system

Abstract

We provide the system. [Solution] A terminal means that sends a request via the company network, A server means for receiving and analyzing requests, A means of retrieving relevant data from a database based on an analyzed request, A means of passing acquired data to a generative AI module and generating data in a specified format, A means of returning the generated data to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional data generation system using generative AI, the risk of data leakage to the outside is high, and it is difficult to utilize in-house data safely and efficiently. In addition, the process of supplying the data required by each department to the generative AI and generating text data based on it is time-consuming and laborious. There is a need for a system to solve such problems.

Means for Solving the Problems

[0005] The present invention provides a system that includes terminal means for sending requests via an internal network, server means for receiving and analyzing requests, means for obtaining relevant data from a database based on the analyzed requests, means for passing the obtained data to a generative AI module to generate data in a specified format, and means for returning the generated data to the user. By including means for analyzing requests that include the user's department information and obtaining data from a database corresponding to that department, and means for verifying and formatting the output data obtained from the generative AI module, the system achieves efficient data generation while ensuring the security of internal company data.

[0006] An "internal network" is a communication infrastructure used within an organization, a system for exchanging data and sharing resources.

[0007] A "request" is a request from a user to a system for a specific operation or data provision.

[0008] "Terminal means" refers to the device or program used by the user to send a request.

[0009] A "server means" is a central device or program for receiving, analyzing, and processing requests.

[0010] A "database" is a system for systematically storing specific information and for quickly and efficiently searching, updating, and managing that information.

[0011] A "generative AI module" is an artificial intelligence program that generates text based on provided data.

[0012] "Means of acquiring data" refers to the process or device used to extract necessary data from a database based on specific criteria or conditions.

[0013] "Means of generating data" refers to processes or devices that use a generative AI module to generate data in a specified format based on acquired data.

[0014] "Means of verifying data" refer to processes or devices that confirm whether the generated data meets predetermined standards.

[0015] "Formatting means" refers to processes or devices that convert generated data into the required format so that it can be displayed or output appropriately.

[0016] "Means of returning data to the user" refers to the process or device that transmits the generated data to the user's terminal. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] The system according to the present invention allows users in each department to send requests via the company's internal network, a server to process those requests, and a generative AI module to generate the specified data. This system enables the efficient generation of necessary data while preventing the leakage of internal company data.

[0039] Explanation of the program's processing

[0040] Send a request

[0041] Users: Users in each department send requests via the company network to generate the data they need for their work. These requests include specific conditions about what data is required.

[0042] Terminal: Sends a request to the server, including the user's department information. This information is used by the server to determine which database to access.

[0043] Receiving and parsing requests

[0044] Server: Analyzes the received request and verifies the user information and content of the request. Based on the user's department information, it determines which database to retrieve the data from.

[0045] Data acquisition

[0046] Server: Generates database queries and accesses internal databases to retrieve necessary data. For example, it might retrieve sales data or customer feedback data from the past year.

[0047] Data generation

[0048] Server: Passes the acquired data to a generative AI module to generate the necessary text data. This AI module uses a pre-trained model to generate data in the specified format.

[0049] Data validation and formatting

[0050] Server: Validates and formats the generated data. It verifies that the generated data meets the specified standards and makes additional corrections if necessary.

[0051] Return to user

[0052] Server: Returns the verified and formatted data to the user's terminal. The user receives the generated data and uses it in their work.

[0053] Specific example

[0054] Sending and receiving requests

[0055] The user (a marketing department employee) requests a report on the next marketing strategy. The request details that the report should include a trend analysis based on sales data and customer feedback from the past year, and a proposal for a new marketing strategy.

[0056] The device sends this request to the server.

[0057] Request parsing and data retrieval

[0058] The server receives the request and verifies that it originates from the marketing department. It then generates a database query to retrieve the necessary data from the internal database, specifically, sales data and customer feedback from the past year.

[0059] Data generation and return

[0060] The server passes the acquired data to a generative AI module to generate the necessary report. The generated report is verified and formatted, and finally sent back to the user's terminal.

[0061] The user reviews the returned report, makes revisions as needed, and proposes it as the final marketing strategy.

[0062] Thus, the system of the present invention can safely and efficiently utilize internal company data and support the operations of each department.

[0063] The following describes the processing flow.

[0064] Step 1:

[0065] A user sends a request from their device to the server via the company network, stating, "Please generate the data necessary for the new product project proposal." The request includes detailed conditions.

[0066] Step 2:

[0067] The terminal receives the request and sends it to the server. The request includes the user's department information.

[0068] Step 3:

[0069] The server receives the request and analyzes the request content and the user's department information. It then determines which database to access.

[0070] Step 4:

[0071] The server generates database queries and accesses the internal database to retrieve the necessary data. For example, it might use queries to retrieve sales data or customer feedback data from the past year.

[0072] Step 5:

[0073] The server temporarily stores the data it acquires and then passes that data to the generative AI module.

[0074] Step 6:

[0075] The server calls a generative AI module to generate the necessary text data based on the acquired data. In this process, the data is generated in a format that matches the user's request.

[0076] Step 7:

[0077] The server receives the generated text data and performs verification. It checks whether the text data meets the specified criteria.

[0078] Step 8:

[0079] The server formats the generated text data as needed, making it easy for users to use.

[0080] Step 9:

[0081] The server returns the completed text data to the user's terminal.

[0082] Step 10:

[0083] Users review the data received on their devices and use it for their work. They make minor adjustments to the data as needed and use it as the final document.

[0084] This series of steps enables the efficient and secure use of internal data to support users' work.

[0085] (Example 1)

[0086] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] To ensure the efficient and secure use of internal data and support users' operations, a system is needed that can respond to requests from multiple departments and generate appropriate data. However, traditional methods require considerable time and effort for request analysis, data acquisition, and data formatting, leading to decreased operational efficiency. Furthermore, from a data security perspective, measures to prevent the leakage of internal data are required.

[0088] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0089] In this invention, the server includes means for receiving and analyzing requests, means for obtaining relevant information from a database, means for passing data to a generative AI module to generate data in a specified format, and means for verifying and formatting the generated data. This enables efficient and secure utilization of internal company data, and allows users to quickly obtain the data necessary for their work.

[0090] An "internal network" is a closed network used to connect computers and other devices within a company, and serves as a means of sharing information and transmitting data.

[0091] A "request" is an instruction or request that a user sends to a server to ask it to generate specific data or provide information.

[0092] "Terminal means" refers to computers, mobile devices, and other devices used by users to create and send requests.

[0093] "Server system" refers to a centralized computer system for receiving and analyzing requests, and for generating and providing the necessary data.

[0094] "Analyzing" refers to understanding the content of a received request and extracting the necessary information and processing details.

[0095] A "database" is a system for systematically storing and managing information, allowing for efficient searching and retrieval of necessary data.

[0096] "Related information" refers to specific data or information retrieved from the database based on a request.

[0097] A "generative AI module" is a software module that uses a pre-trained artificial intelligence model to generate data based on a specific format or content.

[0098] "Verification" refers to the process of checking whether the generated data meets the required specifications and standards.

[0099] "Formatting" refers to the process of arranging generated data into a predetermined format or style.

[0100] A "user" refers to an individual or departmental member who uses the system to request data generation or information provision.

[0101] The system according to the present invention allows users in each department to send requests via the company's internal network, a server to process those requests, and a generative AI module to generate the specified data. This system enables the efficient generation of necessary data while preventing the leakage of internal company data.

[0102] Send a request

[0103] Users: Users in each department create requests using a dedicated client application to generate the data they need for their work. For example, an employee in the marketing department might create a request for a "report on the next marketing strategy" and enter specific criteria (sales data and customer feedback from the past year).

[0104] Terminal: Sends request data to the server. This request data includes a user ID and department information to identify which department the request originated from.

[0105] Receiving and parsing requests

[0106] Server: Parses incoming requests. Checks request metadata to determine which department the user belongs to. Analyzes the request content to determine what type of data is needed. For example, if "sales data for the past year" and "customer feedback data" are requested, it identifies the corresponding database tables. It uses Python parser modules to extract each field for parsing.

[0107] Data acquisition

[0108] Server: Generates database queries based on the analysis results. For example, it generates SQL statements to access internal databases (e.g., PostgreSQL or MySQL®) and retrieve the necessary data. The retrieved data is used for filtering (e.g., by date range or specific customer group). SQLAlchemy is used for database queries, and the results are converted into a data frame (e.g., pandas).

[0109] Data generation

[0110] Server: Passes the acquired data to a generative AI module. This AI module (e.g., GPT-4®) uses a pre-trained model to generate data according to specific format requirements. For example, it creates the framework of a requested report and fills in the details based on the acquired data. It calls an AI API (e.g., OpenAI® API), inputs data along with prompts, and receives the generated text.

[0111] Data validation and formatting

[0112] Server: Validates the generated data to ensure it meets the specified criteria. For example, it checks for typographical errors in the generated report, ensures all necessary information is included, and verifies the report's formatting. The validation process uses natural language processing (NLP) tools (e.g., spaCy) to perform text analysis. If necessary, it formats the text and creates the final report. It uses text processing libraries (e.g., re, textblob) to correct and format the text.

[0113] Return to user

[0114] Server: Returns the validated and formatted data to the user's terminal. The generated data is returned in a user-friendly format (e.g., PDF, Excel file). Appropriate libraries (e.g., ReportLab for PDF generation, openpyxl for Excel file generation) are used to convert to the appropriate file format.

[0115] Terminal: The user's terminal displays data received from the server, allowing the user to review it. The user reviews the generated report and performs further analysis or corrections as needed.

[0116] Example of a prompt

[0117] "Please generate a report that proposes the next marketing strategy based on sales data and customer feedback from the past year."

[0118] In this way, the system of the present invention can safely and efficiently utilize internal company data and support the operations of each department.

[0119] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0120] Step 1:

[0121] Users: Each department's users create requests using a dedicated client application and send them over the company network. Requests include the required data types and conditions (e.g., sales data and customer feedback for the past year).

[0122] Input: Data request specified by the user (e.g., marketing report).

[0123] Output: Request data sent from the terminal to the server.

[0124] Step 2:

[0125] Terminal: The terminal sends requests created by the user to the server. At the same time, metadata such as the user's department information is also sent.

[0126] Input: User-created request data.

[0127] Output: Request data, including user department information, is sent to the server.

[0128] Step 3:

[0129] Server: The server parses the received request. First, it checks the request metadata to determine the user's department. Then, it parses the request content to identify the necessary data types. For example, it might use a Python parser module to extract each field.

[0130] Input: Request data.

[0131] Output: Analysis results (required data types, acquisition conditions, etc.).

[0132] Step 4:

[0133] Server: Generates database queries based on the analysis results. For example, it generates SQL statements to access internal databases (e.g., PostgreSQL or MySQL) and retrieve the necessary data. Specifically, it uses SQLAlchemy to execute queries and converts the results into a data frame (e.g., pandas).

[0134] Input: Analysis results (required data types, acquisition conditions, etc.).

[0135] Output: Required data (e.g., sales data, customer feedback data).

[0136] Step 5:

[0137] Server: Passes the acquired data to a generative AI module. This module (e.g., GPT-4) generates data according to specific format requirements. For example, it calls an AI API (e.g., OpenAI API), inputs a prompt and data, and retrieves the generated text.

[0138] Input: Retrieved data, prompt text.

[0139] Output: Generated text data (e.g., marketing report).

[0140] Step 6:

[0141] Server: Validates and formats the generated data. Performs text analysis using Natural Language Processing (NLP) tools (e.g., spaCy) and makes necessary corrections and formatting. Performs formatting using text processing libraries (e.g., re, textblob).

[0142] Input: Generated text data.

[0143] Output: Validated and formatted final data.

[0144] Step 7:

[0145] Server: Returns the verified and formatted data to the user's terminal. The generated data is returned in user-friendly formats such as PDF and Excel files. Specific examples include using ReportLab for PDF generation and openpyxl for Excel file generation.

[0146] Input: Validated and formatted data.

[0147] Output: The final data sent back to the user's terminal.

[0148] Step 8:

[0149] Terminal: The user's terminal displays the data received from the server, allowing the user to review it. The user reviews the generated data and performs further analysis or corrections as needed.

[0150] Input: Final data from the server.

[0151] Output: Data displayed on the user's device.

[0152] (Application Example 1)

[0153] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0154] Conventional data management systems in logistics centers have problems such as difficulty in providing information in real time, time-consuming data acquisition and generation, and decreased efficiency on site. Furthermore, the lack of means for on-site workers to receive real-time inventory management and efficient delivery route suggestions leads to delays and errors in operations. This invention aims to solve these problems by providing a system that uses smart devices to improve work efficiency and provide information in real time.

[0155] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0156] In this invention, the server includes terminal means for transmitting requests via the company network, server means for receiving and analyzing requests, means for obtaining relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI module and generating data in a specified format, means for returning the generated data to the user and providing information in real time, and means for field workers to receive real-time inventory management and delivery route suggestions using a smart device. This enables field workers at a logistics center to obtain necessary information in real time via a smart device and perform their work quickly and accurately.

[0157] An "internal network" is a network intended for information communication within a company or organization.

[0158] A "request" refers to a request for data or information submitted by a user.

[0159] "Terminal means" refers to devices or equipment used to send requests.

[0160] "Server means" refers to a server that has the function of receiving and analyzing requests.

[0161] "Analysis" refers to understanding the content of a received request and identifying the necessary processing.

[0162] A "database" refers to a data structure or system used to efficiently manage and retrieve information.

[0163] A "generative AI module" is a module that uses artificial intelligence to generate data in a specified format.

[0164] "Real-time" refers to the processing and provision of data and information almost instantaneously.

[0165] A "smart device" refers to an advanced device that can connect to the internet and has a variety of functions.

[0166] "Field workers" refers to people who perform physical tasks at sites such as logistics centers.

[0167] "Inventory management" refers to the task of checking and managing the quantity and condition of products in stock.

[0168] "Delivery route" refers to the optimal path for delivering goods.

[0169] "Information provision" refers to supplying users with necessary data and information.

[0170] This invention provides a real-time information provision system for logistics centers. Specifically, it relates to a system that allows on-site workers to receive inventory management and efficient delivery route suggestions using smart devices. The embodiments of this system are described in detail below.

[0171] Program generation

[0172] The server includes terminal means for sending requests via the company network, server means for receiving and analyzing requests, means for obtaining relevant data from a database based on the analyzed requests, means for passing the obtained data to a generation AI module and generating data in a specified format, means for returning the generated data to the user and providing information in real time, and means for field workers to receive real-time inventory management and delivery route suggestions using smart devices.

[0173] Explanation of the process

[0174] The terminal receives requests sent by field workers via smart devices. These requests may include, for example, "Tell me the next receiving operation" or "Suggest the best delivery route." These requests are sent to the server via the company network.

[0175] The server analyzes the received request to determine which department the user belongs to. Next, it retrieves the necessary data from the corresponding database. Examples of such data include inventory data and past delivery history.

[0176] The acquired data is passed to a generative AI module, which generates data in the specified format. The generative AI module uses advanced AI models such as GPT-3(registered trademark) to generate data according to the user's request.

[0177] The generated data is verified and formatted by the server and sent back to the user in real time. Field workers can then review the generated data via smart devices and proceed with their work efficiently.

[0178] Hardware and software to use

[0179] This system uses smart eyewear such as Google® Glass® and Vuzix as smart devices. It also uses Wi-Fi and 5G networks for data transmission and reception. The server provides API endpoints using the Flask framework, and the generative AI module uses the OpenAI API.

[0180] Specific example

[0181] For example, if a field worker issues a voice command via a smart device saying, "Tell me the next receiving task," the device sends this request to the server. The server analyzes the request, retrieves the necessary inventory data from the database, and passes it to a generative AI module. The generative AI module generates an instruction such as, "The next receiving task is for product X, shelf A," and the server sends this back to the field worker's smart device in real time.

[0182] Example of a prompt:

[0183] "Generate a logistics report based on the following data: 'Inventory Data'"

[0184] "Suggest optimal delivery routes for the following locations: 'Delivery destination A, Delivery destination B, Delivery destination C'"

[0185] In this way, on-site workers at the logistics center can obtain the necessary information in real time and perform their tasks quickly and accurately.

[0186] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0187] Step 1:

[0188] Users send requests via smart devices. Users input requests using voice commands or touch controls, such as "Tell me about the next receiving operation" or "Suggest the best delivery route." The entered requests are sent from the terminal to the server via the company network.

[0189] Input: Request details (e.g., "Please tell me the next receiving procedure.")

[0190] Output: Request sent to the server

[0191] Step 2:

[0192] The server analyzes the received request. Specifically, it analyzes the user's department information and the request content to determine which database to retrieve which data from. Natural language processing technology is used for the analysis.

[0193] Input: Submitted request, user's department information

[0194] Output: Database query (Example: Query to retrieve inventory data)

[0195] Step 3:

[0196] The server accesses the database based on the analysis results and retrieves relevant data. For example, in response to a request for "the next receiving operation," it queries the inventory management database to retrieve product information.

[0197] Input: Database query

[0198] Output: Acquired data (e.g., inventory data, product information)

[0199] Step 4:

[0200] The server passes the acquired data to a generative AI module, which generates data in the specified format. The generative AI module uses OpenAI APIs and other tools to generate optimal instructions and reports in response to the request.

[0201] Input: Acquired data

[0202] Output: Generated data (Example: "The next receiving operation is for product X, shelf A")

[0203] Step 5:

[0204] The server verifies and formats the generated data. In particular, it checks that the generated data is in the correct format and free of errors. It makes corrections as needed and finalizes it.

[0205] Input: Generated data

[0206] Output: Validated and formatted data

[0207] Step 6:

[0208] The server returns the verified and formatted data to the user's device. The user can then view this data in real time via their smart device and use it as instructions to proceed with their work.

[0209] Input: Validated and formatted data

[0210] Output: Data sent back to the user's terminal

[0211] The following example prompts are used as concrete examples of the actions:

[0212] Example 1: "Generate a logistics report based on the following data: 'Inventory data'"

[0213] Example 2: "Suggest optimal delivery routes for the following locations: 'Delivery destination A, Delivery destination B, Delivery destination C'"

[0214] This will enable on-site workers at logistics centers to obtain necessary information in real time and perform their tasks efficiently.

[0215] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0216] The system according to the present invention includes terminal means for sending requests via an internal network, server means for receiving and analyzing requests, means for acquiring relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI module to generate data in a specified format, means for returning the generated data to the user, and an emotion engine for recognizing the user's emotions. This system enables the safe and efficient use of internal company data, and further, enables the generation of data that takes the user's emotions into consideration.

[0217] Explanation of the program's processing

[0218] Send a request

[0219] Users: Users in each department send requests via the company network to generate the data they need for their work. These requests include specific conditions about what data is required.

[0220] Terminal: Sends a request to the server, including the user's department information and the user's sentiment information analyzed by the sentiment engine. This information is used by the server to determine which database to access and to provide highly accurate generated data.

[0221] Receiving and parsing requests

[0222] Server: Analyzes the received request and verifies the user information and content of the request. Based on the user's sentiment information and departmental information, it decides which database to retrieve the data from.

[0223] Data acquisition

[0224] Server: Generates database queries and accesses the internal database to retrieve necessary data. For example, it might use queries to retrieve sales data or customer feedback data from the past year.

[0225] Data generation

[0226] Server: Passes the acquired data to a generative AI module, which generates the necessary text data. This AI module uses a pre-trained model to generate data in the specified format. Furthermore, it executes the generation process while also considering the user's sentiment information provided by the sentiment engine.

[0227] Data validation and formatting

[0228] Server: Validates and formats the generated data. Checks if the generated data meets the specified standards and makes additional corrections if necessary. Also adjusts the data based on sentiment information.

[0229] Return to user

[0230] Server: Returns the completed text data to the user's terminal. The data, which also takes sentiment information into account, is provided in a way that best meets the user's needs.

[0231] Specific example

[0232] Sending and receiving requests

[0233] The user (a marketing department employee) requests a report on the next marketing strategy. The request details that it should include a trend analysis based on sales data and customer feedback from the past year, followed by a proposal for a new marketing strategy. Furthermore, the emotion engine detects the user's positive emotions.

[0234] The device sends this request to the server.

[0235] Request parsing and data retrieval

[0236] The server receives the request and verifies that it originates from the marketing department. It then generates a database query to retrieve the necessary data from the internal database, specifically, sales data and customer feedback from the past year.

[0237] Data generation and return

[0238] The server passes the acquired data to a generative AI module to generate the necessary reports. The generated reports are validated and formatted, and finally sent back to the user's device, including suggestions that reflect the user's positive emotions.

[0239] The user reviews the returned report, makes revisions as needed, and proposes it as the final marketing strategy.

[0240] The system of this invention efficiently and securely utilizes internal company data and generates data that also takes user emotions into consideration, thereby providing advanced support for the operations of each department.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] A user sends a request from their device via the company network, stating, "I would like to create a report on the next marketing strategy." The request includes detailed conditions, such as "Please conduct a trend analysis based on sales data and customer feedback from the past year, and propose a new marketing strategy."

[0244] Step 2:

[0245] The terminal receives the request and sends it to the server. The request includes the user's departmental information and the user's emotional information analyzed by the emotion engine.

[0246] Step 3:

[0247] The server receives the request and analyzes the request content, the user's department information, and sentiment information. It then determines which database to access.

[0248] Step 4:

[0249] The server generates database queries and accesses the internal database to retrieve the necessary data. Specifically, it retrieves sales data and customer feedback data for the past year using queries.

[0250] Step 5:

[0251] The server temporarily stores the acquired data and passes it to the emotion engine for analysis, which correlates it with the user's emotions. Based on these results, adjustments are made to reflect the changes in the generated data.

[0252] Step 6:

[0253] The server passes the acquired data and the analysis results from the emotion engine to the generative AI module, which then generates the necessary text data. For example, if a positive emotion is detected in the user, it generates a report that reflects that emotion.

[0254] Step 7:

[0255] The server receives the generated text data and performs validation. It checks whether the generated data meets the specified standards and makes additional corrections if necessary. It also formats the data appropriately to reflect the user's sentiment information.

[0256] Step 8:

[0257] The server returns the completed text data to the user's terminal.

[0258] Step 9:

[0259] The user reviews the data received on their device and uses it for work. They review the generated reports, make corrections as needed, and propose them as the final marketing strategy.

[0260] This entire process makes it possible to generate data that takes user emotions into account, enabling the efficient creation of highly accurate proposals.

[0261] (Example 2)

[0262] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0263] Conventional data generation systems, while capable of responding quickly and accurately to user requests, faced the challenge of generating data that took user sentiment into account. This made it difficult to provide data that best met user needs. Furthermore, the lack of efficient methods for retrieving data from databases suitable for specific departments resulted in challenges regarding the accuracy and efficiency of data acquisition.

[0264] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an emotion analysis means, a means for including the user's emotion information, and a means for verifying and formatting the output data obtained from the generated AI model and adjusting the data based on the user's emotion information. This makes it possible to generate data while taking the user's emotion information into consideration, and to provide data that is optimally suited to the user's needs. In addition, it is possible to efficiently acquire data from a database suitable for a specific department, improving the accuracy and efficiency of data acquisition.

[0265] "Terminal means" refers to a device or function that allows a user to send a request via the company's internal network.

[0266] A "server means" is a device or function that receives a request, parses it, and accesses the appropriate database.

[0267] "Means of retrieving relevant data from a database" refers to a device or function that retrieves the necessary data from a database based on an analyzed request.

[0268] A "generative AI model" is an artificial intelligence model that generates data in a specified format based on acquired data.

[0269] "Emotional analysis means" refers to a device or function that analyzes a user's emotional information.

[0270] "Means of including user sentiment information in a request" refers to a device or function that adds analyzed sentiment information to a request.

[0271] "Means for verification and formatting" refers to a device or function that checks the output data obtained from the generated AI model and formats it into the required format.

[0272] "Means of adjusting data" refers to a device or function that adjusts the content and tone of data generated based on the user's emotional information.

[0273] A "user" refers to an individual or organization that uses the system to generate data.

[0274] The system according to the present invention includes terminal means for sending requests via an internal network, server means for receiving and analyzing requests, means for acquiring relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI model to generate data in a specified format, means for returning the generated data to the user, and sentiment analysis means for analyzing the user's emotional information. This system enables the safe and efficient use of internal company data, and further, enables the generation of data that takes user emotions into consideration.

[0275] The server receives the request and uses a data analysis module to verify the user information and request details of the requester. For example, if an employee in the marketing department sends a request to create a report on the next marketing strategy, the server receives and analyzes it. Specific conditions include "trend analysis based on sales data and customer feedback from the past year, and proposals for a new marketing strategy."

[0276] When a user enters a request, the terminal's emotion engine analyzes the user's current emotion information, adds the results to the request information, and sends it to the server. This process improves the accuracy of the data the server receives because the user's emotion information is included in the request.

[0277] The server then generates an appropriate database query, such as "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'", to retrieve the necessary data from the internal database. The retrieved data is then loaded into memory.

[0278] Generative AI models (such as pre-trained models like GPT-3) generate reports or text data in a specified format based on the acquired data. The generation process also considers user sentiment, enabling more accurate data generation. For example, it can generate a "proposal for the next marketing strategy based on sales data and customer feedback."

[0279] The server checks the generated data with a validation module to verify the consistency of the text and the format of the data. Corrections are made as needed, and final formatting is performed. The tone and content of the data are also adjusted based on sentiment information.

[0280] Finally, the server sends the completed data to the user's terminal. For example, the generated report is converted to PDF format and sent using a secure communication protocol (HTTPS). The terminal receives the data and displays it for the user to view. The user can download this and further edit it.

[0281] Specific Example

[0282] User: An employee in the marketing department sends a request stating "I want to create a report on the next marketing strategy". This request includes, as specific conditions, "trend analysis based on sales data and customer feedback over the past year and proposals for new marketing strategies".

[0283] Terminal: The terminal enters the request details on the screen and clicks the send button. In addition to the request information, the terminal also sends the positive sentiment information analyzed by the sentiment engine to the server.

[0284] Server: The server processes the received request and verifies that it is from the marketing department. Next, it generates a database query and prepares to access the relevant database. A specific query "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'" is executed.

[0285] Generated AI Model: Based on the acquired data, it generates a report on the next marketing strategy. The generated report includes proposal content that reflects positive sentiment information.

[0286] Server: The server verifies the generated data, makes corrections and formatting as necessary, and then sends it to the user's terminal.

[0287] With this system, it becomes possible to efficiently and securely utilize in-house data and generate data considering the emotions of users.

[0288] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0289] Step 1:

[0290] User: Create a request to generate data necessary for your work. The input should include text detailing the specific data requirements and needs. For example, "I would like a report on our next marketing strategy. I need sales data and customer feedback analysis for the past year."

[0291] Step 2:

[0292] Terminal: Receives request information entered by the user and analyzes the user's current sentiment using the sentiment engine. The results of this analysis are added to the request data. The output generates request data containing the user's conditions and sentiment information.

[0293] Step 3:

[0294] Terminal: Sends request data to the server. Input is the request data, and output is confirmation information for the sent request.

[0295] Step 4:

[0296] Server: Receives requests on the receiving port. Input is the request data, and output is the data to be transferred to the data analysis module.

[0297] Step 5:

[0298] Server: The data analysis module analyzes the request data and extracts user information, request details, and sentiment information. The input is the request data, and the output is the extracted user information and conditions.

[0299] Step 6:

[0300] Server: Generate an appropriate database query based on the extracted user information and conditions. Specifically, generate an SQL query such as "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'". The input is user information and conditions, and the output is a database query.

[0301] Step 7:

[0302] Server: Execute the database query and retrieve relevant data from the database. The input is the database query, and the output is the retrieved data.

[0303] Step 8:

[0304] Server: Pass the retrieved data to a generative AI model (e.g., GPT-3) to generate a report or text data in the specified format. The input is the retrieved data and the user's sentiment information, and the output is the generated report.

[0305] Step 9:

[0306] Server: Check the generated report with a verification module and perform formatting. The input is the generated report, and the output is the formatted report.

[0307] Step 10:

[0308] Server: Adjust the tone and content of the data based on the user's sentiment information if necessary. The input is the formatted report and the sentiment information, and the output is the final adjusted report.

[0309] Step 11:

[0310] Server: Sends the completed report to the user's terminal. The input is the finalized report, and the output is confirmation information for sending the report.

[0311] Step 12:

[0312] Terminal: Displays received reports for user review. For example, it displays received reports in PDF format. The input is the finalized report, and the output is the displayed report.

[0313] (Application Example 2)

[0314] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0315] Conventional factory management systems often involve manual collection and analysis of robot operating status and maintenance information, resulting in inefficiency. Furthermore, they fail to provide appropriate information tailored to the manager's mood and circumstances, making emergency response difficult. Therefore, a system is needed that efficiently and quickly monitors robot operating status, automates the acquisition, analysis, and report generation of necessary data.

[0316] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0317] In this invention, the server includes means for an emotion engine that recognizes the user's emotions, means for obtaining relevant information from a database based on the analyzed request, and means for passing the obtained information to a generation AI model and generating data while taking the emotion information into consideration. This enables efficient and rapid data generation and report provision that takes the user's emotions into consideration.

[0318] An "internal network" is a communication infrastructure used within a company or organization, enabling various terminals and servers to exchange data with each other.

[0319] A "request" is a request sent to a server by a user for the purpose of obtaining the data or information they need.

[0320] "Device" refers to equipment or equipment designed to perform a specific purpose. In this context, it includes the means of sending a request.

[0321] The term "computer" refers to an electronic device that performs data analysis, processing, storage, and communication, and in this context, it includes servers that receive and analyze requests.

[0322] A "database" is a collection of information that systematically organizes and stores related data, making it quickly searchable and usable when needed.

[0323] A "generative AI model" is an artificial intelligence model that uses a pre-trained algorithm to automatically generate data in a specified format.

[0324] An "emotion engine" is a software module that analyzes the user's emotions and adjusts the system's operation and output data based on the results.

[0325] "Information" refers to data obtained from databases or necessary data requested by users.

[0326] "Formatting" refers to the process of organizing and formatting generated data to conform to a predetermined format or standard.

[0327] "Verification" refers to the process of checking whether the data output from a generated AI model is accurate.

[0328] This system is implemented using the following hardware and software. The hardware includes smartphones, tablets, factory robots, various sensor networks, and servers. The software includes Python, Tensorflow® or PyTorch, OpenAI GPT, and an emotion engine. The following describes how each piece of hardware and software functions.

[0329] Send a request

[0330] Users request reports of necessary data using their smartphones or tablets. For example, they might issue a voice command such as, "Please create a report on the forecast for the next maintenance and the current parts inventory status." This request is sent to the server in real time via the company network. User sentiment information is also sent along with the request and analyzed by the sentiment engine.

[0331] Receiving and parsing requests

[0332] The server analyzes incoming requests and determines the optimal database for retrieving information based on the request's content. It also analyzes emotional information transmitted from the user's device and optimizes the data generation process based on the results.

[0333] Data acquisition

[0334] The server generates database queries and retrieves necessary data in real time from the company's internal database and the factory's sensor network. For example, it collects data such as the operating status and maintenance history of specific robots, and the inventory status of parts.

[0335] Data generation

[0336] The server passes the acquired data to OpenAI GPT, an AI model for generating reports, which then generate reports in the specified format. In this process, user sentiment information is taken into consideration, and the urgency and conciseness of the information are optimized.

[0337] Data validation and formatting

[0338] The server validates the generated report data and formats it into the required format. It verifies the accuracy of the data output from the generating AI model and adjusts the data based on sentiment information.

[0339] Return to user

[0340] Finally, the server sends the completed report back to the user's terminal. The user receives this report and uses it to develop factory operations and maintenance plans.

[0341] Specific example

[0342] For example, a factory engineer might make the following voice request:

[0343] "Please provide an urgent report on the expected next maintenance schedule and parts inventory status. Our engineers are currently under pressure."

[0344] This request is sent to the server, which retrieves the necessary data, and if the sentiment engine determines that "the engineer is feeling anxious," a concise report is quickly generated for review. This report provides the necessary information concisely and quickly, such as "Next scheduled maintenance date: October 15, 2023, Parts inventory: Sufficient."

[0345] This system significantly improves efficiency and accuracy compared to conventional manual processing, and can support factory operations.

[0346] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0347] Step 1:

[0348] Users request reports of necessary data using their smartphones or tablets.

[0349] Specific operation: The user issues a voice command such as, "Please create a report on the expected next maintenance and parts inventory status." The voice is converted to text and then sent to the server via the company network.

[0350] Input: User's voice request and sentiment information.

[0351] Output: Request and sentiment information converted to text format.

[0352] Step 2:

[0353] The server analyzes the received request and sentiment information to determine which database to retrieve the information from.

[0354] Specific operation: The server analyzes the request and determines which robots and sensors to collect data from. Additionally, the emotion engine analyzes the user's emotional information and optimizes the data generation process.

[0355] Input: Request and sentiment information converted to text format.

[0356] Output: Generation of database queries.

[0357] Step 3:

[0358] The server uses generated database queries to retrieve necessary data from the company's internal database and sensor network.

[0359] Specific operation: The server generates appropriate database queries to collect data such as the operating status of various sensors and robots within the factory, maintenance history, and parts inventory data.

[0360] Input: Database query.

[0361] Output: Acquired data (operating status data, maintenance data, parts inventory data, etc.).

[0362] Step 4:

[0363] The server passes the acquired data to a generation AI model, which then generates a report in the specified format.

[0364] Specific operation: The collected data is input into a generative AI model such as OpenAI GPT, and prompts are used to generate a report in the format requested by the user. The report content is optimized by also considering the results of the sentiment engine.

[0365] Input: Prompt text based on acquired data and sentiment information.

[0366] Output: Generated report data.

[0367] Step 5:

[0368] The server verifies the generated report data and formats it into the required format.

[0369] Specific actions: Verify the report data output from the generated AI model and check for errors. If necessary, correct or supplement the data and format it into the specified format.

[0370] Input: Generated report data.

[0371] Output: Formatted final report data.

[0372] Step 6:

[0373] The server sends the final report data back to the user's terminal.

[0374] Specific action: The completed report will be sent to the user's smartphone or tablet so that they can view it immediately.

[0375] Input: Formatted final report data.

[0376] Output: Sending report data to the user's terminal.

[0377] In this way, data processing and calculations are performed at each step, making it possible to generate and provide optimal reports that meet the user's requirements.

[0378] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0379] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0380] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0381] [Second Embodiment]

[0382] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0383] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0384] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0385] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0386] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0387] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0388] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0389] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0390] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0391] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0392] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0393] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0394] The system according to the present invention allows users in each department to send requests via the company's internal network, a server to process those requests, and a generative AI module to generate the specified data. This system enables the efficient generation of necessary data while preventing the leakage of internal company data.

[0395] Explanation of the program's processing

[0396] Send a request

[0397] Users: Users in each department send requests via the company network to generate the data they need for their work. These requests include specific conditions about what data is required.

[0398] Terminal: Sends a request to the server, including the user's department information. This information is used by the server to determine which database to access.

[0399] Receiving and parsing requests

[0400] Server: Analyzes the received request and verifies the user information and content of the request. Based on the user's department information, it determines which database to retrieve the data from.

[0401] Data acquisition

[0402] Server: Generates database queries and accesses internal databases to retrieve necessary data. For example, it might retrieve sales data or customer feedback data from the past year.

[0403] Data generation

[0404] Server: Passes the acquired data to a generative AI module to generate the necessary text data. This AI module uses a pre-trained model to generate data in the specified format.

[0405] Data validation and formatting

[0406] Server: Validates and formats the generated data. It verifies that the generated data meets the specified standards and makes additional corrections if necessary.

[0407] Return to user

[0408] Server: Returns the verified and formatted data to the user's terminal. The user receives the generated data and uses it in their work.

[0409] Specific example

[0410] Sending and receiving requests

[0411] The user (a marketing department employee) requests a report on the next marketing strategy. The request details that the report should include a trend analysis based on sales data and customer feedback from the past year, and a proposal for a new marketing strategy.

[0412] The device sends this request to the server.

[0413] Request parsing and data retrieval

[0414] The server receives the request and verifies that it originates from the marketing department. It then generates a database query to retrieve the necessary data from the internal database, specifically, sales data and customer feedback from the past year.

[0415] Data generation and return

[0416] The server passes the acquired data to a generative AI module to generate the necessary report. The generated report is verified and formatted, and finally sent back to the user's terminal.

[0417] The user reviews the returned report, makes revisions as needed, and proposes it as the final marketing strategy.

[0418] Thus, the system of the present invention can safely and efficiently utilize internal company data and support the operations of each department.

[0419] The following describes the processing flow.

[0420] Step 1:

[0421] A user sends a request from their device to the server via the company network, stating, "Please generate the data necessary for the new product project proposal." The request includes detailed conditions.

[0422] Step 2:

[0423] The terminal receives the request and sends it to the server. The request includes the user's department information.

[0424] Step 3:

[0425] The server receives the request and analyzes the request content and the user's department information. It then determines which database to access.

[0426] Step 4:

[0427] The server generates database queries and accesses the internal database to retrieve the necessary data. For example, it might use queries to retrieve sales data or customer feedback data from the past year.

[0428] Step 5:

[0429] The server temporarily stores the data it acquires and then passes that data to the generative AI module.

[0430] Step 6:

[0431] The server calls a generative AI module to generate the necessary text data based on the acquired data. In this process, the data is generated in a format that matches the user's request.

[0432] Step 7:

[0433] The server receives the generated text data and performs verification. It checks whether the text data meets the specified criteria.

[0434] Step 8:

[0435] The server formats the generated text data as needed, making it easy for users to use.

[0436] Step 9:

[0437] The server returns the completed text data to the user's terminal.

[0438] Step 10:

[0439] Users review the data received on their devices and use it for their work. They make minor adjustments to the data as needed and use it as the final document.

[0440] This series of steps enables the efficient and secure use of internal data to support users' work.

[0441] (Example 1)

[0442] Next, we will describe Example 1. 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."

[0443] To ensure the efficient and secure use of internal data and support users' operations, a system is needed that can respond to requests from multiple departments and generate appropriate data. However, traditional methods require considerable time and effort for request analysis, data acquisition, and data formatting, leading to decreased operational efficiency. Furthermore, from a data security perspective, measures to prevent the leakage of internal data are required.

[0444] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0445] In this invention, the server includes means for receiving and analyzing requests, means for obtaining relevant information from a database, means for passing data to a generative AI module to generate data in a specified format, and means for verifying and formatting the generated data. This enables efficient and secure utilization of internal company data, and allows users to quickly obtain the data necessary for their work.

[0446] An "internal network" is a closed network used to connect computers and other devices within a company, and serves as a means of sharing information and transmitting data.

[0447] A "request" is an instruction or request that a user sends to a server to ask it to generate specific data or provide information.

[0448] "Terminal means" refers to computers, mobile devices, and other devices used by users to create and send requests.

[0449] "Server system" refers to a centralized computer system for receiving and analyzing requests, and for generating and providing the necessary data.

[0450] "Analyzing" refers to understanding the content of a received request and extracting the necessary information and processing details.

[0451] A "database" is a system for systematically storing and managing information, allowing for efficient searching and retrieval of necessary data.

[0452] "Related information" refers to specific data or information retrieved from the database based on a request.

[0453] A "generative AI module" is a software module that uses a pre-trained artificial intelligence model to generate data based on a specific format or content.

[0454] "Verification" refers to the process of checking whether the generated data meets the required specifications and standards.

[0455] "Formatting" refers to the process of arranging generated data into a predetermined format or style.

[0456] A "user" refers to an individual or departmental member who uses the system to request data generation or information provision.

[0457] The system according to the present invention allows users in each department to send requests via the company's internal network, a server to process those requests, and a generative AI module to generate the specified data. This system enables the efficient generation of necessary data while preventing the leakage of internal company data.

[0458] Send a request

[0459] Users: Users in each department create requests using a dedicated client application to generate the data they need for their work. For example, an employee in the marketing department might create a request for a "report on the next marketing strategy" and enter specific criteria (sales data and customer feedback from the past year).

[0460] Terminal: Sends request data to the server. This request data includes a user ID and department information to identify which department the request originated from.

[0461] Receiving and parsing requests

[0462] Server: Parses incoming requests. Checks request metadata to determine which department the user belongs to. Analyzes the request content to determine what type of data is needed. For example, if "sales data for the past year" and "customer feedback data" are requested, it identifies the corresponding database tables. It uses Python parser modules to extract each field for parsing.

[0463] Data acquisition

[0464] Server: Generates database queries based on the analysis results. For example, it generates SQL statements to access internal databases (e.g., PostgreSQL or MySQL) and retrieve the necessary data. The retrieved data is used for filtering (e.g., by date range or specific customer group). SQLAlchemy is used for database queries, and the results are converted into a data frame (e.g., pandas).

[0465] Data generation

[0466] Server: Passes the acquired data to a generative AI module. This AI module (e.g., GPT-4) uses a pre-trained model to generate data according to specific format requirements. For example, it creates the framework of a requested report and fills in the details based on the acquired data. It calls an AI API (e.g., OpenAI API), inputs data along with prompts, and receives the generated text.

[0467] Data validation and formatting

[0468] Server: Validates the generated data to ensure it meets the specified criteria. For example, it checks for typographical errors in the generated report, ensures all necessary information is included, and verifies the report's formatting. The validation process uses natural language processing (NLP) tools (e.g., spaCy) to perform text analysis. If necessary, it formats the text and creates the final report. It uses text processing libraries (e.g., re, textblob) to correct and format the text.

[0469] Return to user

[0470] Server: Returns the validated and formatted data to the user's terminal. The generated data is returned in a user-friendly format (e.g., PDF, Excel file). Appropriate libraries (e.g., ReportLab for PDF generation, openpyxl for Excel file generation) are used to convert to the appropriate file format.

[0471] Terminal: The user's terminal displays data received from the server, allowing the user to review it. The user reviews the generated report and performs further analysis or corrections as needed.

[0472] Example of a prompt

[0473] "Please generate a report that proposes the next marketing strategy based on sales data and customer feedback from the past year."

[0474] In this way, the system of the present invention can safely and efficiently utilize internal company data and support the operations of each department.

[0475] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0476] Step 1:

[0477] Users: Each department's users create requests using a dedicated client application and send them over the company network. Requests include the required data types and conditions (e.g., sales data and customer feedback for the past year).

[0478] Input: Data request specified by the user (e.g., marketing report).

[0479] Output: Request data sent from the terminal to the server.

[0480] Step 2:

[0481] Terminal: The terminal sends requests created by the user to the server. At the same time, metadata such as the user's department information is also sent.

[0482] Input: User-created request data.

[0483] Output: Request data, including user department information, is sent to the server.

[0484] Step 3:

[0485] Server: The server parses the received request. First, it checks the request metadata to determine the user's department. Then, it parses the request content to identify the necessary data types. For example, it might use a Python parser module to extract each field.

[0486] Input: Request data.

[0487] Output: Analysis results (required data types, acquisition conditions, etc.).

[0488] Step 4:

[0489] Server: Generates database queries based on the analysis results. For example, it generates SQL statements to access internal databases (e.g., PostgreSQL or MySQL) and retrieve the necessary data. Specifically, it uses SQLAlchemy to execute queries and converts the results into a data frame (e.g., pandas).

[0490] Input: Analysis results (required data types, acquisition conditions, etc.).

[0491] Output: Required data (e.g., sales data, customer feedback data).

[0492] Step 5:

[0493] Server: Passes the acquired data to a generative AI module. This module (e.g., GPT-4) generates data according to specific format requirements. For example, it calls an AI API (e.g., OpenAI API), inputs a prompt and data, and retrieves the generated text.

[0494] Input: Retrieved data, prompt text.

[0495] Output: Generated text data (e.g., marketing report).

[0496] Step 6:

[0497] Server: Validates and formats the generated data. Performs text analysis using Natural Language Processing (NLP) tools (e.g., spaCy) and makes necessary corrections and formatting. Performs formatting using text processing libraries (e.g., re, textblob).

[0498] Input: Generated text data.

[0499] Output: Validated and formatted final data.

[0500] Step 7:

[0501] Server: Returns the verified and formatted data to the user's terminal. The generated data is returned in user-friendly formats such as PDF and Excel files. Specific examples include using ReportLab for PDF generation and openpyxl for Excel file generation.

[0502] Input: Validated and formatted data.

[0503] Output: The final data sent back to the user's terminal.

[0504] Step 8:

[0505] Terminal: The user's terminal displays the data received from the server, allowing the user to review it. The user reviews the generated data and performs further analysis or corrections as needed.

[0506] Input: Final data from the server.

[0507] Output: Data displayed on the user's device.

[0508] (Application Example 1)

[0509] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0510] Conventional data management systems in logistics centers have problems such as difficulty in providing information in real time, time-consuming data acquisition and generation, and decreased efficiency on site. Furthermore, the lack of means for on-site workers to receive real-time inventory management and efficient delivery route suggestions leads to delays and errors in operations. This invention aims to solve these problems by providing a system that uses smart devices to improve work efficiency and provide information in real time.

[0511] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0512] In this invention, the server includes terminal means for transmitting requests via the company network, server means for receiving and analyzing requests, means for obtaining relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI module and generating data in a specified format, means for returning the generated data to the user and providing information in real time, and means for field workers to receive real-time inventory management and delivery route suggestions using a smart device. This enables field workers at a logistics center to obtain necessary information in real time via a smart device and perform their work quickly and accurately.

[0513] An "internal network" is a network intended for information communication within a company or organization.

[0514] A "request" refers to a request for data or information submitted by a user.

[0515] "Terminal means" refers to devices or equipment used to send requests.

[0516] "Server means" refers to a server that has the function of receiving and analyzing requests.

[0517] "Analysis" refers to understanding the content of a received request and identifying the necessary processing.

[0518] A "database" refers to a data structure or system used to efficiently manage and retrieve information.

[0519] A "generative AI module" is a module that uses artificial intelligence to generate data in a specified format.

[0520] "Real-time" refers to the processing and provision of data and information almost instantaneously.

[0521] A "smart device" refers to an advanced device that can connect to the internet and has a variety of functions.

[0522] "Field workers" refers to people who perform physical tasks at sites such as logistics centers.

[0523] "Inventory management" refers to the task of checking and managing the quantity and condition of products in stock.

[0524] "Delivery route" refers to the optimal path for delivering goods.

[0525] "Information provision" refers to supplying users with necessary data and information.

[0526] This invention provides a real-time information provision system for logistics centers. Specifically, it relates to a system that allows on-site workers to receive inventory management and efficient delivery route suggestions using smart devices. The embodiments of this system are described in detail below.

[0527] Program generation

[0528] The server includes terminal means for sending requests via the company network, server means for receiving and analyzing requests, means for obtaining relevant data from a database based on the analyzed requests, means for passing the obtained data to a generation AI module and generating data in a specified format, means for returning the generated data to the user and providing information in real time, and means for field workers to receive real-time inventory management and delivery route suggestions using smart devices.

[0529] Explanation of the process

[0530] The terminal receives requests sent by field workers via smart devices. These requests may include, for example, "Tell me the next receiving operation" or "Suggest the best delivery route." These requests are sent to the server via the company network.

[0531] The server analyzes the received request to determine which department the user belongs to. Next, it retrieves the necessary data from the corresponding database. Examples of such data include inventory data and past delivery history.

[0532] The acquired data is passed to a generative AI module, which generates data in the specified format. The generative AI module uses advanced AI models such as GPT-3 to generate data according to the user's request.

[0533] The generated data is verified and formatted by the server and sent back to the user in real time. Field workers can then review the generated data via smart devices and proceed with their work efficiently.

[0534] Hardware and software to use

[0535] This system uses smart eyewear such as Google Glass and Vuzix as smart devices. It also uses Wi-Fi and 5G networks for data transmission and reception. The server provides API endpoints using the Flask framework, and the generative AI module uses the OpenAI API.

[0536] Specific example

[0537] For example, if a field worker issues a voice command via a smart device saying, "Tell me the next receiving task," the device sends this request to the server. The server analyzes the request, retrieves the necessary inventory data from the database, and passes it to a generative AI module. The generative AI module generates an instruction such as, "The next receiving task is for product X, shelf A," and the server sends this back to the field worker's smart device in real time.

[0538] Example of a prompt:

[0539] "Generate a logistics report based on the following data: 'Inventory Data'"

[0540] "Suggest optimal delivery routes for the following locations: 'Delivery destination A, Delivery destination B, Delivery destination C'"

[0541] In this way, on-site workers at the logistics center can obtain the necessary information in real time and perform their tasks quickly and accurately.

[0542] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0543] Step 1:

[0544] Users send requests via smart devices. Users input requests using voice commands or touch controls, such as "Tell me about the next receiving operation" or "Suggest the best delivery route." The entered requests are sent from the terminal to the server via the company network.

[0545] Input: Request details (e.g., "Please tell me the next receiving procedure.")

[0546] Output: Request sent to the server

[0547] Step 2:

[0548] The server analyzes the received request. Specifically, it analyzes the user's department information and the request content to determine which database to retrieve which data from. Natural language processing technology is used for the analysis.

[0549] Input: Submitted request, user's department information

[0550] Output: Database query (Example: Query to retrieve inventory data)

[0551] Step 3:

[0552] The server accesses the database based on the analysis results and retrieves relevant data. For example, in response to a request for "the next receiving operation," it queries the inventory management database to retrieve product information.

[0553] Input: Database query

[0554] Output: Acquired data (e.g., inventory data, product information)

[0555] Step 4:

[0556] The server passes the acquired data to a generative AI module, which generates data in the specified format. The generative AI module uses OpenAI APIs and other tools to generate optimal instructions and reports in response to the request.

[0557] Input: Acquired data

[0558] Output: Generated data (Example: "The next receiving operation is for product X, shelf A")

[0559] Step 5:

[0560] The server verifies and formats the generated data. In particular, it checks that the generated data is in the correct format and free of errors. It makes corrections as needed and finalizes it.

[0561] Input: Generated data

[0562] Output: Validated and formatted data

[0563] Step 6:

[0564] The server returns the verified and formatted data to the user's device. The user can then view this data in real time via their smart device and use it as instructions to proceed with their work.

[0565] Input: Validated and formatted data

[0566] Output: Data sent back to the user's terminal

[0567] The following example prompts are used as concrete examples of the actions:

[0568] Example 1: "Generate a logistics report based on the following data: 'Inventory data'"

[0569] Example 2: "Suggest optimal delivery routes for the following locations: 'Delivery destination A, Delivery destination B, Delivery destination C'"

[0570] This will enable on-site workers at logistics centers to obtain necessary information in real time and perform their tasks efficiently.

[0571] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0572] The system according to the present invention includes terminal means for sending requests via an internal network, server means for receiving and analyzing requests, means for acquiring relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI module to generate data in a specified format, means for returning the generated data to the user, and an emotion engine for recognizing the user's emotions. This system enables the safe and efficient use of internal company data, and further, enables the generation of data that takes the user's emotions into consideration.

[0573] Explanation of the program's processing

[0574] Send a request

[0575] Users: Users in each department send requests via the company network to generate the data they need for their work. These requests include specific conditions about what data is required.

[0576] Terminal: Sends a request to the server, including the user's department information and the user's sentiment information analyzed by the sentiment engine. This information is used by the server to determine which database to access and to provide highly accurate generated data.

[0577] Receiving and parsing requests

[0578] Server: Analyzes the received request and verifies the user information and content of the request. Based on the user's sentiment information and departmental information, it decides which database to retrieve the data from.

[0579] Data acquisition

[0580] Server: Generates database queries and accesses the internal database to retrieve necessary data. For example, it might use queries to retrieve sales data or customer feedback data from the past year.

[0581] Data generation

[0582] Server: Passes the acquired data to a generative AI module, which generates the necessary text data. This AI module uses a pre-trained model to generate data in the specified format. Furthermore, it executes the generation process while also considering the user's sentiment information provided by the sentiment engine.

[0583] Data validation and formatting

[0584] Server: Validates and formats the generated data. Checks if the generated data meets the specified standards and makes additional corrections if necessary. Also adjusts the data based on sentiment information.

[0585] Return to user

[0586] Server: Returns the completed text data to the user's terminal. The data, which also takes sentiment information into account, is provided in a way that best meets the user's needs.

[0587] Specific example

[0588] Sending and receiving requests

[0589] The user (a marketing department employee) requests a report on the next marketing strategy. The request details that it should include a trend analysis based on sales data and customer feedback from the past year, followed by a proposal for a new marketing strategy. Furthermore, the emotion engine detects the user's positive emotions.

[0590] The device sends this request to the server.

[0591] Request parsing and data retrieval

[0592] The server receives the request and verifies that it originates from the marketing department. It then generates a database query to retrieve the necessary data from the internal database, specifically, sales data and customer feedback from the past year.

[0593] Data generation and return

[0594] The server passes the acquired data to a generative AI module to generate the necessary reports. The generated reports are validated and formatted, and finally sent back to the user's device, including suggestions that reflect the user's positive emotions.

[0595] The user reviews the returned report, makes revisions as needed, and proposes it as the final marketing strategy.

[0596] The system of this invention efficiently and securely utilizes internal company data and generates data that also takes user emotions into consideration, thereby providing advanced support for the operations of each department.

[0597] The following describes the processing flow.

[0598] Step 1:

[0599] A user sends a request from their device via the company network, stating, "I would like to create a report on the next marketing strategy." The request includes detailed conditions, such as "Please conduct a trend analysis based on sales data and customer feedback from the past year, and propose a new marketing strategy."

[0600] Step 2:

[0601] The terminal receives the request and sends it to the server. The request includes the user's departmental information and the user's emotional information analyzed by the emotion engine.

[0602] Step 3:

[0603] The server receives the request and analyzes the request content, the user's department information, and sentiment information. It then determines which database to access.

[0604] Step 4:

[0605] The server generates database queries and accesses the internal database to retrieve the necessary data. Specifically, it retrieves sales data and customer feedback data for the past year using queries.

[0606] Step 5:

[0607] The server temporarily stores the acquired data and passes it to the emotion engine for analysis, which correlates it with the user's emotions. Based on these results, adjustments are made to reflect the changes in the generated data.

[0608] Step 6:

[0609] The server passes the acquired data and the analysis results from the emotion engine to the generative AI module, which then generates the necessary text data. For example, if a positive emotion is detected in the user, it generates a report that reflects that emotion.

[0610] Step 7:

[0611] The server receives the generated text data and performs validation. It checks whether the generated data meets the specified standards and makes additional corrections if necessary. It also formats the data appropriately to reflect the user's sentiment information.

[0612] Step 8:

[0613] The server returns the completed text data to the user's terminal.

[0614] Step 9:

[0615] The user reviews the data received on their device and uses it for work. They review the generated reports, make corrections as needed, and propose them as the final marketing strategy.

[0616] This entire process makes it possible to generate data that takes user emotions into account, enabling the efficient creation of highly accurate proposals.

[0617] (Example 2)

[0618] Next, we will describe Example 2. 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".

[0619] Conventional data generation systems, while capable of responding quickly and accurately to user requests, faced the challenge of generating data that took user sentiment into account. This made it difficult to provide data that best met user needs. Furthermore, the lack of efficient methods for retrieving data from databases suitable for specific departments resulted in challenges regarding the accuracy and efficiency of data acquisition.

[0620] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an emotion analysis means, a means for including the user's emotion information, and a means for verifying and formatting the output data obtained from the generated AI model and adjusting the data based on the user's emotion information. This makes it possible to generate data while taking the user's emotion information into consideration, and to provide data that is optimally suited to the user's needs. In addition, it is possible to efficiently acquire data from a database suitable for a specific department, improving the accuracy and efficiency of data acquisition.

[0621] "Terminal means" refers to a device or function that allows a user to send a request via the company's internal network.

[0622] A "server means" is a device or function that receives a request, parses it, and accesses the appropriate database.

[0623] "Means of retrieving relevant data from a database" refers to a device or function that retrieves the necessary data from a database based on an analyzed request.

[0624] A "generative AI model" is an artificial intelligence model that generates data in a specified format based on acquired data.

[0625] "Emotional analysis means" refers to a device or function that analyzes a user's emotional information.

[0626] "Means of including user sentiment information in a request" refers to a device or function that adds analyzed sentiment information to a request.

[0627] "Means for verification and formatting" refers to a device or function that checks the output data obtained from the generated AI model and formats it into the required format.

[0628] "Means of adjusting data" refers to a device or function that adjusts the content and tone of data generated based on the user's emotional information.

[0629] A "user" refers to an individual or organization that uses the system to generate data.

[0630] The system according to the present invention includes terminal means for sending requests via an internal network, server means for receiving and analyzing requests, means for acquiring relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI model to generate data in a specified format, means for returning the generated data to the user, and sentiment analysis means for analyzing the user's emotional information. This system enables the safe and efficient use of internal company data, and further, enables the generation of data that takes user emotions into consideration.

[0631] The server receives the request and uses a data analysis module to verify the user information and request details of the requester. For example, if an employee in the marketing department sends a request to create a report on the next marketing strategy, the server receives and analyzes it. Specific conditions include "trend analysis based on sales data and customer feedback from the past year, and proposals for a new marketing strategy."

[0632] When a user enters a request, the terminal's emotion engine analyzes the user's current emotion information, adds the results to the request information, and sends it to the server. This process improves the accuracy of the data the server receives because the user's emotion information is included in the request.

[0633] The server then generates an appropriate database query, such as "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'", to retrieve the necessary data from the internal database. The retrieved data is then loaded into memory.

[0634] Generative AI models (such as pre-trained models like GPT-3) generate reports or text data in a specified format based on the acquired data. The generation process also considers user sentiment, enabling more accurate data generation. For example, it can generate a "proposal for the next marketing strategy based on sales data and customer feedback."

[0635] The server checks the generated data with a validation module to verify the consistency of the text and the format of the data. Corrections are made as needed, and final formatting is performed. The tone and content of the data are also adjusted based on sentiment information.

[0636] Finally, the server sends the completed data to the user's terminal. For example, it might convert the generated report to PDF format and send it using a secure communication protocol (HTTPS). The terminal receives the data and displays it for the user to review. The user can then download and further edit it.

[0637] Specific example

[0638] User: A marketing department employee submits a request to create a report on the next marketing strategy. The request includes specific requirements such as "trend analysis based on sales data and customer feedback from the past year, and a proposal for a new marketing strategy."

[0639] Terminal: Enter the request details on the screen and click the send button. In addition to the request information, the terminal also sends positive sentiment information analyzed by the sentiment engine to the server.

[0640] Server: Processes the received request and verifies that it originates from the marketing department. Next, it generates a database query and prepares to access the relevant database. The specific query executed is "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'".

[0641] Generative AI Model: Based on acquired data, it generates the next marketing strategy report. The generated report includes suggestions that reflect positive sentiment information.

[0642] Server: Validates the generated data, makes corrections and formatting as needed, and then sends it to the user's terminal.

[0643] This system enables the efficient and secure use of internal company data, as well as the generation of data that takes user sentiment into consideration.

[0644] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0645] Step 1:

[0646] User: Create a request to generate data necessary for your work. The input should include text detailing the specific data requirements and needs. For example, "I would like a report on our next marketing strategy. I need sales data and customer feedback analysis for the past year."

[0647] Step 2:

[0648] Terminal: Receives request information entered by the user and analyzes the user's current sentiment using the sentiment engine. The results of this analysis are added to the request data. The output generates request data containing the user's conditions and sentiment information.

[0649] Step 3:

[0650] Terminal: Sends request data to the server. Input is the request data, and output is confirmation information for the sent request.

[0651] Step 4:

[0652] Server: Receives requests on the receiving port. Input is the request data, and output is the data to be transferred to the data analysis module.

[0653] Step 5:

[0654] Server: The data analysis module analyzes the request data and extracts user information, request details, and sentiment information. The input is the request data, and the output is the extracted user information and conditions.

[0655] Step 6:

[0656] Server: Generates appropriate database queries based on extracted user information and conditions. Specifically, it generates SQL queries like "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'". The input is user information and conditions, and the output is the database query.

[0657] Step 7:

[0658] Server: Executes database queries and retrieves relevant data from the database. The input is the database query, and the output is the retrieved data.

[0659] Step 8:

[0660] Server: Passes the acquired data to a generation AI model (e.g., GPT-3) to generate reports or text data in the specified format. The input consists of the acquired data and user sentiment information, and the output is the generated report.

[0661] Step 9:

[0662] Server: The generated report is checked by a validation module and formatted. The input is the generated report, and the output is the formatted report.

[0663] Step 10:

[0664] Server: Adjusts the tone and content of the data based on user sentiment information as needed. Inputs include formatted reports and sentiment information, and output is a finalized report.

[0665] Step 11:

[0666] Server: Sends the completed report to the user's terminal. The input is the finalized report, and the output is confirmation information for sending the report.

[0667] Step 12:

[0668] Terminal: Displays received reports for user review. For example, it displays received reports in PDF format. The input is the finalized report, and the output is the displayed report.

[0669] (Application Example 2)

[0670] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0671] Conventional factory management systems often involve manual collection and analysis of robot operating status and maintenance information, resulting in inefficiency. Furthermore, they fail to provide appropriate information tailored to the manager's mood and circumstances, making emergency response difficult. Therefore, a system is needed that efficiently and quickly monitors robot operating status, automates the acquisition, analysis, and report generation of necessary data.

[0672] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0673] In this invention, the server includes means for an emotion engine that recognizes the user's emotions, means for obtaining relevant information from a database based on the analyzed request, and means for passing the obtained information to a generation AI model and generating data while taking the emotion information into consideration. This enables efficient and rapid data generation and report provision that takes the user's emotions into consideration.

[0674] An "internal network" is a communication infrastructure used within a company or organization, enabling various terminals and servers to exchange data with each other.

[0675] A "request" is a request sent to a server by a user for the purpose of obtaining the data or information they need.

[0676] "Device" refers to equipment or equipment designed to perform a specific purpose. In this context, it includes the means of sending a request.

[0677] The term "computer" refers to an electronic device that performs data analysis, processing, storage, and communication, and in this context, it includes servers that receive and analyze requests.

[0678] A "database" is a collection of information that systematically organizes and stores related data, making it quickly searchable and usable when needed.

[0679] A "generative AI model" is an artificial intelligence model that uses a pre-trained algorithm to automatically generate data in a specified format.

[0680] An "emotion engine" is a software module that analyzes the user's emotions and adjusts the system's operation and output data based on the results.

[0681] "Information" refers to data obtained from databases or necessary data requested by users.

[0682] "Formatting" refers to the process of organizing and formatting generated data to conform to a predetermined format or standard.

[0683] "Verification" refers to the process of checking whether the data output from a generated AI model is accurate.

[0684] This system is implemented using the following hardware and software. The hardware includes smartphones, tablets, factory robots, various sensor networks, and servers. The software includes Python, TensorFlow or PyTorch, OpenAI GPT, and an emotion engine. The following describes how each piece of hardware and software functions.

[0685] Send a request

[0686] Users request reports of necessary data using their smartphones or tablets. For example, they might issue a voice command such as, "Please create a report on the forecast for the next maintenance and the current parts inventory status." This request is sent to the server in real time via the company network. User sentiment information is also sent along with the request and analyzed by the sentiment engine.

[0687] Receiving and parsing requests

[0688] The server analyzes incoming requests and determines the optimal database for retrieving information based on the request's content. It also analyzes emotional information transmitted from the user's device and optimizes the data generation process based on the results.

[0689] Data acquisition

[0690] The server generates database queries and retrieves necessary data in real time from the company's internal database and the factory's sensor network. For example, it collects data such as the operating status and maintenance history of specific robots, and the inventory status of parts.

[0691] Data generation

[0692] The server passes the acquired data to OpenAI GPT, an AI model for generating reports, which then generate reports in the specified format. In this process, user sentiment information is taken into consideration, and the urgency and conciseness of the information are optimized.

[0693] Data validation and formatting

[0694] The server validates the generated report data and formats it into the required format. It verifies the accuracy of the data output from the generating AI model and adjusts the data based on sentiment information.

[0695] Return to user

[0696] Finally, the server sends the completed report back to the user's terminal. The user receives this report and uses it to develop factory operations and maintenance plans.

[0697] Specific example

[0698] For example, a factory engineer might make the following voice request:

[0699] "Please provide an urgent report on the expected next maintenance schedule and parts inventory status. Our engineers are currently under pressure."

[0700] This request is sent to the server, which retrieves the necessary data, and if the sentiment engine determines that "the engineer is feeling anxious," a concise report is quickly generated for review. This report provides the necessary information concisely and quickly, such as "Next scheduled maintenance date: October 15, 2023, Parts inventory: Sufficient."

[0701] This system significantly improves efficiency and accuracy compared to conventional manual processing, and can support factory operations.

[0702] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0703] Step 1:

[0704] Users request reports of necessary data using their smartphones or tablets.

[0705] Specific operation: The user issues a voice command such as, "Please create a report on the expected next maintenance and parts inventory status." The voice is converted to text and then sent to the server via the company network.

[0706] Input: User's voice request and sentiment information.

[0707] Output: Request and sentiment information converted to text format.

[0708] Step 2:

[0709] The server analyzes the received request and sentiment information to determine which database to retrieve the information from.

[0710] Specific operation: The server analyzes the request and determines which robots and sensors to collect data from. Additionally, the emotion engine analyzes the user's emotional information and optimizes the data generation process.

[0711] Input: Request and sentiment information converted to text format.

[0712] Output: Generation of database queries.

[0713] Step 3:

[0714] The server uses generated database queries to retrieve necessary data from the company's internal database and sensor network.

[0715] Specific operation: The server generates appropriate database queries to collect data such as the operating status of various sensors and robots within the factory, maintenance history, and parts inventory data.

[0716] Input: Database query.

[0717] Output: Acquired data (operating status data, maintenance data, parts inventory data, etc.).

[0718] Step 4:

[0719] The server passes the acquired data to a generation AI model, which then generates a report in the specified format.

[0720] Specific operation: The collected data is input into a generative AI model such as OpenAI GPT, and prompts are used to generate a report in the format requested by the user. The report content is optimized by also considering the results of the sentiment engine.

[0721] Input: Prompt text based on acquired data and sentiment information.

[0722] Output: Generated report data.

[0723] Step 5:

[0724] The server verifies the generated report data and formats it into the required format.

[0725] Specific actions: Verify the report data output from the generated AI model and check for errors. If necessary, correct or supplement the data and format it into the specified format.

[0726] Input: Generated report data.

[0727] Output: Formatted final report data.

[0728] Step 6:

[0729] The server sends the final report data back to the user's terminal.

[0730] Specific action: The completed report will be sent to the user's smartphone or tablet so that they can view it immediately.

[0731] Input: Formatted final report data.

[0732] Output: Sending report data to the user's terminal.

[0733] In this way, data processing and calculations are performed at each step, making it possible to generate and provide optimal reports that meet the user's requirements.

[0734] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0735] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0736] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0737] [Third Embodiment]

[0738] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0739] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0740] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0741] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0742] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0743] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0744] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0745] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0746] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0747] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0748] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0749] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0750] The system according to the present invention allows users in each department to send requests via the company's internal network, a server to process those requests, and a generative AI module to generate the specified data. This system enables the efficient generation of necessary data while preventing the leakage of internal company data.

[0751] Explanation of the program's processing

[0752] Send a request

[0753] Users: Users in each department send requests via the company network to generate the data they need for their work. These requests include specific conditions about what data is required.

[0754] Terminal: Sends a request to the server, including the user's department information. This information is used by the server to determine which database to access.

[0755] Receiving and parsing requests

[0756] Server: Analyzes the received request and verifies the user information and content of the request. Based on the user's department information, it determines which database to retrieve the data from.

[0757] Data acquisition

[0758] Server: Generates database queries and accesses internal databases to retrieve necessary data. For example, it might retrieve sales data or customer feedback data from the past year.

[0759] Data generation

[0760] Server: Passes the acquired data to a generative AI module to generate the necessary text data. This AI module uses a pre-trained model to generate data in the specified format.

[0761] Data validation and formatting

[0762] Server: Validates and formats the generated data. It verifies that the generated data meets the specified standards and makes additional corrections if necessary.

[0763] Return to user

[0764] Server: Returns the verified and formatted data to the user's terminal. The user receives the generated data and uses it in their work.

[0765] Specific example

[0766] Sending and receiving requests

[0767] The user (a marketing department employee) requests a report on the next marketing strategy. The request details that the report should include a trend analysis based on sales data and customer feedback from the past year, and a proposal for a new marketing strategy.

[0768] The device sends this request to the server.

[0769] Request parsing and data retrieval

[0770] The server receives the request and verifies that it originates from the marketing department. It then generates a database query to retrieve the necessary data from the internal database, specifically, sales data and customer feedback from the past year.

[0771] Data generation and return

[0772] The server passes the acquired data to a generative AI module to generate the necessary report. The generated report is verified and formatted, and finally sent back to the user's terminal.

[0773] The user reviews the returned report, makes revisions as needed, and proposes it as the final marketing strategy.

[0774] Thus, the system of the present invention can safely and efficiently utilize internal company data and support the operations of each department.

[0775] The following describes the processing flow.

[0776] Step 1:

[0777] A user sends a request from their device to the server via the company network, stating, "Please generate the data necessary for the new product project proposal." The request includes detailed conditions.

[0778] Step 2:

[0779] The terminal receives the request and sends it to the server. The request includes the user's department information.

[0780] Step 3:

[0781] The server receives the request and analyzes the request content and the user's department information. It then determines which database to access.

[0782] Step 4:

[0783] The server generates database queries and accesses the internal database to retrieve the necessary data. For example, it might use queries to retrieve sales data or customer feedback data from the past year.

[0784] Step 5:

[0785] The server temporarily stores the data it acquires and then passes that data to the generative AI module.

[0786] Step 6:

[0787] The server calls a generative AI module to generate the necessary text data based on the acquired data. In this process, the data is generated in a format that matches the user's request.

[0788] Step 7:

[0789] The server receives the generated text data and performs verification. It checks whether the text data meets the specified criteria.

[0790] Step 8:

[0791] The server formats the generated text data as needed, making it easy for users to use.

[0792] Step 9:

[0793] The server returns the completed text data to the user's terminal.

[0794] Step 10:

[0795] Users review the data received on their devices and use it for their work. They make minor adjustments to the data as needed and use it as the final document.

[0796] This series of steps enables the efficient and secure use of internal data to support users' work.

[0797] (Example 1)

[0798] Next, we will describe Example 1. 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."

[0799] To ensure the efficient and secure use of internal data and support users' operations, a system is needed that can respond to requests from multiple departments and generate appropriate data. However, traditional methods require considerable time and effort for request analysis, data acquisition, and data formatting, leading to decreased operational efficiency. Furthermore, from a data security perspective, measures to prevent the leakage of internal data are required.

[0800] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0801] In this invention, the server includes means for receiving and analyzing requests, means for obtaining relevant information from a database, means for passing data to a generative AI module to generate data in a specified format, and means for verifying and formatting the generated data. This enables efficient and secure utilization of internal company data, and allows users to quickly obtain the data necessary for their work.

[0802] An "internal network" is a closed network used to connect computers and other devices within a company, and serves as a means of sharing information and transmitting data.

[0803] A "request" is an instruction or request that a user sends to a server to ask it to generate specific data or provide information.

[0804] "Terminal means" refers to computers, mobile devices, and other devices used by users to create and send requests.

[0805] "Server system" refers to a centralized computer system for receiving and analyzing requests, and for generating and providing the necessary data.

[0806] "Analyzing" refers to understanding the content of a received request and extracting the necessary information and processing details.

[0807] A "database" is a system for systematically storing and managing information, allowing for efficient searching and retrieval of necessary data.

[0808] "Related information" refers to specific data or information retrieved from the database based on a request.

[0809] A "generative AI module" is a software module that uses a pre-trained artificial intelligence model to generate data based on a specific format or content.

[0810] "Verification" refers to the process of checking whether the generated data meets the required specifications and standards.

[0811] "Formatting" refers to the process of arranging generated data into a predetermined format or style.

[0812] A "user" refers to an individual or departmental member who uses the system to request data generation or information provision.

[0813] The system according to the present invention allows users in each department to send requests via the company's internal network, a server to process those requests, and a generative AI module to generate the specified data. This system enables the efficient generation of necessary data while preventing the leakage of internal company data.

[0814] Send a request

[0815] Users: Users in each department create requests using a dedicated client application to generate the data they need for their work. For example, an employee in the marketing department might create a request for a "report on the next marketing strategy" and enter specific criteria (sales data and customer feedback from the past year).

[0816] Terminal: Sends request data to the server. This request data includes a user ID and department information to identify which department the request originated from.

[0817] Receiving and parsing requests

[0818] Server: Parses incoming requests. Checks request metadata to determine which department the user belongs to. Analyzes the request content to determine what type of data is needed. For example, if "sales data for the past year" and "customer feedback data" are requested, it identifies the corresponding database tables. It uses Python parser modules to extract each field for parsing.

[0819] Data acquisition

[0820] Server: Generates database queries based on the analysis results. For example, it generates SQL statements to access internal databases (e.g., PostgreSQL or MySQL) and retrieve the necessary data. The retrieved data is used for filtering (e.g., by date range or specific customer group). SQLAlchemy is used for database queries, and the results are converted into a data frame (e.g., pandas).

[0821] Data generation

[0822] Server: Passes the acquired data to a generative AI module. This AI module (e.g., GPT-4) uses a pre-trained model to generate data according to specific format requirements. For example, it creates the framework of a requested report and fills in the details based on the acquired data. It calls an AI API (e.g., OpenAI API), inputs data along with prompts, and receives the generated text.

[0823] Data validation and formatting

[0824] Server: Validates the generated data to ensure it meets the specified criteria. For example, it checks for typographical errors in the generated report, ensures all necessary information is included, and verifies the report's formatting. The validation process uses natural language processing (NLP) tools (e.g., spaCy) to perform text analysis. If necessary, it formats the text and creates the final report. It uses text processing libraries (e.g., re, textblob) to correct and format the text.

[0825] Return to user

[0826] Server: Returns the validated and formatted data to the user's terminal. The generated data is returned in a user-friendly format (e.g., PDF, Excel file). Appropriate libraries (e.g., ReportLab for PDF generation, openpyxl for Excel file generation) are used to convert to the appropriate file format.

[0827] Terminal: The user's terminal displays data received from the server, allowing the user to review it. The user reviews the generated report and performs further analysis or corrections as needed.

[0828] Example of a prompt

[0829] "Please generate a report that proposes the next marketing strategy based on sales data and customer feedback from the past year."

[0830] In this way, the system of the present invention can safely and efficiently utilize internal company data and support the operations of each department.

[0831] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0832] Step 1:

[0833] Users: Each department's users create requests using a dedicated client application and send them over the company network. Requests include the required data types and conditions (e.g., sales data and customer feedback for the past year).

[0834] Input: Data request specified by the user (e.g., marketing report).

[0835] Output: Request data sent from the terminal to the server.

[0836] Step 2:

[0837] Terminal: The terminal sends requests created by the user to the server. At the same time, metadata such as the user's department information is also sent.

[0838] Input: User-created request data.

[0839] Output: Request data, including user department information, is sent to the server.

[0840] Step 3:

[0841] Server: The server parses the received request. First, it checks the request metadata to determine the user's department. Then, it parses the request content to identify the necessary data types. For example, it might use a Python parser module to extract each field.

[0842] Input: Request data.

[0843] Output: Analysis results (required data types, acquisition conditions, etc.).

[0844] Step 4:

[0845] Server: Generates database queries based on the analysis results. For example, it generates SQL statements to access internal databases (e.g., PostgreSQL or MySQL) and retrieve the necessary data. Specifically, it uses SQLAlchemy to execute queries and converts the results into a data frame (e.g., pandas).

[0846] Input: Analysis results (required data types, acquisition conditions, etc.).

[0847] Output: Required data (e.g., sales data, customer feedback data).

[0848] Step 5:

[0849] Server: Passes the acquired data to a generative AI module. This module (e.g., GPT-4) generates data according to specific format requirements. For example, it calls an AI API (e.g., OpenAI API), inputs a prompt and data, and retrieves the generated text.

[0850] Input: Retrieved data, prompt text.

[0851] Output: Generated text data (e.g., marketing report).

[0852] Step 6:

[0853] Server: Validates and formats the generated data. Performs text analysis using Natural Language Processing (NLP) tools (e.g., spaCy) and makes necessary corrections and formatting. Performs formatting using text processing libraries (e.g., re, textblob).

[0854] Input: Generated text data.

[0855] Output: Validated and formatted final data.

[0856] Step 7:

[0857] Server: Returns the verified and formatted data to the user's terminal. The generated data is returned in user-friendly formats such as PDF and Excel files. Specific examples include using ReportLab for PDF generation and openpyxl for Excel file generation.

[0858] Input: Validated and formatted data.

[0859] Output: The final data sent back to the user's terminal.

[0860] Step 8:

[0861] Terminal: The user's terminal displays the data received from the server, allowing the user to review it. The user reviews the generated data and performs further analysis or corrections as needed.

[0862] Input: Final data from the server.

[0863] Output: Data displayed on the user's device.

[0864] (Application Example 1)

[0865] Next, we will explain Application Example 1. In the following explanation, 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."

[0866] Conventional data management systems in logistics centers have problems such as difficulty in providing information in real time, time-consuming data acquisition and generation, and decreased efficiency on site. Furthermore, the lack of means for on-site workers to receive real-time inventory management and efficient delivery route suggestions leads to delays and errors in operations. This invention aims to solve these problems by providing a system that uses smart devices to improve work efficiency and provide information in real time.

[0867] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0868] In this invention, the server includes terminal means for transmitting requests via the company network, server means for receiving and analyzing requests, means for obtaining relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI module and generating data in a specified format, means for returning the generated data to the user and providing information in real time, and means for field workers to receive real-time inventory management and delivery route suggestions using a smart device. This enables field workers at a logistics center to obtain necessary information in real time via a smart device and perform their work quickly and accurately.

[0869] An "internal network" is a network intended for information communication within a company or organization.

[0870] A "request" refers to a request for data or information submitted by a user.

[0871] "Terminal means" refers to devices or equipment used to send requests.

[0872] "Server means" refers to a server that has the function of receiving and analyzing requests.

[0873] "Analysis" refers to understanding the content of a received request and identifying the necessary processing.

[0874] A "database" refers to a data structure or system used to efficiently manage and retrieve information.

[0875] A "generative AI module" is a module that uses artificial intelligence to generate data in a specified format.

[0876] "Real-time" refers to the processing and provision of data and information almost instantaneously.

[0877] A "smart device" refers to an advanced device that can connect to the internet and has a variety of functions.

[0878] "Field workers" refers to people who perform physical tasks at sites such as logistics centers.

[0879] "Inventory management" refers to the task of checking and managing the quantity and condition of products in stock.

[0880] "Delivery route" refers to the optimal path for delivering goods.

[0881] "Information provision" refers to supplying users with necessary data and information.

[0882] This invention provides a real-time information provision system for logistics centers. Specifically, it relates to a system that allows on-site workers to receive inventory management and efficient delivery route suggestions using smart devices. The embodiments of this system are described in detail below.

[0883] Program generation

[0884] The server includes terminal means for sending requests via the company network, server means for receiving and analyzing requests, means for obtaining relevant data from a database based on the analyzed requests, means for passing the obtained data to a generation AI module and generating data in a specified format, means for returning the generated data to the user and providing information in real time, and means for field workers to receive real-time inventory management and delivery route suggestions using smart devices.

[0885] Explanation of the process

[0886] The terminal receives requests sent by field workers via smart devices. These requests may include, for example, "Tell me the next receiving operation" or "Suggest the best delivery route." These requests are sent to the server via the company network.

[0887] The server analyzes the received request to determine which department the user belongs to. Next, it retrieves the necessary data from the corresponding database. Examples of such data include inventory data and past delivery history.

[0888] The acquired data is passed to a generative AI module, which generates data in the specified format. The generative AI module uses advanced AI models such as GPT-3 to generate data according to the user's request.

[0889] The generated data is verified and formatted by the server and sent back to the user in real time. Field workers can then review the generated data via smart devices and proceed with their work efficiently.

[0890] Hardware and software to use

[0891] This system uses smart eyewear such as Google Glass and Vuzix as smart devices. It also uses Wi-Fi and 5G networks for data transmission and reception. The server provides API endpoints using the Flask framework, and the generative AI module uses the OpenAI API.

[0892] Specific example

[0893] For example, if a field worker issues a voice command via a smart device saying, "Tell me the next receiving task," the device sends this request to the server. The server analyzes the request, retrieves the necessary inventory data from the database, and passes it to a generative AI module. The generative AI module generates an instruction such as, "The next receiving task is for product X, shelf A," and the server sends this back to the field worker's smart device in real time.

[0894] Example of a prompt:

[0895] "Generate a logistics report based on the following data: 'Inventory Data'"

[0896] "Suggest optimal delivery routes for the following locations: 'Delivery destination A, Delivery destination B, Delivery destination C'"

[0897] In this way, on-site workers at the logistics center can obtain the necessary information in real time and perform their tasks quickly and accurately.

[0898] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0899] Step 1:

[0900] Users send requests via smart devices. Users input requests using voice commands or touch controls, such as "Tell me about the next receiving operation" or "Suggest the best delivery route." The entered requests are sent from the terminal to the server via the company network.

[0901] Input: Request details (e.g., "Please tell me the next receiving procedure.")

[0902] Output: Request sent to the server

[0903] Step 2:

[0904] The server analyzes the received request. Specifically, it analyzes the user's department information and the request content to determine which database to retrieve which data from. Natural language processing technology is used for the analysis.

[0905] Input: Submitted request, user's department information

[0906] Output: Database query (Example: Query to retrieve inventory data)

[0907] Step 3:

[0908] The server accesses the database based on the analysis results and retrieves relevant data. For example, in response to a request for "the next receiving operation," it queries the inventory management database to retrieve product information.

[0909] Input: Database query

[0910] Output: Acquired data (e.g., inventory data, product information)

[0911] Step 4:

[0912] The server passes the acquired data to a generative AI module, which generates data in the specified format. The generative AI module uses OpenAI APIs and other tools to generate optimal instructions and reports in response to the request.

[0913] Input: Acquired data

[0914] Output: Generated data (Example: "The next receiving operation is for product X, shelf A")

[0915] Step 5:

[0916] The server verifies and formats the generated data. In particular, it checks that the generated data is in the correct format and free of errors. It makes corrections as needed and finalizes it.

[0917] Input: Generated data

[0918] Output: Validated and formatted data

[0919] Step 6:

[0920] The server returns the verified and formatted data to the user's device. The user can then view this data in real time via their smart device and use it as instructions to proceed with their work.

[0921] Input: Validated and formatted data

[0922] Output: Data sent back to the user's terminal

[0923] The following example prompts are used as concrete examples of the actions:

[0924] Example 1: "Generate a logistics report based on the following data: 'Inventory data'"

[0925] Example 2: "Suggest optimal delivery routes for the following locations: 'Delivery destination A, Delivery destination B, Delivery destination C'"

[0926] This will enable on-site workers at logistics centers to obtain necessary information in real time and perform their tasks efficiently.

[0927] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0928] The system according to the present invention includes terminal means for sending requests via an internal network, server means for receiving and analyzing requests, means for acquiring relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI module to generate data in a specified format, means for returning the generated data to the user, and an emotion engine for recognizing the user's emotions. This system enables the safe and efficient use of internal company data, and further, enables the generation of data that takes the user's emotions into consideration.

[0929] Explanation of the program's processing

[0930] Send a request

[0931] Users: Users in each department send requests via the company network to generate the data they need for their work. These requests include specific conditions about what data is required.

[0932] Terminal: Sends a request to the server, including the user's department information and the user's sentiment information analyzed by the sentiment engine. This information is used by the server to determine which database to access and to provide highly accurate generated data.

[0933] Receiving and parsing requests

[0934] Server: Analyzes the received request and verifies the user information and content of the request. Based on the user's sentiment information and departmental information, it decides which database to retrieve the data from.

[0935] Data acquisition

[0936] Server: Generates database queries and accesses the internal database to retrieve necessary data. For example, it might use queries to retrieve sales data or customer feedback data from the past year.

[0937] Data generation

[0938] Server: Passes the acquired data to a generative AI module, which generates the necessary text data. This AI module uses a pre-trained model to generate data in the specified format. Furthermore, it executes the generation process while also considering the user's sentiment information provided by the sentiment engine.

[0939] Data validation and formatting

[0940] Server: Validates and formats the generated data. Checks if the generated data meets the specified standards and makes additional corrections if necessary. Also adjusts the data based on sentiment information.

[0941] Return to user

[0942] Server: Returns the completed text data to the user's terminal. The data, which also takes sentiment information into account, is provided in a way that best meets the user's needs.

[0943] Specific example

[0944] Sending and receiving requests

[0945] The user (a marketing department employee) requests a report on the next marketing strategy. The request details that it should include a trend analysis based on sales data and customer feedback from the past year, followed by a proposal for a new marketing strategy. Furthermore, the emotion engine detects the user's positive emotions.

[0946] The device sends this request to the server.

[0947] Request parsing and data retrieval

[0948] The server receives the request and verifies that it originates from the marketing department. It then generates a database query to retrieve the necessary data from the internal database, specifically, sales data and customer feedback from the past year.

[0949] Data generation and return

[0950] The server passes the acquired data to a generative AI module to generate the necessary reports. The generated reports are validated and formatted, and finally sent back to the user's device, including suggestions that reflect the user's positive emotions.

[0951] The user reviews the returned report, makes revisions as needed, and proposes it as the final marketing strategy.

[0952] The system of this invention efficiently and securely utilizes internal company data and generates data that also takes user emotions into consideration, thereby providing advanced support for the operations of each department.

[0953] The following describes the processing flow.

[0954] Step 1:

[0955] A user sends a request from their device via the company network, stating, "I would like to create a report on the next marketing strategy." The request includes detailed conditions, such as "Please conduct a trend analysis based on sales data and customer feedback from the past year, and propose a new marketing strategy."

[0956] Step 2:

[0957] The terminal receives the request and sends it to the server. The request includes the user's departmental information and the user's emotional information analyzed by the emotion engine.

[0958] Step 3:

[0959] The server receives the request and analyzes the request content, the user's department information, and sentiment information. It then determines which database to access.

[0960] Step 4:

[0961] The server generates database queries and accesses the internal database to retrieve the necessary data. Specifically, it retrieves sales data and customer feedback data for the past year using queries.

[0962] Step 5:

[0963] The server temporarily stores the acquired data and passes it to the emotion engine for analysis, which correlates it with the user's emotions. Based on these results, adjustments are made to reflect the changes in the generated data.

[0964] Step 6:

[0965] The server passes the acquired data and the analysis results from the emotion engine to the generative AI module, which then generates the necessary text data. For example, if a positive emotion is detected in the user, it generates a report that reflects that emotion.

[0966] Step 7:

[0967] The server receives the generated text data and performs validation. It checks whether the generated data meets the specified standards and makes additional corrections if necessary. It also formats the data appropriately to reflect the user's sentiment information.

[0968] Step 8:

[0969] The server returns the completed text data to the user's terminal.

[0970] Step 9:

[0971] The user reviews the data received on their device and uses it for work. They review the generated reports, make corrections as needed, and propose them as the final marketing strategy.

[0972] This entire process makes it possible to generate data that takes user emotions into account, enabling the efficient creation of highly accurate proposals.

[0973] (Example 2)

[0974] Next, we will describe Example 2. 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."

[0975] Conventional data generation systems, while capable of responding quickly and accurately to user requests, faced the challenge of generating data that took user sentiment into account. This made it difficult to provide data that best met user needs. Furthermore, the lack of efficient methods for retrieving data from databases suitable for specific departments resulted in challenges regarding the accuracy and efficiency of data acquisition.

[0976] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an emotion analysis means, a means for including the user's emotion information, and a means for verifying and formatting the output data obtained from the generated AI model and adjusting the data based on the user's emotion information. This makes it possible to generate data while taking the user's emotion information into consideration, and to provide data that is optimally suited to the user's needs. In addition, it is possible to efficiently acquire data from a database suitable for a specific department, improving the accuracy and efficiency of data acquisition.

[0977] "Terminal means" refers to a device or function that allows a user to send a request via the company's internal network.

[0978] A "server means" is a device or function that receives a request, parses it, and accesses the appropriate database.

[0979] "Means of retrieving relevant data from a database" refers to a device or function that retrieves the necessary data from a database based on an analyzed request.

[0980] A "generative AI model" is an artificial intelligence model that generates data in a specified format based on acquired data.

[0981] "Emotional analysis means" refers to a device or function that analyzes a user's emotional information.

[0982] "Means of including user sentiment information in a request" refers to a device or function that adds analyzed sentiment information to a request.

[0983] "Means for verification and formatting" refers to a device or function that checks the output data obtained from the generated AI model and formats it into the required format.

[0984] "Means of adjusting data" refers to a device or function that adjusts the content and tone of data generated based on the user's emotional information.

[0985] A "user" refers to an individual or organization that uses the system to generate data.

[0986] The system according to the present invention includes terminal means for sending requests via an internal network, server means for receiving and analyzing requests, means for acquiring relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI model to generate data in a specified format, means for returning the generated data to the user, and sentiment analysis means for analyzing the user's emotional information. This system enables the safe and efficient use of internal company data, and further, enables the generation of data that takes user emotions into consideration.

[0987] The server receives the request and uses a data analysis module to verify the user information and request details of the requester. For example, if an employee in the marketing department sends a request to create a report on the next marketing strategy, the server receives and analyzes it. Specific conditions include "trend analysis based on sales data and customer feedback from the past year, and proposals for a new marketing strategy."

[0988] When a user enters a request, the terminal's emotion engine analyzes the user's current emotion information, adds the results to the request information, and sends it to the server. This process improves the accuracy of the data the server receives because the user's emotion information is included in the request.

[0989] The server then generates an appropriate database query, such as "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'", to retrieve the necessary data from the internal database. The retrieved data is then loaded into memory.

[0990] Generative AI models (such as pre-trained models like GPT-3) generate reports or text data in a specified format based on the acquired data. The generation process also considers user sentiment, enabling more accurate data generation. For example, it can generate a "proposal for the next marketing strategy based on sales data and customer feedback."

[0991] The server checks the generated data with a validation module to verify the consistency of the text and the format of the data. Corrections are made as needed, and final formatting is performed. The tone and content of the data are also adjusted based on sentiment information.

[0992] Finally, the server sends the completed data to the user's terminal. For example, it might convert the generated report to PDF format and send it using a secure communication protocol (HTTPS). The terminal receives the data and displays it for the user to review. The user can then download and further edit it.

[0993] Specific example

[0994] User: A marketing department employee submits a request to create a report on the next marketing strategy. The request includes specific requirements such as "trend analysis based on sales data and customer feedback from the past year, and a proposal for a new marketing strategy."

[0995] Terminal: Enter the request details on the screen and click the send button. In addition to the request information, the terminal also sends positive sentiment information analyzed by the sentiment engine to the server.

[0996] Server: Processes the received request and verifies that it originates from the marketing department. Next, it generates a database query and prepares to access the relevant database. The specific query executed is "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'".

[0997] Generative AI Model: Based on acquired data, it generates the next marketing strategy report. The generated report includes suggestions that reflect positive sentiment information.

[0998] Server: Validates the generated data, makes corrections and formatting as needed, and then sends it to the user's terminal.

[0999] This system enables the efficient and secure use of internal company data, as well as the generation of data that takes user sentiment into consideration.

[1000] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1001] Step 1:

[1002] User: Create a request to generate data necessary for your work. The input should include text detailing the specific data requirements and needs. For example, "I would like a report on our next marketing strategy. I need sales data and customer feedback analysis for the past year."

[1003] Step 2:

[1004] Terminal: Receives request information entered by the user and analyzes the user's current sentiment using the sentiment engine. The results of this analysis are added to the request data. The output generates request data containing the user's conditions and sentiment information.

[1005] Step 3:

[1006] Terminal: Sends request data to the server. Input is the request data, and output is confirmation information for the sent request.

[1007] Step 4:

[1008] Server: Receives requests on the receiving port. Input is the request data, and output is the data to be transferred to the data analysis module.

[1009] Step 5:

[1010] Server: The data analysis module analyzes the request data and extracts user information, request details, and sentiment information. The input is the request data, and the output is the extracted user information and conditions.

[1011] Step 6:

[1012] Server: Generates appropriate database queries based on extracted user information and conditions. Specifically, it generates SQL queries like "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'". The input is user information and conditions, and the output is the database query.

[1013] Step 7:

[1014] Server: Executes database queries and retrieves relevant data from the database. The input is the database query, and the output is the retrieved data.

[1015] Step 8:

[1016] Server: Passes the acquired data to a generation AI model (e.g., GPT-3) to generate reports or text data in the specified format. The input consists of the acquired data and user sentiment information, and the output is the generated report.

[1017] Step 9:

[1018] Server: The generated report is checked by a validation module and formatted. The input is the generated report, and the output is the formatted report.

[1019] Step 10:

[1020] Server: Adjusts the tone and content of the data based on user sentiment information as needed. Inputs include formatted reports and sentiment information, and output is a finalized report.

[1021] Step 11:

[1022] Server: Sends the completed report to the user's terminal. The input is the finalized report, and the output is confirmation information for sending the report.

[1023] Step 12:

[1024] Terminal: Displays received reports for user review. For example, it displays received reports in PDF format. The input is the finalized report, and the output is the displayed report.

[1025] (Application Example 2)

[1026] Next, we will explain application example 2. In the following explanation, 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."

[1027] Conventional factory management systems often involve manual collection and analysis of robot operating status and maintenance information, resulting in inefficiency. Furthermore, they fail to provide appropriate information tailored to the manager's mood and circumstances, making emergency response difficult. Therefore, a system is needed that efficiently and quickly monitors robot operating status, automates the acquisition, analysis, and report generation of necessary data.

[1028] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1029] In this invention, the server includes means for an emotion engine that recognizes the user's emotions, means for obtaining relevant information from a database based on the analyzed request, and means for passing the obtained information to a generation AI model and generating data while taking the emotion information into consideration. This enables efficient and rapid data generation and report provision that takes the user's emotions into consideration.

[1030] An "internal network" is a communication infrastructure used within a company or organization, enabling various terminals and servers to exchange data with each other.

[1031] A "request" is a request sent to a server by a user for the purpose of obtaining the data or information they need.

[1032] "Device" refers to equipment or equipment designed to perform a specific purpose. In this context, it includes the means of sending a request.

[1033] The term "computer" refers to an electronic device that performs data analysis, processing, storage, and communication, and in this context, it includes servers that receive and analyze requests.

[1034] A "database" is a collection of information that systematically organizes and stores related data, making it quickly searchable and usable when needed.

[1035] A "generative AI model" is an artificial intelligence model that uses a pre-trained algorithm to automatically generate data in a specified format.

[1036] An "emotion engine" is a software module that analyzes the user's emotions and adjusts the system's operation and output data based on the results.

[1037] "Information" refers to data obtained from databases or necessary data requested by users.

[1038] "Formatting" refers to the process of organizing and formatting generated data to conform to a predetermined format or standard.

[1039] "Verification" refers to the process of checking whether the data output from a generated AI model is accurate.

[1040] This system is implemented using the following hardware and software. The hardware includes smartphones, tablets, factory robots, various sensor networks, and servers. The software includes Python, TensorFlow or PyTorch, OpenAI GPT, and an emotion engine. The following describes how each piece of hardware and software functions.

[1041] Send a request

[1042] Users request reports of necessary data using their smartphones or tablets. For example, they might issue a voice command such as, "Please create a report on the forecast for the next maintenance and the current parts inventory status." This request is sent to the server in real time via the company network. User sentiment information is also sent along with the request and analyzed by the sentiment engine.

[1043] Receiving and parsing requests

[1044] The server analyzes incoming requests and determines the optimal database for retrieving information based on the request's content. It also analyzes emotional information transmitted from the user's device and optimizes the data generation process based on the results.

[1045] Data acquisition

[1046] The server generates database queries and retrieves necessary data in real time from the company's internal database and the factory's sensor network. For example, it collects data such as the operating status and maintenance history of specific robots, and the inventory status of parts.

[1047] Data generation

[1048] The server passes the acquired data to OpenAI GPT, an AI model for generating reports, which then generate reports in the specified format. In this process, user sentiment information is taken into consideration, and the urgency and conciseness of the information are optimized.

[1049] Data validation and formatting

[1050] The server validates the generated report data and formats it into the required format. It verifies the accuracy of the data output from the generating AI model and adjusts the data based on sentiment information.

[1051] Return to user

[1052] Finally, the server sends the completed report back to the user's terminal. The user receives this report and uses it to develop factory operations and maintenance plans.

[1053] Specific example

[1054] For example, a factory engineer might make the following voice request:

[1055] "Please provide an urgent report on the expected next maintenance schedule and parts inventory status. Our engineers are currently under pressure."

[1056] This request is sent to the server, which retrieves the necessary data, and if the sentiment engine determines that "the engineer is feeling anxious," a concise report is quickly generated for review. This report provides the necessary information concisely and quickly, such as "Next scheduled maintenance date: October 15, 2023, Parts inventory: Sufficient."

[1057] This system significantly improves efficiency and accuracy compared to conventional manual processing, and can support factory operations.

[1058] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1059] Step 1:

[1060] Users request reports of necessary data using their smartphones or tablets.

[1061] Specific operation: The user issues a voice command such as, "Please create a report on the expected next maintenance and parts inventory status." The voice is converted to text and then sent to the server via the company network.

[1062] Input: User's voice request and sentiment information.

[1063] Output: Request and sentiment information converted to text format.

[1064] Step 2:

[1065] The server analyzes the received request and sentiment information to determine which database to retrieve the information from.

[1066] Specific operation: The server analyzes the request and determines which robots and sensors to collect data from. Additionally, the emotion engine analyzes the user's emotional information and optimizes the data generation process.

[1067] Input: Request and sentiment information converted to text format.

[1068] Output: Generation of database queries.

[1069] Step 3:

[1070] The server uses generated database queries to retrieve necessary data from the company's internal database and sensor network.

[1071] Specific operation: The server generates appropriate database queries to collect data such as the operating status of various sensors and robots within the factory, maintenance history, and parts inventory data.

[1072] Input: Database query.

[1073] Output: Acquired data (operating status data, maintenance data, parts inventory data, etc.).

[1074] Step 4:

[1075] The server passes the acquired data to a generation AI model, which then generates a report in the specified format.

[1076] Specific operation: The collected data is input into a generative AI model such as OpenAI GPT, and prompts are used to generate a report in the format requested by the user. The report content is optimized by also considering the results of the sentiment engine.

[1077] Input: Prompt text based on acquired data and sentiment information.

[1078] Output: Generated report data.

[1079] Step 5:

[1080] The server verifies the generated report data and formats it into the required format.

[1081] Specific actions: Verify the report data output from the generated AI model and check for errors. If necessary, correct or supplement the data and format it into the specified format.

[1082] Input: Generated report data.

[1083] Output: Formatted final report data.

[1084] Step 6:

[1085] The server sends the final report data back to the user's terminal.

[1086] Specific action: The completed report will be sent to the user's smartphone or tablet so that they can view it immediately.

[1087] Input: Formatted final report data.

[1088] Output: Sending report data to the user's terminal.

[1089] In this way, data processing and calculations are performed at each step, making it possible to generate and provide optimal reports that meet the user's requirements.

[1090] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1091] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1092] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1093] [Fourth Embodiment]

[1094] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1095] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1096] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1097] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1098] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1099] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1100] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1101] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1102] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1103] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1104] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1105] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1106] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1107] The system according to the present invention allows users in each department to send requests via the company's internal network, a server to process those requests, and a generative AI module to generate the specified data. This system enables the efficient generation of necessary data while preventing the leakage of internal company data.

[1108] Explanation of the program's processing

[1109] Send a request

[1110] Users: Users in each department send requests via the company network to generate the data they need for their work. These requests include specific conditions about what data is required.

[1111] Terminal: Sends a request to the server, including the user's department information. This information is used by the server to determine which database to access.

[1112] Receiving and parsing requests

[1113] Server: Analyzes the received request and verifies the user information and content of the request. Based on the user's department information, it determines which database to retrieve the data from.

[1114] Data acquisition

[1115] Server: Generates database queries and accesses internal databases to retrieve necessary data. For example, it might retrieve sales data or customer feedback data from the past year.

[1116] Data generation

[1117] Server: Passes the acquired data to a generative AI module to generate the necessary text data. This AI module uses a pre-trained model to generate data in the specified format.

[1118] Data validation and formatting

[1119] Server: Validates and formats the generated data. It verifies that the generated data meets the specified standards and makes additional corrections if necessary.

[1120] Return to user

[1121] Server: Returns the verified and formatted data to the user's terminal. The user receives the generated data and uses it in their work.

[1122] Specific example

[1123] Sending and receiving requests

[1124] The user (a marketing department employee) requests a report on the next marketing strategy. The request details that the report should include a trend analysis based on sales data and customer feedback from the past year, and a proposal for a new marketing strategy.

[1125] The device sends this request to the server.

[1126] Request parsing and data retrieval

[1127] The server receives the request and verifies that it originates from the marketing department. It then generates a database query to retrieve the necessary data from the internal database, specifically, sales data and customer feedback from the past year.

[1128] Data generation and return

[1129] The server passes the acquired data to a generative AI module to generate the necessary report. The generated report is verified and formatted, and finally sent back to the user's terminal.

[1130] The user reviews the returned report, makes revisions as needed, and proposes it as the final marketing strategy.

[1131] Thus, the system of the present invention can safely and efficiently utilize internal company data and support the operations of each department.

[1132] The following describes the processing flow.

[1133] Step 1:

[1134] A user sends a request from their device to the server via the company network, stating, "Please generate the data necessary for the new product project proposal." The request includes detailed conditions.

[1135] Step 2:

[1136] The terminal receives the request and sends it to the server. The request includes the user's department information.

[1137] Step 3:

[1138] The server receives the request and analyzes the request content and the user's department information. It then determines which database to access.

[1139] Step 4:

[1140] The server generates database queries and accesses the internal database to retrieve the necessary data. For example, it might use queries to retrieve sales data or customer feedback data from the past year.

[1141] Step 5:

[1142] The server temporarily stores the data it acquires and then passes that data to the generative AI module.

[1143] Step 6:

[1144] The server calls a generative AI module to generate the necessary text data based on the acquired data. In this process, the data is generated in a format that matches the user's request.

[1145] Step 7:

[1146] The server receives the generated text data and performs verification. It checks whether the text data meets the specified criteria.

[1147] Step 8:

[1148] The server formats the generated text data as needed, making it easy for users to use.

[1149] Step 9:

[1150] The server returns the completed text data to the user's terminal.

[1151] Step 10:

[1152] Users review the data received on their devices and use it for their work. They make minor adjustments to the data as needed and use it as the final document.

[1153] This series of steps enables the efficient and secure use of internal data to support users' work.

[1154] (Example 1)

[1155] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1156] To ensure the efficient and secure use of internal data and support users' operations, a system is needed that can respond to requests from multiple departments and generate appropriate data. However, traditional methods require considerable time and effort for request analysis, data acquisition, and data formatting, leading to decreased operational efficiency. Furthermore, from a data security perspective, measures to prevent the leakage of internal data are required.

[1157] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1158] In this invention, the server includes means for receiving and analyzing requests, means for obtaining relevant information from a database, means for passing data to a generative AI module to generate data in a specified format, and means for verifying and formatting the generated data. This enables efficient and secure utilization of internal company data, and allows users to quickly obtain the data necessary for their work.

[1159] An "internal network" is a closed network used to connect computers and other devices within a company, and serves as a means of sharing information and transmitting data.

[1160] A "request" is an instruction or request that a user sends to a server to ask it to generate specific data or provide information.

[1161] "Terminal means" refers to computers, mobile devices, and other devices used by users to create and send requests.

[1162] "Server system" refers to a centralized computer system for receiving and analyzing requests, and for generating and providing the necessary data.

[1163] "Analyzing" refers to understanding the content of a received request and extracting the necessary information and processing details.

[1164] A "database" is a system for systematically storing and managing information, allowing for efficient searching and retrieval of necessary data.

[1165] "Related information" refers to specific data or information retrieved from the database based on a request.

[1166] A "generative AI module" is a software module that uses a pre-trained artificial intelligence model to generate data based on a specific format or content.

[1167] "Verification" refers to the process of checking whether the generated data meets the required specifications and standards.

[1168] "Formatting" refers to the process of arranging generated data into a predetermined format or style.

[1169] A "user" refers to an individual or departmental member who uses the system to request data generation or information provision.

[1170] The system according to the present invention allows users in each department to send requests via the company's internal network, a server to process those requests, and a generative AI module to generate the specified data. This system enables the efficient generation of necessary data while preventing the leakage of internal company data.

[1171] Send a request

[1172] Users: Users in each department create requests using a dedicated client application to generate the data they need for their work. For example, an employee in the marketing department might create a request for a "report on the next marketing strategy" and enter specific criteria (sales data and customer feedback from the past year).

[1173] Terminal: Sends request data to the server. This request data includes a user ID and department information to identify which department the request originated from.

[1174] Receiving and parsing requests

[1175] Server: Parses incoming requests. Checks request metadata to determine which department the user belongs to. Analyzes the request content to determine what type of data is needed. For example, if "sales data for the past year" and "customer feedback data" are requested, it identifies the corresponding database tables. It uses Python parser modules to extract each field for parsing.

[1176] Data acquisition

[1177] Server: Generates database queries based on the analysis results. For example, it generates SQL statements to access internal databases (e.g., PostgreSQL or MySQL) and retrieve the necessary data. The retrieved data is used for filtering (e.g., by date range or specific customer group). SQLAlchemy is used for database queries, and the results are converted into a data frame (e.g., pandas).

[1178] Data generation

[1179] Server: Passes the acquired data to a generative AI module. This AI module (e.g., GPT-4) uses a pre-trained model to generate data according to specific format requirements. For example, it creates the framework of a requested report and fills in the details based on the acquired data. It calls an AI API (e.g., OpenAI API), inputs data along with prompts, and receives the generated text.

[1180] Data validation and formatting

[1181] Server: Validates the generated data to ensure it meets the specified criteria. For example, it checks for typographical errors in the generated report, ensures all necessary information is included, and verifies the report's formatting. The validation process uses natural language processing (NLP) tools (e.g., spaCy) to perform text analysis. If necessary, it formats the text and creates the final report. It uses text processing libraries (e.g., re, textblob) to correct and format the text.

[1182] Return to user

[1183] Server: Returns the validated and formatted data to the user's terminal. The generated data is returned in a user-friendly format (e.g., PDF, Excel file). Appropriate libraries (e.g., ReportLab for PDF generation, openpyxl for Excel file generation) are used to convert to the appropriate file format.

[1184] Terminal: The user's terminal displays data received from the server, allowing the user to review it. The user reviews the generated report and performs further analysis or corrections as needed.

[1185] Example of a prompt

[1186] "Please generate a report that proposes the next marketing strategy based on sales data and customer feedback from the past year."

[1187] In this way, the system of the present invention can safely and efficiently utilize internal company data and support the operations of each department.

[1188] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1189] Step 1:

[1190] Users: Each department's users create requests using a dedicated client application and send them over the company network. Requests include the required data types and conditions (e.g., sales data and customer feedback for the past year).

[1191] Input: Data request specified by the user (e.g., marketing report).

[1192] Output: Request data sent from the terminal to the server.

[1193] Step 2:

[1194] Terminal: The terminal sends requests created by the user to the server. At the same time, metadata such as the user's department information is also sent.

[1195] Input: User-created request data.

[1196] Output: Request data, including user department information, is sent to the server.

[1197] Step 3:

[1198] Server: The server parses the received request. First, it checks the request metadata to determine the user's department. Then, it parses the request content to identify the necessary data types. For example, it might use a Python parser module to extract each field.

[1199] Input: Request data.

[1200] Output: Analysis results (required data types, acquisition conditions, etc.).

[1201] Step 4:

[1202] Server: Generates database queries based on the analysis results. For example, it generates SQL statements to access internal databases (e.g., PostgreSQL or MySQL) and retrieve the necessary data. Specifically, it uses SQLAlchemy to execute queries and converts the results into a data frame (e.g., pandas).

[1203] Input: Analysis results (required data types, acquisition conditions, etc.).

[1204] Output: Required data (e.g., sales data, customer feedback data).

[1205] Step 5:

[1206] Server: Passes the acquired data to a generative AI module. This module (e.g., GPT-4) generates data according to specific format requirements. For example, it calls an AI API (e.g., OpenAI API), inputs a prompt and data, and retrieves the generated text.

[1207] Input: Retrieved data, prompt text.

[1208] Output: Generated text data (e.g., marketing report).

[1209] Step 6:

[1210] Server: Validates and formats the generated data. Performs text analysis using Natural Language Processing (NLP) tools (e.g., spaCy) and makes necessary corrections and formatting. Performs formatting using text processing libraries (e.g., re, textblob).

[1211] Input: Generated text data.

[1212] Output: Validated and formatted final data.

[1213] Step 7:

[1214] Server: Returns the verified and formatted data to the user's terminal. The generated data is returned in user-friendly formats such as PDF and Excel files. Specific examples include using ReportLab for PDF generation and openpyxl for Excel file generation.

[1215] Input: Validated and formatted data.

[1216] Output: The final data sent back to the user's terminal.

[1217] Step 8:

[1218] Terminal: The user's terminal displays the data received from the server, allowing the user to review it. The user reviews the generated data and performs further analysis or corrections as needed.

[1219] Input: Final data from the server.

[1220] Output: Data displayed on the user's device.

[1221] (Application Example 1)

[1222] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1223] Conventional data management systems in logistics centers have problems such as difficulty in providing information in real time, time-consuming data acquisition and generation, and decreased efficiency on site. Furthermore, the lack of means for on-site workers to receive real-time inventory management and efficient delivery route suggestions leads to delays and errors in operations. This invention aims to solve these problems by providing a system that uses smart devices to improve work efficiency and provide information in real time.

[1224] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1225] In this invention, the server includes terminal means for transmitting requests via the company network, server means for receiving and analyzing requests, means for obtaining relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI module and generating data in a specified format, means for returning the generated data to the user and providing information in real time, and means for field workers to receive real-time inventory management and delivery route suggestions using a smart device. This enables field workers at a logistics center to obtain necessary information in real time via a smart device and perform their work quickly and accurately.

[1226] An "internal network" is a network intended for information communication within a company or organization.

[1227] A "request" refers to a request for data or information submitted by a user.

[1228] "Terminal means" refers to devices or equipment used to send requests.

[1229] "Server means" refers to a server that has the function of receiving and analyzing requests.

[1230] "Analysis" refers to understanding the content of a received request and identifying the necessary processing.

[1231] A "database" refers to a data structure or system used to efficiently manage and retrieve information.

[1232] A "generative AI module" is a module that uses artificial intelligence to generate data in a specified format.

[1233] "Real-time" refers to the processing and provision of data and information almost instantaneously.

[1234] A "smart device" refers to an advanced device that can connect to the internet and has a variety of functions.

[1235] "Field workers" refers to people who perform physical tasks at sites such as logistics centers.

[1236] "Inventory management" refers to the task of checking and managing the quantity and condition of products in stock.

[1237] "Delivery route" refers to the optimal path for delivering goods.

[1238] "Information provision" refers to supplying users with necessary data and information.

[1239] This invention provides a real-time information provision system for logistics centers. Specifically, it relates to a system that allows on-site workers to receive inventory management and efficient delivery route suggestions using smart devices. The embodiments of this system are described in detail below.

[1240] Program generation

[1241] The server includes terminal means for sending requests via the company network, server means for receiving and analyzing requests, means for obtaining relevant data from a database based on the analyzed requests, means for passing the obtained data to a generation AI module and generating data in a specified format, means for returning the generated data to the user and providing information in real time, and means for field workers to receive real-time inventory management and delivery route suggestions using smart devices.

[1242] Explanation of the process

[1243] The terminal receives requests sent by field workers via smart devices. These requests may include, for example, "Tell me the next receiving operation" or "Suggest the best delivery route." These requests are sent to the server via the company network.

[1244] The server analyzes the received request to determine which department the user belongs to. Next, it retrieves the necessary data from the corresponding database. Examples of such data include inventory data and past delivery history.

[1245] The acquired data is passed to a generative AI module, which generates data in the specified format. The generative AI module uses advanced AI models such as GPT-3 to generate data according to the user's request.

[1246] The generated data is verified and formatted by the server and sent back to the user in real time. Field workers can then review the generated data via smart devices and proceed with their work efficiently.

[1247] Hardware and software to use

[1248] This system uses smart eyewear such as Google Glass and Vuzix as smart devices. It also uses Wi-Fi and 5G networks for data transmission and reception. The server provides API endpoints using the Flask framework, and the generative AI module uses the OpenAI API.

[1249] Specific example

[1250] For example, if a field worker issues a voice command via a smart device saying, "Tell me the next receiving task," the device sends this request to the server. The server analyzes the request, retrieves the necessary inventory data from the database, and passes it to a generative AI module. The generative AI module generates an instruction such as, "The next receiving task is for product X, shelf A," and the server sends this back to the field worker's smart device in real time.

[1251] Example of a prompt:

[1252] "Generate a logistics report based on the following data: 'Inventory Data'"

[1253] "Suggest optimal delivery routes for the following locations: 'Delivery destination A, Delivery destination B, Delivery destination C'"

[1254] In this way, on-site workers at the logistics center can obtain the necessary information in real time and perform their tasks quickly and accurately.

[1255] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1256] Step 1:

[1257] Users send requests via smart devices. Users input requests using voice commands or touch controls, such as "Tell me about the next receiving operation" or "Suggest the best delivery route." The entered requests are sent from the terminal to the server via the company network.

[1258] Input: Request details (e.g., "Please tell me the next receiving procedure.")

[1259] Output: Request sent to the server

[1260] Step 2:

[1261] The server analyzes the received request. Specifically, it analyzes the user's department information and the request content to determine which database to retrieve which data from. Natural language processing technology is used for the analysis.

[1262] Input: Submitted request, user's department information

[1263] Output: Database query (Example: Query to retrieve inventory data)

[1264] Step 3:

[1265] The server accesses the database based on the analysis results and retrieves relevant data. For example, in response to a request for "the next receiving operation," it queries the inventory management database to retrieve product information.

[1266] Input: Database query

[1267] Output: Acquired data (e.g., inventory data, product information)

[1268] Step 4:

[1269] The server passes the acquired data to a generative AI module, which generates data in the specified format. The generative AI module uses OpenAI APIs and other tools to generate optimal instructions and reports in response to the request.

[1270] Input: Acquired data

[1271] Output: Generated data (Example: "The next receiving operation is for product X, shelf A")

[1272] Step 5:

[1273] The server verifies and formats the generated data. In particular, it checks that the generated data is in the correct format and free of errors. It makes corrections as needed and finalizes it.

[1274] Input: Generated data

[1275] Output: Validated and formatted data

[1276] Step 6:

[1277] The server returns the verified and formatted data to the user's device. The user can then view this data in real time via their smart device and use it as instructions to proceed with their work.

[1278] Input: Validated and formatted data

[1279] Output: Data sent back to the user's terminal

[1280] The following example prompts are used as concrete examples of the actions:

[1281] Example 1: "Generate a logistics report based on the following data: 'Inventory data'"

[1282] Example 2: "Suggest optimal delivery routes for the following locations: 'Delivery destination A, Delivery destination B, Delivery destination C'"

[1283] This will enable on-site workers at logistics centers to obtain necessary information in real time and perform their tasks efficiently.

[1284] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1285] The system according to the present invention includes terminal means for sending requests via an internal network, server means for receiving and analyzing requests, means for acquiring relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI module to generate data in a specified format, means for returning the generated data to the user, and an emotion engine for recognizing the user's emotions. This system enables the safe and efficient use of internal company data, and further, enables the generation of data that takes the user's emotions into consideration.

[1286] Explanation of the program's processing

[1287] Send a request

[1288] Users: Users in each department send requests via the company network to generate the data they need for their work. These requests include specific conditions about what data is required.

[1289] Terminal: Sends a request to the server, including the user's department information and the user's sentiment information analyzed by the sentiment engine. This information is used by the server to determine which database to access and to provide highly accurate generated data.

[1290] Receiving and parsing requests

[1291] Server: Analyzes the received request and verifies the user information and content of the request. Based on the user's sentiment information and departmental information, it decides which database to retrieve the data from.

[1292] Data acquisition

[1293] Server: Generates database queries and accesses the internal database to retrieve necessary data. For example, it might use queries to retrieve sales data or customer feedback data from the past year.

[1294] Data generation

[1295] Server: Passes the acquired data to a generative AI module, which generates the necessary text data. This AI module uses a pre-trained model to generate data in the specified format. Furthermore, it executes the generation process while also considering the user's sentiment information provided by the sentiment engine.

[1296] Data validation and formatting

[1297] Server: Validates and formats the generated data. Checks if the generated data meets the specified standards and makes additional corrections if necessary. Also adjusts the data based on sentiment information.

[1298] Return to user

[1299] Server: Returns the completed text data to the user's terminal. The data, which also takes sentiment information into account, is provided in a way that best meets the user's needs.

[1300] Specific example

[1301] Sending and receiving requests

[1302] The user (a marketing department employee) requests a report on the next marketing strategy. The request details that it should include a trend analysis based on sales data and customer feedback from the past year, followed by a proposal for a new marketing strategy. Furthermore, the emotion engine detects the user's positive emotions.

[1303] The device sends this request to the server.

[1304] Request parsing and data retrieval

[1305] The server receives the request and verifies that it originates from the marketing department. It then generates a database query to retrieve the necessary data from the internal database, specifically, sales data and customer feedback from the past year.

[1306] Data generation and return

[1307] The server passes the acquired data to a generative AI module to generate the necessary reports. The generated reports are validated and formatted, and finally sent back to the user's device, including suggestions that reflect the user's positive emotions.

[1308] The user reviews the returned report, makes revisions as needed, and proposes it as the final marketing strategy.

[1309] The system of this invention efficiently and securely utilizes internal company data and generates data that also takes user emotions into consideration, thereby providing advanced support for the operations of each department.

[1310] The following describes the processing flow.

[1311] Step 1:

[1312] A user sends a request from their device via the company network, stating, "I would like to create a report on the next marketing strategy." The request includes detailed conditions, such as "Please conduct a trend analysis based on sales data and customer feedback from the past year, and propose a new marketing strategy."

[1313] Step 2:

[1314] The terminal receives the request and sends it to the server. The request includes the user's departmental information and the user's emotional information analyzed by the emotion engine.

[1315] Step 3:

[1316] The server receives the request and analyzes the request content, the user's department information, and sentiment information. It then determines which database to access.

[1317] Step 4:

[1318] The server generates database queries and accesses the internal database to retrieve the necessary data. Specifically, it retrieves sales data and customer feedback data for the past year using queries.

[1319] Step 5:

[1320] The server temporarily stores the acquired data and passes it to the emotion engine for analysis, which correlates it with the user's emotions. Based on these results, adjustments are made to reflect the changes in the generated data.

[1321] Step 6:

[1322] The server passes the acquired data and the analysis results from the emotion engine to the generative AI module, which then generates the necessary text data. For example, if a positive emotion is detected in the user, it generates a report that reflects that emotion.

[1323] Step 7:

[1324] The server receives the generated text data and performs validation. It checks whether the generated data meets the specified standards and makes additional corrections if necessary. It also formats the data appropriately to reflect the user's sentiment information.

[1325] Step 8:

[1326] The server returns the completed text data to the user's terminal.

[1327] Step 9:

[1328] The user reviews the data received on their device and uses it for work. They review the generated reports, make corrections as needed, and propose them as the final marketing strategy.

[1329] This entire process makes it possible to generate data that takes user emotions into account, enabling the efficient creation of highly accurate proposals.

[1330] (Example 2)

[1331] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1332] Conventional data generation systems, while capable of responding quickly and accurately to user requests, faced the challenge of generating data that took user sentiment into account. This made it difficult to provide data that best met user needs. Furthermore, the lack of efficient methods for retrieving data from databases suitable for specific departments resulted in challenges regarding the accuracy and efficiency of data acquisition.

[1333] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an emotion analysis means, a means for including the user's emotion information, and a means for verifying and formatting the output data obtained from the generated AI model and adjusting the data based on the user's emotion information. This makes it possible to generate data while taking the user's emotion information into consideration, and to provide data that is optimally suited to the user's needs. In addition, it is possible to efficiently acquire data from a database suitable for a specific department, improving the accuracy and efficiency of data acquisition.

[1334] "Terminal means" refers to a device or function that allows a user to send a request via the company's internal network.

[1335] A "server means" is a device or function that receives a request, parses it, and accesses the appropriate database.

[1336] "Means of retrieving relevant data from a database" refers to a device or function that retrieves the necessary data from a database based on an analyzed request.

[1337] A "generative AI model" is an artificial intelligence model that generates data in a specified format based on acquired data.

[1338] "Emotional analysis means" refers to a device or function that analyzes a user's emotional information.

[1339] "Means of including user sentiment information in a request" refers to a device or function that adds analyzed sentiment information to a request.

[1340] "Means for verification and formatting" refers to a device or function that checks the output data obtained from the generated AI model and formats it into the required format.

[1341] "Means of adjusting data" refers to a device or function that adjusts the content and tone of data generated based on the user's emotional information.

[1342] A "user" refers to an individual or organization that uses the system to generate data.

[1343] The system according to the present invention includes terminal means for sending requests via an internal network, server means for receiving and analyzing requests, means for acquiring relevant data from a database based on the analyzed requests, means for passing the acquired data to a generation AI model to generate data in a specified format, means for returning the generated data to the user, and sentiment analysis means for analyzing the user's emotional information. This system enables the safe and efficient use of internal company data, and further, enables the generation of data that takes user emotions into consideration.

[1344] The server receives the request and uses a data analysis module to verify the user information and request details of the requester. For example, if an employee in the marketing department sends a request to create a report on the next marketing strategy, the server receives and analyzes it. Specific conditions include "trend analysis based on sales data and customer feedback from the past year, and proposals for a new marketing strategy."

[1345] When a user enters a request, the terminal's emotion engine analyzes the user's current emotion information, adds the results to the request information, and sends it to the server. This process improves the accuracy of the data the server receives because the user's emotion information is included in the request.

[1346] The server then generates an appropriate database query, such as "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'", to retrieve the necessary data from the internal database. The retrieved data is then loaded into memory.

[1347] Generative AI models (such as pre-trained models like GPT-3) generate reports or text data in a specified format based on the acquired data. The generation process also considers user sentiment, enabling more accurate data generation. For example, it can generate a "proposal for the next marketing strategy based on sales data and customer feedback."

[1348] The server checks the generated data with a validation module to verify the consistency of the text and the format of the data. Corrections are made as needed, and final formatting is performed. The tone and content of the data are also adjusted based on sentiment information.

[1349] Finally, the server sends the completed data to the user's terminal. For example, it might convert the generated report to PDF format and send it using a secure communication protocol (HTTPS). The terminal receives the data and displays it for the user to review. The user can then download and further edit it.

[1350] Specific example

[1351] User: A marketing department employee submits a request to create a report on the next marketing strategy. The request includes specific requirements such as "trend analysis based on sales data and customer feedback from the past year, and a proposal for a new marketing strategy."

[1352] Terminal: Enter the request details on the screen and click the send button. In addition to the request information, the terminal also sends positive sentiment information analyzed by the sentiment engine to the server.

[1353] Server: Processes the received request and verifies that it originates from the marketing department. Next, it generates a database query and prepares to access the relevant database. The specific query executed is "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'".

[1354] Generative AI Model: Based on acquired data, it generates the next marketing strategy report. The generated report includes suggestions that reflect positive sentiment information.

[1355] Server: Validates the generated data, makes corrections and formatting as needed, and then sends it to the user's terminal.

[1356] This system enables the efficient and secure use of internal company data, as well as the generation of data that takes user sentiment into consideration.

[1357] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1358] Step 1:

[1359] User: Create a request to generate data necessary for your work. The input should include text detailing the specific data requirements and needs. For example, "I would like a report on our next marketing strategy. I need sales data and customer feedback analysis for the past year."

[1360] Step 2:

[1361] Terminal: Receives request information entered by the user and analyzes the user's current sentiment using the sentiment engine. The results of this analysis are added to the request data. The output generates request data containing the user's conditions and sentiment information.

[1362] Step 3:

[1363] Terminal: Sends request data to the server. Input is the request data, and output is confirmation information for the sent request.

[1364] Step 4:

[1365] Server: Receives requests on the receiving port. Input is the request data, and output is the data to be transferred to the data analysis module.

[1366] Step 5:

[1367] Server: The data analysis module analyzes the request data and extracts user information, request details, and sentiment information. The input is the request data, and the output is the extracted user information and conditions.

[1368] Step 6:

[1369] Server: Generates appropriate database queries based on extracted user information and conditions. Specifically, it generates SQL queries like "SELECT FROM sales_data WHERE date >= '2022-01-01' AND date <= '2022-12-31'". The input is user information and conditions, and the output is the database query.

[1370] Step 7:

[1371] Server: Executes database queries and retrieves relevant data from the database. The input is the database query, and the output is the retrieved data.

[1372] Step 8:

[1373] Server: Passes the acquired data to a generation AI model (e.g., GPT-3) to generate reports or text data in the specified format. The input consists of the acquired data and user sentiment information, and the output is the generated report.

[1374] Step 9:

[1375] Server: The generated report is checked by a validation module and formatted. The input is the generated report, and the output is the formatted report.

[1376] Step 10:

[1377] Server: Adjusts the tone and content of the data based on user sentiment information as needed. Inputs include formatted reports and sentiment information, and output is a finalized report.

[1378] Step 11:

[1379] Server: Sends the completed report to the user's terminal. The input is the finalized report, and the output is confirmation information for sending the report.

[1380] Step 12:

[1381] Terminal: Displays received reports for user review. For example, it displays received reports in PDF format. The input is the finalized report, and the output is the displayed report.

[1382] (Application Example 2)

[1383] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1384] Conventional factory management systems often involve manual collection and analysis of robot operating status and maintenance information, resulting in inefficiency. Furthermore, they fail to provide appropriate information tailored to the manager's mood and circumstances, making emergency response difficult. Therefore, a system is needed that efficiently and quickly monitors robot operating status, automates the acquisition, analysis, and report generation of necessary data.

[1385] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1386] In this invention, the server includes means for an emotion engine that recognizes the user's emotions, means for obtaining relevant information from a database based on the analyzed request, and means for passing the obtained information to a generation AI model and generating data while taking the emotion information into consideration. This enables efficient and rapid data generation and report provision that takes the user's emotions into consideration.

[1387] An "internal network" is a communication infrastructure used within a company or organization, enabling various terminals and servers to exchange data with each other.

[1388] A "request" is a request sent to a server by a user for the purpose of obtaining the data or information they need.

[1389] "Device" refers to equipment or equipment designed to perform a specific purpose. In this context, it includes the means of sending a request.

[1390] The term "computer" refers to an electronic device that performs data analysis, processing, storage, and communication, and in this context, it includes servers that receive and analyze requests.

[1391] A "database" is a collection of information that systematically organizes and stores related data, making it quickly searchable and usable when needed.

[1392] A "generative AI model" is an artificial intelligence model that uses a pre-trained algorithm to automatically generate data in a specified format.

[1393] An "emotion engine" is a software module that analyzes the user's emotions and adjusts the system's operation and output data based on the results.

[1394] "Information" refers to data obtained from databases or necessary data requested by users.

[1395] "Formatting" refers to the process of organizing and formatting generated data to conform to a predetermined format or standard.

[1396] "Verification" refers to the process of checking whether the data output from a generated AI model is accurate.

[1397] This system is implemented using the following hardware and software. The hardware includes smartphones, tablets, factory robots, various sensor networks, and servers. The software includes Python, TensorFlow or PyTorch, OpenAI GPT, and an emotion engine. The following describes how each piece of hardware and software functions.

[1398] Send a request

[1399] Users request reports of necessary data using their smartphones or tablets. For example, they might issue a voice command such as, "Please create a report on the forecast for the next maintenance and the current parts inventory status." This request is sent to the server in real time via the company network. User sentiment information is also sent along with the request and analyzed by the sentiment engine.

[1400] Receiving and parsing requests

[1401] The server analyzes incoming requests and determines the optimal database for retrieving information based on the request's content. It also analyzes emotional information transmitted from the user's device and optimizes the data generation process based on the results.

[1402] Data acquisition

[1403] The server generates database queries and retrieves necessary data in real time from the company's internal database and the factory's sensor network. For example, it collects data such as the operating status and maintenance history of specific robots, and the inventory status of parts.

[1404] Data generation

[1405] The server passes the acquired data to OpenAI GPT, an AI model for generating reports, which then generate reports in the specified format. In this process, user sentiment information is taken into consideration, and the urgency and conciseness of the information are optimized.

[1406] Data validation and formatting

[1407] The server validates the generated report data and formats it into the required format. It verifies the accuracy of the data output from the generating AI model and adjusts the data based on sentiment information.

[1408] Return to user

[1409] Finally, the server sends the completed report back to the user's terminal. The user receives this report and uses it to develop factory operations and maintenance plans.

[1410] Specific example

[1411] For example, a factory engineer might make the following voice request:

[1412] "Please provide an urgent report on the expected next maintenance schedule and parts inventory status. Our engineers are currently under pressure."

[1413] This request is sent to the server, which retrieves the necessary data, and if the sentiment engine determines that "the engineer is feeling anxious," a concise report is quickly generated for review. This report provides the necessary information concisely and quickly, such as "Next scheduled maintenance date: October 15, 2023, Parts inventory: Sufficient."

[1414] This system significantly improves efficiency and accuracy compared to conventional manual processing, and can support factory operations.

[1415] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1416] Step 1:

[1417] Users request reports of necessary data using their smartphones or tablets.

[1418] Specific operation: The user issues a voice command such as, "Please create a report on the expected next maintenance and parts inventory status." The voice is converted to text and then sent to the server via the company network.

[1419] Input: User's voice request and sentiment information.

[1420] Output: Request and sentiment information converted to text format.

[1421] Step 2:

[1422] The server analyzes the received request and sentiment information to determine which database to retrieve the information from.

[1423] Specific operation: The server analyzes the request and determines which robots and sensors to collect data from. Additionally, the emotion engine analyzes the user's emotional information and optimizes the data generation process.

[1424] Input: Request and sentiment information converted to text format.

[1425] Output: Generation of database queries.

[1426] Step 3:

[1427] The server uses generated database queries to retrieve necessary data from the company's internal database and sensor network.

[1428] Specific operation: The server generates appropriate database queries to collect data such as the operating status of various sensors and robots within the factory, maintenance history, and parts inventory data.

[1429] Input: Database query.

[1430] Output: Acquired data (operating status data, maintenance data, parts inventory data, etc.).

[1431] Step 4:

[1432] The server passes the acquired data to a generation AI model, which then generates a report in the specified format.

[1433] Specific operation: The collected data is input into a generative AI model such as OpenAI GPT, and prompts are used to generate a report in the format requested by the user. The report content is optimized by also considering the results of the sentiment engine.

[1434] Input: Prompt text based on acquired data and sentiment information.

[1435] Output: Generated report data.

[1436] Step 5:

[1437] The server verifies the generated report data and formats it into the required format.

[1438] Specific actions: Verify the report data output from the generated AI model and check for errors. If necessary, correct or supplement the data and format it into the specified format.

[1439] Input: Generated report data.

[1440] Output: Formatted final report data.

[1441] Step 6:

[1442] The server sends the final report data back to the user's terminal.

[1443] Specific action: The completed report will be sent to the user's smartphone or tablet so that they can view it immediately.

[1444] Input: Formatted final report data.

[1445] Output: Sending report data to the user's terminal.

[1446] In this way, data processing and calculations are performed at each step, making it possible to generate and provide optimal reports that meet the user's requirements.

[1447] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1448] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1449] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1450] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1451] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1452] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1453] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1454] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1455] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1456] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1457] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1458] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1459] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1460] 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.

[1461] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1462] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1463] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1464] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1465] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1466] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1467] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1468] The following is further disclosed regarding the embodiments described above.

[1469] (Claim 1)

[1470] A terminal means for sending requests via the internal network,

[1471] A server means for receiving and analyzing requests,

[1472] A means of retrieving relevant data from a database based on an analyzed request,

[1473] A means of passing acquired data to a generative AI module and generating data in a specified format,

[1474] A means of returning the generated data to the user,

[1475] A system that includes this.

[1476] (Claim 2)

[1477] The system according to claim 1, comprising means for analyzing a request that includes information about the user's department and obtaining data from a database corresponding to the relevant department.

[1478] (Claim 3)

[1479] The system according to claim 1, comprising means for verifying and formatting output data obtained from a generative AI module.

[1480] "Example 1"

[1481] (Claim 1)

[1482] A terminal means for sending requests via the internal network,

[1483] A server means for receiving and analyzing requests,

[1484] A means of obtaining relevant information from the database based on the analyzed request,

[1485] A means of passing acquired information to a generative AI module and generating data in a specified format,

[1486] Means for verifying and formatting the generated data,

[1487] A means of returning the generated data to the user,

[1488] A system that includes this.

[1489] (Claim 2)

[1490] The system according to claim 1, comprising means for analyzing a request that includes information about the user's department and obtaining data from a database corresponding to the relevant department.

[1491] (Claim 3)

[1492] The system according to claim 1, comprising means of using an internal database system when retrieving data based on an analyzed request.

[1493] "Application Example 1"

[1494] (Claim 1)

[1495] A terminal means for sending requests via the internal network,

[1496] A server means for receiving and analyzing requests,

[1497] A means of retrieving relevant data from a database based on an analyzed request,

[1498] A means of passing acquired data to a generative AI module and generating data in a specified format,

[1499] A means of returning the generated data to the user and providing information in real time,

[1500] A system that includes this.

[1501] (Claim 2)

[1502] The system according to claim 1, comprising means for analyzing a request that includes information about the user's department and obtaining data from a database corresponding to the relevant department.

[1503] (Claim 3)

[1504] The system according to claim 1, comprising means for field workers to receive real-time inventory management and delivery route suggestions using a smart device.

[1505] "Example 2 of combining an emotion engine"

[1506] (Claim 1)

[1507] A terminal means for sending requests via the internal network,

[1508] A server means for receiving and analyzing requests,

[1509] A means of retrieving relevant data from a database based on an analyzed request,

[1510] A means of passing acquired data to a generation AI model and generating data in a specified format,

[1511] A means of returning the generated data to the user,

[1512] A means of analyzing user emotional information,

[1513] Means of including user sentiment information in requests,

[1514] A system that includes this.

[1515] (Claim 2)

[1516] The system according to claim 1, comprising means for analyzing a request that includes the user's departmental information and emotional information, and obtaining data from a database corresponding to the relevant department.

[1517] (Claim 3)

[1518] The system according to claim 1, comprising means for verifying and formatting output data obtained from a generated AI model and adjusting the data based on user sentiment information.

[1519] "Application example 2 when combining with an emotional engine"

[1520] (Claim 1)

[1521] A device that sends requests via the internal network,

[1522] A computer that receives and analyzes requests,

[1523] A means of obtaining relevant information from the database based on the analyzed request,

[1524] A means of passing acquired information to a generation AI model and generating data in a specified format,

[1525] A means of returning the generated data to the user,

[1526] It includes an emotion engine that recognizes the user's emotions, passes the acquired information to a generation AI model, and means for generating data while considering the emotional information.

[1527] A system that includes this.

[1528] (Claim 2)

[1529] The system according to claim 1, comprising means for analyzing a request that includes information about the user's department and obtaining information from a database corresponding to the relevant department.

[1530] (Claim 3)

[1531] The system according to claim 1, comprising means for verifying and formatting output data obtained from a generative AI model, and means for adjusting the data based on the results of an emotion engine. [Explanation of symbols]

[1532] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A terminal means for sending requests via the internal network, A server means for receiving and analyzing requests, A means of retrieving relevant data from a database based on an analyzed request, A means of passing acquired data to a generative AI module and generating data in a specified format, A means of returning the generated data to the user, A system that includes this.

2. The system according to claim 1, comprising means for analyzing a request that includes information about the user's department and obtaining data from a database corresponding to the relevant department.

3. The system according to claim 1, further comprising means for verifying and formatting output data obtained from a generative AI module.

Images