System

Abstract

A system is provided.SOLUTION: A system includes means for using a generative AI model to quickly and accurately respond to a remote worker's question, means for providing access to in-house resources and documents needed by the remote worker, and means for assisting the remote worker to efficiently communicate with a team.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] Compared to an office environment, remote workers have fewer opportunities to ask questions directly to their colleagues and superiors, making it more difficult to resolve doubts and problems. They also have difficulty accessing necessary resources and documents, and communication with their teams tends to be lacking. As a result, remote workers experience challenges such as reduced productivity and increased stress. [Means for solving the problem]

[0005] The present invention provides a system that includes means for using generative AI models to quickly and accurately respond to remote workers' questions, means for providing remote workers with access to internal resources and documents they need, and means for supporting remote workers in efficiently communicating with their teams.

[0006] Specifically, the system includes a means for receiving a remote worker's question in text format and passing the question to a generative AI model, and a means for sending the answer generated by the generative AI model to the remote worker's device. It also includes a means for receiving a remote worker's resource request and analyzing the request using a generative AI model, and a means for retrieving resources from an internal database and providing them to the remote worker. It also includes a means for receiving a remote worker's communication request and analyzing the request using a generative AI model, a means for automatically executing actions such as adjusting meeting schedules and sharing documents, and a means for notifying the remote worker of the execution results. This improves the productivity and reduces stress for remote workers.

[0007] A "remote worker" is someone who is not based in an office and performs their work remotely from home or another location.

[0008] A "generative AI model" refers to a system that uses artificial intelligence technology to generate appropriate answers or actions in response to questions or requests in natural language.

[0009] A "question" refers to information that a remote worker inputs into a generative AI model to resolve a question or problem that arises while performing their work.

[0010] "Resources" refers to information such as internal documentation, guidelines, and tools that remote workers need to get their jobs done.

[0011] "Communication requests" refer to requests made by remote workers to the generative AI model to schedule meetings, share documents, report on project progress, etc.

[0012] "Device" refers to the device used by a remote worker to input questions or requests into the generative AI model.

[0013] "Server" refers to the computing system on which the generative AI model runs and which processes the questions and requests of remote workers.

[0014] "Answer" refers to the information that the generative AI model generates in response to a remote worker's question.

[0015] "Database" refers to the collection of internal company information that the generative AI model references to answer remote workers' questions and requests.

[0016] "Schedule adjustment" refers to the process in which the generative AI model coordinates meeting dates and times and participants.

[0017] "Document sharing" refers to the process by which a generative AI model shares internal documents with other members at the request of a remote worker.

[0018] "Progress reporting" refers to the process by which remote workers report the status and progress of a project to their team or superiors.

[0019] "Access" refers to the means and procedures necessary for remote workers to reach the resources and information they need.

[0020] "Notification" refers to the process by which the generative AI model informs the remote worker of the results of the request execution. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] To implement this invention, it is necessary to build a remote worker support system that utilizes a generative AI model. This system has three main functions: answering questions, providing resources, and supporting communication. Below, we will explain in detail how to implement this system.

[0043] Handling inquiries

[0044] A user types a question into a terminal, for example, "Please let me know the latest information about our company policies."

[0045] The terminal sends this question in text format to the server.

[0046] The server passes the received question to a generative AI model, which analyzes the question and initiates a process to generate an appropriate answer based on the question's content. Specifically, the model tokenizes the question, analyzes its intent, and queries an internal database to retrieve relevant information.

[0047] The generative AI model generates the optimal answer based on the analysis results, for example, "The latest version of our internal policy was updated in January 2023. Please see this link for details."

[0048] The server receives this response and sends it to the terminal.

[0049] The terminal displays the received response to the user.

[0050] Handling resource offerings

[0051] A user types a request into a terminal for a required resource or document, such as "Teach me how to use a project management tool."

[0052] The terminal sends this request in text format to the server.

[0053] The server passes the request to the generative AI model, which then analyzes the location and access method of the required resources based on the request, as well as searches for the necessary materials from its internal database.

[0054] The generative AI model searches for documents and retrieves their links and files, generating information such as, "Please refer to these guidelines for how to use project management tools."

[0055] The server transmits the acquired information to the terminal.

[0056] The device will display links and required files to the user.

[0057] Handling team communication support

[0058] A user enters a request into their device to schedule a meeting or share a document, such as "Please send a reminder for tomorrow's meeting to everyone on my team."

[0059] The terminal sends this request in text format to the server.

[0060] The server passes the request to the generative AI model, which analyzes the request and determines the corresponding action.

[0061] The generative AI model accesses internal resources and tools to perform each action, for example, getting team member contact information and sending reminders.

[0062] The server transmits the execution result to the terminal.

[0063] The device will display a result to the user, such as "Reminder has been sent."

[0064] This allows remote workers to quickly access the information and resources they need and communicate with their teams efficiently. Utilizing generative AI models with these capabilities can improve productivity and reduce stress for remote workers.

[0065] The processing flow will be explained below.

[0066] Handling inquiries

[0067] Step 1:

[0068] The user types a question into the terminal, for example, "What is the latest information about our company policies?"

[0069] Step 2:

[0070] The terminal sends the question in text format to the server.

[0071] Step 3:

[0072] The server passes the received questions to a generative AI model.

[0073] Step 4:

[0074] The generative AI model analyzes the question, specifically tokenizing it and analyzing its intent.

[0075] Step 5:

[0076] The generative AI model generates database queries based on intent and queries internal databases to retrieve relevant information.

[0077] Step 6:

[0078] The server receives the answer from the generative AI model and sends it to the device.

[0079] Step 7:

[0080] The device will then display the received response to the user, for example, "The latest version of our internal policies was updated in January 2023. Please see this link for details."

[0081] Handling resource offerings

[0082] Step 1:

[0083] A user types a request into a terminal for a required resource or document, such as "Teach me how to use a project management tool."

[0084] Step 2:

[0085] The terminal sends the request in text format to the server.

[0086] Step 3:

[0087] The server passes the request to the generative AI model.

[0088] Step 4:

[0089] Based on the request, the generative AI model analyzes where the required resources are located and how to access them.

[0090] Step 5:

[0091] The generative AI model searches for the necessary materials from an internal database.

[0092] Step 6:

[0093] The generative AI model searches for documents and retrieves their links and files, generating information such as, "Please refer to these guidelines for how to use project management tools."

[0094] Step 7:

[0095] The server transmits the acquired information to the terminal.

[0096] Step 8:

[0097] The device will display links and required files to the user.

[0098] Handling team communication support

[0099] Step 1:

[0100] A user enters a request into their device to schedule a meeting or share a document, such as "Please send a reminder for tomorrow's meeting to everyone on my team."

[0101] Step 2:

[0102] The terminal sends the request in text format to the server.

[0103] Step 3:

[0104] The server passes the request to the generative AI model.

[0105] Step 4:

[0106] The generative AI model analyzes the request and determines the corresponding action.

[0107] Step 5:

[0108] The generative AI model accesses the necessary internal resources and tools to perform each action.

[0109] Step 6:

[0110] For example, a generative AI model can retrieve contact information for team members and send reminders.

[0111] Step 7:

[0112] The server transmits the execution result to the terminal.

[0113] Step 8:

[0114] The device will display a result to the user, such as "Reminder has been sent."

[0115] Example 1

[0116] 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."

[0117] Remote workers often find it difficult to work efficiently because they are unable to quickly access the information and resources they need. Communication with their team can also be difficult in a remote work environment, leading to lower productivity and increased stress.

[0118] 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.

[0119] In this invention, the server includes means for using a generative AI model to quickly and accurately respond to the remote worker's questions, means for providing access to information resources and data required by the remote worker, and means for supporting the remote worker in efficiently communicating with colleagues, thereby enabling the remote worker to quickly access the information and resources they need and to communicate smoothly with their team.

[0120] A "remote worker" is someone who works remotely (from a remote location) without coming to the office.

[0121] A "generative AI model" refers to algorithms or software that generate information based on artificial intelligence technology.

[0122] "Information resources" refers to information resources such as data, knowledge bases, and documents that users need.

[0123] "Support for efficient communication" refers to providing the features and tools remote workers need to effectively exchange information and collaborate with colleagues.

[0124] A "server" refers to a computer system that provides various services over a network.

[0125] "Terminal" refers to a device (such as a personal computer or smartphone) that is directly operated by a user.

[0126] An "internal database" is a collection of data managed within an organization, and refers to a searchable and retrieval-capable information storage system.

[0127] A "protocol" refers to the rules and procedures for communicating data over a computer network.

[0128] A "query" is a request or question made to a database to retrieve specific information.

[0129] An "action" refers to a specific operation or process that the system executes based on a user request.

[0130] "Execution result" refers to the result of an operation or process that the server performed in response to a user request.

[0131] MODE FOR CARRYING OUT THE INVENTION

[0132] To implement this invention, a system combining a server, a terminal, and a generative AI model must be constructed. This system has three main functions: responding to questions from remote workers, providing resources, and supporting communication.

[0133] Hardware and software used

[0134] server

[0135] The server plays a central role in managing data exchange between the generative AI model and other system components, using the following software and services:

[0136] Generative AI model: OpenAI (registered trademark) GPT-3 (registered trademark)

[0137] In-house database: MongoDB, MySQL (registered trademark), PostgreSQL

[0138] Communication protocol: HTTPS, SMTP

[0139] Terminal

[0140] The terminal used by the user is used to input questions and requests and display responses from the system. It uses the following hardware and software:

[0141] Devices: PC, smartphone

[0142] Display software: Web browser, dedicated application

[0143] Data processing and data calculation

[0144] Answering questions

[0145] The user inputs a question into the terminal and the question is processed by sending it to the server.

[0146] The server passes the question data to a generative AI model, which analyzes the question.

[0147] The generative AI model tokenizes the question and analyzes its intent, using NLTK for tokenization and the BERT model for intent analysis.

[0148] Based on the analysis results, the generative AI model queries the company's internal database to retrieve relevant information.

[0149] The generative AI model generates answers based on the information it obtains.

[0150] The server sends the generated answer to the terminal, which displays the answer to the user.

[0151] Resource provision

[0152] A user inputs a request for a required resource into a terminal and sends it to a server.

[0153] The server passes the request content to the generative AI model and analyzes the location of the request.

[0154] The generative AI model retrieves the necessary materials from an internal database.

[0155] The generative AI model takes links and files to resources and generates appropriate answers.

[0156] The server transmits the acquired information to the terminal, which then displays the information to the user.

[0157] Communication Support

[0158] A user inputs a request to schedule a meeting or share a document into a terminal and sends it to the server.

[0159] The server passes the request to the generative AI model and analyzes the content.

[0160] The generative AI model retrieves team member contact information from an internal database and sends reminders.

[0161] The server sends the execution results to the terminal, which then displays the results to the user.

[0162] Specific examples

[0163] Specific prompt examples for questions:

[0164] "What are the latest changes to our company's policies?"

[0165] Examples of specific prompts for resource provision:

[0166] "Please provide guidelines for project management tools."

[0167] Examples of specific communication prompts:

[0168] "Send a reminder to my team for our next meeting."

[0169] This system will enable remote workers to quickly access the information and resources they need and communicate efficiently with their teams, which is expected to increase productivity and reduce stress.

[0170] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0171] Question response processing flow

[0172] Step 1:

[0173] The user inputs a question into the terminal. The input question is text data such as "Please tell me the latest information about the company's policies."

[0174] Step 2:

[0175] The terminal sends the question data entered by the user in text format to the server using the HTTPS protocol.

[0176] Step 3:

[0177] The server passes the received question data to the generative AI model, OpenAI GPT-3, which the server accesses using the required API key.

[0178] Input: Question data from the user

[0179] Output: Text data passed to the generative AI model

[0180] Step 4:

[0181] The generative AI model tokenizes the question and analyzes its intent, using NLTK for tokenization and the BERT model for intent analysis.

[0182] Input: Text data from the server

[0183] Output: Parsed intent data

[0184] Step 5:

[0185] Based on the analysis results, the generative AI model queries the internal database (MongoDB) to retrieve relevant information, for example, searching for information on the latest internal policies.

[0186] Input: Parsed intent data

[0187] Output: Retrieved company policy information

[0188] Step 6:

[0189] The generative AI model generates the most appropriate answer based on information retrieved from the company's database, such as "The latest version of our company policy was updated in January 2023. Please see this link for details."

[0190] Input: Information data obtained from the company database

[0191] Output: Generated answer text

[0192] Step 7:

[0193] The server receives the generated response data and sends it to the terminal, also using the HTTPS protocol.

[0194] Input: Generated answer text

[0195] Output: Response data sent to the device

[0196] Step 8:

[0197] The terminal displays the received answer data to the user. The terminal displays the answer text on the screen so that it can be seen by the user.

[0198] Input: Response data sent from the server

[0199] Output: The answer text that is displayed to the user

[0200] Resource provisioning process flow

[0201] Step 1:

[0202] A user types a request for a resource they need into a terminal, for example, "Teach me how to use a project management tool."

[0203] Step 2:

[0204] The device sends this request in text format to the server using the HTTPS protocol.

[0205] Step 3:

[0206] The server passes the request to the generative AI model, OpenAI GPT-3, which the server accesses using an API key.

[0207] Input: Request data from the user

[0208] Output: Text data passed to the generative AI model

[0209] Step 4:

[0210] The generative AI model analyzes the request and identifies the required resources, possibly using the BERT model, to analyze what the requested resources are.

[0211] Input: Request data from the server

[0212] Output: Parsed resource specific data

[0213] Step 5:

[0214] The generative AI model retrieves necessary materials from an internal database (MySQL), for example, searching for guideline materials for a project management tool.

[0215] Input: Parsed resource-specific data

[0216] Output: Acquired data

[0217] Step 6:

[0218] The generative AI model retrieves links and files to documents and generates appropriate answers, such as "Please refer to these guidelines for how to use project management tools."

[0219] Input: Material data obtained from the internal database

[0220] Output: Generated answer text

[0221] Step 7:

[0222] The server sends the obtained information to the terminal, also using the HTTPS protocol.

[0223] Input: Generated answer text

[0224] Output: Response data sent to the device

[0225] Step 8:

[0226] The terminal displays the link and required files to the user. The terminal displays the generated link and text on the screen.

[0227] Input: Response data sent from the server

[0228] Output: The link and answer text that is displayed to the user

[0229] Communication support processing flow

[0230] Step 1:

[0231] A user types a request into their device to schedule a meeting or share a document, for example, "Send a reminder to the whole team for tomorrow's meeting."

[0232] Step 2:

[0233] The device sends this request in text format to the server using the HTTPS protocol.

[0234] Step 3:

[0235] The server passes the request to the generative AI model, OpenAI GPT-3, which is accessed using an API key.

[0236] Input: Request data from the user

[0237] Output: Text data passed to the generative AI model

[0238] Step 4:

[0239] The generative AI model analyzes the received request and determines the corresponding action, which can be done using the BERT model to analyze what the requested action is.

[0240] Input: Request data from the server

[0241] Output: Parsed action decision data

[0242] Step 5:

[0243] For example, the generative AI model retrieves team member contact information from an internal database (PostgreSQL) and sends reminders, using the SMTP protocol to send emails.

[0244] Input: Parsed action decision data

[0245] Output: Reminder email sent

[0246] Step 6:

[0247] The server sends the execution result (e.g., "Reminder has been sent") to the device using the HTTPS protocol.

[0248] Input: Record of reminder email sent

[0249] Output: Execution result data sent to the terminal

[0250] Step 7:

[0251] The device displays the execution result to the user. The device displays text such as "Reminder sent" on the screen.

[0252] Input: Execution result data sent from the server

[0253] Output: The execution result text that is displayed to the user

[0254] (Application example 1)

[0255] 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."

[0256] Conventional remote worker support systems have had problems with efficiency and accuracy when responding to questions, providing resources, and supporting communication. Furthermore, factory workers are unable to quickly obtain the information they need on-site or properly understand how to operate machines, leading to reduced productivity. For this reason, a new system is needed that allows both remote workers and factory workers to efficiently access the information they need and communicate smoothly.

[0257] 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.

[0258] In this invention, the server includes means for using a generative AI model to quickly and accurately respond to questions from remote workers, means for providing access to information resources and documents required by remote workers, means for supporting remote workers in efficiently communicating with their teams, means for converting questions from factory workers into text format using speech recognition when the factory workers ask questions about machine settings or operation methods, means for obtaining and providing operation manuals and procedures required by factory workers via the server, and means for relaying communication between factory workers or managers by voice, and for adjusting schedules and transmitting messages. This enables remote workers and factory workers to quickly access the information they need and perform their work efficiently.

[0259] A "remote worker" is a worker who performs their work remotely via the Internet.

[0260] A "generative AI model" is an artificial intelligence algorithm that uses natural language processing to generate appropriate answers to human questions.

[0261] "Information resources" are business-related data, documents, manuals, and other materials in electronic form.

[0262] "Speech recognition" is a technology that converts speech into text form.

[0263] "Text format" is a data format expressed as character information.

[0264] A "server" is a computer system that processes and stores data over a network.

[0265] An "operation manual" is a document that details how to set up and use a machine or device.

[0266] A "procedure" is a document that lists the steps to be taken to perform a specific task.

[0267] To implement this invention, it is necessary to build a remote worker and factory worker support system that utilizes a generative AI model. The system of the present invention combines speech recognition technology, a generative AI model, database management, text output, and communication tools. This system uses the following hardware and software:

[0268] Hardware and software used:

[0269] Hardware: microphone, speakers, display, computer (e.g. Raspberry Pi).

[0270] Software: Python program, speech_recognition library, pyttsx3 library, openai library.

[0271] Data processing and calculation:

[0272] 1. Voice to text conversion:

[0273] The device uses voice recognition technology to convert the user's (remote worker or factory worker's) speech into text. The speech_recognition library is used for voice recognition. This process obtains the user's question or request in text format.

[0274] 2. Question and Request Analysis:

[0275] The server passes text questions or requests to a generative AI model for analysis. The generative AI model uses an OpenAI AI model (e.g., GPT-3). The generative AI model analyzes the text and generates appropriate answers or necessary information.

[0276] 3. Response and Information Provision:

[0277] The server receives the answers generated by the generative AI model and the searched resources. The server then sends them to the device, which then provides the results to the user in voice and text format. The pyttsx3 library is used for voice output.

[0278] Examples:

[0279] Examples of how to respond to questions:

[0280] The user asks into the microphone, "How do I set up this machine?" The question is converted into text using voice recognition and sent to the server. The generative AI model analyzes the question and generates an appropriate answer, such as "First, turn on this machine, then set it up by following the instructions displayed on the control panel." The server sends this to the device and provides it to the user as voice and on-screen.

[0281] Example prompt sentence:

[0282] "Question: How do I set up this machine?" Answer:

[0283] "Question: Can you provide the operation manual?"Answer: The operation manual can be downloaded from this link.

[0284] This allows users to quickly access the information they need and carry out their work efficiently. This system provides high convenience to both remote workers and factory workers.

[0285] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0286] Step 1:

[0287] The user speaks a question or request into the microphone, which inputs voice data.

[0288] Step 2:

[0289] The device uses voice recognition technology to convert the voice data into text format. Specifically, it uses the speech_recognition library to output the voice data as text data.

[0290] Step 3:

[0291] A textual question or request is sent to the server, which receives the input data by sending data from the device to the server.

[0292] Step 4:

[0293] The server passes the text data to a generative AI model, which then analyzes the question or request. An OpenAI AI model (e.g., GPT-3) is used to analyze the prompt and generate an answer. The analysis results include the answer text and any necessary information.

[0294] Step 5:

[0295] The server receives the answers generated by the generative AI model and the resources searched, and sends them to the device. Data transmission from the server to the device provides output data to the device.

[0296] Step 6:

[0297] The device provides the received answers and information to the user. Specifically, it uses the pyttsx3 library to read the answers aloud and display them in text format on the display, allowing the user to obtain information in both audio and text formats.

[0298] Step 7:

[0299] The user can ask additional questions or make requests as needed, and the process repeats from step 1, ensuring the user receives ongoing support.

[0300] This makes it possible to effectively implement functions such as answering questions, providing resources, and supporting communication.

[0301] 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.

[0302] To implement this invention, it is necessary to combine an emotion engine with a remote worker support system that utilizes a generative AI model. This system has three main functions: answering questions, providing resources, and supporting communication. It also has the ability to recognize user emotions and generate responses based on those emotions. Below, we will explain in detail how to implement this system.

[0303] Handling inquiries

[0304] The user inputs a question into the terminal, for example, "Please tell me the latest information about company policies." At this time, the emotion engine recognizes the user's emotion (e.g., confusion, tension, calmness, etc.) from the question input.

[0305] The terminal sends the question in text format to the server.

[0306] The server passes the received question to an emotion engine to analyze the emotion before passing it to the generative AI model. The generative AI model analyzes the question and the recognized emotion and generates an appropriate answer based on the content. For example, it generates an answer such as, "The latest version of our internal policy was updated in January 2023. Please rest assured. For more information, please see this link."

[0307] The server receives this response and sends it to the terminal.

[0308] The device displays the received answer to the user, for example, the answer that conveys the above sense of security.

[0309] Handling resource offerings

[0310] A user inputs a request for the required resources or documents into a terminal. For example, a request might be, "Please teach me how to use a project management tool." At this time, the emotion engine recognizes the user's emotion from the input of the request.

[0311] The terminal sends the request in text format to the server.

[0312] The server passes the request and the recognized emotion to the generative AI model, which then analyzes the location and access method of the required resources based on the request.

[0313] The generative AI model searches for the necessary materials from an internal database and retrieves the links and files. For example, it generates information such as, "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to support you."

[0314] The server transmits the acquired information to the terminal.

[0315] The device will display links and necessary files to the user, for example, a response conveying the above-mentioned willingness to help.

[0316] Handling team communication support

[0317] A user inputs a request into their device to schedule a meeting or share a document. For example, they might request, "Please send a reminder for tomorrow's meeting to everyone on the team." At this time, the emotion engine recognizes the user's emotion from the input request.

[0318] The terminal sends the request in text format to the server.

[0319] The server passes the request and the recognized emotion to the generative AI model, which analyzes the request and determines the corresponding action.

[0320] The generative AI model accesses the necessary internal resources and tools to perform each action, such as retrieving team member contact information and sending reminders, while also taking into account the user's sentiment and tailoring the reminder text.

[0321] The server transmits the execution result to the terminal.

[0322] The device will display a message to the user expressing gratitude, such as "The reminder has been sent. Thank you for your cooperation."

[0323] This allows remote workers to quickly access the information and resources they need and communicate with their teams efficiently.Furthermore, by recognizing users' emotions and adjusting responses, it is possible to reduce the psychological burden on remote workers and provide a more comfortable working environment.

[0324] The processing flow will be explained below.

[0325] Handling inquiries

[0326] Step 1:

[0327] The user types a question into the terminal, for example, "What's the latest on our company policies?"

[0328] Step 2:

[0329] The terminal sends the question in text format to the server.

[0330] Step 3:

[0331] The server receives the question and passes it to the emotion engine.

[0332] Step 4:

[0333] The emotion engine analyzes the user's emotions from the question input and generates emotion data (e.g., confusion, tension, calmness, etc.).

[0334] Step 5:

[0335] The server passes the question, including the emotional data, to the generative AI model.

[0336] Step 6:

[0337] The generative AI model analyzes the question content and sentiment data, then queries the company's internal database to retrieve relevant information.

[0338] Step 7:

[0339] Based on the analysis results, the generative AI model generates an appropriate response based on the sentiment, such as, "The latest version of our internal policy was updated in January 2023. Please rest assured, please see this link for details."

[0340] Step 8:

[0341] The server sends the generated response to the terminal.

[0342] Step 9:

[0343] The terminal displays the received response to the user.

[0344] Handling resource offerings

[0345] Step 1:

[0346] A user types a request into a terminal for a needed resource or document, for example, "Teach me how to use a project management tool."

[0347] Step 2:

[0348] The terminal sends the request in text format to the server.

[0349] Step 3:

[0350] The server receives the request and passes it to the emotion engine.

[0351] Step 4:

[0352] The emotion engine analyzes the user's emotions from the request input and generates emotion data.

[0353] Step 5:

[0354] The server passes the request, including the emotion data, to the generative AI model.

[0355] Step 6:

[0356] The generative AI model analyzes the request content and emotional data, and searches for the necessary materials from an internal database.

[0357] Step 7:

[0358] Based on the analysis results, the generative AI model generates appropriate information according to the emotion, such as "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to help."

[0359] Step 8:

[0360] The server transmits the acquired information to the terminal.

[0361] Step 9:

[0362] The device will display links and required files to the user.

[0363] Handling team communication support

[0364] Step 1:

[0365] A user types a request into their device to schedule a meeting or share a document, for example, "Send a reminder for tomorrow's meeting to everyone on my team."

[0366] Step 2:

[0367] The terminal sends the request in text format to the server.

[0368] Step 3:

[0369] The server receives the request and passes it to the emotion engine.

[0370] Step 4:

[0371] The emotion engine analyzes the user's emotions from the request input and generates emotion data.

[0372] Step 5:

[0373] The server passes the request, including the emotion data, to the generative AI model.

[0374] Step 6:

[0375] The generative AI model analyzes the request content and sentiment data to determine the corresponding action (such as scheduling a meeting or sharing a document).

[0376] Step 7:

[0377] The generative AI model accesses the necessary internal resources and tools to perform each action, such as getting team member contact information and sending a reminder, while also taking into account the user's sentiment and tailoring the reminder text.

[0378] Step 8:

[0379] The server transmits the execution result to the terminal.

[0380] Step 9:

[0381] The device will display a message to the user expressing gratitude, such as "The reminder has been sent. Thank you for your cooperation."

[0382] Example 2

[0383] 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."

[0384] Remote workers need to quickly obtain information in their work environment and communicate efficiently with their team. However, there are limited systems in place to improve information access and communication efficiency in a remote work environment. Furthermore, there is a lack of systems to reduce the psychological burden on remote workers and maintain a comfortable work environment. In such an environment, remote workers often feel confused and nervous, leading to problems with reduced productivity.

[0385] 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 a means for receiving the content of a question from a remote worker in text format and passing the question to a generative AI model, a means for analyzing the user's emotions and passing the analysis result to the generative AI model, and a means for sending an answer generated by the generative AI model to the remote worker's terminal. This makes it possible to generate and provide an appropriate answer that takes into account the user's emotions when the user inputs a question.

[0386] The server also includes a means for receiving resource requests from remote workers and analyzing the request content using a generative AI model, a means for retrieving resources from an internal database and providing them to the remote workers, and a means for adjusting a response to the request based on user sentiment, thereby enabling the resources needed by the remote workers to be provided quickly and accurately.

[0387] Furthermore, the server includes a means for supporting the remote worker in efficiently communicating with the team, and a means for recognizing the user's emotions and generating a response based on the emotions. This makes it possible to provide communication support that takes the emotions of the remote worker into consideration, thereby realizing an efficient work environment while reducing psychological burden.

[0388] A "remote worker" is an employee or contractor who performs work away from a company or organization's physical offices.

[0389] A "generative AI model" refers to an artificial intelligence model that analyzes input data and generates appropriate answers in natural language based on the results.

[0390] "Emotion engine" refers to a software component that analyzes and recognizes a user's emotional state from input text data.

[0391] "Internal resources" refers to resources such as information, data, tools, and documents owned by a company or organization.

[0392] "Terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[0393] "Server" refers to a central computer system for processing, analyzing, storing, and distributing data.

[0394] "Text format" refers to a representation format of information structured as character data.

[0395] "Analysis" refers to the process of examining input data and information in detail and converting it into an understandable form.

[0396] "Response" means a response generated in response to an entered question or request.

[0397] "Adjusting a response" refers to the process of appropriately changing the content and expression of a generated reply based on the user's emotional state.

[0398] "Communication support" refers to the technical and functional support provided to remote workers to collaborate effectively with other employees and team members.

[0399] The present invention is a system for supporting remote workers that utilizes a generative AI model and an emotion engine. The following describes in detail how the present invention is specifically implemented.

[0400] Answering questions

[0401] The user inputs a question into the terminal. For example, "Please tell me the latest information about company policies." At this time, the emotion engine recognizes the user's emotion (e.g., confusion, tension) from the question input.

[0402] The terminal sends the question in text format to the server.

[0403] The server analyzes emotions by passing the received question and emotion data to the emotion engine. The analyzed emotion and question content are input into the generative AI model to generate an appropriate answer.

[0404] The generative AI model might generate an answer like, "The latest version of our internal policies was updated in January 2023. Don't worry, please see this link for more details."

[0405] The server receives this response and sends it to the terminal, which then displays it to the user.

[0406] Resource provision

[0407] When a user inputs a request for resources or documents into a terminal, for example, "Please tell me how to use the project management tool," the emotion engine recognizes the user's emotion from the input of the request.

[0408] The terminal sends the request in text format to the server.

[0409] The server passes the request content and emotion data to the generative AI model, which analyzes the content, searches the internal database for the necessary materials, and retrieves the links and files.

[0410] For example, the generative AI model generates information such as, "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to support you."

[0411] The server sends the acquired information to the terminal, which displays resources and links to the user.

[0412] Communication Support

[0413] When a user inputs a request into a device to schedule a meeting or share a document, for example, "Please send a reminder for tomorrow's meeting to everyone on the team," the emotion engine recognizes the user's emotion from the request.

[0414] The terminal sends the request in text format to the server.

[0415] The server passes the request and emotion data to the generative AI model, which analyzes the request and accesses the necessary internal resources and tools to execute each action.

[0416] For example, a generative AI model might generate a response like, "Reminder has been sent. Thank you for your cooperation."

[0417] The server sends the execution result to the device, which confirms that the reminder was sent and displays a message of thanks to the user.

[0418] Example prompt

[0419] 1. Examples of how to respond to questions:

[0420] Prompt: "What's the latest information about our company policies?"

[0421] Generative AI model response: "Our internal policies were last updated in January 2023. Rest assured, please see this link for more details."

[0422] 2. Examples of resource provision:

[0423] Prompt: "How do I use a project management tool?"

[0424] Generative AI model response: "Please refer to these guidelines to learn how to use our project management tools. If you need help, we're always here to help."

[0425] 3. Examples of communication support:

[0426] Prompt: "Please send a reminder to the whole team for tomorrow's meeting."

[0427] Generative AI model response: "Reminder has been sent. Thank you for your cooperation."

[0428] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0429] Handling inquiries

[0430] Step 1:

[0431] The user enters a question into an input field on the terminal.

[0432] Example: "Please let me know the latest information about our company policies."

[0433] Here, the emotion engine recognizes the user's emotion (e.g., confusion, tension) from the content of the text.

[0434] Step 2:

[0435] The device sends the question and emotion data entered by the user in text format to the server.

[0436] Input data: Question text and sentiment data

[0437] Output: Text data sent to the server

[0438] Step 3:

[0439] The server receives the question and emotion data and passes it to the emotion engine for detailed emotion analysis.

[0440] Input data: Question text and initial emotion data

[0441] Output: Detailed emotion analysis data (e.g., high confusion, medium tension)

[0442] Step 4:

[0443] The server inputs the question and detailed emotional data into the generative AI model, which then generates an answer based on this.

[0444] Input data: Question text and detailed sentiment data

[0445] Output: Generated response text (e.g., "Our internal policy was last updated in January 2023. Don't worry, see this link for more details.")

[0446] Step 5:

[0447] The server sends the answer obtained from the generative AI model to the device.

[0448] Input data: Generated answer text

[0449] Output: Answer text sent to terminal

[0450] Step 6:

[0451] The terminal displays the received response to the user.

[0452] Output: Answer text to be displayed to the user (e.g. "Our internal policy was last updated in January 2023. Don't worry, see this link for more details.")

[0453] Handling resource offerings

[0454] Step 1:

[0455] A user inputs a request for a resource or document into a terminal.

[0456] Example: "How do I use a project management tool?"

[0457] Here, the emotion engine recognizes the user's emotion from the content of the text.

[0458] Step 2:

[0459] The device sends the request and emotion data in text format to the server.

[0460] Input data: resource request text and sentiment data

[0461] Output: Text data sent to the server

[0462] Step 3:

[0463] The server passes the request content and emotion data to the generative AI model, which analyzes the content and generates appropriate information.

[0464] Input data: request text and emotion data

[0465] Output: Generated guideline link text (e.g., "Please refer to these guidelines for how to use project management tools. If you need help, we're always here to help you.")

[0466] Step 4:

[0467] The server sends the information obtained from the generative AI model to the terminal.

[0468] Input data: Generated guideline link text

[0469] Output: Guideline link text sent to terminal

[0470] Step 5:

[0471] The device will display links and required files to the user.

[0472] Output: Guideline link text that will be displayed to the user (e.g., "Please refer to these guidelines for how to use the project management tool. If you need help, we're always here to help you.")

[0473] Communication support processing

[0474] Step 1:

[0475] The user inputs a request to schedule a meeting or share a document into the terminal.

[0476] Example: "Please send a reminder to the whole team for tomorrow's meeting."

[0477] Here, the emotion engine recognizes the user's emotion from the content of the text.

[0478] Step 2:

[0479] The device sends the request and emotion data in text format to the server.

[0480] Input data: Request text and emotion data

[0481] Output: Text data sent to the server

[0482] Step 3:

[0483] The server passes the request and emotion data to the generative AI model, which analyzes the request and determines the corresponding action.

[0484] Input data: Request text and emotion data

[0485] Output: The generated action text (e.g., "Reminder sent. Thank you for your cooperation.")

[0486] Step 4:

[0487] The generative AI model accesses internal resources and tools to execute each action, such as getting team member contact information and sending reminders.

[0488] Input data: Team member contact information

[0489] Output: Reminders sent

[0490] Step 5:

[0491] The server transmits the execution result to the terminal.

[0492] Input data: Execution result text

[0493] Output: The resulting text sent to the terminal.

[0494] Step 6:

[0495] The device will display a message of thanks to the user, such as "The reminder has been sent. Thank you for your cooperation."

[0496] Output: A thank you message that will be displayed to the user (e.g., "Reminder has been sent. Thank you for your cooperation.")

[0497] (Application example 2)

[0498] 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."

[0499] With the increase in remote workers, there is a need for systems that can provide efficient and prompt support. It is also important to understand customer emotions and provide optimal suggestions in virtual stores. Conventional systems lack the ability to respond in a way that takes into account the emotions of remote workers, and emotional support is not realized in virtual stores. This leads to issues such as lower satisfaction for remote workers and customers, and reduced utilization efficiency.

[0500] 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.

[0501] In this invention, the server includes means for combining a generative AI model and an emotion engine to quickly and accurately respond to questions from remote workers, means for providing access to internal resources and documents required by the remote workers, means for supporting the remote workers in efficiently communicating with groups, and means for supporting the virtual store by recognizing customer emotions and generating optimal responses and suggestions based thereon. This makes it possible to provide appropriate support that takes emotions into consideration for remote workers and customers of the virtual store, thereby improving satisfaction and usage efficiency.

[0502] A "generative AI model" is a system that uses artificial intelligence technology to automatically generate responses and suggestions in response to user input.

[0503] An "emotion engine" is a system that analyzes and recognizes emotions from user input text and voice data.

[0504] A "remote worker" is someone who performs their work outside of an office.

[0505] "Internal resources" refers to resources such as various information, tools, and databases used within a company.

[0506] "Document" refers to a digital file or paper document created in text format.

[0507] A "group" refers to a group of workers who work together with a common purpose.

[0508] "Communication" refers to the act of exchanging information or messages.

[0509] A "virtual store" refers to an online platform that offers products and services over the Internet.

[0510] "Support means" refers to a method or system for providing information or services required by users.

[0511] "Customer" means a purchaser or user of goods or services.

[0512] This invention is a system that effectively supports remote workers and virtual store customers, utilizing a generative AI model and emotion engine. Specifically, it responds quickly and accurately to questions and challenges faced by remote workers, provides access to necessary internal resources and documents, and supports efficient communication within groups. It can also recognize the emotions of virtual store customers and generate optimal responses and suggestions based on those emotions.

[0513] System configuration

[0514] server

[0515] It receives questions and requests and passes them to a generative AI model and emotion engine.

[0516] Analyzes sentiment from customer input text and generates responses based on it.

[0517] Provide access to necessary internal resources and product databases.

[0518] Terminal

[0519] Input from remote workers and customers is sent to the server in text format.

[0520] Displays the answers and suggestions received from the server.

[0521] User

[0522] Remote workers and virtual store customers.

[0523] Hardware and software used

[0524] Hardware

[0525] Processing is performed using servers or cloud services (e.g., Amazon Web Services, Google (registered trademark) Cloud Platform).

[0526] The devices used by users include smartphones, PCs, tablets, etc.

[0527] software

[0528] The generative AI model uses OpenAI's GPT-4 (registered trademark) API.

[0529] The emotion engine uses the TextBlob library.

[0530] MongoDB is used as the database.

[0531] React Native is used for front-end development.

[0532] Processing Description

[0533] 1. Emotion recognition

[0534] The text data entered by the user is analyzed using the TextBlob library to recognize emotions, which identifies the emotions of remote workers and customers.

[0535] 2. Response generation using a generative AI model

[0536] It uses OpenAI's GPT-4 API to generate appropriate responses based on emotions and inputs. It provides the best answer based on the user's input and the perceived emotions.

[0537] 3. Database Access

[0538] MongoDB is used to retrieve the necessary product information and resources. The server accesses the database and provides the necessary information to the user.

[0539] 4. Sending a Response

[0540] The application uses React Native to display the response to the user. The terminal displays the information received from the server so that the user can easily understand it.

[0541] Examples of concrete examples and prompts

[0542] For example, consider a remote worker typing, "Please let me know the latest information about our company policies," and the emotion of confusion is detected.

[0543] Example prompt sentence:

[0544] "User is feeling confused. Please generate a response to the following query: What is the latest information regarding internal policies?"

[0545] Based on this prompt, the generative AI model generates an appropriate response and provides it to remote workers, such as, "The latest version of our internal policies was updated in January 2023. Please rest assured, please see this link for details."

[0546] This makes it possible to provide appropriate support that takes into account the emotions of remote workers and customers in virtual stores, thereby improving satisfaction and usage efficiency.

[0547] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0548] Step 1:

[0549] The user types into the terminal.

[0550] The user types a question or request (e.g., "Please let me know the latest information about our company policies") into the device's input field. This input text is passed to the next process as is.

[0551] Step 2:

[0552] The device sends input to the server.

[0553] The terminal sends the text entered by the user to the server in text format, while the input data is sent in plain text and received by the server.

[0554] Step 3:

[0555] The server performs emotion analysis using an emotion engine.

[0556] The server passes the received text data to an emotion engine (e.g., TextBlob library) for emotion analysis, which identifies the user's emotion (e.g., confusion).

[0557] Input: User-entered text

[0558] Output: User's emotional information

[0559] Step 4:

[0560] The server generates a response using a generative AI model.

[0561] The server passes the user's input text and emotion information to a generative AI model (e.g., OpenAI's GPT-4 API) to generate an appropriate response. The prompt sentence used is "The user is feeling confused. Please generate a response to the following query: Please tell me the latest information about our company policy."

[0562] Input: User input text and emotion information

[0563] Output: The generated response

[0564] Step 5:

[0565] The server accesses the database to retrieve additional information (if necessary).

[0566] If the generated response contains links to internal resources or documents, the server retrieves the necessary data from a database (e.g. MongoDB) to complete the response with the necessary details.

[0567] Input: Generated response

[0568] Output: The completed response

[0569] Step 6:

[0570] The server sends the completed response to the terminal.

[0571] The server sends the generated response and any necessary details to the terminal in plain text format.

[0572] Input: Completed response

[0573] Output: Sending response data to the terminal

[0574] Step 7:

[0575] The terminal displays the response to the user.

[0576] The device will display the response data received from the server to the user. For example, a response such as "The latest version of our internal policy was updated in January 2023. Please rest assured, please refer to this link for details."

[0577] Input: Response data from the server

[0578] Output: What is displayed to the user

[0579] This allows users to receive appropriate responses to their questions and requests that take emotion into account.

[0580] 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.

[0581] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0582] 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.

[0583] [Second embodiment]

[0584] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0585] 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.

[0586] 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).

[0587] 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.

[0588] 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.

[0589] 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).

[0590] 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.

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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."

[0596] To implement this invention, it is necessary to build a remote worker support system that utilizes a generative AI model. This system has three main functions: answering questions, providing resources, and supporting communication. Below, we will explain in detail how to implement this system.

[0597] Handling inquiries

[0598] A user types a question into a terminal, for example, "Please let me know the latest information about our company policies."

[0599] The terminal sends this question in text format to the server.

[0600] The server passes the received question to a generative AI model, which analyzes the question and initiates a process to generate an appropriate answer based on the question's content. Specifically, the model tokenizes the question, analyzes its intent, and queries an internal database to retrieve relevant information.

[0601] The generative AI model generates the optimal answer based on the analysis results, for example, "The latest version of our internal policy was updated in January 2023. Please see this link for details."

[0602] The server receives this response and sends it to the terminal.

[0603] The terminal displays the received response to the user.

[0604] Handling resource offerings

[0605] A user types a request into a terminal for a required resource or document, such as "Teach me how to use a project management tool."

[0606] The terminal sends this request in text format to the server.

[0607] The server passes the request to the generative AI model, which then analyzes the location and access method of the required resources based on the request, as well as searches for the necessary materials from its internal database.

[0608] The generative AI model searches for documents and retrieves their links and files, generating information such as, "Please refer to these guidelines for how to use project management tools."

[0609] The server transmits the acquired information to the terminal.

[0610] The device will display links and required files to the user.

[0611] Handling team communication support

[0612] A user enters a request into their device to schedule a meeting or share a document, such as "Please send a reminder for tomorrow's meeting to everyone on my team."

[0613] The terminal sends this request in text format to the server.

[0614] The server passes the request to the generative AI model, which analyzes the request and determines the corresponding action.

[0615] The generative AI model accesses internal resources and tools to perform each action, for example, getting team member contact information and sending reminders.

[0616] The server transmits the execution result to the terminal.

[0617] The device will display a result to the user, such as "Reminder has been sent."

[0618] This allows remote workers to quickly access the information and resources they need and communicate with their teams efficiently. Utilizing generative AI models with these capabilities can improve productivity and reduce stress for remote workers.

[0619] The processing flow will be explained below.

[0620] Handling inquiries

[0621] Step 1:

[0622] The user types a question into the terminal, for example, "What is the latest information about our company policies?"

[0623] Step 2:

[0624] The terminal sends the question in text format to the server.

[0625] Step 3:

[0626] The server passes the received questions to a generative AI model.

[0627] Step 4:

[0628] The generative AI model analyzes the question, specifically tokenizing it and analyzing its intent.

[0629] Step 5:

[0630] The generative AI model generates database queries based on intent and queries internal databases to retrieve relevant information.

[0631] Step 6:

[0632] The server receives the answer from the generative AI model and sends it to the device.

[0633] Step 7:

[0634] The device will then display the received response to the user, for example, "The latest version of our internal policies was updated in January 2023. Please see this link for details."

[0635] Handling resource offerings

[0636] Step 1:

[0637] A user types a request into a terminal for a required resource or document, such as "Teach me how to use a project management tool."

[0638] Step 2:

[0639] The terminal sends the request in text format to the server.

[0640] Step 3:

[0641] The server passes the request to the generative AI model.

[0642] Step 4:

[0643] Based on the request, the generative AI model analyzes where the required resources are located and how to access them.

[0644] Step 5:

[0645] The generative AI model searches for the necessary materials from an internal database.

[0646] Step 6:

[0647] The generative AI model searches for documents and retrieves their links and files, generating information such as, "Please refer to these guidelines for how to use project management tools."

[0648] Step 7:

[0649] The server transmits the acquired information to the terminal.

[0650] Step 8:

[0651] The device will display links and required files to the user.

[0652] Handling team communication support

[0653] Step 1:

[0654] A user enters a request into their device to schedule a meeting or share a document, such as "Please send a reminder for tomorrow's meeting to everyone on my team."

[0655] Step 2:

[0656] The terminal sends the request in text format to the server.

[0657] Step 3:

[0658] The server passes the request to the generative AI model.

[0659] Step 4:

[0660] The generative AI model analyzes the request and determines the corresponding action.

[0661] Step 5:

[0662] The generative AI model accesses the necessary internal resources and tools to perform each action.

[0663] Step 6:

[0664] For example, a generative AI model can retrieve contact information for team members and send reminders.

[0665] Step 7:

[0666] The server transmits the execution result to the terminal.

[0667] Step 8:

[0668] The device will display a result to the user, such as "Reminder has been sent."

[0669] Example 1

[0670] 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."

[0671] Remote workers often find it difficult to work efficiently because they are unable to quickly access the information and resources they need. Communication with their team can also be difficult in a remote work environment, leading to lower productivity and increased stress.

[0672] 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.

[0673] In this invention, the server includes means for using a generative AI model to quickly and accurately respond to the remote worker's questions, means for providing access to information resources and data required by the remote worker, and means for supporting the remote worker in efficiently communicating with colleagues, thereby enabling the remote worker to quickly access the information and resources they need and to communicate smoothly with their team.

[0674] A "remote worker" is someone who works remotely (from a remote location) without coming to the office.

[0675] A "generative AI model" refers to algorithms or software that generate information based on artificial intelligence technology.

[0676] "Information resources" refers to information resources such as data, knowledge bases, and documents that users need.

[0677] "Support for efficient communication" refers to providing the features and tools remote workers need to effectively exchange information and collaborate with colleagues.

[0678] A "server" refers to a computer system that provides various services over a network.

[0679] "Terminal" refers to a device (such as a personal computer or smartphone) that is directly operated by a user.

[0680] An "internal database" is a collection of data managed within an organization, and refers to a searchable and retrieval-capable information storage system.

[0681] A "protocol" refers to the rules and procedures for communicating data over a computer network.

[0682] A "query" is a request or question made to a database to retrieve specific information.

[0683] An "action" refers to a specific operation or process that the system executes based on a user request.

[0684] "Execution result" refers to the result of an operation or process that the server performed in response to a user request.

[0685] MODE FOR CARRYING OUT THE INVENTION

[0686] To implement this invention, a system combining a server, a terminal, and a generative AI model must be constructed. This system has three main functions: responding to questions from remote workers, providing resources, and supporting communication.

[0687] Hardware and software used

[0688] server

[0689] The server plays a central role in managing data exchange between the generative AI model and other system components, using the following software and services:

[0690] Generative AI model: OpenAI GPT-3

[0691] In-house databases: MongoDB, MySQL, PostgreSQL

[0692] Communication protocol: HTTPS, SMTP

[0693] Terminal

[0694] The terminal used by the user is used to input questions and requests and display responses from the system. It uses the following hardware and software:

[0695] Devices: PC, smartphone

[0696] Display software: Web browser, dedicated application

[0697] Data processing and data calculation

[0698] Answering questions

[0699] The user inputs a question into the terminal and the question is processed by sending it to the server.

[0700] The server passes the question data to a generative AI model, which analyzes the question.

[0701] The generative AI model tokenizes the question and analyzes its intent, using NLTK for tokenization and the BERT model for intent analysis.

[0702] Based on the analysis results, the generative AI model queries the company's internal database to retrieve relevant information.

[0703] The generative AI model generates answers based on the information it obtains.

[0704] The server sends the generated answer to the terminal, which displays the answer to the user.

[0705] Resource provision

[0706] A user inputs a request for a required resource into a terminal and sends it to a server.

[0707] The server passes the request content to the generative AI model and analyzes the location of the request.

[0708] The generative AI model retrieves the necessary materials from an internal database.

[0709] The generative AI model takes links and files to resources and generates appropriate answers.

[0710] The server transmits the acquired information to the terminal, which then displays the information to the user.

[0711] Communication Support

[0712] A user inputs a request to schedule a meeting or share a document into a terminal and sends it to the server.

[0713] The server passes the request to the generative AI model and analyzes the content.

[0714] The generative AI model retrieves team member contact information from an internal database and sends reminders.

[0715] The server sends the execution results to the terminal, which then displays the results to the user.

[0716] Specific examples

[0717] Specific prompt examples for questions:

[0718] "What are the latest changes to our company's policies?"

[0719] Examples of specific prompts for resource provision:

[0720] "Please provide guidelines for project management tools."

[0721] Examples of specific communication prompts:

[0722] "Send a reminder to my team for our next meeting."

[0723] This system will enable remote workers to quickly access the information and resources they need and communicate efficiently with their teams, which is expected to increase productivity and reduce stress.

[0724] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0725] Question response processing flow

[0726] Step 1:

[0727] The user inputs a question into the terminal. The input question is text data such as "Please tell me the latest information about the company's policies."

[0728] Step 2:

[0729] The terminal sends the question data entered by the user in text format to the server using the HTTPS protocol.

[0730] Step 3:

[0731] The server passes the received question data to the generative AI model, OpenAI GPT-3, which the server accesses using the required API key.

[0732] Input: Question data from the user

[0733] Output: Text data passed to the generative AI model

[0734] Step 4:

[0735] The generative AI model tokenizes the question and analyzes its intent, using NLTK for tokenization and the BERT model for intent analysis.

[0736] Input: Text data from the server

[0737] Output: Parsed intent data

[0738] Step 5:

[0739] Based on the analysis results, the generative AI model queries the internal database (MongoDB) to retrieve relevant information, for example, searching for information on the latest internal policies.

[0740] Input: Parsed intent data

[0741] Output: Retrieved company policy information

[0742] Step 6:

[0743] The generative AI model generates the most appropriate answer based on information retrieved from the company's database, such as "The latest version of our company policy was updated in January 2023. Please see this link for details."

[0744] Input: Information data obtained from the company database

[0745] Output: Generated answer text

[0746] Step 7:

[0747] The server receives the generated response data and sends it to the terminal, also using the HTTPS protocol.

[0748] Input: Generated answer text

[0749] Output: Response data sent to the device

[0750] Step 8:

[0751] The terminal displays the received answer data to the user. The terminal displays the answer text on the screen so that it can be seen by the user.

[0752] Input: Response data sent from the server

[0753] Output: The answer text that is displayed to the user

[0754] Resource provisioning process flow

[0755] Step 1:

[0756] A user types a request for a resource they need into a terminal, for example, "Teach me how to use a project management tool."

[0757] Step 2:

[0758] The device sends this request in text format to the server using the HTTPS protocol.

[0759] Step 3:

[0760] The server passes the request to the generative AI model, OpenAI GPT-3, which the server accesses using an API key.

[0761] Input: Request data from the user

[0762] Output: Text data passed to the generative AI model

[0763] Step 4:

[0764] The generative AI model analyzes the request and identifies the required resources, possibly using the BERT model, to analyze what the requested resources are.

[0765] Input: Request data from the server

[0766] Output: Parsed resource specific data

[0767] Step 5:

[0768] The generative AI model retrieves necessary materials from an internal database (MySQL), for example, searching for guideline materials for a project management tool.

[0769] Input: Parsed resource-specific data

[0770] Output: Acquired data

[0771] Step 6:

[0772] The generative AI model retrieves links and files to documents and generates appropriate answers, such as "Please refer to these guidelines for how to use project management tools."

[0773] Input: Material data obtained from the internal database

[0774] Output: Generated answer text

[0775] Step 7:

[0776] The server sends the obtained information to the terminal, also using the HTTPS protocol.

[0777] Input: Generated answer text

[0778] Output: Response data sent to the device

[0779] Step 8:

[0780] The terminal displays the link and required files to the user. The terminal displays the generated link and text on the screen.

[0781] Input: Response data sent from the server

[0782] Output: The link and answer text that is displayed to the user

[0783] Communication support processing flow

[0784] Step 1:

[0785] A user types a request into their device to schedule a meeting or share a document, for example, "Send a reminder to the whole team for tomorrow's meeting."

[0786] Step 2:

[0787] The device sends this request in text format to the server using the HTTPS protocol.

[0788] Step 3:

[0789] The server passes the request to the generative AI model, OpenAI GPT-3, which is accessed using an API key.

[0790] Input: Request data from the user

[0791] Output: Text data passed to the generative AI model

[0792] Step 4:

[0793] The generative AI model analyzes the received request and determines the corresponding action, which can be done using the BERT model to analyze what the requested action is.

[0794] Input: Request data from the server

[0795] Output: Parsed action decision data

[0796] Step 5:

[0797] For example, the generative AI model retrieves team member contact information from an internal database (PostgreSQL) and sends reminders, using the SMTP protocol to send emails.

[0798] Input: Parsed action decision data

[0799] Output: Reminder email sent

[0800] Step 6:

[0801] The server sends the execution result (e.g., "Reminder has been sent") to the device using the HTTPS protocol.

[0802] Input: Record of reminder email sent

[0803] Output: Execution result data sent to the terminal

[0804] Step 7:

[0805] The device displays the execution result to the user. The device displays text such as "Reminder sent" on the screen.

[0806] Input: Execution result data sent from the server

[0807] Output: The execution result text that is displayed to the user

[0808] (Application example 1)

[0809] 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."

[0810] Conventional remote worker support systems have had problems with efficiency and accuracy when responding to questions, providing resources, and supporting communication. Furthermore, factory workers are unable to quickly obtain the information they need on-site or properly understand how to operate machines, leading to reduced productivity. For this reason, a new system is needed that allows both remote workers and factory workers to efficiently access the information they need and communicate smoothly.

[0811] 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.

[0812] In this invention, the server includes means for using a generative AI model to quickly and accurately respond to questions from remote workers, means for providing access to information resources and documents required by remote workers, means for supporting remote workers in efficiently communicating with their teams, means for converting questions from factory workers into text format using speech recognition when the factory workers ask questions about machine settings or operation methods, means for obtaining and providing operation manuals and procedures required by factory workers via the server, and means for relaying communication between factory workers or managers by voice, and for adjusting schedules and transmitting messages. This enables remote workers and factory workers to quickly access the information they need and perform their work efficiently.

[0813] A "remote worker" is a worker who performs their work remotely via the Internet.

[0814] A "generative AI model" is an artificial intelligence algorithm that uses natural language processing to generate appropriate answers to human questions.

[0815] "Information resources" are business-related data, documents, manuals, and other materials in electronic form.

[0816] "Speech recognition" is a technology that converts speech into text form.

[0817] "Text format" is a data format expressed as character information.

[0818] A "server" is a computer system that processes and stores data over a network.

[0819] An "operation manual" is a document that details how to set up and use a machine or device.

[0820] A "procedure" is a document that lists the steps to be taken to perform a specific task.

[0821] To implement this invention, it is necessary to build a remote worker and factory worker support system that utilizes a generative AI model. The system of the present invention combines speech recognition technology, a generative AI model, database management, text output, and communication tools. This system uses the following hardware and software:

[0822] Hardware and software used:

[0823] Hardware: microphone, speakers, display, computer (e.g. Raspberry Pi).

[0824] Software: Python program, speech_recognition library, pyttsx3 library, openai library.

[0825] Data processing and calculation:

[0826] 1. Voice to text conversion:

[0827] The device uses voice recognition technology to convert the user's (remote worker or factory worker's) speech into text. The speech_recognition library is used for voice recognition. This process obtains the user's question or request in text format.

[0828] 2. Question and Request Analysis:

[0829] The server passes text questions or requests to a generative AI model for analysis. The generative AI model uses an OpenAI AI model (e.g., GPT-3). The generative AI model analyzes the text and generates appropriate answers or necessary information.

[0830] 3. Response and Information Provision:

[0831] The server receives the answers generated by the generative AI model and the searched resources. The server then sends them to the device, which then provides the results to the user in voice and text format. The pyttsx3 library is used for voice output.

[0832] Examples:

[0833] Examples of how to respond to questions:

[0834] The user asks into the microphone, "How do I set up this machine?" The question is converted into text using voice recognition and sent to the server. The generative AI model analyzes the question and generates an appropriate answer, such as "First, turn on this machine, then set it up by following the instructions displayed on the control panel." The server sends this to the device and provides it to the user as voice and on-screen.

[0835] Example prompt sentence:

[0836] "Question: How do I set up this machine?" Answer:

[0837] "Question: Can you provide the operation manual?"Answer: The operation manual can be downloaded from this link.

[0838] This allows users to quickly access the information they need and carry out their work efficiently. This system provides high convenience to both remote workers and factory workers.

[0839] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0840] Step 1:

[0841] The user speaks a question or request into the microphone, which inputs voice data.

[0842] Step 2:

[0843] The device uses voice recognition technology to convert the voice data into text format. Specifically, it uses the speech_recognition library to output the voice data as text data.

[0844] Step 3:

[0845] A textual question or request is sent to the server, which receives the input data by sending data from the device to the server.

[0846] Step 4:

[0847] The server passes the text data to a generative AI model, which then analyzes the question or request. An OpenAI AI model (e.g., GPT-3) is used to analyze the prompt and generate an answer. The analysis results include the answer text and any necessary information.

[0848] Step 5:

[0849] The server receives the answers generated by the generative AI model and the resources searched, and sends them to the device. Data transmission from the server to the device provides output data to the device.

[0850] Step 6:

[0851] The device provides the received answers and information to the user. Specifically, it uses the pyttsx3 library to read the answers aloud and display them in text format on the display, allowing the user to obtain information in both audio and text formats.

[0852] Step 7:

[0853] The user can ask additional questions or make requests as needed, and the process repeats from step 1, ensuring the user receives ongoing support.

[0854] This makes it possible to effectively implement functions such as answering questions, providing resources, and supporting communication.

[0855] 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.

[0856] To implement this invention, it is necessary to combine an emotion engine with a remote worker support system that utilizes a generative AI model. This system has three main functions: answering questions, providing resources, and supporting communication. It also has the ability to recognize user emotions and generate responses based on those emotions. Below, we will explain in detail how to implement this system.

[0857] Handling inquiries

[0858] The user inputs a question into the terminal, for example, "Please tell me the latest information about company policies." At this time, the emotion engine recognizes the user's emotion (e.g., confusion, tension, calmness, etc.) from the question input.

[0859] The terminal sends the question in text format to the server.

[0860] The server passes the received question to an emotion engine to analyze the emotion before passing it to the generative AI model. The generative AI model analyzes the question and the recognized emotion and generates an appropriate answer based on the content. For example, it generates an answer such as, "The latest version of our internal policy was updated in January 2023. Please rest assured. For more information, please see this link."

[0861] The server receives this response and sends it to the terminal.

[0862] The device displays the received answer to the user, for example, the answer that conveys the above sense of security.

[0863] Handling resource offerings

[0864] A user inputs a request for the required resources or documents into a terminal. For example, a request might be, "Please teach me how to use a project management tool." At this time, the emotion engine recognizes the user's emotion from the input of the request.

[0865] The terminal sends the request in text format to the server.

[0866] The server passes the request and the recognized emotion to the generative AI model, which then analyzes the location and access method of the required resources based on the request.

[0867] The generative AI model searches for the necessary materials from an internal database and retrieves the links and files. For example, it generates information such as, "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to support you."

[0868] The server transmits the acquired information to the terminal.

[0869] The device will display links and necessary files to the user, for example, a response conveying the above-mentioned willingness to help.

[0870] Handling team communication support

[0871] A user inputs a request into their device to schedule a meeting or share a document. For example, they might request, "Please send a reminder for tomorrow's meeting to everyone on the team." At this time, the emotion engine recognizes the user's emotion from the input request.

[0872] The terminal sends the request in text format to the server.

[0873] The server passes the request and the recognized emotion to the generative AI model, which analyzes the request and determines the corresponding action.

[0874] The generative AI model accesses the necessary internal resources and tools to perform each action, such as retrieving team member contact information and sending reminders, while also taking into account the user's sentiment and tailoring the reminder text.

[0875] The server transmits the execution result to the terminal.

[0876] The device will display a message to the user expressing gratitude, such as "The reminder has been sent. Thank you for your cooperation."

[0877] This allows remote workers to quickly access the information and resources they need and communicate with their teams efficiently.Furthermore, by recognizing users' emotions and adjusting responses, it is possible to reduce the psychological burden on remote workers and provide a more comfortable working environment.

[0878] The processing flow will be explained below.

[0879] Handling inquiries

[0880] Step 1:

[0881] The user types a question into the terminal, for example, "What's the latest on our company policies?"

[0882] Step 2:

[0883] The terminal sends the question in text format to the server.

[0884] Step 3:

[0885] The server receives the question and passes it to the emotion engine.

[0886] Step 4:

[0887] The emotion engine analyzes the user's emotions from the question input and generates emotion data (e.g., confusion, tension, calmness, etc.).

[0888] Step 5:

[0889] The server passes the question, including the emotional data, to the generative AI model.

[0890] Step 6:

[0891] The generative AI model analyzes the question content and sentiment data, then queries the company's internal database to retrieve relevant information.

[0892] Step 7:

[0893] Based on the analysis results, the generative AI model generates an appropriate response based on the sentiment, such as, "The latest version of our internal policy was updated in January 2023. Please rest assured, please see this link for details."

[0894] Step 8:

[0895] The server sends the generated response to the terminal.

[0896] Step 9:

[0897] The terminal displays the received response to the user.

[0898] Handling resource offerings

[0899] Step 1:

[0900] A user types a request into a terminal for a needed resource or document, for example, "Teach me how to use a project management tool."

[0901] Step 2:

[0902] The terminal sends the request in text format to the server.

[0903] Step 3:

[0904] The server receives the request and passes it to the emotion engine.

[0905] Step 4:

[0906] The emotion engine analyzes the user's emotions from the request input and generates emotion data.

[0907] Step 5:

[0908] The server passes the request, including the emotion data, to the generative AI model.

[0909] Step 6:

[0910] The generative AI model analyzes the request content and emotional data, and searches for the necessary materials from an internal database.

[0911] Step 7:

[0912] Based on the analysis results, the generative AI model generates appropriate information according to the emotion, such as "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to help."

[0913] Step 8:

[0914] The server transmits the acquired information to the terminal.

[0915] Step 9:

[0916] The device will display links and required files to the user.

[0917] Handling team communication support

[0918] Step 1:

[0919] A user types a request into their device to schedule a meeting or share a document, for example, "Send a reminder for tomorrow's meeting to everyone on my team."

[0920] Step 2:

[0921] The terminal sends the request in text format to the server.

[0922] Step 3:

[0923] The server receives the request and passes it to the emotion engine.

[0924] Step 4:

[0925] The emotion engine analyzes the user's emotions from the request input and generates emotion data.

[0926] Step 5:

[0927] The server passes the request, including the emotion data, to the generative AI model.

[0928] Step 6:

[0929] The generative AI model analyzes the request content and sentiment data to determine the corresponding action (such as scheduling a meeting or sharing a document).

[0930] Step 7:

[0931] The generative AI model accesses the necessary internal resources and tools to perform each action, such as getting team member contact information and sending a reminder, while also taking into account the user's sentiment and tailoring the reminder text.

[0932] Step 8:

[0933] The server transmits the execution result to the terminal.

[0934] Step 9:

[0935] The device will display a message to the user expressing gratitude, such as "The reminder has been sent. Thank you for your cooperation."

[0936] Example 2

[0937] 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."

[0938] Remote workers need to quickly obtain information in their work environment and communicate efficiently with their team. However, there are limited systems in place to improve information access and communication efficiency in a remote work environment. Furthermore, there is a lack of systems to reduce the psychological burden on remote workers and maintain a comfortable work environment. In such an environment, remote workers often feel confused and nervous, leading to problems with reduced productivity.

[0939] 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 a means for receiving the content of a question from a remote worker in text format and passing the question to a generative AI model, a means for analyzing the user's emotions and passing the analysis result to the generative AI model, and a means for sending an answer generated by the generative AI model to the remote worker's terminal. This makes it possible to generate and provide an appropriate answer that takes into account the user's emotions when the user inputs a question.

[0940] The server also includes a means for receiving resource requests from remote workers and analyzing the request content using a generative AI model, a means for retrieving resources from an internal database and providing them to the remote workers, and a means for adjusting a response to the request based on user sentiment, thereby enabling the resources needed by the remote workers to be provided quickly and accurately.

[0941] Furthermore, the server includes a means for supporting the remote worker in efficiently communicating with the team, and a means for recognizing the user's emotions and generating a response based on the emotions. This makes it possible to provide communication support that takes the emotions of the remote worker into consideration, thereby realizing an efficient work environment while reducing psychological burden.

[0942] A "remote worker" is an employee or contractor who performs work away from a company or organization's physical offices.

[0943] A "generative AI model" refers to an artificial intelligence model that analyzes input data and generates appropriate answers in natural language based on the results.

[0944] "Emotion engine" refers to a software component that analyzes and recognizes a user's emotional state from input text data.

[0945] "Internal resources" refers to resources such as information, data, tools, and documents owned by a company or organization.

[0946] "Terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[0947] "Server" refers to a central computer system for processing, analyzing, storing, and distributing data.

[0948] "Text format" refers to a representation format of information structured as character data.

[0949] "Analysis" refers to the process of examining input data and information in detail and converting it into an understandable form.

[0950] "Response" means a response generated in response to an entered question or request.

[0951] "Adjusting a response" refers to the process of appropriately changing the content and expression of a generated reply based on the user's emotional state.

[0952] "Communication support" refers to the technical and functional support provided to remote workers to collaborate effectively with other employees and team members.

[0953] The present invention is a system for supporting remote workers that utilizes a generative AI model and an emotion engine. The following describes in detail how the present invention is specifically implemented.

[0954] Answering questions

[0955] The user inputs a question into the terminal. For example, "Please tell me the latest information about company policies." At this time, the emotion engine recognizes the user's emotion (e.g., confusion, tension) from the question input.

[0956] The terminal sends the question in text format to the server.

[0957] The server analyzes emotions by passing the received question and emotion data to the emotion engine. The analyzed emotion and question content are input into the generative AI model to generate an appropriate answer.

[0958] The generative AI model might generate an answer like, "The latest version of our internal policies was updated in January 2023. Don't worry, please see this link for more details."

[0959] The server receives this response and sends it to the terminal, which then displays it to the user.

[0960] Resource provision

[0961] When a user inputs a request for resources or documents into a terminal, for example, "Please tell me how to use the project management tool," the emotion engine recognizes the user's emotion from the input of the request.

[0962] The terminal sends the request in text format to the server.

[0963] The server passes the request content and emotion data to the generative AI model, which analyzes the content, searches the internal database for the necessary materials, and retrieves the links and files.

[0964] For example, the generative AI model generates information such as, "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to support you."

[0965] The server sends the acquired information to the terminal, which displays resources and links to the user.

[0966] Communication Support

[0967] When a user inputs a request into a device to schedule a meeting or share a document, for example, "Please send a reminder for tomorrow's meeting to everyone on the team," the emotion engine recognizes the user's emotion from the request.

[0968] The terminal sends the request in text format to the server.

[0969] The server passes the request and emotion data to the generative AI model, which analyzes the request and accesses the necessary internal resources and tools to execute each action.

[0970] For example, a generative AI model might generate a response like, "Reminder has been sent. Thank you for your cooperation."

[0971] The server sends the execution result to the device, which confirms that the reminder was sent and displays a message of thanks to the user.

[0972] Example prompt

[0973] 1. Examples of how to respond to questions:

[0974] Prompt: "What's the latest information about our company policies?"

[0975] Generative AI model response: "Our internal policies were last updated in January 2023. Rest assured, please see this link for more details."

[0976] 2. Examples of resource provision:

[0977] Prompt: "How do I use a project management tool?"

[0978] Generative AI model response: "Please refer to these guidelines to learn how to use our project management tools. If you need help, we're always here to help."

[0979] 3. Examples of communication support:

[0980] Prompt: "Please send a reminder to the whole team for tomorrow's meeting."

[0981] Generative AI model response: "Reminder has been sent. Thank you for your cooperation."

[0982] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0983] Handling inquiries

[0984] Step 1:

[0985] The user enters a question into an input field on the terminal.

[0986] Example: "Please let me know the latest information about our company policies."

[0987] Here, the emotion engine recognizes the user's emotion (e.g., confusion, tension) from the content of the text.

[0988] Step 2:

[0989] The device sends the question and emotion data entered by the user in text format to the server.

[0990] Input data: Question text and sentiment data

[0991] Output: Text data sent to the server

[0992] Step 3:

[0993] The server receives the question and emotion data and passes it to the emotion engine for detailed emotion analysis.

[0994] Input data: Question text and initial emotion data

[0995] Output: Detailed emotion analysis data (e.g., high confusion, medium tension)

[0996] Step 4:

[0997] The server inputs the question and detailed emotional data into the generative AI model, which then generates an answer based on this.

[0998] Input data: Question text and detailed sentiment data

[0999] Output: Generated response text (e.g., "Our internal policy was last updated in January 2023. Don't worry, see this link for more details.")

[1000] Step 5:

[1001] The server sends the answer obtained from the generative AI model to the device.

[1002] Input data: Generated answer text

[1003] Output: Answer text sent to terminal

[1004] Step 6:

[1005] The terminal displays the received response to the user.

[1006] Output: Answer text to be displayed to the user (e.g. "Our internal policy was last updated in January 2023. Don't worry, see this link for more details.")

[1007] Handling resource offerings

[1008] Step 1:

[1009] A user inputs a request for a resource or document into a terminal.

[1010] Example: "How do I use a project management tool?"

[1011] Here, the emotion engine recognizes the user's emotion from the content of the text.

[1012] Step 2:

[1013] The device sends the request and emotion data in text format to the server.

[1014] Input data: resource request text and sentiment data

[1015] Output: Text data sent to the server

[1016] Step 3:

[1017] The server passes the request content and emotion data to the generative AI model, which analyzes the content and generates appropriate information.

[1018] Input data: request text and emotion data

[1019] Output: Generated guideline link text (e.g., "Please refer to these guidelines for how to use project management tools. If you need help, we're always here to help you.")

[1020] Step 4:

[1021] The server sends the information obtained from the generative AI model to the terminal.

[1022] Input data: Generated guideline link text

[1023] Output: Guideline link text sent to terminal

[1024] Step 5:

[1025] The device will display links and required files to the user.

[1026] Output: Guideline link text that will be displayed to the user (e.g., "Please refer to these guidelines for how to use the project management tool. If you need help, we're always here to help you.")

[1027] Communication support processing

[1028] Step 1:

[1029] The user inputs a request to schedule a meeting or share a document into the terminal.

[1030] Example: "Please send a reminder to the whole team for tomorrow's meeting."

[1031] Here, the emotion engine recognizes the user's emotion from the content of the text.

[1032] Step 2:

[1033] The device sends the request and emotion data in text format to the server.

[1034] Input data: Request text and emotion data

[1035] Output: Text data sent to the server

[1036] Step 3:

[1037] The server passes the request and emotion data to the generative AI model, which analyzes the request and determines the corresponding action.

[1038] Input data: Request text and emotion data

[1039] Output: The generated action text (e.g., "Reminder sent. Thank you for your cooperation.")

[1040] Step 4:

[1041] The generative AI model accesses internal resources and tools to execute each action, such as getting team member contact information and sending reminders.

[1042] Input data: Team member contact information

[1043] Output: Reminders sent

[1044] Step 5:

[1045] The server transmits the execution result to the terminal.

[1046] Input data: Execution result text

[1047] Output: The resulting text sent to the terminal.

[1048] Step 6:

[1049] The device will display a message of thanks to the user, such as "The reminder has been sent. Thank you for your cooperation."

[1050] Output: A thank you message that will be displayed to the user (e.g., "Reminder has been sent. Thank you for your cooperation.")

[1051] (Application example 2)

[1052] 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."

[1053] With the increase in remote workers, there is a need for systems that can provide efficient and prompt support. It is also important to understand customer emotions and provide optimal suggestions in virtual stores. Conventional systems lack the ability to respond in a way that takes into account the emotions of remote workers, and emotional support is not realized in virtual stores. This leads to issues such as lower satisfaction for remote workers and customers, and reduced utilization efficiency.

[1054] 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.

[1055] In this invention, the server includes means for combining a generative AI model and an emotion engine to quickly and accurately respond to questions from remote workers, means for providing access to internal resources and documents required by the remote workers, means for supporting the remote workers in efficiently communicating with groups, and means for supporting the virtual store by recognizing customer emotions and generating optimal responses and suggestions based thereon. This makes it possible to provide appropriate support that takes emotions into consideration for remote workers and customers of the virtual store, thereby improving satisfaction and usage efficiency.

[1056] A "generative AI model" is a system that uses artificial intelligence technology to automatically generate responses and suggestions in response to user input.

[1057] An "emotion engine" is a system that analyzes and recognizes emotions from user input text and voice data.

[1058] A "remote worker" is someone who performs their work outside of an office.

[1059] "Internal resources" refers to resources such as various information, tools, and databases used within a company.

[1060] "Document" refers to a digital file or paper document created in text format.

[1061] A "group" refers to a group of workers who work together with a common purpose.

[1062] "Communication" refers to the act of exchanging information or messages.

[1063] A "virtual store" refers to an online platform that offers products and services over the Internet.

[1064] "Support means" refers to a method or system for providing information or services required by users.

[1065] "Customer" means a purchaser or user of goods or services.

[1066] This invention is a system that effectively supports remote workers and virtual store customers, utilizing a generative AI model and emotion engine. Specifically, it responds quickly and accurately to questions and challenges faced by remote workers, provides access to necessary internal resources and documents, and supports efficient communication within groups. It can also recognize the emotions of virtual store customers and generate optimal responses and suggestions based on those emotions.

[1067] System configuration

[1068] server

[1069] It receives questions and requests and passes them to a generative AI model and emotion engine.

[1070] Analyzes sentiment from customer input text and generates responses based on it.

[1071] Provide access to necessary internal resources and product databases.

[1072] Terminal

[1073] Input from remote workers and customers is sent to the server in text format.

[1074] Displays the answers and suggestions received from the server.

[1075] User

[1076] Remote workers and virtual store customers.

[1077] Hardware and software used

[1078] Hardware

[1079] Processing is performed using servers or cloud services (e.g., Amazon Web Services, Google Cloud Platform).

[1080] The devices used by users include smartphones, PCs, tablets, etc.

[1081] software

[1082] The generative AI model uses OpenAI's GPT-4 API.

[1083] The emotion engine uses the TextBlob library.

[1084] MongoDB is used as the database.

[1085] React Native is used for front-end development.

[1086] Processing Description

[1087] 1. Emotion recognition

[1088] The text data entered by the user is analyzed using the TextBlob library to recognize emotions, which identifies the emotions of remote workers and customers.

[1089] 2. Response generation using a generative AI model

[1090] It uses OpenAI's GPT-4 API to generate appropriate responses based on emotions and inputs. It provides the best answer based on the user's input and the perceived emotions.

[1091] 3. Database Access

[1092] MongoDB is used to retrieve the necessary product information and resources. The server accesses the database and provides the necessary information to the user.

[1093] 4. Sending a Response

[1094] The application uses React Native to display the response to the user. The terminal displays the information received from the server so that the user can easily understand it.

[1095] Examples of concrete examples and prompts

[1096] For example, consider a remote worker typing, "Please let me know the latest information about our company policies," and the emotion of confusion is detected.

[1097] Example prompt sentence:

[1098] "User is feeling confused. Please generate a response to the following query: What is the latest information regarding internal policies?"

[1099] Based on this prompt, the generative AI model generates an appropriate response and provides it to remote workers, such as, "The latest version of our internal policies was updated in January 2023. Please rest assured, please see this link for details."

[1100] This makes it possible to provide appropriate support that takes into account the emotions of remote workers and customers in virtual stores, thereby improving satisfaction and usage efficiency.

[1101] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1102] Step 1:

[1103] The user types into the terminal.

[1104] The user types a question or request (e.g., "Please let me know the latest information about our company policies") into the device's input field. This input text is passed to the next process as is.

[1105] Step 2:

[1106] The device sends input to the server.

[1107] The terminal sends the text entered by the user to the server in text format, while the input data is sent in plain text and received by the server.

[1108] Step 3:

[1109] The server performs emotion analysis using an emotion engine.

[1110] The server passes the received text data to an emotion engine (e.g., TextBlob library) for emotion analysis, which identifies the user's emotion (e.g., confusion).

[1111] Input: User-entered text

[1112] Output: User's emotional information

[1113] Step 4:

[1114] The server generates a response using a generative AI model.

[1115] The server passes the user's input text and emotion information to a generative AI model (e.g., OpenAI's GPT-4 API) to generate an appropriate response. The prompt sentence used is "The user is feeling confused. Please generate a response to the following query: Please tell me the latest information about our company policy."

[1116] Input: User input text and emotion information

[1117] Output: The generated response

[1118] Step 5:

[1119] The server accesses the database to retrieve additional information (if necessary).

[1120] If the generated response contains links to internal resources or documents, the server retrieves the necessary data from a database (e.g. MongoDB) to complete the response with the necessary details.

[1121] Input: Generated response

[1122] Output: The completed response

[1123] Step 6:

[1124] The server sends the completed response to the terminal.

[1125] The server sends the generated response and any necessary details to the terminal in plain text format.

[1126] Input: Completed response

[1127] Output: Sending response data to the terminal

[1128] Step 7:

[1129] The terminal displays the response to the user.

[1130] The device will display the response data received from the server to the user. For example, a response such as "The latest version of our internal policy was updated in January 2023. Please rest assured, please refer to this link for details."

[1131] Input: Response data from the server

[1132] Output: What is displayed to the user

[1133] This allows users to receive appropriate responses to their questions and requests that take emotion into account.

[1134] 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.

[1135] 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.

[1136] 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.

[1137] [Third embodiment]

[1138] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1139] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1140] 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).

[1141] 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.

[1142] 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.

[1143] 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).

[1144] 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.

[1145] 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.

[1146] 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.

[1147] 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.

[1148] 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.

[1149] 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."

[1150] To implement this invention, it is necessary to build a remote worker support system that utilizes a generative AI model. This system has three main functions: answering questions, providing resources, and supporting communication. Below, we will explain in detail how to implement this system.

[1151] Handling inquiries

[1152] A user types a question into a terminal, for example, "Please let me know the latest information about our company policies."

[1153] The terminal sends this question in text format to the server.

[1154] The server passes the received question to a generative AI model, which analyzes the question and initiates a process to generate an appropriate answer based on the question's content. Specifically, the model tokenizes the question, analyzes its intent, and queries an internal database to retrieve relevant information.

[1155] The generative AI model generates the optimal answer based on the analysis results, for example, "The latest version of our internal policy was updated in January 2023. Please see this link for details."

[1156] The server receives this response and sends it to the terminal.

[1157] The terminal displays the received response to the user.

[1158] Handling resource offerings

[1159] A user types a request into a terminal for a required resource or document, such as "Teach me how to use a project management tool."

[1160] The terminal sends this request in text format to the server.

[1161] The server passes the request to the generative AI model, which then analyzes the location and access method of the required resources based on the request, as well as searches for the necessary materials from its internal database.

[1162] The generative AI model searches for documents and retrieves their links and files, generating information such as, "Please refer to these guidelines for how to use project management tools."

[1163] The server transmits the acquired information to the terminal.

[1164] The device will display links and required files to the user.

[1165] Handling team communication support

[1166] A user enters a request into their device to schedule a meeting or share a document, such as "Please send a reminder for tomorrow's meeting to everyone on my team."

[1167] The terminal sends this request in text format to the server.

[1168] The server passes the request to the generative AI model, which analyzes the request and determines the corresponding action.

[1169] The generative AI model accesses internal resources and tools to perform each action, for example, getting team member contact information and sending reminders.

[1170] The server transmits the execution result to the terminal.

[1171] The device will display a result to the user, such as "Reminder has been sent."

[1172] This allows remote workers to quickly access the information and resources they need and communicate with their teams efficiently. Utilizing generative AI models with these capabilities can improve productivity and reduce stress for remote workers.

[1173] The processing flow will be explained below.

[1174] Handling inquiries

[1175] Step 1:

[1176] The user types a question into the terminal, for example, "What is the latest information about our company policies?"

[1177] Step 2:

[1178] The terminal sends the question in text format to the server.

[1179] Step 3:

[1180] The server passes the received questions to a generative AI model.

[1181] Step 4:

[1182] The generative AI model analyzes the question, specifically tokenizing it and analyzing its intent.

[1183] Step 5:

[1184] The generative AI model generates database queries based on intent and queries internal databases to retrieve relevant information.

[1185] Step 6:

[1186] The server receives the answer from the generative AI model and sends it to the device.

[1187] Step 7:

[1188] The device will then display the received response to the user, for example, "The latest version of our internal policies was updated in January 2023. Please see this link for details."

[1189] Handling resource offerings

[1190] Step 1:

[1191] A user types a request into a terminal for a required resource or document, such as "Teach me how to use a project management tool."

[1192] Step 2:

[1193] The terminal sends the request in text format to the server.

[1194] Step 3:

[1195] The server passes the request to the generative AI model.

[1196] Step 4:

[1197] Based on the request, the generative AI model analyzes where the required resources are located and how to access them.

[1198] Step 5:

[1199] The generative AI model searches for the necessary materials from an internal database.

[1200] Step 6:

[1201] The generative AI model searches for documents and retrieves their links and files, generating information such as, "Please refer to these guidelines for how to use project management tools."

[1202] Step 7:

[1203] The server transmits the acquired information to the terminal.

[1204] Step 8:

[1205] The device will display links and required files to the user.

[1206] Handling team communication support

[1207] Step 1:

[1208] A user enters a request into their device to schedule a meeting or share a document, such as "Please send a reminder for tomorrow's meeting to everyone on my team."

[1209] Step 2:

[1210] The terminal sends the request in text format to the server.

[1211] Step 3:

[1212] The server passes the request to the generative AI model.

[1213] Step 4:

[1214] The generative AI model analyzes the request and determines the corresponding action.

[1215] Step 5:

[1216] The generative AI model accesses the necessary internal resources and tools to perform each action.

[1217] Step 6:

[1218] For example, a generative AI model can retrieve contact information for team members and send reminders.

[1219] Step 7:

[1220] The server transmits the execution result to the terminal.

[1221] Step 8:

[1222] The device will display a result to the user, such as "Reminder has been sent."

[1223] Example 1

[1224] 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."

[1225] Remote workers often find it difficult to work efficiently because they are unable to quickly access the information and resources they need. Communication with their team can also be difficult in a remote work environment, leading to lower productivity and increased stress.

[1226] 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.

[1227] In this invention, the server includes means for using a generative AI model to quickly and accurately respond to the remote worker's questions, means for providing access to information resources and data required by the remote worker, and means for supporting the remote worker in efficiently communicating with colleagues, thereby enabling the remote worker to quickly access the information and resources they need and to communicate smoothly with their team.

[1228] A "remote worker" is someone who works remotely (from a remote location) without coming to the office.

[1229] A "generative AI model" refers to algorithms or software that generate information based on artificial intelligence technology.

[1230] "Information resources" refers to information resources such as data, knowledge bases, and documents that users need.

[1231] "Support for efficient communication" refers to providing the features and tools remote workers need to effectively exchange information and collaborate with colleagues.

[1232] A "server" refers to a computer system that provides various services over a network.

[1233] "Terminal" refers to a device (such as a personal computer or smartphone) that is directly operated by a user.

[1234] An "internal database" is a collection of data managed within an organization, and refers to a searchable and retrieval-capable information storage system.

[1235] A "protocol" refers to the rules and procedures for communicating data over a computer network.

[1236] A "query" is a request or question made to a database to retrieve specific information.

[1237] An "action" refers to a specific operation or process that the system executes based on a user request.

[1238] "Execution result" refers to the result of an operation or process that the server performed in response to a user request.

[1239] MODE FOR CARRYING OUT THE INVENTION

[1240] To implement this invention, a system combining a server, a terminal, and a generative AI model must be constructed. This system has three main functions: responding to questions from remote workers, providing resources, and supporting communication.

[1241] Hardware and software used

[1242] server

[1243] The server plays a central role in managing data exchange between the generative AI model and other system components, using the following software and services:

[1244] Generative AI model: OpenAI GPT-3

[1245] In-house databases: MongoDB, MySQL, PostgreSQL

[1246] Communication protocol: HTTPS, SMTP

[1247] Terminal

[1248] The terminal used by the user is used to input questions and requests and display responses from the system. It uses the following hardware and software:

[1249] Devices: PC, smartphone

[1250] Display software: Web browser, dedicated application

[1251] Data processing and data calculation

[1252] Answering questions

[1253] The user inputs a question into the terminal and the question is processed by sending it to the server.

[1254] The server passes the question data to a generative AI model, which analyzes the question.

[1255] The generative AI model tokenizes the question and analyzes its intent, using NLTK for tokenization and the BERT model for intent analysis.

[1256] Based on the analysis results, the generative AI model queries the company's internal database to retrieve relevant information.

[1257] The generative AI model generates answers based on the information it obtains.

[1258] The server sends the generated answer to the terminal, which displays the answer to the user.

[1259] Resource provision

[1260] A user inputs a request for a required resource into a terminal and sends it to a server.

[1261] The server passes the request content to the generative AI model and analyzes the location of the request.

[1262] The generative AI model retrieves the necessary materials from an internal database.

[1263] The generative AI model takes links and files to resources and generates appropriate answers.

[1264] The server transmits the acquired information to the terminal, which then displays the information to the user.

[1265] Communication Support

[1266] A user inputs a request to schedule a meeting or share a document into a terminal and sends it to the server.

[1267] The server passes the request to the generative AI model and analyzes the content.

[1268] The generative AI model retrieves team member contact information from an internal database and sends reminders.

[1269] The server sends the execution results to the terminal, which then displays the results to the user.

[1270] Specific examples

[1271] Specific prompt examples for questions:

[1272] "What are the latest changes to our company's policies?"

[1273] Examples of specific prompts for resource provision:

[1274] "Please provide guidelines for project management tools."

[1275] Examples of specific communication prompts:

[1276] "Send a reminder to my team for our next meeting."

[1277] This system will enable remote workers to quickly access the information and resources they need and communicate efficiently with their teams, which is expected to increase productivity and reduce stress.

[1278] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1279] Question response processing flow

[1280] Step 1:

[1281] The user inputs a question into the terminal. The input question is text data such as "Please tell me the latest information about the company's policies."

[1282] Step 2:

[1283] The terminal sends the question data entered by the user in text format to the server using the HTTPS protocol.

[1284] Step 3:

[1285] The server passes the received question data to the generative AI model, OpenAI GPT-3, which the server accesses using the required API key.

[1286] Input: Question data from the user

[1287] Output: Text data passed to the generative AI model

[1288] Step 4:

[1289] The generative AI model tokenizes the question and analyzes its intent, using NLTK for tokenization and the BERT model for intent analysis.

[1290] Input: Text data from the server

[1291] Output: Parsed intent data

[1292] Step 5:

[1293] Based on the analysis results, the generative AI model queries the internal database (MongoDB) to retrieve relevant information, for example, searching for information on the latest internal policies.

[1294] Input: Parsed intent data

[1295] Output: Retrieved company policy information

[1296] Step 6:

[1297] The generative AI model generates the most appropriate answer based on information retrieved from the company's database, such as "The latest version of our company policy was updated in January 2023. Please see this link for details."

[1298] Input: Information data obtained from the company database

[1299] Output: Generated answer text

[1300] Step 7:

[1301] The server receives the generated response data and sends it to the terminal, also using the HTTPS protocol.

[1302] Input: Generated answer text

[1303] Output: Response data sent to the device

[1304] Step 8:

[1305] The terminal displays the received answer data to the user. The terminal displays the answer text on the screen so that it can be seen by the user.

[1306] Input: Response data sent from the server

[1307] Output: The answer text that is displayed to the user

[1308] Resource provisioning process flow

[1309] Step 1:

[1310] A user types a request for a resource they need into a terminal, for example, "Teach me how to use a project management tool."

[1311] Step 2:

[1312] The device sends this request in text format to the server using the HTTPS protocol.

[1313] Step 3:

[1314] The server passes the request to the generative AI model, OpenAI GPT-3, which the server accesses using an API key.

[1315] Input: Request data from the user

[1316] Output: Text data passed to the generative AI model

[1317] Step 4:

[1318] The generative AI model analyzes the request and identifies the required resources, possibly using the BERT model, to analyze what the requested resources are.

[1319] Input: Request data from the server

[1320] Output: Parsed resource specific data

[1321] Step 5:

[1322] The generative AI model retrieves necessary materials from an internal database (MySQL), for example, searching for guideline materials for a project management tool.

[1323] Input: Parsed resource-specific data

[1324] Output: Acquired data

[1325] Step 6:

[1326] The generative AI model retrieves links and files to documents and generates appropriate answers, such as "Please refer to these guidelines for how to use project management tools."

[1327] Input: Material data obtained from the internal database

[1328] Output: Generated answer text

[1329] Step 7:

[1330] The server sends the obtained information to the terminal, also using the HTTPS protocol.

[1331] Input: Generated answer text

[1332] Output: Response data sent to the device

[1333] Step 8:

[1334] The terminal displays the link and required files to the user. The terminal displays the generated link and text on the screen.

[1335] Input: Response data sent from the server

[1336] Output: The link and answer text that is displayed to the user

[1337] Communication support processing flow

[1338] Step 1:

[1339] A user types a request into their device to schedule a meeting or share a document, for example, "Send a reminder to the whole team for tomorrow's meeting."

[1340] Step 2:

[1341] The device sends this request in text format to the server using the HTTPS protocol.

[1342] Step 3:

[1343] The server passes the request to the generative AI model, OpenAI GPT-3, which is accessed using an API key.

[1344] Input: Request data from the user

[1345] Output: Text data passed to the generative AI model

[1346] Step 4:

[1347] The generative AI model analyzes the received request and determines the corresponding action, which can be done using the BERT model to analyze what the requested action is.

[1348] Input: Request data from the server

[1349] Output: Parsed action decision data

[1350] Step 5:

[1351] For example, the generative AI model retrieves team member contact information from an internal database (PostgreSQL) and sends reminders, using the SMTP protocol to send emails.

[1352] Input: Parsed action decision data

[1353] Output: Reminder email sent

[1354] Step 6:

[1355] The server sends the execution result (e.g., "Reminder has been sent") to the device using the HTTPS protocol.

[1356] Input: Record of reminder email sent

[1357] Output: Execution result data sent to the terminal

[1358] Step 7:

[1359] The device displays the execution result to the user. The device displays text such as "Reminder sent" on the screen.

[1360] Input: Execution result data sent from the server

[1361] Output: The execution result text that is displayed to the user

[1362] (Application example 1)

[1363] 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."

[1364] Conventional remote worker support systems have had problems with efficiency and accuracy when responding to questions, providing resources, and supporting communication. Furthermore, factory workers are unable to quickly obtain the information they need on-site or properly understand how to operate machines, leading to reduced productivity. For this reason, a new system is needed that allows both remote workers and factory workers to efficiently access the information they need and communicate smoothly.

[1365] 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.

[1366] In this invention, the server includes means for using a generative AI model to quickly and accurately respond to questions from remote workers, means for providing access to information resources and documents required by remote workers, means for supporting remote workers in efficiently communicating with their teams, means for converting questions from factory workers into text format using speech recognition when the factory workers ask questions about machine settings or operation methods, means for obtaining and providing operation manuals and procedures required by factory workers via the server, and means for relaying communication between factory workers or managers by voice, and for adjusting schedules and transmitting messages. This enables remote workers and factory workers to quickly access the information they need and perform their work efficiently.

[1367] A "remote worker" is a worker who performs their work remotely via the Internet.

[1368] A "generative AI model" is an artificial intelligence algorithm that uses natural language processing to generate appropriate answers to human questions.

[1369] "Information resources" are business-related data, documents, manuals, and other materials in electronic form.

[1370] "Speech recognition" is a technology that converts speech into text form.

[1371] "Text format" is a data format expressed as character information.

[1372] A "server" is a computer system that processes and stores data over a network.

[1373] An "operation manual" is a document that details how to set up and use a machine or device.

[1374] A "procedure" is a document that lists the steps to be taken to perform a specific task.

[1375] To implement this invention, it is necessary to build a remote worker and factory worker support system that utilizes a generative AI model. The system of the present invention combines speech recognition technology, a generative AI model, database management, text output, and communication tools. This system uses the following hardware and software:

[1376] Hardware and software used:

[1377] Hardware: microphone, speakers, display, computer (e.g. Raspberry Pi).

[1378] Software: Python program, speech_recognition library, pyttsx3 library, openai library.

[1379] Data processing and calculation:

[1380] 1. Voice to text conversion:

[1381] The device uses voice recognition technology to convert the user's (remote worker or factory worker's) speech into text. The speech_recognition library is used for voice recognition. This process obtains the user's question or request in text format.

[1382] 2. Question and Request Analysis:

[1383] The server passes text questions or requests to a generative AI model for analysis. The generative AI model uses an OpenAI AI model (e.g., GPT-3). The generative AI model analyzes the text and generates appropriate answers or necessary information.

[1384] 3. Response and Information Provision:

[1385] The server receives the answers generated by the generative AI model and the searched resources. The server then sends them to the device, which then provides the results to the user in voice and text format. The pyttsx3 library is used for voice output.

[1386] Examples:

[1387] Examples of how to respond to questions:

[1388] The user asks into the microphone, "How do I set up this machine?" The question is converted into text using voice recognition and sent to the server. The generative AI model analyzes the question and generates an appropriate answer, such as "First, turn on this machine, then set it up by following the instructions displayed on the control panel." The server sends this to the device and provides it to the user as voice and on-screen.

[1389] Example prompt sentence:

[1390] "Question: How do I set up this machine?" Answer:

[1391] "Question: Can you provide the operation manual?"Answer: The operation manual can be downloaded from this link.

[1392] This allows users to quickly access the information they need and carry out their work efficiently. This system provides high convenience to both remote workers and factory workers.

[1393] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1394] Step 1:

[1395] The user speaks a question or request into the microphone, which inputs voice data.

[1396] Step 2:

[1397] The device uses voice recognition technology to convert the voice data into text format. Specifically, it uses the speech_recognition library to output the voice data as text data.

[1398] Step 3:

[1399] A textual question or request is sent to the server, which receives the input data by sending data from the device to the server.

[1400] Step 4:

[1401] The server passes the text data to a generative AI model, which then analyzes the question or request. An OpenAI AI model (e.g., GPT-3) is used to analyze the prompt and generate an answer. The analysis results include the answer text and any necessary information.

[1402] Step 5:

[1403] The server receives the answers generated by the generative AI model and the resources searched, and sends them to the device. Data transmission from the server to the device provides output data to the device.

[1404] Step 6:

[1405] The device provides the received answers and information to the user. Specifically, it uses the pyttsx3 library to read the answers aloud and display them in text format on the display, allowing the user to obtain information in both audio and text formats.

[1406] Step 7:

[1407] The user can ask additional questions or make requests as needed, and the process repeats from step 1, ensuring the user receives ongoing support.

[1408] This makes it possible to effectively implement functions such as answering questions, providing resources, and supporting communication.

[1409] 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.

[1410] To implement this invention, it is necessary to combine an emotion engine with a remote worker support system that utilizes a generative AI model. This system has three main functions: answering questions, providing resources, and supporting communication. It also has the ability to recognize user emotions and generate responses based on those emotions. Below, we will explain in detail how to implement this system.

[1411] Handling inquiries

[1412] The user inputs a question into the terminal, for example, "Please tell me the latest information about company policies." At this time, the emotion engine recognizes the user's emotion (e.g., confusion, tension, calmness, etc.) from the question input.

[1413] The terminal sends the question in text format to the server.

[1414] The server passes the received question to an emotion engine to analyze the emotion before passing it to the generative AI model. The generative AI model analyzes the question and the recognized emotion and generates an appropriate answer based on the content. For example, it generates an answer such as, "The latest version of our internal policy was updated in January 2023. Please rest assured. For more information, please see this link."

[1415] The server receives this response and sends it to the terminal.

[1416] The device displays the received answer to the user, for example, the answer that conveys the above sense of security.

[1417] Handling resource offerings

[1418] A user inputs a request for the required resources or documents into a terminal. For example, a request might be, "Please teach me how to use a project management tool." At this time, the emotion engine recognizes the user's emotion from the input of the request.

[1419] The terminal sends the request in text format to the server.

[1420] The server passes the request and the recognized emotion to the generative AI model, which then analyzes the location and access method of the required resources based on the request.

[1421] The generative AI model searches for the necessary materials from an internal database and retrieves the links and files. For example, it generates information such as, "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to support you."

[1422] The server transmits the acquired information to the terminal.

[1423] The device will display links and necessary files to the user, for example, a response conveying the above-mentioned willingness to help.

[1424] Handling team communication support

[1425] A user inputs a request into their device to schedule a meeting or share a document. For example, they might request, "Please send a reminder for tomorrow's meeting to everyone on the team." At this time, the emotion engine recognizes the user's emotion from the input request.

[1426] The terminal sends the request in text format to the server.

[1427] The server passes the request and the recognized emotion to the generative AI model, which analyzes the request and determines the corresponding action.

[1428] The generative AI model accesses the necessary internal resources and tools to perform each action, such as retrieving team member contact information and sending reminders, while also taking into account the user's sentiment and tailoring the reminder text.

[1429] The server transmits the execution result to the terminal.

[1430] The device will display a message to the user expressing gratitude, such as "The reminder has been sent. Thank you for your cooperation."

[1431] This allows remote workers to quickly access the information and resources they need and communicate with their teams efficiently.Furthermore, by recognizing users' emotions and adjusting responses, it is possible to reduce the psychological burden on remote workers and provide a more comfortable working environment.

[1432] The processing flow will be explained below.

[1433] Handling inquiries

[1434] Step 1:

[1435] The user types a question into the terminal, for example, "What's the latest on our company policies?"

[1436] Step 2:

[1437] The terminal sends the question in text format to the server.

[1438] Step 3:

[1439] The server receives the question and passes it to the emotion engine.

[1440] Step 4:

[1441] The emotion engine analyzes the user's emotions from the question input and generates emotion data (e.g., confusion, tension, calmness, etc.).

[1442] Step 5:

[1443] The server passes the question, including the emotional data, to the generative AI model.

[1444] Step 6:

[1445] The generative AI model analyzes the question content and sentiment data, then queries the company's internal database to retrieve relevant information.

[1446] Step 7:

[1447] Based on the analysis results, the generative AI model generates an appropriate response based on the sentiment, such as, "The latest version of our internal policy was updated in January 2023. Please rest assured, please see this link for details."

[1448] Step 8:

[1449] The server sends the generated response to the terminal.

[1450] Step 9:

[1451] The terminal displays the received response to the user.

[1452] Handling resource offerings

[1453] Step 1:

[1454] A user types a request into a terminal for a needed resource or document, for example, "Teach me how to use a project management tool."

[1455] Step 2:

[1456] The terminal sends the request in text format to the server.

[1457] Step 3:

[1458] The server receives the request and passes it to the emotion engine.

[1459] Step 4:

[1460] The emotion engine analyzes the user's emotions from the request input and generates emotion data.

[1461] Step 5:

[1462] The server passes the request, including the emotion data, to the generative AI model.

[1463] Step 6:

[1464] The generative AI model analyzes the request content and emotional data, and searches for the necessary materials from an internal database.

[1465] Step 7:

[1466] Based on the analysis results, the generative AI model generates appropriate information according to the emotion, such as "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to help."

[1467] Step 8:

[1468] The server transmits the acquired information to the terminal.

[1469] Step 9:

[1470] The device will display links and required files to the user.

[1471] Handling team communication support

[1472] Step 1:

[1473] A user types a request into their device to schedule a meeting or share a document, for example, "Send a reminder for tomorrow's meeting to everyone on my team."

[1474] Step 2:

[1475] The terminal sends the request in text format to the server.

[1476] Step 3:

[1477] The server receives the request and passes it to the emotion engine.

[1478] Step 4:

[1479] The emotion engine analyzes the user's emotions from the request input and generates emotion data.

[1480] Step 5:

[1481] The server passes the request, including the emotion data, to the generative AI model.

[1482] Step 6:

[1483] The generative AI model analyzes the request content and sentiment data to determine the corresponding action (such as scheduling a meeting or sharing a document).

[1484] Step 7:

[1485] The generative AI model accesses the necessary internal resources and tools to perform each action, such as getting team member contact information and sending a reminder, while also taking into account the user's sentiment and tailoring the reminder text.

[1486] Step 8:

[1487] The server transmits the execution result to the terminal.

[1488] Step 9:

[1489] The device will display a message to the user expressing gratitude, such as "The reminder has been sent. Thank you for your cooperation."

[1490] Example 2

[1491] 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."

[1492] Remote workers need to quickly obtain information in their work environment and communicate efficiently with their team. However, there are limited systems in place to improve information access and communication efficiency in a remote work environment. Furthermore, there is a lack of systems to reduce the psychological burden on remote workers and maintain a comfortable work environment. In such an environment, remote workers often feel confused and nervous, leading to problems with reduced productivity.

[1493] 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 a means for receiving the content of a question from a remote worker in text format and passing the question to a generative AI model, a means for analyzing the user's emotions and passing the analysis result to the generative AI model, and a means for sending an answer generated by the generative AI model to the remote worker's terminal. This makes it possible to generate and provide an appropriate answer that takes into account the user's emotions when the user inputs a question.

[1494] The server also includes a means for receiving resource requests from remote workers and analyzing the request content using a generative AI model, a means for retrieving resources from an internal database and providing them to the remote workers, and a means for adjusting a response to the request based on user sentiment, thereby enabling the resources needed by the remote workers to be provided quickly and accurately.

[1495] Furthermore, the server includes a means for supporting the remote worker in efficiently communicating with the team, and a means for recognizing the user's emotions and generating a response based on the emotions. This makes it possible to provide communication support that takes the emotions of the remote worker into consideration, thereby realizing an efficient work environment while reducing psychological burden.

[1496] A "remote worker" is an employee or contractor who performs work away from a company or organization's physical offices.

[1497] A "generative AI model" refers to an artificial intelligence model that analyzes input data and generates appropriate answers in natural language based on the results.

[1498] "Emotion engine" refers to a software component that analyzes and recognizes a user's emotional state from input text data.

[1499] "Internal resources" refers to resources such as information, data, tools, and documents owned by a company or organization.

[1500] "Terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[1501] "Server" refers to a central computer system for processing, analyzing, storing, and distributing data.

[1502] "Text format" refers to a representation format of information structured as character data.

[1503] "Analysis" refers to the process of examining input data and information in detail and converting it into an understandable form.

[1504] "Response" means a response generated in response to an entered question or request.

[1505] "Adjusting a response" refers to the process of appropriately changing the content and expression of a generated reply based on the user's emotional state.

[1506] "Communication support" refers to the technical and functional support provided to remote workers to collaborate effectively with other employees and team members.

[1507] The present invention is a system for supporting remote workers that utilizes a generative AI model and an emotion engine. The following describes in detail how the present invention is specifically implemented.

[1508] Answering questions

[1509] The user inputs a question into the terminal. For example, "Please tell me the latest information about company policies." At this time, the emotion engine recognizes the user's emotion (e.g., confusion, tension) from the question input.

[1510] The terminal sends the question in text format to the server.

[1511] The server analyzes emotions by passing the received question and emotion data to the emotion engine. The analyzed emotion and question content are input into the generative AI model to generate an appropriate answer.

[1512] The generative AI model might generate an answer like, "The latest version of our internal policies was updated in January 2023. Don't worry, please see this link for more details."

[1513] The server receives this response and sends it to the terminal, which then displays it to the user.

[1514] Resource provision

[1515] When a user inputs a request for resources or documents into a terminal, for example, "Please tell me how to use the project management tool," the emotion engine recognizes the user's emotion from the input of the request.

[1516] The terminal sends the request in text format to the server.

[1517] The server passes the request content and emotion data to the generative AI model, which analyzes the content, searches the internal database for the necessary materials, and retrieves the links and files.

[1518] For example, the generative AI model generates information such as, "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to support you."

[1519] The server sends the acquired information to the terminal, which displays resources and links to the user.

[1520] Communication Support

[1521] When a user inputs a request into a device to schedule a meeting or share a document, for example, "Please send a reminder for tomorrow's meeting to everyone on the team," the emotion engine recognizes the user's emotion from the request.

[1522] The terminal sends the request in text format to the server.

[1523] The server passes the request and emotion data to the generative AI model, which analyzes the request and accesses the necessary internal resources and tools to execute each action.

[1524] For example, a generative AI model might generate a response like, "Reminder has been sent. Thank you for your cooperation."

[1525] The server sends the execution result to the device, which confirms that the reminder was sent and displays a message of thanks to the user.

[1526] Example prompt

[1527] 1. Examples of how to respond to questions:

[1528] Prompt: "What's the latest information about our company policies?"

[1529] Generative AI model response: "Our internal policies were last updated in January 2023. Rest assured, please see this link for more details."

[1530] 2. Examples of resource provision:

[1531] Prompt: "How do I use a project management tool?"

[1532] Generative AI model response: "Please refer to these guidelines to learn how to use our project management tools. If you need help, we're always here to help."

[1533] 3. Examples of communication support:

[1534] Prompt: "Please send a reminder to the whole team for tomorrow's meeting."

[1535] Generative AI model response: "Reminder has been sent. Thank you for your cooperation."

[1536] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1537] Handling inquiries

[1538] Step 1:

[1539] The user enters a question into an input field on the terminal.

[1540] Example: "Please let me know the latest information about our company policies."

[1541] Here, the emotion engine recognizes the user's emotion (e.g., confusion, tension) from the content of the text.

[1542] Step 2:

[1543] The device sends the question and emotion data entered by the user in text format to the server.

[1544] Input data: Question text and sentiment data

[1545] Output: Text data sent to the server

[1546] Step 3:

[1547] The server receives the question and emotion data and passes it to the emotion engine for detailed emotion analysis.

[1548] Input data: Question text and initial emotion data

[1549] Output: Detailed emotion analysis data (e.g., high confusion, medium tension)

[1550] Step 4:

[1551] The server inputs the question and detailed emotional data into the generative AI model, which then generates an answer based on this.

[1552] Input data: Question text and detailed sentiment data

[1553] Output: Generated response text (e.g., "Our internal policy was last updated in January 2023. Don't worry, see this link for more details.")

[1554] Step 5:

[1555] The server sends the answer obtained from the generative AI model to the device.

[1556] Input data: Generated answer text

[1557] Output: Answer text sent to terminal

[1558] Step 6:

[1559] The terminal displays the received response to the user.

[1560] Output: Answer text to be displayed to the user (e.g. "Our internal policy was last updated in January 2023. Don't worry, see this link for more details.")

[1561] Handling resource offerings

[1562] Step 1:

[1563] A user inputs a request for a resource or document into a terminal.

[1564] Example: "How do I use a project management tool?"

[1565] Here, the emotion engine recognizes the user's emotion from the content of the text.

[1566] Step 2:

[1567] The device sends the request and emotion data in text format to the server.

[1568] Input data: resource request text and sentiment data

[1569] Output: Text data sent to the server

[1570] Step 3:

[1571] The server passes the request content and emotion data to the generative AI model, which analyzes the content and generates appropriate information.

[1572] Input data: request text and emotion data

[1573] Output: Generated guideline link text (e.g., "Please refer to these guidelines for how to use project management tools. If you need help, we're always here to help you.")

[1574] Step 4:

[1575] The server sends the information obtained from the generative AI model to the terminal.

[1576] Input data: Generated guideline link text

[1577] Output: Guideline link text sent to terminal

[1578] Step 5:

[1579] The device will display links and required files to the user.

[1580] Output: Guideline link text that will be displayed to the user (e.g., "Please refer to these guidelines for how to use the project management tool. If you need help, we're always here to help you.")

[1581] Communication support processing

[1582] Step 1:

[1583] The user inputs a request to schedule a meeting or share a document into the terminal.

[1584] Example: "Please send a reminder to the whole team for tomorrow's meeting."

[1585] Here, the emotion engine recognizes the user's emotion from the content of the text.

[1586] Step 2:

[1587] The device sends the request and emotion data in text format to the server.

[1588] Input data: Request text and emotion data

[1589] Output: Text data sent to the server

[1590] Step 3:

[1591] The server passes the request and emotion data to the generative AI model, which analyzes the request and determines the corresponding action.

[1592] Input data: Request text and emotion data

[1593] Output: The generated action text (e.g., "Reminder sent. Thank you for your cooperation.")

[1594] Step 4:

[1595] The generative AI model accesses internal resources and tools to execute each action, such as getting team member contact information and sending reminders.

[1596] Input data: Team member contact information

[1597] Output: Reminders sent

[1598] Step 5:

[1599] The server transmits the execution result to the terminal.

[1600] Input data: Execution result text

[1601] Output: The resulting text sent to the terminal.

[1602] Step 6:

[1603] The device will display a message of thanks to the user, such as "The reminder has been sent. Thank you for your cooperation."

[1604] Output: A thank you message that will be displayed to the user (e.g., "Reminder has been sent. Thank you for your cooperation.")

[1605] (Application example 2)

[1606] 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."

[1607] With the increase in remote workers, there is a need for systems that can provide efficient and prompt support. It is also important to understand customer emotions and provide optimal suggestions in virtual stores. Conventional systems lack the ability to respond in a way that takes into account the emotions of remote workers, and emotional support is not realized in virtual stores. This leads to issues such as lower satisfaction for remote workers and customers, and reduced utilization efficiency.

[1608] 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.

[1609] In this invention, the server includes means for combining a generative AI model and an emotion engine to quickly and accurately respond to questions from remote workers, means for providing access to internal resources and documents required by the remote workers, means for supporting the remote workers in efficiently communicating with groups, and means for supporting the virtual store by recognizing customer emotions and generating optimal responses and suggestions based thereon. This makes it possible to provide appropriate support that takes emotions into consideration for remote workers and customers of the virtual store, thereby improving satisfaction and usage efficiency.

[1610] A "generative AI model" is a system that uses artificial intelligence technology to automatically generate responses and suggestions in response to user input.

[1611] An "emotion engine" is a system that analyzes and recognizes emotions from user input text and voice data.

[1612] A "remote worker" is someone who performs their work outside of an office.

[1613] "Internal resources" refers to resources such as various information, tools, and databases used within a company.

[1614] "Document" refers to a digital file or paper document created in text format.

[1615] A "group" refers to a group of workers who work together with a common purpose.

[1616] "Communication" refers to the act of exchanging information or messages.

[1617] A "virtual store" refers to an online platform that offers products and services over the Internet.

[1618] "Support means" refers to a method or system for providing information or services required by users.

[1619] "Customer" means a purchaser or user of goods or services.

[1620] This invention is a system that effectively supports remote workers and virtual store customers, utilizing a generative AI model and emotion engine. Specifically, it responds quickly and accurately to questions and challenges faced by remote workers, provides access to necessary internal resources and documents, and supports efficient communication within groups. It can also recognize the emotions of virtual store customers and generate optimal responses and suggestions based on those emotions.

[1621] System configuration

[1622] server

[1623] It receives questions and requests and passes them to a generative AI model and emotion engine.

[1624] Analyzes sentiment from customer input text and generates responses based on it.

[1625] Provide access to necessary internal resources and product databases.

[1626] Terminal

[1627] Input from remote workers and customers is sent to the server in text format.

[1628] Displays the answers and suggestions received from the server.

[1629] User

[1630] Remote workers and virtual store customers.

[1631] Hardware and software used

[1632] Hardware

[1633] Processing is performed using servers or cloud services (e.g., Amazon Web Services, Google Cloud Platform).

[1634] The devices used by users include smartphones, PCs, tablets, etc.

[1635] software

[1636] The generative AI model uses OpenAI's GPT-4 API.

[1637] The emotion engine uses the TextBlob library.

[1638] MongoDB is used as the database.

[1639] React Native is used for front-end development.

[1640] Processing Description

[1641] 1. Emotion recognition

[1642] The text data entered by the user is analyzed using the TextBlob library to recognize emotions, which identifies the emotions of remote workers and customers.

[1643] 2. Response generation using a generative AI model

[1644] It uses OpenAI's GPT-4 API to generate appropriate responses based on emotions and inputs. It provides the best answer based on the user's input and the perceived emotions.

[1645] 3. Database Access

[1646] MongoDB is used to retrieve the necessary product information and resources. The server accesses the database and provides the necessary information to the user.

[1647] 4. Sending a Response

[1648] The application uses React Native to display the response to the user. The terminal displays the information received from the server so that the user can easily understand it.

[1649] Examples of concrete examples and prompts

[1650] For example, consider a remote worker typing, "Please let me know the latest information about our company policies," and the emotion of confusion is detected.

[1651] Example prompt sentence:

[1652] "User is feeling confused. Please generate a response to the following query: What is the latest information regarding internal policies?"

[1653] Based on this prompt, the generative AI model generates an appropriate response and provides it to remote workers, such as, "The latest version of our internal policies was updated in January 2023. Please rest assured, please see this link for details."

[1654] This makes it possible to provide appropriate support that takes into account the emotions of remote workers and customers in virtual stores, thereby improving satisfaction and usage efficiency.

[1655] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1656] Step 1:

[1657] The user types into the terminal.

[1658] The user types a question or request (e.g., "Please let me know the latest information about our company policies") into the device's input field. This input text is passed to the next process as is.

[1659] Step 2:

[1660] The device sends input to the server.

[1661] The terminal sends the text entered by the user to the server in text format, while the input data is sent in plain text and received by the server.

[1662] Step 3:

[1663] The server performs emotion analysis using an emotion engine.

[1664] The server passes the received text data to an emotion engine (e.g., TextBlob library) for emotion analysis, which identifies the user's emotion (e.g., confusion).

[1665] Input: User-entered text

[1666] Output: User's emotional information

[1667] Step 4:

[1668] The server generates a response using a generative AI model.

[1669] The server passes the user's input text and emotion information to a generative AI model (e.g., OpenAI's GPT-4 API) to generate an appropriate response. The prompt sentence used is "The user is feeling confused. Please generate a response to the following query: Please tell me the latest information about our company policy."

[1670] Input: User input text and emotion information

[1671] Output: The generated response

[1672] Step 5:

[1673] The server accesses the database to retrieve additional information (if necessary).

[1674] If the generated response contains links to internal resources or documents, the server retrieves the necessary data from a database (e.g. MongoDB) to complete the response with the necessary details.

[1675] Input: Generated response

[1676] Output: The completed response

[1677] Step 6:

[1678] The server sends the completed response to the terminal.

[1679] The server sends the generated response and any necessary details to the terminal in plain text format.

[1680] Input: Completed response

[1681] Output: Sending response data to the terminal

[1682] Step 7:

[1683] The terminal displays the response to the user.

[1684] The device will display the response data received from the server to the user. For example, a response such as "The latest version of our internal policy was updated in January 2023. Please rest assured, please refer to this link for details."

[1685] Input: Response data from the server

[1686] Output: What is displayed to the user

[1687] This allows users to receive appropriate responses to their questions and requests that take emotion into account.

[1688] 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.

[1689] 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.

[1690] 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.

[1691] [Fourth embodiment]

[1692] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1693] 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.

[1694] 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).

[1695] 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.

[1696] 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.

[1697] 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).

[1698] 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.

[1699] 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.

[1700] 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.

[1701] 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.

[1702] 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.

[1703] 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.

[1704] 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."

[1705] To implement this invention, it is necessary to build a remote worker support system that utilizes a generative AI model. This system has three main functions: answering questions, providing resources, and supporting communication. Below, we will explain in detail how to implement this system.

[1706] Handling inquiries

[1707] A user types a question into a terminal, for example, "Please let me know the latest information about our company policies."

[1708] The terminal sends this question in text format to the server.

[1709] The server passes the received question to a generative AI model, which analyzes the question and initiates a process to generate an appropriate answer based on the question's content. Specifically, the model tokenizes the question, analyzes its intent, and queries an internal database to retrieve relevant information.

[1710] The generative AI model generates the optimal answer based on the analysis results, for example, "The latest version of our internal policy was updated in January 2023. Please see this link for details."

[1711] The server receives this response and sends it to the terminal.

[1712] The terminal displays the received response to the user.

[1713] Handling resource offerings

[1714] A user types a request into a terminal for a required resource or document, such as "Teach me how to use a project management tool."

[1715] The terminal sends this request in text format to the server.

[1716] The server passes the request to the generative AI model, which then analyzes the location and access method of the required resources based on the request, as well as searches for the necessary materials from its internal database.

[1717] The generative AI model searches for documents and retrieves their links and files, generating information such as, "Please refer to these guidelines for how to use project management tools."

[1718] The server transmits the acquired information to the terminal.

[1719] The device will display links and required files to the user.

[1720] Handling team communication support

[1721] A user enters a request into their device to schedule a meeting or share a document, such as "Please send a reminder for tomorrow's meeting to everyone on my team."

[1722] The terminal sends this request in text format to the server.

[1723] The server passes the request to the generative AI model, which analyzes the request and determines the corresponding action.

[1724] The generative AI model accesses internal resources and tools to perform each action, for example, getting team member contact information and sending reminders.

[1725] The server transmits the execution result to the terminal.

[1726] The device will display a result to the user, such as "Reminder has been sent."

[1727] This allows remote workers to quickly access the information and resources they need and communicate with their teams efficiently. Utilizing generative AI models with these capabilities can improve productivity and reduce stress for remote workers.

[1728] The processing flow will be explained below.

[1729] Handling inquiries

[1730] Step 1:

[1731] The user types a question into the terminal, for example, "What is the latest information about our company policies?"

[1732] Step 2:

[1733] The terminal sends the question in text format to the server.

[1734] Step 3:

[1735] The server passes the received questions to a generative AI model.

[1736] Step 4:

[1737] The generative AI model analyzes the question, specifically tokenizing it and analyzing its intent.

[1738] Step 5:

[1739] The generative AI model generates database queries based on intent and queries internal databases to retrieve relevant information.

[1740] Step 6:

[1741] The server receives the answer from the generative AI model and sends it to the device.

[1742] Step 7:

[1743] The device will then display the received response to the user, for example, "The latest version of our internal policies was updated in January 2023. Please see this link for details."

[1744] Handling resource offerings

[1745] Step 1:

[1746] A user types a request into a terminal for a required resource or document, such as "Teach me how to use a project management tool."

[1747] Step 2:

[1748] The terminal sends the request in text format to the server.

[1749] Step 3:

[1750] The server passes the request to the generative AI model.

[1751] Step 4:

[1752] Based on the request, the generative AI model analyzes where the required resources are located and how to access them.

[1753] Step 5:

[1754] The generative AI model searches for the necessary materials from an internal database.

[1755] Step 6:

[1756] The generative AI model searches for documents and retrieves their links and files, generating information such as, "Please refer to these guidelines for how to use project management tools."

[1757] Step 7:

[1758] The server transmits the acquired information to the terminal.

[1759] Step 8:

[1760] The device will display links and required files to the user.

[1761] Handling team communication support

[1762] Step 1:

[1763] A user enters a request into their device to schedule a meeting or share a document, such as "Please send a reminder for tomorrow's meeting to everyone on my team."

[1764] Step 2:

[1765] The terminal sends the request in text format to the server.

[1766] Step 3:

[1767] The server passes the request to the generative AI model.

[1768] Step 4:

[1769] The generative AI model analyzes the request and determines the corresponding action.

[1770] Step 5:

[1771] The generative AI model accesses the necessary internal resources and tools to perform each action.

[1772] Step 6:

[1773] For example, a generative AI model can retrieve contact information for team members and send reminders.

[1774] Step 7:

[1775] The server transmits the execution result to the terminal.

[1776] Step 8:

[1777] The device will display a result to the user, such as "Reminder has been sent."

[1778] Example 1

[1779] 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."

[1780] Remote workers often find it difficult to work efficiently because they are unable to quickly access the information and resources they need. Communication with their team can also be difficult in a remote work environment, leading to lower productivity and increased stress.

[1781] 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.

[1782] In this invention, the server includes means for using a generative AI model to quickly and accurately respond to the remote worker's questions, means for providing access to information resources and data required by the remote worker, and means for supporting the remote worker in efficiently communicating with colleagues, thereby enabling the remote worker to quickly access the information and resources they need and to communicate smoothly with their team.

[1783] A "remote worker" is someone who works remotely (from a remote location) without coming to the office.

[1784] A "generative AI model" refers to algorithms or software that generate information based on artificial intelligence technology.

[1785] "Information resources" refers to information resources such as data, knowledge bases, and documents that users need.

[1786] "Support for efficient communication" refers to providing the features and tools remote workers need to effectively exchange information and collaborate with colleagues.

[1787] A "server" refers to a computer system that provides various services over a network.

[1788] "Terminal" refers to a device (such as a personal computer or smartphone) that is directly operated by a user.

[1789] An "internal database" is a collection of data managed within an organization, and refers to a searchable and retrieval-capable information storage system.

[1790] A "protocol" refers to the rules and procedures for communicating data over a computer network.

[1791] A "query" is a request or question made to a database to retrieve specific information.

[1792] An "action" refers to a specific operation or process that the system executes based on a user request.

[1793] "Execution result" refers to the result of an operation or process that the server performed in response to a user request.

[1794] MODE FOR CARRYING OUT THE INVENTION

[1795] To implement this invention, a system combining a server, a terminal, and a generative AI model must be constructed. This system has three main functions: responding to questions from remote workers, providing resources, and supporting communication.

[1796] Hardware and software used

[1797] server

[1798] The server plays a central role in managing data exchange between the generative AI model and other system components, using the following software and services:

[1799] Generative AI model: OpenAI GPT-3

[1800] In-house databases: MongoDB, MySQL, PostgreSQL

[1801] Communication protocol: HTTPS, SMTP

[1802] Terminal

[1803] The terminal used by the user is used to input questions and requests and display responses from the system. It uses the following hardware and software:

[1804] Devices: PC, smartphone

[1805] Display software: Web browser, dedicated application

[1806] Data processing and data calculation

[1807] Answering questions

[1808] The user inputs a question into the terminal and the question is processed by sending it to the server.

[1809] The server passes the question data to a generative AI model, which analyzes the question.

[1810] The generative AI model tokenizes the question and analyzes its intent, using NLTK for tokenization and the BERT model for intent analysis.

[1811] Based on the analysis results, the generative AI model queries the company's internal database to retrieve relevant information.

[1812] The generative AI model generates answers based on the information it obtains.

[1813] The server sends the generated answer to the terminal, which displays the answer to the user.

[1814] Resource provision

[1815] A user inputs a request for a required resource into a terminal and sends it to a server.

[1816] The server passes the request content to the generative AI model and analyzes the location of the request.

[1817] The generative AI model retrieves the necessary materials from an internal database.

[1818] The generative AI model takes links and files to resources and generates appropriate answers.

[1819] The server transmits the acquired information to the terminal, which then displays the information to the user.

[1820] Communication Support

[1821] A user inputs a request to schedule a meeting or share a document into a terminal and sends it to the server.

[1822] The server passes the request to the generative AI model and analyzes the content.

[1823] The generative AI model retrieves team member contact information from an internal database and sends reminders.

[1824] The server sends the execution results to the terminal, which then displays the results to the user.

[1825] Specific examples

[1826] Specific prompt examples for questions:

[1827] "What are the latest changes to our company's policies?"

[1828] Examples of specific prompts for resource provision:

[1829] "Please provide guidelines for project management tools."

[1830] Examples of specific communication prompts:

[1831] "Send a reminder to my team for our next meeting."

[1832] This system will enable remote workers to quickly access the information and resources they need and communicate efficiently with their teams, which is expected to increase productivity and reduce stress.

[1833] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1834] Question response processing flow

[1835] Step 1:

[1836] The user inputs a question into the terminal. The input question is text data such as "Please tell me the latest information about the company's policies."

[1837] Step 2:

[1838] The terminal sends the question data entered by the user in text format to the server using the HTTPS protocol.

[1839] Step 3:

[1840] The server passes the received question data to the generative AI model, OpenAI GPT-3, which the server accesses using the required API key.

[1841] Input: Question data from the user

[1842] Output: Text data passed to the generative AI model

[1843] Step 4:

[1844] The generative AI model tokenizes the question and analyzes its intent, using NLTK for tokenization and the BERT model for intent analysis.

[1845] Input: Text data from the server

[1846] Output: Parsed intent data

[1847] Step 5:

[1848] Based on the analysis results, the generative AI model queries the internal database (MongoDB) to retrieve relevant information, for example, searching for information on the latest internal policies.

[1849] Input: Parsed intent data

[1850] Output: Retrieved company policy information

[1851] Step 6:

[1852] The generative AI model generates the most appropriate answer based on information retrieved from the company's database, such as "The latest version of our company policy was updated in January 2023. Please see this link for details."

[1853] Input: Information data obtained from the company database

[1854] Output: Generated answer text

[1855] Step 7:

[1856] The server receives the generated response data and sends it to the terminal, also using the HTTPS protocol.

[1857] Input: Generated answer text

[1858] Output: Response data sent to the device

[1859] Step 8:

[1860] The terminal displays the received answer data to the user. The terminal displays the answer text on the screen so that it can be seen by the user.

[1861] Input: Response data sent from the server

[1862] Output: The answer text that is displayed to the user

[1863] Resource provisioning process flow

[1864] Step 1:

[1865] A user types a request for a resource they need into a terminal, for example, "Teach me how to use a project management tool."

[1866] Step 2:

[1867] The device sends this request in text format to the server using the HTTPS protocol.

[1868] Step 3:

[1869] The server passes the request to the generative AI model, OpenAI GPT-3, which the server accesses using an API key.

[1870] Input: Request data from the user

[1871] Output: Text data passed to the generative AI model

[1872] Step 4:

[1873] The generative AI model analyzes the request and identifies the required resources, possibly using the BERT model, to analyze what the requested resources are.

[1874] Input: Request data from the server

[1875] Output: Parsed resource specific data

[1876] Step 5:

[1877] The generative AI model retrieves necessary materials from an internal database (MySQL), for example, searching for guideline materials for a project management tool.

[1878] Input: Parsed resource-specific data

[1879] Output: Acquired data

[1880] Step 6:

[1881] The generative AI model retrieves links and files to documents and generates appropriate answers, such as "Please refer to these guidelines for how to use project management tools."

[1882] Input: Material data obtained from the internal database

[1883] Output: Generated answer text

[1884] Step 7:

[1885] The server sends the obtained information to the terminal, also using the HTTPS protocol.

[1886] Input: Generated answer text

[1887] Output: Response data sent to the device

[1888] Step 8:

[1889] The terminal displays the link and required files to the user. The terminal displays the generated link and text on the screen.

[1890] Input: Response data sent from the server

[1891] Output: The link and answer text that is displayed to the user

[1892] Communication support processing flow

[1893] Step 1:

[1894] A user types a request into their device to schedule a meeting or share a document, for example, "Send a reminder to the whole team for tomorrow's meeting."

[1895] Step 2:

[1896] The device sends this request in text format to the server using the HTTPS protocol.

[1897] Step 3:

[1898] The server passes the request to the generative AI model, OpenAI GPT-3, which is accessed using an API key.

[1899] Input: Request data from the user

[1900] Output: Text data passed to the generative AI model

[1901] Step 4:

[1902] The generative AI model analyzes the received request and determines the corresponding action, which can be done using the BERT model to analyze what the requested action is.

[1903] Input: Request data from the server

[1904] Output: Parsed action decision data

[1905] Step 5:

[1906] For example, the generative AI model retrieves team member contact information from an internal database (PostgreSQL) and sends reminders, using the SMTP protocol to send emails.

[1907] Input: Parsed action decision data

[1908] Output: Reminder email sent

[1909] Step 6:

[1910] The server sends the execution result (e.g., "Reminder has been sent") to the device using the HTTPS protocol.

[1911] Input: Record of reminder email sent

[1912] Output: Execution result data sent to the terminal

[1913] Step 7:

[1914] The device displays the execution result to the user. The device displays text such as "Reminder sent" on the screen.

[1915] Input: Execution result data sent from the server

[1916] Output: The execution result text that is displayed to the user

[1917] (Application example 1)

[1918] 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."

[1919] Conventional remote worker support systems have had problems with efficiency and accuracy when responding to questions, providing resources, and supporting communication. Furthermore, factory workers are unable to quickly obtain the information they need on-site or properly understand how to operate machines, leading to reduced productivity. For this reason, a new system is needed that allows both remote workers and factory workers to efficiently access the information they need and communicate smoothly.

[1920] 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.

[1921] In this invention, the server includes means for using a generative AI model to quickly and accurately respond to questions from remote workers, means for providing access to information resources and documents required by remote workers, means for supporting remote workers in efficiently communicating with their teams, means for converting questions from factory workers into text format using speech recognition when the factory workers ask questions about machine settings or operation methods, means for obtaining and providing operation manuals and procedures required by factory workers via the server, and means for relaying communication between factory workers or managers by voice, and for adjusting schedules and transmitting messages. This enables remote workers and factory workers to quickly access the information they need and perform their work efficiently.

[1922] A "remote worker" is a worker who performs their work remotely via the Internet.

[1923] A "generative AI model" is an artificial intelligence algorithm that uses natural language processing to generate appropriate answers to human questions.

[1924] "Information resources" are business-related data, documents, manuals, and other materials in electronic form.

[1925] "Speech recognition" is a technology that converts speech into text form.

[1926] "Text format" is a data format expressed as character information.

[1927] A "server" is a computer system that processes and stores data over a network.

[1928] An "operation manual" is a document that details how to set up and use a machine or device.

[1929] A "procedure" is a document that lists the steps to be taken to perform a specific task.

[1930] To implement this invention, it is necessary to build a remote worker and factory worker support system that utilizes a generative AI model. The system of the present invention combines speech recognition technology, a generative AI model, database management, text output, and communication tools. This system uses the following hardware and software:

[1931] Hardware and software used:

[1932] Hardware: microphone, speakers, display, computer (e.g. Raspberry Pi).

[1933] Software: Python program, speech_recognition library, pyttsx3 library, openai library.

[1934] Data processing and calculation:

[1935] 1. Voice to text conversion:

[1936] The device uses voice recognition technology to convert the user's (remote worker or factory worker's) speech into text. The speech_recognition library is used for voice recognition. This process obtains the user's question or request in text format.

[1937] 2. Question and Request Analysis:

[1938] The server passes text questions or requests to a generative AI model for analysis. The generative AI model uses an OpenAI AI model (e.g., GPT-3). The generative AI model analyzes the text and generates appropriate answers or necessary information.

[1939] 3. Response and Information Provision:

[1940] The server receives the answers generated by the generative AI model and the searched resources. The server then sends them to the device, which then provides the results to the user in voice and text format. The pyttsx3 library is used for voice output.

[1941] Examples:

[1942] Examples of how to respond to questions:

[1943] The user asks into the microphone, "How do I set up this machine?" The question is converted into text using voice recognition and sent to the server. The generative AI model analyzes the question and generates an appropriate answer, such as "First, turn on this machine, then set it up by following the instructions displayed on the control panel." The server sends this to the device and provides it to the user as voice and on-screen.

[1944] Example prompt sentence:

[1945] "Question: How do I set up this machine?" Answer:

[1946] "Question: Can you provide the operation manual?"Answer: The operation manual can be downloaded from this link.

[1947] This allows users to quickly access the information they need and carry out their work efficiently. This system provides high convenience to both remote workers and factory workers.

[1948] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1949] Step 1:

[1950] The user speaks a question or request into the microphone, which inputs voice data.

[1951] Step 2:

[1952] The device uses voice recognition technology to convert the voice data into text format. Specifically, it uses the speech_recognition library to output the voice data as text data.

[1953] Step 3:

[1954] A textual question or request is sent to the server, which receives the input data by sending data from the device to the server.

[1955] Step 4:

[1956] The server passes the text data to a generative AI model, which then analyzes the question or request. An OpenAI AI model (e.g., GPT-3) is used to analyze the prompt and generate an answer. The analysis results include the answer text and any necessary information.

[1957] Step 5:

[1958] The server receives the answers generated by the generative AI model and the resources searched, and sends them to the device. Data transmission from the server to the device provides output data to the device.

[1959] Step 6:

[1960] The device provides the received answers and information to the user. Specifically, it uses the pyttsx3 library to read the answers aloud and display them in text format on the display, allowing the user to obtain information in both audio and text formats.

[1961] Step 7:

[1962] The user can ask additional questions or make requests as needed, and the process repeats from step 1, ensuring the user receives ongoing support.

[1963] This makes it possible to effectively implement functions such as answering questions, providing resources, and supporting communication.

[1964] 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.

[1965] To implement this invention, it is necessary to combine an emotion engine with a remote worker support system that utilizes a generative AI model. This system has three main functions: answering questions, providing resources, and supporting communication. It also has the ability to recognize user emotions and generate responses based on those emotions. Below, we will explain in detail how to implement this system.

[1966] Handling inquiries

[1967] The user inputs a question into the terminal, for example, "Please tell me the latest information about company policies." At this time, the emotion engine recognizes the user's emotion (e.g., confusion, tension, calmness, etc.) from the question input.

[1968] The terminal sends the question in text format to the server.

[1969] The server passes the received question to an emotion engine to analyze the emotion before passing it to the generative AI model. The generative AI model analyzes the question and the recognized emotion and generates an appropriate answer based on the content. For example, it generates an answer such as, "The latest version of our internal policy was updated in January 2023. Please rest assured. For more information, please see this link."

[1970] The server receives this response and sends it to the terminal.

[1971] The device displays the received answer to the user, for example, the answer that conveys the above sense of security.

[1972] Handling resource offerings

[1973] A user inputs a request for the required resources or documents into a terminal. For example, a request might be, "Please teach me how to use a project management tool." At this time, the emotion engine recognizes the user's emotion from the input of the request.

[1974] The terminal sends the request in text format to the server.

[1975] The server passes the request and the recognized emotion to the generative AI model, which then analyzes the location and access method of the required resources based on the request.

[1976] The generative AI model searches for the necessary materials from an internal database and retrieves the links and files. For example, it generates information such as, "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to support you."

[1977] The server transmits the acquired information to the terminal.

[1978] The device will display links and necessary files to the user, for example, a response conveying the above-mentioned willingness to help.

[1979] Handling team communication support

[1980] A user inputs a request into their device to schedule a meeting or share a document. For example, they might request, "Please send a reminder for tomorrow's meeting to everyone on the team." At this time, the emotion engine recognizes the user's emotion from the input request.

[1981] The terminal sends the request in text format to the server.

[1982] The server passes the request and the recognized emotion to the generative AI model, which analyzes the request and determines the corresponding action.

[1983] The generative AI model accesses the necessary internal resources and tools to perform each action, such as retrieving team member contact information and sending reminders, while also taking into account the user's sentiment and tailoring the reminder text.

[1984] The server transmits the execution result to the terminal.

[1985] The device will display a message to the user expressing gratitude, such as "The reminder has been sent. Thank you for your cooperation."

[1986] This allows remote workers to quickly access the information and resources they need and communicate with their teams efficiently.Furthermore, by recognizing users' emotions and adjusting responses, it is possible to reduce the psychological burden on remote workers and provide a more comfortable working environment.

[1987] The processing flow will be explained below.

[1988] Handling inquiries

[1989] Step 1:

[1990] The user types a question into the terminal, for example, "What's the latest on our company policies?"

[1991] Step 2:

[1992] The terminal sends the question in text format to the server.

[1993] Step 3:

[1994] The server receives the question and passes it to the emotion engine.

[1995] Step 4:

[1996] The emotion engine analyzes the user's emotions from the question input and generates emotion data (e.g., confusion, tension, calmness, etc.).

[1997] Step 5:

[1998] The server passes the question, including the emotional data, to the generative AI model.

[1999] Step 6:

[2000] The generative AI model analyzes the question content and sentiment data, then queries the company's internal database to retrieve relevant information.

[2001] Step 7:

[2002] Based on the analysis results, the generative AI model generates an appropriate response based on the sentiment, such as, "The latest version of our internal policy was updated in January 2023. Please rest assured, please see this link for details."

[2003] Step 8:

[2004] The server sends the generated response to the terminal.

[2005] Step 9:

[2006] The terminal displays the received response to the user.

[2007] Handling resource offerings

[2008] Step 1:

[2009] A user types a request into a terminal for a needed resource or document, for example, "Teach me how to use a project management tool."

[2010] Step 2:

[2011] The terminal sends the request in text format to the server.

[2012] Step 3:

[2013] The server receives the request and passes it to the emotion engine.

[2014] Step 4:

[2015] The emotion engine analyzes the user's emotions from the request input and generates emotion data.

[2016] Step 5:

[2017] The server passes the request, including the emotion data, to the generative AI model.

[2018] Step 6:

[2019] The generative AI model analyzes the request content and emotional data, and searches for the necessary materials from an internal database.

[2020] Step 7:

[2021] Based on the analysis results, the generative AI model generates appropriate information according to the emotion, such as "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to help."

[2022] Step 8:

[2023] The server transmits the acquired information to the terminal.

[2024] Step 9:

[2025] The device will display links and required files to the user.

[2026] Handling team communication support

[2027] Step 1:

[2028] A user types a request into their device to schedule a meeting or share a document, for example, "Send a reminder for tomorrow's meeting to everyone on my team."

[2029] Step 2:

[2030] The terminal sends the request in text format to the server.

[2031] Step 3:

[2032] The server receives the request and passes it to the emotion engine.

[2033] Step 4:

[2034] The emotion engine analyzes the user's emotions from the request input and generates emotion data.

[2035] Step 5:

[2036] The server passes the request, including the emotion data, to the generative AI model.

[2037] Step 6:

[2038] The generative AI model analyzes the request content and sentiment data to determine the corresponding action (such as scheduling a meeting or sharing a document).

[2039] Step 7:

[2040] The generative AI model accesses the necessary internal resources and tools to perform each action, such as getting team member contact information and sending a reminder, while also taking into account the user's sentiment and tailoring the reminder text.

[2041] Step 8:

[2042] The server transmits the execution result to the terminal.

[2043] Step 9:

[2044] The device will display a message to the user expressing gratitude, such as "The reminder has been sent. Thank you for your cooperation."

[2045] Example 2

[2046] 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."

[2047] Remote workers need to quickly obtain information in their work environment and communicate efficiently with their team. However, there are limited systems in place to improve information access and communication efficiency in a remote work environment. Furthermore, there is a lack of systems to reduce the psychological burden on remote workers and maintain a comfortable work environment. In such an environment, remote workers often feel confused and nervous, leading to problems with reduced productivity.

[2048] 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 a means for receiving the content of a question from a remote worker in text format and passing the question to a generative AI model, a means for analyzing the user's emotions and passing the analysis result to the generative AI model, and a means for sending an answer generated by the generative AI model to the remote worker's terminal. This makes it possible to generate and provide an appropriate answer that takes into account the user's emotions when the user inputs a question.

[2049] The server also includes a means for receiving resource requests from remote workers and analyzing the request content using a generative AI model, a means for retrieving resources from an internal database and providing them to the remote workers, and a means for adjusting a response to the request based on user sentiment, thereby enabling the resources needed by the remote workers to be provided quickly and accurately.

[2050] Furthermore, the server includes a means for supporting the remote worker in efficiently communicating with the team, and a means for recognizing the user's emotions and generating a response based on the emotions. This makes it possible to provide communication support that takes the emotions of the remote worker into consideration, thereby realizing an efficient work environment while reducing psychological burden.

[2051] A "remote worker" is an employee or contractor who performs work away from a company or organization's physical offices.

[2052] A "generative AI model" refers to an artificial intelligence model that analyzes input data and generates appropriate answers in natural language based on the results.

[2053] "Emotion engine" refers to a software component that analyzes and recognizes a user's emotional state from input text data.

[2054] "Internal resources" refers to resources such as information, data, tools, and documents owned by a company or organization.

[2055] "Terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[2056] "Server" refers to a central computer system for processing, analyzing, storing, and distributing data.

[2057] "Text format" refers to a representation format of information structured as character data.

[2058] "Analysis" refers to the process of examining input data and information in detail and converting it into an understandable form.

[2059] "Response" means a response generated in response to an entered question or request.

[2060] "Adjusting a response" refers to the process of appropriately changing the content and expression of a generated reply based on the user's emotional state.

[2061] "Communication support" refers to the technical and functional support provided to remote workers to collaborate effectively with other employees and team members.

[2062] The present invention is a system for supporting remote workers that utilizes a generative AI model and an emotion engine. The following describes in detail how the present invention is specifically implemented.

[2063] Answering questions

[2064] The user inputs a question into the terminal. For example, "Please tell me the latest information about company policies." At this time, the emotion engine recognizes the user's emotion (e.g., confusion, tension) from the question input.

[2065] The terminal sends the question in text format to the server.

[2066] The server analyzes emotions by passing the received question and emotion data to the emotion engine. The analyzed emotion and question content are input into the generative AI model to generate an appropriate answer.

[2067] The generative AI model might generate an answer like, "The latest version of our internal policies was updated in January 2023. Don't worry, please see this link for more details."

[2068] The server receives this response and sends it to the terminal, which then displays it to the user.

[2069] Resource provision

[2070] When a user inputs a request for resources or documents into a terminal, for example, "Please tell me how to use the project management tool," the emotion engine recognizes the user's emotion from the input of the request.

[2071] The terminal sends the request in text format to the server.

[2072] The server passes the request content and emotion data to the generative AI model, which analyzes the content, searches the internal database for the necessary materials, and retrieves the links and files.

[2073] For example, the generative AI model generates information such as, "Please refer to these guidelines for how to use the project management tool. If you have any problems, we are always here to support you."

[2074] The server sends the acquired information to the terminal, which displays resources and links to the user.

[2075] Communication Support

[2076] When a user inputs a request into a device to schedule a meeting or share a document, for example, "Please send a reminder for tomorrow's meeting to everyone on the team," the emotion engine recognizes the user's emotion from the request.

[2077] The terminal sends the request in text format to the server.

[2078] The server passes the request and emotion data to the generative AI model, which analyzes the request and accesses the necessary internal resources and tools to execute each action.

[2079] For example, a generative AI model might generate a response like, "Reminder has been sent. Thank you for your cooperation."

[2080] The server sends the execution result to the device, which confirms that the reminder was sent and displays a message of thanks to the user.

[2081] Example prompt

[2082] 1. Examples of how to respond to questions:

[2083] Prompt: "What's the latest information about our company policies?"

[2084] Generative AI model response: "Our internal policies were last updated in January 2023. Rest assured, please see this link for more details."

[2085] 2. Examples of resource provision:

[2086] Prompt: "How do I use a project management tool?"

[2087] Generative AI model response: "Please refer to these guidelines to learn how to use our project management tools. If you need help, we're always here to help."

[2088] 3. Examples of communication support:

[2089] Prompt: "Please send a reminder to the whole team for tomorrow's meeting."

[2090] Generative AI model response: "Reminder has been sent. Thank you for your cooperation."

[2091] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2092] Handling inquiries

[2093] Step 1:

[2094] The user enters a question into an input field on the terminal.

[2095] Example: "Please let me know the latest information about our company policies."

[2096] Here, the emotion engine recognizes the user's emotion (e.g., confusion, tension) from the content of the text.

[2097] Step 2:

[2098] The device sends the question and emotion data entered by the user in text format to the server.

[2099] Input data: Question text and sentiment data

[2100] Output: Text data sent to the server

[2101] Step 3:

[2102] The server receives the question and emotion data and passes it to the emotion engine for detailed emotion analysis.

[2103] Input data: Question text and initial emotion data

[2104] Output: Detailed emotion analysis data (e.g., high confusion, medium tension)

[2105] Step 4:

[2106] The server inputs the question and detailed emotional data into the generative AI model, which then generates an answer based on this.

[2107] Input data: Question text and detailed sentiment data

[2108] Output: Generated response text (e.g., "Our internal policy was last updated in January 2023. Don't worry, see this link for more details.")

[2109] Step 5:

[2110] The server sends the answer obtained from the generative AI model to the device.

[2111] Input data: Generated answer text

[2112] Output: Answer text sent to terminal

[2113] Step 6:

[2114] The terminal displays the received response to the user.

[2115] Output: Answer text to be displayed to the user (e.g. "Our internal policy was last updated in January 2023. Don't worry, see this link for more details.")

[2116] Handling resource offerings

[2117] Step 1:

[2118] A user inputs a request for a resource or document into a terminal.

[2119] Example: "How do I use a project management tool?"

[2120] Here, the emotion engine recognizes the user's emotion from the content of the text.

[2121] Step 2:

[2122] The device sends the request and emotion data in text format to the server.

[2123] Input data: resource request text and sentiment data

[2124] Output: Text data sent to the server

[2125] Step 3:

[2126] The server passes the request content and emotion data to the generative AI model, which analyzes the content and generates appropriate information.

[2127] Input data: request text and emotion data

[2128] Output: Generated guideline link text (e.g., "Please refer to these guidelines for how to use project management tools. If you need help, we're always here to help you.")

[2129] Step 4:

[2130] The server sends the information obtained from the generative AI model to the terminal.

[2131] Input data: Generated guideline link text

[2132] Output: Guideline link text sent to terminal

[2133] Step 5:

[2134] The device will display links and required files to the user.

[2135] Output: Guideline link text that will be displayed to the user (e.g., "Please refer to these guidelines for how to use the project management tool. If you need help, we're always here to help you.")

[2136] Communication support processing

[2137] Step 1:

[2138] The user inputs a request to schedule a meeting or share a document into the terminal.

[2139] Example: "Please send a reminder to the whole team for tomorrow's meeting."

[2140] Here, the emotion engine recognizes the user's emotion from the content of the text.

[2141] Step 2:

[2142] The device sends the request and emotion data in text format to the server.

[2143] Input data: Request text and emotion data

[2144] Output: Text data sent to the server

[2145] Step 3:

[2146] The server passes the request and emotion data to the generative AI model, which analyzes the request and determines the corresponding action.

[2147] Input data: Request text and emotion data

[2148] Output: The generated action text (e.g., "Reminder sent. Thank you for your cooperation.")

[2149] Step 4:

[2150] The generative AI model accesses internal resources and tools to execute each action, such as getting team member contact information and sending reminders.

[2151] Input data: Team member contact information

[2152] Output: Reminders sent

[2153] Step 5:

[2154] The server transmits the execution result to the terminal.

[2155] Input data: Execution result text

[2156] Output: The resulting text sent to the terminal.

[2157] Step 6:

[2158] The device will display a message of thanks to the user, such as "The reminder has been sent. Thank you for your cooperation."

[2159] Output: A thank you message that will be displayed to the user (e.g., "Reminder has been sent. Thank you for your cooperation.")

[2160] (Application example 2)

[2161] 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."

[2162] With the increase in remote workers, there is a need for systems that can provide efficient and prompt support. It is also important to understand customer emotions and provide optimal suggestions in virtual stores. Conventional systems lack the ability to respond in a way that takes into account the emotions of remote workers, and emotional support is not realized in virtual stores. This leads to issues such as lower satisfaction for remote workers and customers, and reduced utilization efficiency.

[2163] 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.

[2164] In this invention, the server includes means for combining a generative AI model and an emotion engine to quickly and accurately respond to questions from remote workers, means for providing access to internal resources and documents required by the remote workers, means for supporting the remote workers in efficiently communicating with groups, and means for supporting the virtual store by recognizing customer emotions and generating optimal responses and suggestions based thereon. This makes it possible to provide appropriate support that takes emotions into consideration for remote workers and customers of the virtual store, thereby improving satisfaction and usage efficiency.

[2165] A "generative AI model" is a system that uses artificial intelligence technology to automatically generate responses and suggestions in response to user input.

[2166] An "emotion engine" is a system that analyzes and recognizes emotions from user input text and voice data.

[2167] A "remote worker" is someone who performs their work outside of an office.

[2168] "Internal resources" refers to resources such as various information, tools, and databases used within a company.

[2169] "Document" refers to a digital file or paper document created in text format.

[2170] A "group" refers to a group of workers who work together with a common purpose.

[2171] "Communication" refers to the act of exchanging information or messages.

[2172] A "virtual store" refers to an online platform that offers products and services over the Internet.

[2173] "Support means" refers to a method or system for providing information or services required by users.

[2174] "Customer" means a purchaser or user of goods or services.

[2175] This invention is a system that effectively supports remote workers and virtual store customers, utilizing a generative AI model and emotion engine. Specifically, it responds quickly and accurately to questions and challenges faced by remote workers, provides access to necessary internal resources and documents, and supports efficient communication within groups. It can also recognize the emotions of virtual store customers and generate optimal responses and suggestions based on those emotions.

[2176] System configuration

[2177] server

[2178] It receives questions and requests and passes them to a generative AI model and emotion engine.

[2179] Analyzes sentiment from customer input text and generates responses based on it.

[2180] Provide access to necessary internal resources and product databases.

[2181] Terminal

[2182] Input from remote workers and customers is sent to the server in text format.

[2183] Displays the answers and suggestions received from the server.

[2184] User

[2185] Remote workers and virtual store customers.

[2186] Hardware and software used

[2187] Hardware

[2188] Processing is performed using servers or cloud services (e.g., Amazon Web Services, Google Cloud Platform).

[2189] The devices used by users include smartphones, PCs, tablets, etc.

[2190] software

[2191] The generative AI model uses OpenAI's GPT-4 API.

[2192] The emotion engine uses the TextBlob library.

[2193] MongoDB is used as the database.

[2194] React Native is used for front-end development.

[2195] Processing Description

[2196] 1. Emotion recognition

[2197] The text data entered by the user is analyzed using the TextBlob library to recognize emotions, which identifies the emotions of remote workers and customers.

[2198] 2. Response generation using a generative AI model

[2199] It uses OpenAI's GPT-4 API to generate appropriate responses based on emotions and inputs. It provides the best answer based on the user's input and the perceived emotions.

[2200] 3. Database Access

[2201] MongoDB is used to retrieve the necessary product information and resources. The server accesses the database and provides the necessary information to the user.

[2202] 4. Sending a Response

[2203] The application uses React Native to display the response to the user. The terminal displays the information received from the server so that the user can easily understand it.

[2204] Examples of concrete examples and prompts

[2205] For example, consider a remote worker typing, "Please let me know the latest information about our company policies," and the emotion of confusion is detected.

[2206] Example prompt sentence:

[2207] "User is feeling confused. Please generate a response to the following query: What is the latest information regarding internal policies?"

[2208] Based on this prompt, the generative AI model generates an appropriate response and provides it to remote workers, such as, "The latest version of our internal policies was updated in January 2023. Please rest assured, please see this link for details."

[2209] This makes it possible to provide appropriate support that takes into account the emotions of remote workers and customers in virtual stores, thereby improving satisfaction and usage efficiency.

[2210] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2211] Step 1:

[2212] The user types into the terminal.

[2213] The user types a question or request (e.g., "Please let me know the latest information about our company policies") into the device's input field. This input text is passed to the next process as is.

[2214] Step 2:

[2215] The device sends input to the server.

[2216] The terminal sends the text entered by the user to the server in text format, while the input data is sent in plain text and received by the server.

[2217] Step 3:

[2218] The server performs emotion analysis using an emotion engine.

[2219] The server passes the received text data to an emotion engine (e.g., TextBlob library) for emotion analysis, which identifies the user's emotion (e.g., confusion).

[2220] Input: User-entered text

[2221] Output: User's emotional information

[2222] Step 4:

[2223] The server generates a response using a generative AI model.

[2224] The server passes the user's input text and emotion information to a generative AI model (e.g., OpenAI's GPT-4 API) to generate an appropriate response. The prompt sentence used is "The user is feeling confused. Please generate a response to the following query: Please tell me the latest information about our company policy."

[2225] Input: User input text and emotion information

[2226] Output: The generated response

[2227] Step 5:

[2228] The server accesses the database to retrieve additional information (if necessary).

[2229] If the generated response contains links to internal resources or documents, the server retrieves the necessary data from a database (e.g. MongoDB) to complete the response with the necessary details.

[2230] Input: Generated response

[2231] Output: The completed response

[2232] Step 6:

[2233] The server sends the completed response to the terminal.

[2234] The server sends the generated response and any necessary details to the terminal in plain text format.

[2235] Input: Completed response

[2236] Output: Sending response data to the terminal

[2237] Step 7:

[2238] The terminal displays the response to the user.

[2239] The device will display the response data received from the server to the user. For example, a response such as "The latest version of our internal policy was updated in January 2023. Please rest assured, please refer to this link for details."

[2240] Input: Response data from the server

[2241] Output: What is displayed to the user

[2242] This allows users to receive appropriate responses to their questions and requests that take emotion into account.

[2243] 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.

[2244] 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.

[2245] 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.

[2246] 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.

[2247] 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.

[2248] 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.

[2249] 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).

[2250] 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.

[2251] 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."

[2252] 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.

[2253] 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).

[2254] 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.

[2255] 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.

[2256] 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.

[2257] 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.

[2258] 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.

[2259] 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.

[2260] 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.

[2261] 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.

[2262] 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.

[2263] 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.

[2264] The following is further disclosed regarding the above embodiment.

[2265] (Claim 1)

[2266] A means to use generative AI models to quickly and accurately respond to remote worker questions;

[2267] A way to provide remote workers with access to the internal resources and documents they need;

[2268] A means to help remote workers communicate effectively with their teams,

[2269] A system including:

[2270] (Claim 2)

[2271] A means to receive remote workers' questions in text format and pass them to a generative AI model;

[2272] A means for transmitting the answer generated by the generative AI model to the remote worker's device;

[2273] 10. The system of claim 1, comprising:

[2274] (Claim 3)

[2275] a means for receiving resource requests from remote workers and analyzing the requests using a generative AI model;

[2276] A means to retrieve resources from an internal database and provide them to remote workers;

[2277] 10. The system of claim 1, comprising:

[2278] (Claim 4)

[2279] A means for receiving communication requests from remote workers and analyzing the request content using a generative AI model;

[2280] A way to automate actions like scheduling meetings and sharing documents,

[2281] A means of notifying the remote worker of the execution results;

[2282] 10. The system of claim 1, comprising:

[2283] "Example 1"

[2284] (Claim 1)

[2285] A means to use generative AI models to quickly and accurately respond to remote worker questions;

[2286] A means to provide remote workers with access to the information resources and data they need;

[2287] A means to help remote workers communicate effectively with their colleagues,

[2288] A means for receiving questions entered by remote workers in text format;

[2289] A means for passing received questions to a generative AI model;

[2290] A means for generating appropriate answers to questions analyzed by the generative AI model; and

[2291] a means for transmitting the generated answer to the remote worker's terminal and displaying it;

[2292] a means for receiving resource requests from remote workers and analyzing the requests using a generative AI model;

[2293] A means of retrieving resources from an internal database and providing them to remote workers;

[2294] A means for receiving communication requests from remote workers, analyzing them using a generative AI model, and taking action;

[2295] A means for transmitting and displaying the execution results on the remote worker's terminal;

[2296] A system including:

[2297] (Claim 2)

[2298] 10. The system of claim 1, further comprising means for transmitting the answer generated by the generative AI model to a terminal of a remote worker.

[2299] (Claim 3)

[2300] 10. The system of claim 1, further comprising means for retrieving resources from an internal database and providing them to the remote worker.

[2301] "Application Example 1"

[2302] (Claim 1)

[2303] A means to use generative AI models to quickly and accurately respond to remote worker questions;

[2304] A means of providing remote workers with access to the information resources and documentation they need;

[2305] A means to help remote workers communicate effectively with their teams,

[2306] A means for converting questions into text format using voice recognition when factory workers ask about machine settings or operation methods;

[2307] A means for factory workers to obtain and provide the necessary operation manuals and procedures via a server,

[2308] A means for communicating between factory workers or managers by voice, adjusting schedules and conveying important information;

[2309] A system including:

[2310] (Claim 2)

[2311] A means to receive remote workers' questions in text format and pass them to a generative AI model;

[2312] A means for transmitting the answer generated by the generative AI model to the remote worker's device;

[2313] A means of converting factory workers' questions into text using speech recognition and passing the questions to a generative AI model;

[2314] a means for providing answers generated by the generative AI model to the factory worker via voice and on-screen display;

[2315] 10. The system of claim 1, comprising:

[2316] (Claim 3)

[2317] a means for receiving resource requests from remote workers and analyzing the requests using a generative AI model;

[2318] A means of retrieving resources from the database and providing them to remote workers;

[2319] A means for receiving resource requests from factory workers, searching for the necessary information resources using a generative AI model, and obtaining and providing them via a server;

[2320] 10. The system of claim 1, comprising:

[2321] "Example 2: Combining Emotion Engines"

[2322] (Claim 1)

[2323] A means to use generative AI models to quickly and accurately respond to remote worker questions;

[2324] A means to provide remote workers with access to the internal resources and documentation they need;

[2325] A means to help remote workers communicate effectively with their teams,

[2326] means for recognizing a user's emotion and generating a response based on the emotion;

[2327] A system including:

[2328] (Claim 2)

[2329] A means to receive remote workers' questions in text format and pass them to a generative AI model;

[2330] A means of analyzing user emotions and passing the analysis results to a generative AI model;

[2331] A means for transmitting the answer generated by the generative AI model to the remote worker's device;

[2332] 10. The system of claim 1, comprising:

[2333] (Claim 3)

[2334] a means for receiving resource requests from remote workers and analyzing the requests using a generative AI model;

[2335] A means of retrieving resources from an internal database and providing them to remote workers;

[2336] means for adjusting a response to a request based on a user's sentiment;

[2337] 10. The system of claim 1, comprising:

[2338] "Application example 2 when combining emotion engines"

[2339] (Claim 1)

[2340] A combination of generative AI models and emotion engines that respond quickly and accurately to remote worker questions, and

[2341] A means of providing remote workers with access to the internal resources and documentation they need;

[2342] A means to help remote workers communicate effectively with groups;

[2343] Supporting virtual stores that recognize customer sentiment and generate optimal responses and suggestions based on it;

[2344] A system including:

[2345] (Claim 2)

[2346] A means to receive remote workers' questions in text format and pass them to the generative AI model and emotion engine;

[2347] A means for transmitting the answers generated by the generative AI model and the emotion engine to the remote worker's device;

[2348] It has a virtual store support function that analyzes emotions from customer input text and provides appropriate suggestions based on that.

[2349] 10. The system of claim 1.

[2350] (Claim 3)

[2351] A means for receiving resource requests from remote workers and analyzing the request content using a generative AI model and an emotion engine;

[2352] A means to retrieve resources from an internal database and provide them to remote workers;

[2353] A means for accessing a product database in a virtual store and providing optimal product information to customers;

[2354] 10. The system of claim 1, comprising: [Explanation of symbols]

[2355] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to use generative AI models to quickly and accurately respond to remote worker questions; A way to provide remote workers with access to the internal resources and documents they need; A means to help remote workers communicate effectively with their teams, A system including:

2. A means to receive remote workers' questions in text format and pass them to a generative AI model; A means for transmitting the answer generated by the generative AI model to the remote worker's device; The system of claim 1 , comprising:

3. a means for receiving resource requests from remote workers and analyzing the requests using a generative AI model; A means to retrieve resources from an internal database and provide them to remote workers; The system of claim 1 , comprising:

4. A means for receiving communication requests from remote workers and analyzing the request content using a generative AI model; A way to automate actions like scheduling meetings and sharing documents, A means of notifying the remote worker of the execution results; The system of claim 1 , comprising:

Images