[1799] Step 21:

[1800] The emotion engine analyzes the input data and classifies the emotional state as positive, negative, or neutral.

[1801] Step 22:

[1802] The server stores the analysis results in a database and categorizes the feedback based on the emotional state.

[1803] Real-time sentiment analysis during the event:

[1804] Step 23:

[1805] Users view presentations delivered in real time during the event.

[1806] Step 24:

[1807] The emotion engine collects and analyzes real-time user emotion data to evaluate how the presentation content is perceived by the user.

[1808] Step 25:

[1809] The server dynamically adjusts the presentation content based on data from the emotion engine, providing information to keep the user engaged.

[1810] Specific examples

[1811] For example, let's say Company A used a generative AI model to automate customer service inquiries, resulting in an average 30% reduction in inquiry response time and an annual cost reduction of 300,000 yen. The user (company A's representative) accesses the data collection portal, enters the case title "Customer Service Automation," a detailed description, and the results, and presses the submit button. The server saves this information in a database and assigns the tags "Customer Service" and "Cost Reduction."

[1812] Later, when a user at Company B searches for "customer service" cases on the shared portal, the case study from Company A appears and the user can view the details. Company B uses this as a reference to consider similar improvement measures at their own company.

[1813] If this case receives high praise at a quarterly event, the server will prepare materials for the event and a representative from Company A will give a presentation. Other companies will learn from the content and apply it to their own operations.

[1814] Furthermore, the emotion engine analyzes user reactions during the event, and if there are many positive reactions, it dynamically adjusts the presentation content to emphasize those points, maximizing the effectiveness of the presentation and increasing participant understanding and interest.

[1815] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and improved productivity, but also improving the quality of feedback by utilizing user emotional data.

[1816] The processing flow will be explained below.

[1817] Specific processing flow of the program

[1818] (Data Collection Portal Processing)

[1819] Step 1:

[1820] The user accesses the data collection portal website.

[1821] Step 2:

[1822] The user enters authentication information (user ID and password) on the login screen and clicks the login button.

[1823] Step 3:

[1824] The server receives the entered authentication information and authenticates the user. If authentication is successful, the case registration form is displayed.

[1825] Step 4:

[1826] The user enters the case title, details, and results (such as reduced work time or increased profits) in the case registration form and presses the submit button.

[1827] Step 5:

[1828] The terminal transmits the input case data to the server.

[1829] Step 6:

[1830] The server stores the received case data in a database, automatically tagging it with categories such as "customer service" and "cost reduction."

[1831] (Shared Portal Processing)

[1832] Step 7:

[1833] The user accesses the shared portal and proceeds to the case search screen.

[1834] Step 8:

[1835] The user enters search criteria (keywords and tags) and presses the search button.

[1836] Step 9:

[1837] The terminal transmits the user's search conditions to the server.

[1838] Step 10:

[1839] The server extracts cases that match the search criteria from the database and generates a list of related cases.

[1840] Step 11:

[1841] The server transmits the generated case list to the user's terminal and displays the search results.

[1842] Step 12:

[1843] Users can click on a case that interests them from the search results to access the details page and view more information.

[1844] Step 13:

[1845] The server records user access logs and accumulates data for analyzing usage trends.

[1846] (Rating and ranking system processing)

[1847] Step 14:

[1848] The server extracts new use cases from the database every quarter.

[1849] Step 15:

[1850] The server scores the extracted cases based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.).

[1851] Step 16:

[1852] The server creates a ranking based on the scoring results.

[1853] Step 17:

[1854] The server prepares the top case studies, along with the ranking results, as presentation materials for the event.

[1855] Step 18:

[1856] The server notifies the event schedule and a list of participating companies.

[1857] (Event management system processing)

[1858] Step 19:

[1859] The user follows the notified event date and participates in the event online or offline.

[1860] Step 20:

[1861] The server will give a presentation based on the top-ranked cases, announcing details of each case and its evaluation points.

[1862] Step 21:

[1863] Users will study the case studies presented at the event and take notes on points that can be applied to their own company's operations.

[1864] Step 22:

[1865] After the event, the server registers the awarded cases in a database as a priority display, and makes them accessible to all users through a shared portal.

[1866] (Handling feedback and system improvements)

[1867] Step 23:

[1868] Users can submit feedback and suggestions for improvement while using the system through a feedback form.

[1869] Step 24:

[1870] The server aggregates the feedback and improvement suggestions received and notifies the administrator.

[1871] Step 25:

[1872] The server implements system improvement measures based on instructions from the administrator and updates the system version.

[1873] (Processed by emotion engine)

[1874] Step 26:

[1875] Users can enter their thoughts and suggestions for improvement through a feedback form.

[1876] Step 27:

[1877] The terminal transmits the user's input data to the emotion engine.

[1878] Step 28:

[1879] The emotion engine analyzes the input data and classifies the emotional state as positive, negative, or neutral.

[1880] Step 29:

[1881] The server stores the analysis results in a database and categorizes the feedback based on the emotional state.

[1882] (Real-time sentiment analysis during the event)

[1883] Step 30:

[1884] Users view presentations delivered in real time during the event.

[1885] Step 31:

[1886] The emotion engine collects and analyzes real-time user emotion data to evaluate how the presentation content is perceived by the user.

[1887] Step 32:

[1888] The server dynamically adjusts the presentation content based on data from the emotion engine, providing information to keep the user engaged.

[1889] This specific process flow allows companies to efficiently collect, evaluate, and share use cases of generative AI models within their group, improving overall productivity and promoting innovation. Furthermore, the introduction of an emotion engine improves the quality of feedback and maximizes the effectiveness of events.

[1890] Example 2

[1891] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1892] To effectively utilize generative AI models within a corporate group and promote productivity and innovation within each company, effective sharing and evaluation of use cases is necessary. However, with conventional systems, collecting, tagging, and categorizing use cases is done manually, which is time-consuming and labor-intensive. Another issue is that user feedback is not collected and analyzed sufficiently, which hinders the quality of the feedback. Furthermore, it is difficult to analyze user reactions in real time during an event and dynamically adjust presentation content.

[1893] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting use cases from each company in a corporate group, means for saving the collected use cases in a database and tagging and categorizing them, means for scoring the use cases based on evaluation criteria every quarter and creating rankings, means for preparing an event based on the evaluation results and presenting excellent use cases, means for preferentially displaying excellent use cases in the database after the event, means for collecting feedback from users and classifying the feedback as positive, negative, or neutral using an emotion analysis engine, and means for analyzing user emotion data in real time during the event and dynamically adjusting the content of the presentation. This enables effective collection and sharing of use cases, improves the quality of user feedback, and enables real-time presentation adjustments.

[1894] A "corporate group" is an organization formed by multiple companies working together to pursue common goals and interests.

[1895] "Use cases" are the results of specific applications or projects in which companies have used generative AI models, as well as the information gained in the process.

[1896] A "database" is a recording medium that systematically stores collected use cases and feedback, allowing for efficient search and management.

[1897] "Tagging" is a method of categorizing use cases and data with specific categories or keywords to make them easier to search and view.

[1898] "Categorization" is a method of classifying and structuring collected data according to specific criteria.

[1899] "Scoring" is the process of numerically evaluating use cases based on evaluation criteria and creating a ranking.

[1900] "Evaluation criteria" are indicators or rules established to judge the value or usefulness of a use case.

[1901] A "ranking" is a list of multiple use cases ordered based on evaluation criteria.

[1902] A "presentation" is a presentation format for introducing evaluated use cases to other companies and sharing knowledge.

[1903] "Portal" means a website or application that users within a corporate group can access to collect, view, and share information.

[1904] "Feedback" is data that expresses users' feelings, suggestions, and opinions about use cases and systems.

[1905] An "emotion analysis engine" is software or algorithms that analyze user feedback and real-time data and classify the emotions contained in that content as positive, negative, or neutral.

[1906] "Real-time analytics" is the process of analyzing data and obtaining results immediately as the data is generated.

[1907] "Dynamic adjustment" is the means by which presentations and system behavior can be instantly changed and adapted based on real-time analysis results.

[1908] MODE FOR CARRYING OUT THE INVENTION

[1909] This invention is a system that uses a generative AI model to effectively collect, evaluate, and share case studies within a corporate group, thereby improving productivity and promoting innovation across the entire company. In particular, by combining it with an emotion analysis engine that analyzes user emotions in real time, we aim to improve the quality of feedback and maximize the effectiveness of events.

[1910] Data Collection Portal

[1911] Users enter use cases that utilize generative AI models through a data collection portal. The data collection portal has fields for the case title, details, and results obtained (e.g., reduced work time, increased profits), and users enter these and press the submit button. The data collection portal has an authentication function, and only authenticated users can access it. A common ID and password are used for authentication.

[1912] Database Management Systems

[1913] The server receives the use cases submitted by users and stores them in a database. At this time, text analysis algorithms are used to automatically tag and categorize the cases based on their content, making them easier to search for later. The database management system can be a relational database management system (RDBMS), such as MySQL or PostgreSQL.

[1914] Shared Portal

[1915] Users can access the shared portal and search for and view use cases registered by other companies. Users search for specific keywords or categories, and the server executes a search within the database and displays a list of relevant use cases to the user. The shared portal is built as a web application that can be accessed from a web browser.

[1916] Rating and Ranking System

[1917] Every quarter, the server scores new use cases based on evaluation criteria, such as "time saved," "profit increase," and "uniqueness of use," and creates a ranking. The scoring uses machine learning algorithms to ensure fair and consistent evaluations.

[1918] Event Management System

[1919] The server prepares events based on the quarterly evaluation results. At the events, highly rated use cases are presented, allowing other companies to learn from them. During the events, real-time user feedback is collected and analyzed by a sentiment analysis engine. After the events, outstanding use cases are prioritized in the database.

[1920] Sentiment Analysis Engine

[1921] A sentiment analysis engine collects user-provided feedback and real-time comments and uses natural language processing (NLP) techniques to classify them into positive, negative, or neutral sentiment. A sentiment analysis engine can use machine learning models built in Python (e.g., TensorFlow or PyTorch), for example.

[1922] Specific operation example

[1923] For example, consider a case where Company A used a generative AI model to automate customer service, reducing inquiry response times by 30% and saving 300,000 yen per year. A user enters this case into the data collection portal, enters the title "Customer Service Automation," a detailed description, and the results, and presses the submit button.

[1924] The server receives the information and stores it in a database, automatically tagging it with "customer service" and "cost reduction." Later, when a user from Company B searches for cases related to "customer service" on the shared portal, Company A's cases will be listed and the user can view their details.

[1925] This case study was highly rated and was presented at the event. During the presentation, a sentiment analysis engine analyzed user reactions in real time, and if there were a lot of positive reactions, the content of the presentation was dynamically adjusted to emphasize those parts, maintaining the participants' interest and deepening their understanding.

[1926] Prompt Sentence Examples

[1927] "Please give us a specific example of how a generative AI model has been used to improve business processes."

[1928] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and productivity improvements, but also improving the quality of feedback.

[1929] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1930] Step 1:

[1931] The user accesses the data collection portal and enters authentication information (ID and password). The entered authentication information is sent to the server by the terminal. The server checks the authentication information against the database, and if authentication is successful, displays a data input form to the user. As a result, the user can access the data input form.

[1932] Step 2:

[1933] The user enters a use case for the generative AI model into a data entry form and presses the submit button. The input data includes the case title, details, and outcomes (e.g., reduced work time, increased profits). The device then sends this data to the server. The server stores the received data in a database and applies text analysis algorithms to automatically assign tags such as "customer service" or "cost reduction." This makes the stored data easier to search later.

[1934] Step 3:

[1935] A user accesses the shared portal and searches for use cases using a specific keyword (e.g., "customer service"). The device sends the search query to the server, which performs a search in the database and lists relevant use cases. As a result, the device displays the search results sent from the server to the user. The user can view the displayed use cases and check detailed information.

[1936] Step 4:

[1937] The server extracts new use cases from the database every quarter. It scores the extracted data based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use") using a machine learning algorithm. Based on the scoring results, the server creates a ranking, which allows the best use cases to be identified.

[1938] Step 5:

[1939] The server will use the quarterly evaluation results to prepare the schedule and content for the next event. At the event, materials will be created and presenters will be selected so that the most highly rated use cases will be presented. A function to collect feedback in real time will be provided during the event. Event materials and a feedback function will be provided.

[1940] Step 6:

[1941] Users attend the event and watch the presentations provided. A form is provided to collect feedback from users in real time during the event. Users enter their impressions and suggestions for improvement in the feedback form and press the submit button. The device then sends the feedback data to the server.

[1942] Step 7:

[1943] The server sends the received feedback data to the sentiment analysis engine, which analyzes the feedback data and classifies it into positive, negative, or neutral sentiment. The analysis results are sent to the server, which stores them in a database. This allows the system to consider improvements based on the content of the feedback.

[1944] Step 8:

[1945] Users watch presentations in real time during an event. The sentiment analysis engine collects and analyzes users' real-time emotional data to evaluate how the presentation content is perceived by the users. The server receives the data from the sentiment analysis engine and dynamically adjusts the content of the presentation, thereby maintaining user interest and providing a better presentation.

[1946] (Application example 2)

[1947] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1948] In systems that effectively utilize generative AI models within corporate groups to improve productivity and promote innovation across the entire company, there is a need for a mechanism that can recognize user emotions in real time and reflect them in high-quality feedback and work instructions.If this requirement is not met, it is difficult to maximize the quality of feedback and the effectiveness of events, and there is also the problem of not being able to improve the efficiency of factory work.

[1949] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1950] In this invention, the server includes: means for collecting use cases from each company in the corporate group; means for storing the collected use cases in a database and tagging and categorizing them; means for scoring the use cases based on evaluation criteria every quarter and creating rankings; means for preparing events based on the evaluation results and presenting outstanding use cases; means for displaying outstanding use cases in a prioritized manner in the database after the event; means for analyzing operator emotion data in real time and providing work instructions and feedback; and means for dynamically adjusting presentation content based on the emotion data. This enables the effective use of generative AI models across the entire corporate group, improving business efficiency and productivity. Furthermore, the quality of feedback can be improved by utilizing user emotion data, maximizing the effectiveness of events.

[1951] A "corporate group" is a group of multiple companies that share common goals and interests, and among which there are cooperative and business relationships.

[1952] A "use case" refers to a real-world application or outcome that utilizes a generative AI model in a specific setting or situation.

[1953] A "database" is a system for systematically and efficiently storing and managing use cases and other related information.

[1954] "Tagging" refers to the act of assigning labels to information in a database that indicate specific attributes or categories.

[1955] "Categorization" is a method of classifying information in a database based on certain commonalities.

[1956] "Scoring" is a method of assigning points to each use case based on specific evaluation criteria to determine its merits or demerits.

[1957] "Ranking" refers to ranking use cases based on the scoring results.

[1958] "Event" refers to a gathering or presentation held within a corporate group for the purpose of sharing evaluation results and use cases.

[1959] "Emotion data" is information that indicates an emotional state analyzed from user input and feedback.

[1960] "Presentation" refers to the act of explaining and announcing information about use cases and evaluation results verbally and visually to other companies and stakeholders.

[1961] "Real-time" refers to a time frame in which analysis and processing occur almost immediately.

[1962] The "emotion engine" is a system that analyzes the user's emotional data and classifies and evaluates their emotional state.

[1963] This invention is a system that effectively utilizes generative AI models within a corporate group to improve productivity and promote innovation across the entire company. In particular, it aims to maximize the effectiveness of events by combining it with an emotion engine that recognizes user emotions in real time to improve the quality of feedback and work instructions.

[1964] System configuration

[1965] The system consists of the following main components:

[1966] 1. Data Collection Portal

[1967] 2. Database Management System

[1968] 3. Shared Portal

[1969] 4. Rating and Ranking System

[1970] 5. Event Management System

[1971] 6. Emotion Engine

[1972] Data Collection Portal

[1973] Users enter use cases that utilize generative AI models through a data collection portal. Specifically, they enter the case title, details, and results (e.g., reduction in work time or increased profits) and submit the data. The portal has an authentication function, and only authenticated users can access it.

[1974] Database Management Systems

[1975] The server stores the submitted use cases in a database, automatically tagging and categorizing them with categories such as "customer service" or "cost reduction," making them easier to search for later.

[1976] Shared Portal

[1977] Users can access the shared portal and search for and view use cases from other companies. The server lists relevant cases based on the search criteria and displays them to the user. It also records user access logs and analyzes usage trends.

[1978] Rating and Ranking System

[1979] The server extracts new use cases from the database every quarter and scores them based on set evaluation criteria (such as "reduced work time," "increased profits," and "uniqueness of use"). Rankings are created based on the scoring results, and outstanding cases are selected.

[1980] Event Management System

[1981] The server prepares events based on the quarterly evaluation results. At the events, highly evaluated cases are presented so that other companies can learn from them. Outstanding cases are awarded and displayed preferentially in the database.

[1982] Emotion Engine

[1983] The emotion engine is a component that recognizes and analyzes user emotions in real time. Specifically, it analyzes emotions contained in feedback and comments and categorizes them into emotional states such as positive, negative, and neutral.

[1984] Specific use cases

[1985] For example, a user operating a factory robot can enter a case study of "improving robot operation speed" through a data collection portal, providing a title, details, and results (e.g., a 90% efficiency improvement), and submit the study. The server stores this information in a database and automatically assigns tags such as "efficiency improvement" and "cost reduction."

[1986] When users at other factories search for "efficiency improvement" cases on the shared portal, this case will appear and they can view the details. If this case receives high praise at a quarterly event, event materials will be prepared. Users can give presentations that other companies can use as reference.

[1987] Furthermore, during the event, the emotion engine analyzes users' real-time reactions, and if there are a lot of positive reactions, the presentation content is dynamically adjusted to emphasize those points, maximizing the effectiveness of the presentation and increasing participant understanding and interest.

[1988] Prompt Sentence Examples

[1989] An example prompt for a generative AI model is:

[1990] Based on the feedback analysis of the robot's work, create a presentation to improve work efficiency. Highlight the positive feedback points and propose improvements for the negative feedback.

[1991] This will promote the effective use of generative AI models across the entire corporate group, not only achieving business efficiency and improved productivity, but also improving the quality of feedback by utilizing user emotional data.

[1992] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1993] Step 1:

[1994] Users access a data collection portal and input use cases that utilize generative AI models, including the case title, details, and results achieved (e.g., time saved or increased profits). This input data is then sent to the data collection portal.

[1995] Step 2:

[1996] The device receives the use case data sent by the user and sends it to the server. The server receives this data and stores it in a database. When storing it, it automatically tags and categorizes the cases based on their characteristics, such as "customer service" or "cost reduction." This tagging and categorization makes it easier to search the data.

[1997] Step 3:

[1998] Users access the shared portal to search and browse use cases in the database. When users enter search criteria, the server lists relevant use cases based on tagging and categories and displays them to the user, allowing users to quickly access the information they need.

[1999] Step 4:

[2000] The server extracts new use cases from the database every quarter. It scores each case based on set evaluation criteria (e.g., "reduced work time," "increased profits," "uniqueness of use," etc.). It then assigns points to each evaluation criterion and calculates an overall score.

[2001] Step 5:

[2002] The server creates a ranking of the use cases based on the scoring results. Use cases with high scores are placed at the top of the list, and those with low scores are placed at the bottom. The ranking results are used to prepare for the event.

[2003] Step 6:

[2004] The server prepares an event based on the evaluation results. The highly evaluated cases are prepared to be presented at the event. At this time, the outstanding use cases are given special recognition and are prioritized in the database.

[2005] Step 7:

[2006] During the event, users will watch presentations delivered in real time, including top use cases.

[2007] Step 8:

[2008] The emotion engine analyzes user emotion data collected from devices during the event in real time. Input data includes user comments and feedback. The emotion engine analyzes this data and classifies it into positive, negative, or neutral emotional states.

[2009] Step 9:

[2010] The server receives the analysis results and dynamically adjusts the presentation content based on them. For example, if there are a lot of positive reactions, it will emphasize the success points, and if there are a lot of negative reactions, it will add improvement measures. This will help maintain and improve the understanding and interest of event participants.

[2011] Step 10:

[2012] After the event, the server will prioritize the best use cases in the database and encourage information sharing among participating companies, allowing other companies to learn from the best use cases and consider ways to use them in their own companies.

[2013] This series of processes promotes the effective use of generative AI models across the entire corporate group, improving business efficiency and productivity. Furthermore, by utilizing user emotion data, the quality of feedback is improved and the effectiveness of events is maximized.

[2014] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2015] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2016] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2017] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2018] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2019] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2020] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2021] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2022] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2023] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2024] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2025] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2026] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2027] 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.

[2028] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2029] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2030] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2031] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2032] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2033] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2034] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2035] The following is further disclosed regarding the above embodiment.

[2036] (Claim 1)

[2037] A means of collecting use cases from each company within the corporate group;

[2038] A means to store the collected use cases in a database and tag and categorize them.

[2039] A method for scoring and ranking use cases based on evaluation criteria each quarter; and

[2040] A means to prepare events based on the evaluation results and present excellent use cases,

[2041] A system that includes a means for prioritizing excellent use cases in a database after the event has concluded.

[2042] (Claim 2)

[2043] The system of claim 1, further comprising a means for other companies to search and view each company's use cases through a shared portal.

[2044] (Claim 3)

[2045] 10. The system of claim 1, further comprising means for collecting feedback from users and for considering and implementing improvements to the system.

[2046] "Example 1"

[2047] (Claim 1)

[2048] means for performing user authentication using authentication information;

[2049] A means of collecting use cases from each company within the corporate group;

[2050] A means to store the collected use cases in a database and tag and categorize them using an NLP model.

[2051] A means for other companies to search and view use cases through a shared portal;

[2052] A means for scoring and ranking use cases based on criteria using machine learning algorithms on a quarterly basis; and

[2053] A means to prepare events based on the evaluation results and present excellent use cases,

[2054] A system that includes a means for prioritizing excellent use cases in a database after the event has concluded.

[2055] (Claim 2)

[2056] 10. The system of claim 1, further comprising means for collecting feedback from users and for considering and implementing improvements to the system.

[2057] (Claim 3)

[2058] 10. The system of claim 1, further comprising means for recording a user access log on the shared portal and analyzing usage trends.

[2059] "Application Example 1"

[2060] (Claim 1)

[2061] A means of collecting use cases from each company within the corporate group;

[2062] A means to store the collected use cases in a database and tag and categorize them.

[2063] A method for scoring and ranking use cases based on evaluation criteria each quarter; and

[2064] A means to prepare events based on the evaluation results and present excellent use cases,

[2065] A means to prioritize excellent use cases in a database after the event has ended, and

[2066] a means including an AI assistant application for smart glasses available to workers in the logistics center;

[2067] A means of managing tasks and providing real-time work instructions using voice recognition;

[2068] A means to monitor task progress and suggest next steps;

[2069] A system including:

[2070] (Claim 2)

[2071] A means for other companies to search and view each company's use case through a shared portal,

[2072] 10. The system of claim 1, further comprising means for allowing a user to receive work instructions through voice input using the smart glasses.

[2073] (Claim 3)

[2074] A means to collect user feedback and consider and implement improvements to the system;

[2075] 10. The system of claim 1, further comprising means for optimizing work efficiency and task management within a logistics center.

[2076] "Example 2: Combining Emotion Engines"

[2077] (Claim 1)

[2078] A means of collecting use cases from each company within the corporate group;

[2079] ...

Claims

1. A means of collecting use cases from each company within the corporate group; A means to store the collected use cases in a database and tag and categorize them. A method for scoring and ranking use cases based on evaluation criteria each quarter; and A means to prepare events based on the evaluation results and present excellent use cases, A system that includes a means for prioritizing excellent use cases in a database after the event has concluded.

2. The system according to claim 1, further comprising a means for allowing other companies to search and view the use cases of each company through a shared portal.

3. 2. The system according to claim 1, further comprising means for collecting feedback from users and for considering and implementing measures to improve the system.

Images