System

Abstract

A system is provided.SOLUTION: A system, comprising: means for utilizing a generative model to extract and integrate data relevant to a specified search query from a plurality of data sources; means for utilizing the generative model to analyze uploaded datasets and automatically generate materials; and means for utilizing the generative model to analyze marketing data and extract trends and insights.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, various tools utilizing generative models have been developed, but there are many challenges in integrating these tools to increase utilization and improve business efficiency. Specifically, because internal tools and data sources are dispersed, information search, document creation, and data analysis require a lot of time and effort. Therefore, it is necessary to integrate business processes using generative models, reduce employee work time, and improve business efficiency. [Means for solving the problem]

[0005] This invention provides a system that uses a generative model to extract and integrate data related to a specified search query from multiple data sources. It also provides a system that uses a generative model to analyze uploaded datasets and automatically create documents. It also provides a system that uses a generative model to analyze marketing data and extract trends and insights. This enables information search, document creation, and data analysis to be performed quickly and efficiently, significantly improving business efficiency.

[0006] A "generative model" is an artificial intelligence model that uses deep learning technology to perform advanced analysis of input data and generate results.

[0007] A "search query" is a search request entered by a user to obtain information.

[0008] A "data source" is a data system or database from which information is obtained.

[0009] A "dataset" is a collection of data used for analysis or processing.

[0010] "Analysis" is the process of examining data in detail and extracting meaning.

[0011] "Materials" refers to information media such as documents and presentations created based on the analysis results.

[0012] "Marketing data" refers to data that contains information related to markets, consumers, and products.

[0013] A "trend" is a pattern that shows a specific direction or change through data analysis.

[0014] An "insight" is a significant insight or understanding gained from analyzing data. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention is a system for improving business efficiency by utilizing generative models. Specific examples include improving the efficiency of information search, document creation, and shortening analysis time. Specific embodiments of this system are described below.

[0037] Efficient information search

[0038] The server receives the search query entered by the user and passes it to the generative model. The generative model analyzes the query and collects information from relevant data sources (e.g., email systems, word processing tools, company intranets). The collected information is integrated and sent to the user's device. This allows the user to quickly access the information they need from a single interface.

[0039] Specific examples

[0040] When a user searches for "latest marketing report," the server collects relevant documents from Gmail, Google Docs, and the intranet and displays them on the device, allowing users to obtain the information they need in one place without having to use multiple tools.

[0041] Improving the efficiency of document creation

[0042] When a user uploads a dataset for document creation, the server passes it to a generative model. The generative model analyzes the data and automatically creates key statistics and graphs. These analysis results are integrated into the specified format (e.g., presentation, report) and sent to the user's device. Users can obtain high-quality documents in a short time.

[0043] Specific examples

[0044] When a user uploads new product sales data (an Excel file), the server analyzes it and automatically graphs sales trends and key indicators, generating a PowerPoint presentation that is instantly delivered to the user's device.

[0045] Shorter analysis time

[0046] When users provide marketing data for analysis, the server passes it to the generative model, which analyzes the data and extracts trends and insights. The analysis results are generated as interactive dashboards and detailed reports and sent to the user's device, allowing users to quickly understand the current market situation and trends.

[0047] Specific examples

[0048] Users can upload customer data for a specific market, and the server analyzes it to extract purchasing patterns by age group and sales trends by region. The results are displayed on the device as an interactive dashboard, allowing users to perform detailed data analysis.

[0049] This system integrates the processes of information search, document creation, and data analysis around a generative model, significantly improving users' work efficiency.

[0050] The processing flow will be explained below.

[0051] Efficient information search

[0052] Step 1:

[0053] A user enters a search query into the search bar.

[0054] Step 2:

[0055] The terminal transmits the entered search query to the server.

[0056] Step 3:

[0057] The server passes the received search query to the generative model.

[0058] Step 4:

[0059] A generative model parses the search query and generates requests to relevant data sources (e.g., email system, word processing tool, company intranet).

[0060] Step 5:

[0061] The server sends a request to each data source via an API.

[0062] Step 6:

[0063] Each data source responds with relevant data in response to a request.

[0064] Step 7:

[0065] The server receives the collected data, analyzes it with a generative model, and integrates it.

[0066] Step 8:

[0067] The server sends the integrated search results to the terminal.

[0068] Step 9:

[0069] The terminal displays the results to the user.

[0070] Improving the efficiency of document creation

[0071] Step 1:

[0072] The user uploads a dataset (e.g., an Excel file) from their device to create a document.

[0073] Step 2:

[0074] The device sends the data set to the server.

[0075] Step 3:

[0076] The server receives the data and passes it to the generative model.

[0077] Step 4:

[0078] A generative model analyzes the dataset and produces key statistics and graphs.

[0079] Step 5:

[0080] Based on the analysis results, the generative model automatically generates materials in the specified format (e.g., presentation, report).

[0081] Step 6:

[0082] The server transmits the generated materials to the user's terminal.

[0083] Step 7:

[0084] The terminal allows the user to display or download the material.

[0085] Shorter analysis time

[0086] Step 1:

[0087] The user uploads data (e.g., customer data) for analysis from their device.

[0088] Step 2:

[0089] The device sends the data to the server.

[0090] Step 3:

[0091] The server receives the data and passes it to the generative model.

[0092] Step 4:

[0093] Generative models analyze the data and extract trends and insights.

[0094] Step 5:

[0095] The generative model generates the analysis results in the form of reports and dashboards.

[0096] Step 6:

[0097] The server sends the generated results to the user's terminal.

[0098] Step 7:

[0099] The terminal displays the results to the user and provides interactivity where necessary.

[0100] The above steps enable efficient information search, document creation, and data analysis, greatly improving the user's work efficiency.

[0101] Example 1

[0102] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0103] In the past, the processes of information search, document creation, and data analysis required separate tasks, significantly reducing user efficiency. Furthermore, the need to use multiple tools and platforms made it difficult to centrally manage information, which required time and effort.

[0104] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0105] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple information sources using a generative AI model, means for analyzing a dataset uploaded from a terminal using the generative AI model and automatically generating materials, means for analyzing marketing data using the generative AI model and extracting trends and insights, means for analyzing the search query and collecting information from specific information sources, means for integrating the collected information and sending it to the terminal, means for analyzing the dataset and integrating the analysis results into a specified format, and means for compiling the analysis results into an interactive dashboard or a detailed report. This allows users to integrate information search, document creation, and data analysis within a single system, significantly improving work efficiency.

[0106] A "generative AI model" is an artificial intelligence algorithm that analyzes natural language queries and datasets entered by users and generates appropriate responses or analytical results.

[0107] A "search query" refers to a question or keyword that a user enters to search for specific information.

[0108] "Sources" refer to multiple databases or systems that contain information relevant to a search query, such as email systems, word processing tools, and intranets.

[0109] A "dataset" refers to a set of data provided by a user for a specific analysis or document creation, and examples include Excel files and CSV files.

[0110] "Integration" refers to the process of bringing together information obtained from different sources and data formats and making it easy for users to use.

[0111] "Documents" refers to documents such as reports and presentations created using generative AI models.

[0112] "Insights" refers to useful insights and understanding gained through data analysis, and is information that is useful for business decision-making.

[0113] A "dashboard" refers to an interface for visually displaying the results of data analysis, including graphs and charts.

[0114] This invention is a system for improving business efficiency using a generative AI model. Specifically, it aims to automate the processes of information search, document creation, and data analysis, thereby improving the business efficiency of users. Specific embodiments for implementing this invention are described below.

[0115] Efficient information search

[0116] A user enters a search query into a device. For example, they enter "latest marketing report." The device sends this search query to a server. The server passes the received search query to a generative AI model (e.g., GPT-4 (registered trademark)) for analysis. The generative AI model analyzes the search query and identifies relevant information sources (e.g., email system, word processing tool, company intranet). The server collects the necessary information from the identified information sources and integrates it. The integrated information is sent from the server to the user's device, allowing the user to quickly access the information they need from a single interface.

[0117] Specific examples

[0118] When a user searches for "latest marketing reports," the server gathers relevant documents from Gmail, Google Docs, and your intranet, consolidates them, and displays them on the user's device.

[0119] Prompt example

[0120] "Find the latest marketing reports!"

[0121] Improving the efficiency of document creation

[0122] A user uploads a dataset from their device to create a document. For example, they upload "New Product Sales Data.xlsx." The device sends the dataset to the server. The server passes the dataset to a generative AI model (e.g., OpenAI (registered trademark) Codex) and requests data analysis. The generative AI model analyzes the dataset and automatically generates key statistical information and graphs. The generated statistical information and graphs are integrated into a specified format (e.g., PowerPoint presentation) and sent to the user's device. The user can obtain high-quality documents in a short amount of time.

[0123] Specific examples

[0124] When a user uploads new product sales data (an Excel file), the server passes it through a generative AI model, which automatically graphs sales trends and key indicators, and the resulting PowerPoint presentation is instantly delivered to the user's device.

[0125] Prompt example

[0126] "Analyze sales data for new products and create presentation materials!"

[0127] Shorter analysis time

[0128] The user uploads marketing data from their device. For example, they upload "CustomerData.csv". The device sends the marketing data to the server. The server passes the received data to a generative AI model (e.g., BERT) for data analysis. The generative AI model analyzes the data and extracts trends and insights. The extracted information is compiled into interactive dashboards and detailed reports, which are then sent from the server to the user's device. The user can quickly grasp the current market situation and trends.

[0129] Specific examples

[0130] Users upload customer data for a specific market, and the server analyzes the data to extract customer purchasing patterns and regional sales trends. These results are displayed on the user's device as an interactive dashboard.

[0131] Prompt example

[0132] "Analyze customer data for a specific market and create a report highlighting key trends!"

[0133] This system utilizes generative AI models to streamline the processes of information search, document creation, and data analysis, significantly improving user work efficiency. This implementation frees users from the hassle of using multiple tools and platforms, allowing them to manage and use all information through a single interface.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Efficient information search

[0136] Step 1:

[0137] A user enters a search query into a device.

[0138] Input: Search query (e.g. "latest marketing report")

[0139] Action: Enter keywords in the search field

[0140] Output: The search query entered by the user

[0141] Step 2:

[0142] The terminal transmits the entered search query to the server.

[0143] Input: Search query

[0144] What it does: Creates an HTTP request and sends it to the server. The query is packaged in JSON format.

[0145] Output: The search query sent (received on the server side)

[0146] Step 3:

[0147] The server passes the search query to the generative AI model.

[0148] Input: Received search query

[0149] How it works: Passing a query to a generative AI model and requesting analysis

[0150] Output: The search query sent to the generative AI model

[0151] Step 4:

[0152] A generative AI model analyzes search queries.

[0153] Input: Search query passed by the server

[0154] How it works: Analyzes the query content and identifies relevant sources of information (e.g., company intranet, email system, word processing tool)

[0155] Output: List of relevant sources

[0156] Step 5:

[0157] The server identifies relevant data sources and collects the information.

[0158] Input: List of relevant sources

[0159] Operation: Calls the API of each information source and collects relevant information

[0160] Output: Information collected from each data source

[0161] Step 6:

[0162] The server aggregates the collected information.

[0163] Input: Collected information

[0164] What it does: Consolidates information into a single response dataset

[0165] Output: A consolidated response dataset

[0166] Step 7:

[0167] The server sends the integrated information to the user's terminal.

[0168] Input: Consolidated response dataset

[0169] Behavior: Creates an HTTP response and sends it to the user's device.

[0170] Output: The aggregated information sent to the user's device

[0171] Step 8:

[0172] The terminal displays the integrated information to the user.

[0173] Input: Received consolidated information

[0174] What it does: Parses JSON-formatted data and displays it visually (e.g., in a web browser)

[0175] Output: Consolidated information displayed to the user

[0176] Improving the efficiency of document creation

[0177] Step 1:

[0178] The user uploads a dataset from the terminal to create a document.

[0179] Input: File (e.g. "New Product Sales Data.xlsx")

[0180] Action: Select a dataset from the file selection dialog

[0181] Output: Selected files

[0182] Step 2:

[0183] The device sends the data set to the server.

[0184] Input: File (dataset)

[0185] What it does: Sends a file via an HTTP POST request, with the data encoded in multipart format.

[0186] Output: The file sent

[0187] Step 3:

[0188] The server passes the dataset to the generative AI model.

[0189] Input: The received dataset

[0190] What it does: Pass a dataset to a generative AI model and make a request to analyze it

[0191] Output: The dataset sent to the generative AI model

[0192] Step 4:

[0193] A generative AI model analyzes the dataset.

[0194] Input: Dataset passed from the server

[0195] What it does: Analyzes data and generates key statistics and graphs

[0196] Output: Analyzed statistics and graphs

[0197] Step 5:

[0198] The server integrates the analysis results into the specified format (e.g. PowerPoint).

[0199] Input: Analyzed statistics and graphs

[0200] Action: Integrates into a specified document format and creates a document (e.g., PowerPoint slides)

[0201] Output: Generated documentation file

[0202] Step 6:

[0203] The server transmits the generated materials to the user's terminal.

[0204] Input: Generated document file

[0205] Action: Sends a document file in the HTTP response

[0206] Output: The file sent to the user's device

[0207] Step 7:

[0208] The terminal displays the material to the user.

[0209] Input: Received document file

[0210] Behavior: Generates a download link and provides it to the user

[0211] Output: A file of the displayed material that can be downloaded by the user.

[0212] Shorter analysis time

[0213] Step 1:

[0214] The user uploads marketing data from the device.

[0215] Input: File (e.g. "CustomerData.csv")

[0216] Action: Select data from file selection dialog

[0217] Output: Selected files

[0218] Step 2:

[0219] The device sends the marketing data to the server.

[0220] Input: File (Marketing Data)

[0221] What it does: Sends a file via an HTTP POST request, with the data encoded in multipart format.

[0222] Output: The file sent

[0223] Step 3:

[0224] The server passes the data to the generative AI model.

[0225] Input: Received file

[0226] Action: Pass a file to the generative AI model and request analysis

[0227] Output: The file sent to the generative AI model

[0228] Step 4:

[0229] Generative AI models analyze the data and extract trends and insights.

[0230] Input: File passed from the server

[0231] Action: Analyze data and extract trends and insights

[0232] Output: Analyzed trends and insights

[0233] Step 5:

[0234] The server compiles the analysis results into interactive dashboards and detailed reports.

[0235] Input: Analyzed trends and insights

[0236] How it works: Generate interactive dashboards and detailed reports

[0237] Output: Generated dashboards and reports

[0238] Step 6:

[0239] The server sends the results to the user's terminal.

[0240] Input: Generated dashboards and reports

[0241] Action: Send the result in an HTTP response

[0242] Output: Dashboards and reports sent to the user's device

[0243] Step 7:

[0244] The terminal displays the results to the user.

[0245] Input: Incoming dashboards and reports

[0246] Action: Visually displays a dashboard or report (e.g., in a web browser)

[0247] Output: The results displayed in a form that the user can interact with.

[0248] (Application example 1)

[0249] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0250] In logistics centers, quickly collecting and integrating information from multiple data sources is challenging when searching for necessary information in real time. Uploading data sets for document creation and manually compiling analytical and statistical information is time-consuming and labor-intensive. Analyzing marketing data quickly and effectively to extract important trends and insights is also a challenge. To streamline on-site operations, it is necessary to process this information in real time and display it on visual devices such as smart glasses, thereby improving efficiency.

[0251] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0252] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model to automatically create materials, means for analyzing marketing data using a generative model to extract trends and insights, means for converting real-time voice input into text data and processing it as the specified search query, and means for outputting related information based on the search query to a visual device for displaying it, thereby enabling logistics center staff to quickly and centrally obtain information through the smart glasses to create materials and analyze data.

[0253] A "generative model" is an algorithm that analyzes data or queries entered by a user and automatically generates related information or data.

[0254] A "specified search query" is a search request entered by a user into a server to obtain the information desired.

[0255] "Data Source" refers to multiple databases or information resources that are referenced to obtain information.

[0256] "Means of integration" refers to a method of consolidating information obtained from multiple data sources into one and providing it in a centralized manner.

[0257] A "dataset" is a set of data uploaded by a user for analysis or documentation purposes.

[0258] "Material creation means" refers to a method for automatically generating materials in a specified format by analyzing and processing the uploaded dataset.

[0259] "Marketing data" refers to data used for market research and consumer behavior analysis.

[0260] A "trend" is a specific tendency or tendency found in data.

[0261] "Insights" refers to insights and findings revealed through data analysis.

[0262] "Real-time voice input" is a technology that instantly processes the voice spoken by the user as digital data.

[0263] "Text data" refers to voice input converted into text information.

[0264] A "visual device" is a tool for visually presenting information to a user, and specifically includes smart glasses.

[0265] This invention is a system for improving operational efficiency in logistics centers, specifically, a method for using generative AI models to perform information retrieval, document creation, and data analysis in real time, and providing information to visual devices such as smart glasses.

[0266] Hardware and software used

[0267] Hardware: Smart glasses (e.g., Google Glass®)

[0268] Software: Generative AI models (e.g., GPT-4), database systems (e.g., MySQL, PostgreSQL), real-time speech recognition (e.g., Google Speech-to-Text API)

[0269] Processing flow and system operation

[0270] 1. Voice to Text

[0271] The user speaks into the microphone of the smart glasses to input voice commands. The voice commands (e.g., "Show me the latest inventory list") are captured by the microphone and converted into text data in real time using the Google Speech-to-Text API.

[0272] 2. Search query analysis and data collection

[0273] The text search query is analyzed by a generative AI model (GPT-4), which understands the query and generates appropriate SQL queries to gather relevant information from multiple data sources (e.g., corporate databases, inventory management systems, etc.). The generated SQL queries are then executed in a database system to extract the relevant data.

[0274] 3. Data integration and documentation

[0275] The extracted data is integrated with a generative AI model to automatically generate documents and reports in the specified format. For example, sales data and inventory data can be automatically graphed and compiled into a detailed report.

[0276] 4. Real-time display

[0277] The generated information and materials are displayed in real time on the smart glasses' display, allowing users to quickly access the information they need without using their hands.

[0278] Example prompt

[0279] Below are some examples of prompts that can be used with this system:

[0280] "View the latest inventory list"

[0281] I'd like to check the delivery schedule.

[0282] "Please prepare yesterday's shipping report."

[0283] This invention allows staff at logistics centers to use voice input to efficiently perform complex information searches, data analysis, document creation, etc. By implementing this system, work efficiency is improved and work can be carried out quickly and accurately.

[0284] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0285] Step 1:

[0286] The user speaks into the microphone in the smart glasses, for example, saying, "Show me the latest inventory list." The microphone in the smart glasses captures the voice and sends it in real time to the Google Speech-to-Text API.

[0287] Input: User voice input

[0288] Output: Audio data

[0289] Step 2:

[0290] The server uses the Google Speech-to-Text API to convert the voice data into text data. For example, the voice input "Show me the latest inventory list" is converted into text data "Show me the latest inventory list."

[0291] Input: Audio data

[0292] Output: Text data

[0293] Step 3:

[0294] The server passes the text data to a generative AI model (GPT-4) for analysis, which uses natural language understanding to analyze the search query and generate the SQL queries needed to retrieve information from relevant data sources.

[0295] Input: Text data

[0296] Output: Generated SQL query

[0297] Step 4:

[0298] The server sends an SQL query to a database system (e.g., MySQL, PostgreSQL) to extract the required data. For example, an SQL query to get the "latest inventory list" is executed, and the relevant data is extracted from the inventory management system.

[0299] Input: SQL query

[0300] Output: Data extracted from the database

[0301] Step 5:

[0302] The server integrates the extracted data with a generative AI model and automatically generates documents in the specified format (e.g., list format, table format). For example, an inventory list can be compiled in a table format.

[0303] Input: Extracted data

[0304] Output: Automatically generated materials

[0305] Step 6:

[0306] The server sends the automatically generated information to the smart glasses and displays it in real time, allowing the user to check the information displayed on the smart glasses' display.

[0307] Input: Auto-generated material

[0308] Output: Information displayed on the smart glasses

[0309] This allows users to use voice input to quickly and efficiently perform complex information searches, data analysis, and document creation.

[0310] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0311] This invention provides a system that combines a generative model and an emotion engine to recognize user emotions and automatically adjust business processes. Specific examples include improving the efficiency of information search, document creation, and shortening analysis time, as well as presenting and editing data according to the user's emotions.

[0312] Efficient information search

[0313] The server receives the search query entered by the user and passes it to the generative model. The generative model analyzes the query and collects information from relevant data sources (e.g., email systems, word processing tools, company intranets). In parallel, the emotion engine analyzes the user's emotions and adjusts the order and display format of the search results, allowing the user to retrieve information more appropriately.

[0314] Specific examples

[0315] When a user searches for "latest marketing reports," the server gathers relevant documents from Gmail, Google Docs, and the intranet. If the emotion engine determines that the user's stress level is high, it prioritizes the most concise and important information.

[0316] Improving the efficiency of document creation

[0317] When a user uploads a dataset to create a document, the server passes it to a generative model. The generative model analyzes the data and automatically creates key statistics and graphs. In addition, an emotion engine analyzes the user's emotions and adjusts the tone and style of the document. This allows users to create high-quality documents without spending a lot of time.

[0318] Specific examples

[0319] When a user uploads sales data (Excel file) for a new product, the server analyzes it and automatically graphs sales trends and key indicators. If the user is nervous about preparing a presentation, the emotion engine generates presentation materials using simple language and plenty of visual support.

[0320] Shorter analysis time

[0321] When a user provides marketing data for analysis, the server passes it to the generative model. The generative model analyzes the data and extracts trends and insights. The emotion engine analyzes the user's emotions and adjusts the presentation method and interface of the analysis results as needed. This allows users to quickly understand the current market situation and trends, and work at an appropriate stress level.

[0322] Specific examples

[0323] Users upload customer data for a specific market, and the server analyzes it to extract purchasing patterns by age group and sales trends by region. If the emotion engine determines that the user is calm, it will provide an interactive dashboard with detailed data, but if it determines that the user is anxious, it will provide a concise report highlighting only the key points.

[0324] By combining a generative model with an emotion engine, this system enables flexible responses according to the user's emotional state, significantly improving work efficiency and user satisfaction.

[0325] The processing flow will be explained below.

[0326] Efficient information search

[0327] Step 1:

[0328] A user enters a search query into the search bar.

[0329] Step 2:

[0330] The terminal transmits the entered search query to the server.

[0331] Step 3:

[0332] The server passes the received search query to the generative model.

[0333] Step 4:

[0334] A generative model parses the search query and generates requests to relevant data sources (e.g., email system, word processing tool, company intranet).

[0335] Step 5:

[0336] The server sends a request to each data source via an API.

[0337] Step 6:

[0338] Each data source responds with relevant data in response to a request.

[0339] Step 7:

[0340] The server receives the collected data, analyzes it with a generative model, and integrates it.

[0341] Step 8:

[0342] The emotion engine analyzes the user's emotions and adjusts the order and display format of search results.

[0343] Step 9:

[0344] The server sends the adjusted search results to the device.

[0345] Step 10:

[0346] The terminal displays the results to the user.

[0347] Improving the efficiency of document creation

[0348] Step 1:

[0349] The user uploads a dataset (e.g., an Excel file) from their device to create a document.

[0350] Step 2:

[0351] The device sends the data set to the server.

[0352] Step 3:

[0353] The server receives the data and passes it to the generative model.

[0354] Step 4:

[0355] A generative model analyzes the dataset and produces key statistics and graphs.

[0356] Step 5:

[0357] Based on the analysis results, the generative model automatically generates materials in the specified format (e.g., presentation, report).

[0358] Step 6:

[0359] The emotion engine analyzes the user's emotions and adjusts the tone and style of the material.

[0360] Step 7:

[0361] The server transmits the generated materials to the terminal.

[0362] Step 8:

[0363] The terminal allows the user to display or download the material.

[0364] Shorter analysis time

[0365] Step 1:

[0366] The user uploads data (e.g., customer data) for analysis from their device.

[0367] Step 2:

[0368] The device sends the data to the server.

[0369] Step 3:

[0370] The server receives the data and passes it to the generative model.

[0371] Step 4:

[0372] Generative models analyze the data and extract trends and insights.

[0373] Step 5:

[0374] The generative model generates the analysis results in the form of reports and dashboards.

[0375] Step 6:

[0376] The emotion engine analyzes the user's emotions and adjusts the way the analysis results are presented and the interface.

[0377] Step 7:

[0378] The server transmits the generated results to the terminal.

[0379] Step 8:

[0380] The terminal displays the results to the user and provides interactivity where necessary.

[0381] These steps allow for efficient information search, document creation, and data analysis, and enable flexible responses to the user's emotional state.

[0382] Example 2

[0383] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0384] In conventional systems, even when a user enters a search query, the results are not optimized according to the user's emotional state, making information acquisition and document creation inefficient. Furthermore, analyzing large amounts of data takes time, and the system does not provide an interface that responds to the user's emotions, resulting in problems such as reduced work efficiency and user satisfaction.

[0385] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0386] In this invention, the server includes means for extracting and integrating data related to a search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model and automatically creating materials, means for analyzing marketing data using a generative model and extracting trends and insights, and means for adjusting search results, materials, and analysis results using an emotion engine that analyzes the user's emotional state. This enables flexible responses according to the user's emotional state, making it possible to significantly improve business efficiency and user satisfaction.

[0387] A "generative model" is a means of analyzing user input and generating or extracting relevant data using machine learning algorithms.

[0388] An "emotion engine" is a means of analyzing a user's emotional state and adjusting the display order and format of data based on the results.

[0389] A "search query" is the text or keywords that a user enters to obtain information.

[0390] "Data sources" are various sources for collecting information, including, for example, email systems, word processing tools, and company intranets.

[0391] A "dataset" is a collection of data that is the subject of document creation or data analysis, and includes, for example, data in spreadsheet format.

[0392] A "trend" is a temporal fluctuation or tendency obtained as a result of data analysis.

[0393] "Insight" refers to useful knowledge and insight gained through data analysis.

[0394] "User emotional state" refers to the psychological state of the user when searching for information, creating materials, or analyzing data, and includes stress, tension, calmness, etc.

[0395] "Adjustment" refers to changing the way information is presented or the format of the display based on the user's emotional state.

[0396] "Interface" refers to the means or display screen through which a user interacts with a system.

[0397] This invention provides a system that combines a generative model and an emotion engine to recognize user emotions and automatically adjust business processes. Specifically, it presents and edits data according to the user's emotions, improving the efficiency of information search, document creation, and shortening analysis time.

[0398] Efficient information search

[0399] When a user enters a search query (e.g., "latest marketing report"), the device sends this search query to the server. The server uses a generative model to analyze the query and collects information from related data sources (e.g., email system, word processing tool, company intranet). At the same time, the emotion engine analyzes the user's emotions and adjusts the order and display format of the search results. This allows the user to efficiently obtain optimized information. For example, when a user searches for "latest marketing report," the server collects related documents from the email system and word processing tool, and if the emotion engine determines that the user's stress level is high, it prioritizes displaying the most concise and important information.

[0400] Improving the efficiency of document creation

[0401] When a user uploads a dataset (e.g., an Excel file) from their device to create a presentation, the server passes the dataset to a generative model. The generative model analyzes the data and automatically creates key statistical information and graphs. Furthermore, an emotion engine analyzes the user's emotions and adjusts the tone and style of the presentation. This allows users to create high-quality presentations in a short amount of time. For example, when a user uploads sales data for a new product, the server analyzes it and automatically graphs sales trends and key indicators. If the emotion engine determines that the user is nervous about preparing a presentation, it generates presentation materials that use simple language and plenty of visual support elements.

[0402] Shorter analysis time

[0403] When a user uploads marketing data (e.g., customer data) from their device for analysis, the server passes the data to a generative model. The generative model analyzes the data and extracts trends and insights. The emotion engine analyzes the user's emotions and adjusts the presentation of the analysis results as needed. This allows users to quickly understand the current market situation and trends and work with an appropriate stress level. For example, when a user uploads customer data for a specific market, the server analyzes it and extracts purchasing patterns by age group and sales trends by region. If the emotion engine determines that the user is calm, it will provide an interactive dashboard with detailed data, but if it determines that the user is anxious, it will provide a concise report that highlights only the key points.

[0404] This invention allows for flexible responses according to the user's emotional state by combining a generative model and an emotion engine, thereby significantly improving business efficiency and user satisfaction.

[0405] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0406] Efficient information search

[0407] Step 1:

[0408] A user enters a search query into a device. This query is in text format (e.g., "latest marketing reports"), and this query triggers the start of an information search.

[0409] Step 2:

[0410] The device sends the entered search query to the server, which analyzes it on the server side.

[0411] Step 3:

[0412] The server passes the received query to the generative model for analysis. The generative model uses natural language understanding to analyze the query and extract the necessary information from relevant data sources (e.g., email systems, document creation tools, company intranets). The output is a list of relevant documents.

[0413] Step 4:

[0414] The server sends the user's input information and facial recognition data to the emotion engine, which analyzes the user's emotional state. The emotion engine evaluates the user's stress level and emotional state, and the results of this evaluation influence subsequent steps.

[0415] Step 5:

[0416] The server adjusts the presentation order and display format of the collected information based on the analysis results of the emotion engine. For example, if the user's stress level is high, the server will prioritize the most concise and important information. This process results in an ergonomic presentation of information.

[0417] Step 6:

[0418] The terminal receives the adjusted search results sent from the server and displays them to the user, with the output being displayed as an optimized list of information for the user to view.

[0419] Improving the efficiency of document creation

[0420] Step 1:

[0421] The user uploads a data set to the terminal for document creation, usually in the form of a spreadsheet (e.g., Excel file).

[0422] Step 2:

[0423] The device sends the uploaded dataset to the server, where the data is passed to the server in its raw format.

[0424] Step 3:

[0425] The server passes the dataset to a generative model for analysis. The generative model analyzes the data and automatically creates key statistics and graphs. The output is generated as a first draft of the document.

[0426] Step 4:

[0427] The server sends the user's emotional state to the emotion engine for analysis. The emotion engine evaluates the user's emotional state, such as stress or tension. The evaluation results are reflected in the content and format of the document.

[0428] Step 5:

[0429] The server adjusts the tone and style of the materials based on the analysis results of the emotion engine. For example, if the user is nervous, the server will create materials that use simple language and plenty of visual support. This results in user-friendly materials.

[0430] Step 6:

[0431] The terminal displays the adjusted material to the user, and the output is provided in a format that can be used for presentations or reports.

[0432] Shorter analysis time

[0433] Step 1:

[0434] The user provides marketing data to the device, typically in the form of a database or spreadsheet (e.g., customer data).

[0435] Step 2:

[0436] The device sends the provided marketing data to the server, which passes the data to the server in its raw form.

[0437] Step 3:

[0438] The server passes the data to a generative model for analysis. The generative model analyzes the data and extracts trends and insights. The output is generated as a list or graph of the analysis results.

[0439] Step 4:

[0440] The server sends the user's emotional state to the emotion engine for analysis, which evaluates the user's emotional state and influences how the results are presented.

[0441] Step 5:

[0442] The server adjusts the presentation of the analysis results based on the emotion engine's analysis: if the user is deemed calm, detailed data is displayed, but if the user is deemed anxious, a concise report highlighting only the main points is created, providing information in a format that is optimal for the user.

[0443] Step 6:

[0444] The terminal receives the adjusted analysis results sent from the server and displays them to the user, providing the output as reports and graphs of the optimized analysis results.

[0445] (Application example 2)

[0446] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0447] Conventional information search systems and document creation systems provide uniform results without considering the user's emotional state, resulting in problems such as reduced user satisfaction and reduced work efficiency. Furthermore, they lacked the flexibility to respond to user emotions and lacked a system to reduce user stress. As a result, there was concern that the user experience would deteriorate and the utilization rate of content distribution services would decline.

[0448] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0449] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model and automatically creating materials, means for analyzing marketing data using a generative model and extracting trends and insights, means for analyzing user emotions using an emotion engine and adjusting the data presentation method accordingly, and means for suggesting content based on the user's emotional state using the emotion engine, thereby enabling the presentation of appropriate content and materials according to the user's emotional state.

[0450] A "generative model" is a type of artificial intelligence that analyzes user input or datasets and generates relevant information based on them.

[0451] The "emotion engine" is a part of artificial intelligence that analyzes a user's facial expressions, voice, vital signs, etc. to identify the user's emotional state.

[0452] "Data Source" means a system or device that contains the raw data that provides the information.

[0453] A "search query" is a phrase or keyword that a user enters to search for specific information.

[0454] "Uploading" is the act of a user sending data from a local device to a server or cloud storage.

[0455] A "dataset" is a collection of data collected for the purposes of statistical analysis or machine learning.

[0456] A "trend" is the tendency or movement of data or events over a specific period of time.

[0457] "Insights" refers to insights and findings gained from data analysis and research.

[0458] "Content suggestion" refers to suggesting information or entertainment that a user is looking for.

[0459] In this invention, the server, the terminal, and the user work closely together to realize an emotion-adaptive content suggestion system.

[0460] System Program

[0461] The server collects information from various data sources (email systems, document creation tools, intranets, etc.) and passes it to the generative model for analysis. The server also uses an emotion engine to analyze the user's emotions and adjust the way data is presented accordingly. The emotion engine analyzes the user's emotions in real time using a camera, microphone, and vital signs sensors.

[0462] Hardware and Software

[0463] Hardware:

[0464] Camera (acquiring video data for emotion analysis)

[0465] Microphone (audio data acquisition)

[0466] Vital sensors (monitoring heart rate and stress levels)

[0467] software:

[0468] OpenCV: Analyze camera images using image processing library

[0469] TENSORFLOW® and Keras: Implements generative models used in natural language processing and image / audio data analysis.

[0470] scikit-learn: Used for data preprocessing and scaling

[0471] Specific example explanation

[0472] Efficient information search

[0473] When a user searches for "latest marketing reports," the server gathers relevant information from each data source. A generative model uses natural language understanding to parse the query and extract the relevant information. An emotion engine analyzes the user's stress level and prioritizes concise, important information if the stress level is high.

[0474] Improving the efficiency of document creation

[0475] When users upload sales data for new products, the server passes the data through a generative model that automatically generates key statistics and graphs. The emotion engine provides presentation materials with plain language and ample visual support for users who are nervous about preparing a presentation.

[0476] Shorter analysis time

[0477] Users provide marketing data, and the server uses generative models to analyze the data and extract trends and insights. The emotion engine analyzes the user's calmness level and provides an interactive dashboard with detailed information if they are calm, or a concise report highlighting the key points if they are anxious.

[0478] Prompt Sentence Examples

[0479] "Generate a list of movies to recommend when the user is in a happy state."

[0480] "Generate content that has a relaxing effect that is perfect for when the user is feeling stressed."

[0481] This combines the generative AI model with the emotion engine to provide flexible data that responds to the user's emotional state.

[0482] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0483] Step 1:

[0484] The user device collects real-time data from the user using a camera, microphone, and vital sensors. Specifically, the camera captures the user's facial expressions, the microphone collects voice data, and the vital sensors measure heart rate and stress level. The input is the user's facial expression data, voice data, and heart rate data, which are then sent to the server.

[0485] Step 2:

[0486] The server uses an emotion engine to analyze the user's emotional state. It uses camera data (facial expressions), microphone data (audio), and vital data (heart rate, etc.) as input. Specifically, it uses OpenCV to extract facial features, and TensorFlow and Keras to analyze audio and vital data. The output is the user's emotional state (e.g., joy, sadness, stress).

[0487] Step 3:

[0488] A user searches for information or uploads data. In this case, the user inputs a search query or a dataset. For example, a user might input "latest marketing report" as a search query or upload sales data. The input is a search query or a dataset.

[0489] Step 4:

[0490] The server uses the generative model to analyze user input (search query or dataset). Specifically, it uses natural language understanding to parse the search query and extract information from relevant data sources (e.g., email systems, word processing tools, intranets, etc.). It also analyzes uploaded datasets (e.g., Excel files) and automatically generates key statistics and graphs. The output is a list of relevant information or an automatically generated resource.

[0491] Step 5:

[0492] The server adjusts the display order and presentation format of the data based on the user's emotional state. Specifically, based on the output of the emotion engine (user's emotional state), it makes adjustments such as prioritizing concise information when the stress level is high. The inputs are the output of the emotion engine and the output of the generative model, and the output is the adjusted information or materials.

[0493] Step 6:

[0494] The server uses an emotion engine to suggest content based on the user's emotional state. Specifically, the emotion engine analyzes the user's current emotions and uses a generative model to suggest appropriate content (movies, music, articles, etc.). The inputs are the output of the emotion engine and a content database, and the output is a list of recommended content.

[0495] Step 7:

[0496] The user's device presents the adjusted information and recommended content sent from the server to the user. Specifically, the generated materials and recommended content are displayed on a device such as a smartphone or head-mounted display. The input is data from the server, and the output is information displayed in a form that the user can see.

[0497] This series of processes enables users to receive the most appropriate data and content according to their emotional state.

[0498] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0499] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0500] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0501] [Second embodiment]

[0502] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0503] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0504] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0505] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0506] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0507] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0508] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0509] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0510] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0511] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0512] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0513] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0514] This invention is a system for improving business efficiency by utilizing generative models. Specific examples include improving the efficiency of information search, document creation, and shortening analysis time. Specific embodiments of this system are described below.

[0515] Efficient information search

[0516] The server receives the search query entered by the user and passes it to the generative model. The generative model analyzes the query and collects information from relevant data sources (e.g., email systems, word processing tools, company intranets). The collected information is integrated and sent to the user's device. This allows the user to quickly access the information they need from a single interface.

[0517] Specific examples

[0518] When a user searches for "latest marketing reports," the server gathers relevant documents from Gmail, Google Docs, and the intranet and displays them on the device, allowing users to get the information they need in one place without having to use multiple tools.

[0519] Improving the efficiency of document creation

[0520] When a user uploads a dataset for document creation, the server passes it to a generative model. The generative model analyzes the data and automatically creates key statistics and graphs. These analysis results are integrated into the specified format (e.g., presentation, report) and sent to the user's device. Users can obtain high-quality documents in a short time.

[0521] Specific examples

[0522] When a user uploads new product sales data (an Excel file), the server analyzes it and automatically graphs sales trends and key indicators, generating a PowerPoint presentation that is instantly delivered to the user's device.

[0523] Shorter analysis time

[0524] When users provide marketing data for analysis, the server passes it to the generative model, which analyzes the data and extracts trends and insights. The analysis results are generated as interactive dashboards and detailed reports and sent to the user's device, allowing users to quickly understand the current market situation and trends.

[0525] Specific examples

[0526] Users can upload customer data for a specific market, and the server analyzes it to extract purchasing patterns by age group and sales trends by region. The results are displayed on the device as an interactive dashboard, allowing users to perform detailed data analysis.

[0527] This system integrates the processes of information search, document creation, and data analysis around a generative model, significantly improving users' work efficiency.

[0528] The processing flow will be explained below.

[0529] Efficient information search

[0530] Step 1:

[0531] A user enters a search query into the search bar.

[0532] Step 2:

[0533] The terminal transmits the entered search query to the server.

[0534] Step 3:

[0535] The server passes the received search query to the generative model.

[0536] Step 4:

[0537] A generative model parses the search query and generates requests to relevant data sources (e.g., email system, word processing tool, company intranet).

[0538] Step 5:

[0539] The server sends a request to each data source via an API.

[0540] Step 6:

[0541] Each data source responds with relevant data in response to a request.

[0542] Step 7:

[0543] The server receives the collected data, analyzes it with a generative model, and integrates it.

[0544] Step 8:

[0545] The server sends the integrated search results to the terminal.

[0546] Step 9:

[0547] The terminal displays the results to the user.

[0548] Improving the efficiency of document creation

[0549] Step 1:

[0550] The user uploads a dataset (e.g., an Excel file) from their device to create a document.

[0551] Step 2:

[0552] The device sends the data set to the server.

[0553] Step 3:

[0554] The server receives the data and passes it to the generative model.

[0555] Step 4:

[0556] A generative model analyzes the dataset and produces key statistics and graphs.

[0557] Step 5:

[0558] Based on the analysis results, the generative model automatically generates materials in the specified format (e.g., presentation, report).

[0559] Step 6:

[0560] The server transmits the generated materials to the user's terminal.

[0561] Step 7:

[0562] The terminal allows the user to display or download the material.

[0563] Shorter analysis time

[0564] Step 1:

[0565] The user uploads data (e.g., customer data) for analysis from their device.

[0566] Step 2:

[0567] The device sends the data to the server.

[0568] Step 3:

[0569] The server receives the data and passes it to the generative model.

[0570] Step 4:

[0571] Generative models analyze the data and extract trends and insights.

[0572] Step 5:

[0573] The generative model generates the analysis results in the form of reports and dashboards.

[0574] Step 6:

[0575] The server sends the generated results to the user's terminal.

[0576] Step 7:

[0577] The terminal displays the results to the user and provides interactivity where necessary.

[0578] The above steps enable efficient information search, document creation, and data analysis, greatly improving the user's work efficiency.

[0579] Example 1

[0580] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0581] In the past, the processes of information search, document creation, and data analysis required separate tasks, significantly reducing user efficiency. Furthermore, the need to use multiple tools and platforms made it difficult to centrally manage information, which required time and effort.

[0582] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0583] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple information sources using a generative AI model, means for analyzing a dataset uploaded from a terminal using the generative AI model and automatically generating materials, means for analyzing marketing data using the generative AI model and extracting trends and insights, means for analyzing the search query and collecting information from specific information sources, means for integrating the collected information and sending it to the terminal, means for analyzing the dataset and integrating the analysis results into a specified format, and means for compiling the analysis results into an interactive dashboard or a detailed report. This allows users to integrate information search, document creation, and data analysis within a single system, significantly improving work efficiency.

[0584] A "generative AI model" is an artificial intelligence algorithm that analyzes natural language queries and datasets entered by users and generates appropriate responses or analytical results.

[0585] A "search query" refers to a question or keyword that a user enters to search for specific information.

[0586] "Sources" refer to multiple databases or systems that contain information relevant to a search query, such as email systems, word processing tools, and intranets.

[0587] A "dataset" refers to a set of data provided by a user for a specific analysis or document creation, and examples include Excel files and CSV files.

[0588] "Integration" refers to the process of bringing together information obtained from different sources and data formats and making it easy for users to use.

[0589] "Documents" refers to documents such as reports and presentations created using generative AI models.

[0590] "Insights" refers to useful insights and understanding gained through data analysis, and is information that is useful for business decision-making.

[0591] A "dashboard" refers to an interface for visually displaying the results of data analysis, including graphs and charts.

[0592] This invention is a system for improving business efficiency using a generative AI model. Specifically, it aims to automate the processes of information search, document creation, and data analysis, thereby improving the business efficiency of users. Specific embodiments for implementing this invention are described below.

[0593] Efficient information search

[0594] A user enters a search query into their device. For example, they might type "latest marketing report." The device then sends this search query to a server. The server then passes the received search query to a generative AI model (e.g., GPT-4) for analysis. The generative AI model analyzes the search query and identifies relevant information sources (e.g., email system, word processing tool, company intranet). The server then collects and integrates the necessary information from the identified information sources. The integrated information is then sent from the server to the user's device, allowing the user to quickly access the information they need from a single interface.

[0595] Specific examples

[0596] When a user searches for "latest marketing reports," the server gathers relevant documents from Gmail, Google Docs, and your intranet, consolidates them, and displays them on the user's device.

[0597] Prompt example

[0598] "Find the latest marketing reports!"

[0599] Improving the efficiency of document creation

[0600] A user uploads a dataset from their device to create a document. For example, they upload "New Product Sales Data.xlsx." The device sends the dataset to a server. The server passes the dataset to a generative AI model (e.g., OpenAI Codex) and requests data analysis. The generative AI model analyzes the dataset and automatically generates key statistics and graphs. The generated statistics and graphs are integrated into a specified format (e.g., PowerPoint presentation) and sent to the user's device. The user can obtain high-quality documents in a short amount of time.

[0601] Specific examples

[0602] When a user uploads new product sales data (an Excel file), the server passes it through a generative AI model, which automatically graphs sales trends and key indicators, and the resulting PowerPoint presentation is instantly delivered to the user's device.

[0603] Prompt example

[0604] "Analyze sales data for new products and create presentation materials!"

[0605] Shorter analysis time

[0606] The user uploads marketing data from their device. For example, they upload "CustomerData.csv". The device sends the marketing data to the server. The server passes the received data to a generative AI model (e.g., BERT) for data analysis. The generative AI model analyzes the data and extracts trends and insights. The extracted information is compiled into interactive dashboards and detailed reports, which are then sent from the server to the user's device. The user can quickly grasp the current market situation and trends.

[0607] Specific examples

[0608] Users upload customer data for a specific market, and the server analyzes the data to extract customer purchasing patterns and regional sales trends. These results are displayed on the user's device as an interactive dashboard.

[0609] Prompt example

[0610] "Analyze customer data for a specific market and create a report highlighting key trends!"

[0611] This system utilizes generative AI models to streamline the processes of information search, document creation, and data analysis, significantly improving user work efficiency. This implementation frees users from the hassle of using multiple tools and platforms, allowing them to manage and use all information through a single interface.

[0612] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0613] Efficient information search

[0614] Step 1:

[0615] A user enters a search query into a device.

[0616] Input: Search query (e.g. "latest marketing report")

[0617] Action: Enter keywords in the search field

[0618] Output: The search query entered by the user

[0619] Step 2:

[0620] The terminal transmits the entered search query to the server.

[0621] Input: Search query

[0622] What it does: Creates an HTTP request and sends it to the server. The query is packaged in JSON format.

[0623] Output: The search query sent (received on the server side)

[0624] Step 3:

[0625] The server passes the search query to the generative AI model.

[0626] Input: Received search query

[0627] How it works: Passing a query to a generative AI model and requesting analysis

[0628] Output: The search query sent to the generative AI model

[0629] Step 4:

[0630] A generative AI model analyzes search queries.

[0631] Input: Search query passed by the server

[0632] How it works: Analyzes the query content and identifies relevant sources of information (e.g., company intranet, email system, word processing tool)

[0633] Output: List of relevant sources

[0634] Step 5:

[0635] The server identifies relevant data sources and collects the information.

[0636] Input: List of relevant sources

[0637] Operation: Calls the API of each information source and collects relevant information

[0638] Output: Information collected from each data source

[0639] Step 6:

[0640] The server aggregates the collected information.

[0641] Input: Collected information

[0642] What it does: Consolidates information into a single response dataset

[0643] Output: A consolidated response dataset

[0644] Step 7:

[0645] The server sends the integrated information to the user's terminal.

[0646] Input: Consolidated response dataset

[0647] Behavior: Creates an HTTP response and sends it to the user's device.

[0648] Output: The aggregated information sent to the user's device

[0649] Step 8:

[0650] The terminal displays the integrated information to the user.

[0651] Input: Received consolidated information

[0652] What it does: Parses JSON-formatted data and displays it visually (e.g., in a web browser)

[0653] Output: Consolidated information displayed to the user

[0654] Improving the efficiency of document creation

[0655] Step 1:

[0656] The user uploads a dataset from the terminal to create a document.

[0657] Input: File (e.g. "New Product Sales Data.xlsx")

[0658] Action: Select a dataset from the file selection dialog

[0659] Output: Selected files

[0660] Step 2:

[0661] The device sends the data set to the server.

[0662] Input: File (dataset)

[0663] What it does: Sends a file via an HTTP POST request, with the data encoded in multipart format.

[0664] Output: The file sent

[0665] Step 3:

[0666] The server passes the dataset to the generative AI model.

[0667] Input: The received dataset

[0668] What it does: Pass a dataset to a generative AI model and make a request to analyze it

[0669] Output: The dataset sent to the generative AI model

[0670] Step 4:

[0671] A generative AI model analyzes the dataset.

[0672] Input: Dataset passed from the server

[0673] What it does: Analyzes data and generates key statistics and graphs

[0674] Output: Analyzed statistics and graphs

[0675] Step 5:

[0676] The server integrates the analysis results into the specified format (e.g. PowerPoint).

[0677] Input: Analyzed statistics and graphs

[0678] Action: Integrates into a specified document format and creates a document (e.g., PowerPoint slides)

[0679] Output: Generated documentation file

[0680] Step 6:

[0681] The server transmits the generated materials to the user's terminal.

[0682] Input: Generated document file

[0683] Action: Sends a document file in the HTTP response

[0684] Output: The file sent to the user's device

[0685] Step 7:

[0686] The terminal displays the material to the user.

[0687] Input: Received document file

[0688] Behavior: Generates a download link and provides it to the user

[0689] Output: A file of the displayed material that can be downloaded by the user.

[0690] Shorter analysis time

[0691] Step 1:

[0692] The user uploads marketing data from the device.

[0693] Input: File (e.g. "CustomerData.csv")

[0694] Action: Select data from file selection dialog

[0695] Output: Selected files

[0696] Step 2:

[0697] The device sends the marketing data to the server.

[0698] Input: File (Marketing Data)

[0699] What it does: Sends a file via an HTTP POST request, with the data encoded in multipart format.

[0700] Output: The file sent

[0701] Step 3:

[0702] The server passes the data to the generative AI model.

[0703] Input: Received file

[0704] Action: Pass a file to the generative AI model and request analysis

[0705] Output: The file sent to the generative AI model

[0706] Step 4:

[0707] Generative AI models analyze the data and extract trends and insights.

[0708] Input: File passed from the server

[0709] Action: Analyze data and extract trends and insights

[0710] Output: Analyzed trends and insights

[0711] Step 5:

[0712] The server compiles the analysis results into interactive dashboards and detailed reports.

[0713] Input: Analyzed trends and insights

[0714] How it works: Generate interactive dashboards and detailed reports

[0715] Output: Generated dashboards and reports

[0716] Step 6:

[0717] The server sends the results to the user's terminal.

[0718] Input: Generated dashboards and reports

[0719] Action: Send the result in an HTTP response

[0720] Output: Dashboards and reports sent to the user's device

[0721] Step 7:

[0722] The terminal displays the results to the user.

[0723] Input: Incoming dashboards and reports

[0724] Action: Visually displays a dashboard or report (e.g., in a web browser)

[0725] Output: The results displayed in a form that the user can interact with.

[0726] (Application example 1)

[0727] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0728] In logistics centers, quickly collecting and integrating information from multiple data sources is challenging when searching for necessary information in real time. Uploading data sets for document creation and manually compiling analytical and statistical information is time-consuming and labor-intensive. Analyzing marketing data quickly and effectively to extract important trends and insights is also a challenge. To streamline on-site operations, it is necessary to process this information in real time and display it on visual devices such as smart glasses, thereby improving efficiency.

[0729] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0730] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model to automatically create materials, means for analyzing marketing data using a generative model to extract trends and insights, means for converting real-time voice input into text data and processing it as the specified search query, and means for outputting related information based on the search query to a visual device for displaying it, thereby enabling logistics center staff to quickly and centrally obtain information through the smart glasses to create materials and analyze data.

[0731] A "generative model" is an algorithm that analyzes data or queries entered by a user and automatically generates related information or data.

[0732] A "specified search query" is a search request entered by a user into a server to obtain the information desired.

[0733] "Data Source" refers to multiple databases or information resources that are referenced to obtain information.

[0734] "Means of integration" refers to a method of consolidating information obtained from multiple data sources into one and providing it in a centralized manner.

[0735] A "dataset" is a set of data uploaded by a user for analysis or documentation purposes.

[0736] "Material creation means" refers to a method for automatically generating materials in a specified format by analyzing and processing the uploaded dataset.

[0737] "Marketing data" refers to data used for market research and consumer behavior analysis.

[0738] A "trend" is a specific tendency or tendency found in data.

[0739] "Insights" refers to insights and findings revealed through data analysis.

[0740] "Real-time voice input" is a technology that instantly processes the voice spoken by the user as digital data.

[0741] "Text data" refers to voice input converted into text information.

[0742] A "visual device" is a tool for visually presenting information to a user, and specifically includes smart glasses.

[0743] This invention is a system for improving operational efficiency in logistics centers, specifically, a method for using generative AI models to perform information retrieval, document creation, and data analysis in real time, and providing information to visual devices such as smart glasses.

[0744] Hardware and software used

[0745] Hardware: Smart glasses (e.g., Google Glass)

[0746] Software: Generative AI models (e.g., GPT-4), database systems (e.g., MySQL, PostgreSQL), real-time speech recognition (e.g., Google Speech-to-Text API)

[0747] Processing flow and system operation

[0748] 1. Voice to Text

[0749] The user speaks into the microphone of the smart glasses to input voice commands. The voice commands (e.g., "Show me the latest inventory list") are captured by the microphone and converted into text data in real time using the Google Speech-to-Text API.

[0750] 2. Search query analysis and data collection

[0751] The text search query is analyzed by a generative AI model (GPT-4), which understands the query and generates appropriate SQL queries to gather relevant information from multiple data sources (e.g., corporate databases, inventory management systems, etc.). The generated SQL queries are then executed in a database system to extract the relevant data.

[0752] 3. Data integration and documentation

[0753] The extracted data is integrated with a generative AI model to automatically generate documents and reports in the specified format. For example, sales data and inventory data can be automatically graphed and compiled into a detailed report.

[0754] 4. Real-time display

[0755] The generated information and materials are displayed in real time on the smart glasses' display, allowing users to quickly access the information they need without using their hands.

[0756] Example prompt

[0757] Below are some examples of prompts that can be used with this system:

[0758] "View the latest inventory list"

[0759] I'd like to check the delivery schedule.

[0760] "Please prepare yesterday's shipping report."

[0761] This invention allows staff at logistics centers to use voice input to efficiently perform complex information searches, data analysis, document creation, etc. By implementing this system, work efficiency is improved and work can be carried out quickly and accurately.

[0762] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0763] Step 1:

[0764] The user speaks into the microphone in the smart glasses, for example, saying, "Show me the latest inventory list." The microphone in the smart glasses captures the voice and sends it in real time to the Google Speech-to-Text API.

[0765] Input: User voice input

[0766] Output: Audio data

[0767] Step 2:

[0768] The server uses the Google Speech-to-Text API to convert the voice data into text data. For example, the voice input "Show me the latest inventory list" is converted into text data "Show me the latest inventory list."

[0769] Input: Audio data

[0770] Output: Text data

[0771] Step 3:

[0772] The server passes the text data to a generative AI model (GPT-4) for analysis, which uses natural language understanding to analyze the search query and generate the SQL queries needed to retrieve information from relevant data sources.

[0773] Input: Text data

[0774] Output: Generated SQL query

[0775] Step 4:

[0776] The server sends an SQL query to a database system (e.g., MySQL, PostgreSQL) to extract the required data. For example, an SQL query to get the "latest inventory list" is executed, and the relevant data is extracted from the inventory management system.

[0777] Input: SQL query

[0778] Output: Data extracted from the database

[0779] Step 5:

[0780] The server integrates the extracted data with a generative AI model and automatically generates documents in the specified format (e.g., list format, table format). For example, an inventory list can be compiled in a table format.

[0781] Input: Extracted data

[0782] Output: Automatically generated materials

[0783] Step 6:

[0784] The server sends the automatically generated information to the smart glasses and displays it in real time, allowing the user to check the information displayed on the smart glasses' display.

[0785] Input: Auto-generated material

[0786] Output: Information displayed on the smart glasses

[0787] This allows users to use voice input to quickly and efficiently perform complex information searches, data analysis, and document creation.

[0788] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0789] This invention provides a system that combines a generative model and an emotion engine to recognize user emotions and automatically adjust business processes. Specific examples include improving the efficiency of information search, document creation, and shortening analysis time, as well as presenting and editing data according to the user's emotions.

[0790] Efficient information search

[0791] The server receives the search query entered by the user and passes it to the generative model. The generative model analyzes the query and collects information from relevant data sources (e.g., email systems, word processing tools, company intranets). In parallel, the emotion engine analyzes the user's emotions and adjusts the order and display format of the search results, allowing the user to retrieve information more appropriately.

[0792] Specific examples

[0793] When a user searches for "latest marketing reports," the server gathers relevant documents from Gmail, Google Docs, and the intranet. If the emotion engine determines that the user's stress level is high, it prioritizes the most concise and important information.

[0794] Improving the efficiency of document creation

[0795] When a user uploads a dataset to create a document, the server passes it to a generative model. The generative model analyzes the data and automatically creates key statistics and graphs. In addition, an emotion engine analyzes the user's emotions and adjusts the tone and style of the document. This allows users to create high-quality documents without spending a lot of time.

[0796] Specific examples

[0797] When a user uploads sales data (Excel file) for a new product, the server analyzes it and automatically graphs sales trends and key indicators. If the user is nervous about preparing a presentation, the emotion engine generates presentation materials using simple language and plenty of visual support.

[0798] Shorter analysis time

[0799] When a user provides marketing data for analysis, the server passes it to the generative model. The generative model analyzes the data and extracts trends and insights. The emotion engine analyzes the user's emotions and adjusts the presentation method and interface of the analysis results as needed. This allows users to quickly understand the current market situation and trends, and work at an appropriate stress level.

[0800] Specific examples

[0801] Users upload customer data for a specific market, and the server analyzes it to extract purchasing patterns by age group and sales trends by region. If the emotion engine determines that the user is calm, it will provide an interactive dashboard with detailed data, but if it determines that the user is anxious, it will provide a concise report highlighting only the key points.

[0802] By combining a generative model with an emotion engine, this system enables flexible responses according to the user's emotional state, significantly improving work efficiency and user satisfaction.

[0803] The processing flow will be explained below.

[0804] Efficient information search

[0805] Step 1:

[0806] A user enters a search query into the search bar.

[0807] Step 2:

[0808] The terminal transmits the entered search query to the server.

[0809] Step 3:

[0810] The server passes the received search query to the generative model.

[0811] Step 4:

[0812] A generative model parses the search query and generates requests to relevant data sources (e.g., email system, word processing tool, company intranet).

[0813] Step 5:

[0814] The server sends a request to each data source via an API.

[0815] Step 6:

[0816] Each data source responds with relevant data in response to a request.

[0817] Step 7:

[0818] The server receives the collected data, analyzes it with a generative model, and integrates it.

[0819] Step 8:

[0820] The emotion engine analyzes the user's emotions and adjusts the order and display format of search results.

[0821] Step 9:

[0822] The server sends the adjusted search results to the device.

[0823] Step 10:

[0824] The terminal displays the results to the user.

[0825] Improving the efficiency of document creation

[0826] Step 1:

[0827] The user uploads a dataset (e.g., an Excel file) from their device to create a document.

[0828] Step 2:

[0829] The device sends the data set to the server.

[0830] Step 3:

[0831] The server receives the data and passes it to the generative model.

[0832] Step 4:

[0833] A generative model analyzes the dataset and produces key statistics and graphs.

[0834] Step 5:

[0835] Based on the analysis results, the generative model automatically generates materials in the specified format (e.g., presentation, report).

[0836] Step 6:

[0837] The emotion engine analyzes the user's emotions and adjusts the tone and style of the material.

[0838] Step 7:

[0839] The server transmits the generated materials to the terminal.

[0840] Step 8:

[0841] The terminal allows the user to display or download the material.

[0842] Shorter analysis time

[0843] Step 1:

[0844] The user uploads data (e.g., customer data) for analysis from their device.

[0845] Step 2:

[0846] The device sends the data to the server.

[0847] Step 3:

[0848] The server receives the data and passes it to the generative model.

[0849] Step 4:

[0850] Generative models analyze the data and extract trends and insights.

[0851] Step 5:

[0852] The generative model generates the analysis results in the form of reports and dashboards.

[0853] Step 6:

[0854] The emotion engine analyzes the user's emotions and adjusts the way the analysis results are presented and the interface.

[0855] Step 7:

[0856] The server transmits the generated results to the terminal.

[0857] Step 8:

[0858] The terminal displays the results to the user and provides interactivity where necessary.

[0859] These steps allow for efficient information search, document creation, and data analysis, and enable flexible responses to the user's emotional state.

[0860] Example 2

[0861] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0862] In conventional systems, even when a user enters a search query, the results are not optimized according to the user's emotional state, making information acquisition and document creation inefficient. Furthermore, analyzing large amounts of data takes time, and the system does not provide an interface that responds to the user's emotions, resulting in problems such as reduced work efficiency and user satisfaction.

[0863] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0864] In this invention, the server includes means for extracting and integrating data related to a search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model and automatically creating materials, means for analyzing marketing data using a generative model and extracting trends and insights, and means for adjusting search results, materials, and analysis results using an emotion engine that analyzes the user's emotional state. This enables flexible responses according to the user's emotional state, making it possible to significantly improve business efficiency and user satisfaction.

[0865] A "generative model" is a means of analyzing user input and generating or extracting relevant data using machine learning algorithms.

[0866] An "emotion engine" is a means of analyzing a user's emotional state and adjusting the display order and format of data based on the results.

[0867] A "search query" is the text or keywords that a user enters to obtain information.

[0868] "Data sources" are various sources for collecting information, including, for example, email systems, word processing tools, and company intranets.

[0869] A "dataset" is a collection of data that is the subject of document creation or data analysis, and includes, for example, data in spreadsheet format.

[0870] A "trend" is a temporal fluctuation or tendency obtained as a result of data analysis.

[0871] "Insight" refers to useful knowledge and insight gained through data analysis.

[0872] "User emotional state" refers to the psychological state of the user when searching for information, creating materials, or analyzing data, and includes stress, tension, calmness, etc.

[0873] "Adjustment" refers to changing the way information is presented or the format of the display based on the user's emotional state.

[0874] "Interface" refers to the means or display screen through which a user interacts with a system.

[0875] This invention provides a system that combines a generative model and an emotion engine to recognize user emotions and automatically adjust business processes. Specifically, it presents and edits data according to the user's emotions, improving the efficiency of information search, document creation, and shortening analysis time.

[0876] Efficient information search

[0877] When a user enters a search query (e.g., "latest marketing report"), the device sends this search query to the server. The server uses a generative model to analyze the query and collects information from related data sources (e.g., email system, word processing tool, company intranet). At the same time, the emotion engine analyzes the user's emotions and adjusts the order and display format of the search results. This allows the user to efficiently obtain optimized information. For example, when a user searches for "latest marketing report," the server collects related documents from the email system and word processing tool, and if the emotion engine determines that the user's stress level is high, it prioritizes displaying the most concise and important information.

[0878] Improving the efficiency of document creation

[0879] When a user uploads a dataset (e.g., an Excel file) from their device to create a presentation, the server passes the dataset to a generative model. The generative model analyzes the data and automatically creates key statistical information and graphs. Furthermore, an emotion engine analyzes the user's emotions and adjusts the tone and style of the presentation. This allows users to create high-quality presentations in a short amount of time. For example, when a user uploads sales data for a new product, the server analyzes it and automatically graphs sales trends and key indicators. If the emotion engine determines that the user is nervous about preparing a presentation, it generates presentation materials that use simple language and plenty of visual support elements.

[0880] Shorter analysis time

[0881] When a user uploads marketing data (e.g., customer data) from their device for analysis, the server passes the data to a generative model. The generative model analyzes the data and extracts trends and insights. The emotion engine analyzes the user's emotions and adjusts the presentation of the analysis results as needed. This allows users to quickly understand the current market situation and trends and work with an appropriate stress level. For example, when a user uploads customer data for a specific market, the server analyzes it and extracts purchasing patterns by age group and sales trends by region. If the emotion engine determines that the user is calm, it will provide an interactive dashboard with detailed data, but if it determines that the user is anxious, it will provide a concise report that highlights only the key points.

[0882] This invention allows for flexible responses according to the user's emotional state by combining a generative model and an emotion engine, thereby significantly improving business efficiency and user satisfaction.

[0883] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0884] Efficient information search

[0885] Step 1:

[0886] A user enters a search query into a device. This query is in text format (e.g., "latest marketing reports"), and this query triggers the start of an information search.

[0887] Step 2:

[0888] The device sends the entered search query to the server, which analyzes it on the server side.

[0889] Step 3:

[0890] The server passes the received query to the generative model for analysis. The generative model uses natural language understanding to analyze the query and extract the necessary information from relevant data sources (e.g., email systems, document creation tools, company intranets). The output is a list of relevant documents.

[0891] Step 4:

[0892] The server sends the user's input information and facial recognition data to the emotion engine, which analyzes the user's emotional state. The emotion engine evaluates the user's stress level and emotional state, and the results of this evaluation influence subsequent steps.

[0893] Step 5:

[0894] The server adjusts the presentation order and display format of the collected information based on the analysis results of the emotion engine. For example, if the user's stress level is high, the server will prioritize the most concise and important information. This process results in an ergonomic presentation of information.

[0895] Step 6:

[0896] The terminal receives the adjusted search results sent from the server and displays them to the user, with the output being displayed as an optimized list of information for the user to view.

[0897] Improving the efficiency of document creation

[0898] Step 1:

[0899] The user uploads a data set to the terminal for document creation, usually in the form of a spreadsheet (e.g., Excel file).

[0900] Step 2:

[0901] The device sends the uploaded dataset to the server, where the data is passed to the server in its raw format.

[0902] Step 3:

[0903] The server passes the dataset to a generative model for analysis. The generative model analyzes the data and automatically creates key statistics and graphs. The output is generated as a first draft of the document.

[0904] Step 4:

[0905] The server sends the user's emotional state to the emotion engine for analysis. The emotion engine evaluates the user's emotional state, such as stress or tension. The evaluation results are reflected in the content and format of the document.

[0906] Step 5:

[0907] The server adjusts the tone and style of the materials based on the analysis results of the emotion engine. For example, if the user is nervous, the server will create materials that use simple language and plenty of visual support. This results in user-friendly materials.

[0908] Step 6:

[0909] The terminal displays the adjusted material to the user, and the output is provided in a format that can be used for presentations or reports.

[0910] Shorter analysis time

[0911] Step 1:

[0912] The user provides marketing data to the device, typically in the form of a database or spreadsheet (e.g., customer data).

[0913] Step 2:

[0914] The device sends the provided marketing data to the server, which passes the data to the server in its raw form.

[0915] Step 3:

[0916] The server passes the data to a generative model for analysis. The generative model analyzes the data and extracts trends and insights. The output is generated as a list or graph of the analysis results.

[0917] Step 4:

[0918] The server sends the user's emotional state to the emotion engine for analysis, which evaluates the user's emotional state and influences how the results are presented.

[0919] Step 5:

[0920] The server adjusts the presentation of the analysis results based on the emotion engine's analysis: if the user is deemed calm, detailed data is displayed, but if the user is deemed anxious, a concise report highlighting only the main points is created, providing information in a format that is optimal for the user.

[0921] Step 6:

[0922] The terminal receives the adjusted analysis results sent from the server and displays them to the user, providing the output as reports and graphs of the optimized analysis results.

[0923] (Application example 2)

[0924] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0925] Conventional information search systems and document creation systems provide uniform results without considering the user's emotional state, resulting in problems such as reduced user satisfaction and reduced work efficiency. Furthermore, they lacked the flexibility to respond to user emotions and lacked a system to reduce user stress. As a result, there was concern that the user experience would deteriorate and the utilization rate of content distribution services would decline.

[0926] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0927] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model and automatically creating materials, means for analyzing marketing data using a generative model and extracting trends and insights, means for analyzing user emotions using an emotion engine and adjusting the data presentation method accordingly, and means for suggesting content based on the user's emotional state using the emotion engine, thereby enabling the presentation of appropriate content and materials according to the user's emotional state.

[0928] A "generative model" is a type of artificial intelligence that analyzes user input or datasets and generates relevant information based on them.

[0929] The "emotion engine" is a part of artificial intelligence that analyzes a user's facial expressions, voice, vital signs, etc. to identify the user's emotional state.

[0930] "Data Source" means a system or device that contains the raw data that provides the information.

[0931] A "search query" is a phrase or keyword that a user enters to search for specific information.

[0932] "Uploading" is the act of a user sending data from a local device to a server or cloud storage.

[0933] A "dataset" is a collection of data collected for the purposes of statistical analysis or machine learning.

[0934] A "trend" is the tendency or movement of data or events over a specific period of time.

[0935] "Insights" refers to insights and findings gained from data analysis and research.

[0936] "Content suggestion" refers to suggesting information or entertainment that a user is looking for.

[0937] In this invention, the server, the terminal, and the user work closely together to realize an emotion-adaptive content suggestion system.

[0938] System Program

[0939] The server collects information from various data sources (email systems, document creation tools, intranets, etc.) and passes it to the generative model for analysis. The server also uses an emotion engine to analyze the user's emotions and adjust the way data is presented accordingly. The emotion engine analyzes the user's emotions in real time using a camera, microphone, and vital signs sensors.

[0940] Hardware and Software

[0941] Hardware:

[0942] Camera (acquiring video data for emotion analysis)

[0943] Microphone (audio data acquisition)

[0944] Vital sensors (monitoring heart rate and stress levels)

[0945] software:

[0946] OpenCV: Analyze camera images using image processing library

[0947] TensorFlow and Keras: Implementing generative models used in natural language processing and image / audio data analysis

[0948] scikit-learn: Used for data preprocessing and scaling

[0949] Specific example explanation

[0950] Efficient information search

[0951] When a user searches for "latest marketing reports," the server gathers relevant information from each data source. A generative model uses natural language understanding to parse the query and extract the relevant information. An emotion engine analyzes the user's stress level and prioritizes concise, important information if the stress level is high.

[0952] Improving the efficiency of document creation

[0953] When users upload sales data for new products, the server passes the data through a generative model that automatically generates key statistics and graphs. The emotion engine provides presentation materials with plain language and ample visual support for users who are nervous about preparing a presentation.

[0954] Shorter analysis time

[0955] Users provide marketing data, and the server uses generative models to analyze the data and extract trends and insights. The emotion engine analyzes the user's calmness level and provides an interactive dashboard with detailed information if they are calm, or a concise report highlighting the key points if they are anxious.

[0956] Prompt Sentence Examples

[0957] "Generate a list of movies to recommend when the user is in a happy state."

[0958] "Generate content that has a relaxing effect that is perfect for when the user is feeling stressed."

[0959] This combines the generative AI model with the emotion engine to provide flexible data that responds to the user's emotional state.

[0960] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0961] Step 1:

[0962] The user device collects real-time data from the user using a camera, microphone, and vital sensors. Specifically, the camera captures the user's facial expressions, the microphone collects voice data, and the vital sensors measure heart rate and stress level. The input is the user's facial expression data, voice data, and heart rate data, which are then sent to the server.

[0963] Step 2:

[0964] The server uses an emotion engine to analyze the user's emotional state. It uses camera data (facial expressions), microphone data (audio), and vital data (heart rate, etc.) as input. Specifically, it uses OpenCV to extract facial features, and TensorFlow and Keras to analyze audio and vital data. The output is the user's emotional state (e.g., joy, sadness, stress).

[0965] Step 3:

[0966] A user searches for information or uploads data. In this case, the user inputs a search query or a dataset. For example, a user might input "latest marketing report" as a search query or upload sales data. The input is a search query or a dataset.

[0967] Step 4:

[0968] The server uses the generative model to analyze user input (search query or dataset). Specifically, it uses natural language understanding to parse the search query and extract information from relevant data sources (e.g., email systems, word processing tools, intranets, etc.). It also analyzes uploaded datasets (e.g., Excel files) and automatically generates key statistics and graphs. The output is a list of relevant information or an automatically generated resource.

[0969] Step 5:

[0970] The server adjusts the display order and presentation format of the data based on the user's emotional state. Specifically, based on the output of the emotion engine (user's emotional state), it makes adjustments such as prioritizing concise information when the stress level is high. The inputs are the output of the emotion engine and the output of the generative model, and the output is the adjusted information or materials.

[0971] Step 6:

[0972] The server uses an emotion engine to suggest content based on the user's emotional state. Specifically, the emotion engine analyzes the user's current emotions and uses a generative model to suggest appropriate content (movies, music, articles, etc.). The inputs are the output of the emotion engine and a content database, and the output is a list of recommended content.

[0973] Step 7:

[0974] The user's device presents the adjusted information and recommended content sent from the server to the user. Specifically, the generated materials and recommended content are displayed on a device such as a smartphone or head-mounted display. The input is data from the server, and the output is information displayed in a form that the user can see.

[0975] This series of processes enables users to receive the most appropriate data and content according to their emotional state.

[0976] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0977] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0978] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0979] [Third embodiment]

[0980] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0981] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0982] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0983] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0984] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0985] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0986] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0987] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0988] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0989] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0990] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0991] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0992] This invention is a system for improving business efficiency by utilizing generative models. Specific examples include improving the efficiency of information search, document creation, and shortening analysis time. Specific embodiments of this system are described below.

[0993] Efficient information search

[0994] The server receives the search query entered by the user and passes it to the generative model. The generative model analyzes the query and collects information from relevant data sources (e.g., email systems, word processing tools, company intranets). The collected information is integrated and sent to the user's device. This allows the user to quickly access the information they need from a single interface.

[0995] Specific examples

[0996] When a user searches for "latest marketing reports," the server gathers relevant documents from Gmail, Google Docs, and the intranet and displays them on the device, allowing users to get the information they need in one place without having to use multiple tools.

[0997] Improving the efficiency of document creation

[0998] When a user uploads a dataset for document creation, the server passes it to a generative model. The generative model analyzes the data and automatically creates key statistics and graphs. These analysis results are integrated into the specified format (e.g., presentation, report) and sent to the user's device. Users can obtain high-quality documents in a short time.

[0999] Specific examples

[1000] When a user uploads new product sales data (an Excel file), the server analyzes it and automatically graphs sales trends and key indicators, generating a PowerPoint presentation that is instantly delivered to the user's device.

[1001] Shorter analysis time

[1002] When users provide marketing data for analysis, the server passes it to the generative model, which analyzes the data and extracts trends and insights. The analysis results are generated as interactive dashboards and detailed reports and sent to the user's device, allowing users to quickly understand the current market situation and trends.

[1003] Specific examples

[1004] Users can upload customer data for a specific market, and the server analyzes it to extract purchasing patterns by age group and sales trends by region. The results are displayed on the device as an interactive dashboard, allowing users to perform detailed data analysis.

[1005] This system integrates the processes of information search, document creation, and data analysis around a generative model, significantly improving users' work efficiency.

[1006] The processing flow will be explained below.

[1007] Efficient information search

[1008] Step 1:

[1009] A user enters a search query into the search bar.

[1010] Step 2:

[1011] The terminal transmits the entered search query to the server.

[1012] Step 3:

[1013] The server passes the received search query to the generative model.

[1014] Step 4:

[1015] A generative model parses the search query and generates requests to relevant data sources (e.g., email system, word processing tool, company intranet).

[1016] Step 5:

[1017] The server sends a request to each data source via an API.

[1018] Step 6:

[1019] Each data source responds with relevant data in response to a request.

[1020] Step 7:

[1021] The server receives the collected data, analyzes it with a generative model, and integrates it.

[1022] Step 8:

[1023] The server sends the integrated search results to the terminal.

[1024] Step 9:

[1025] The terminal displays the results to the user.

[1026] Improving the efficiency of document creation

[1027] Step 1:

[1028] The user uploads a dataset (e.g., an Excel file) from their device to create a document.

[1029] Step 2:

[1030] The device sends the data set to the server.

[1031] Step 3:

[1032] The server receives the data and passes it to the generative model.

[1033] Step 4:

[1034] A generative model analyzes the dataset and produces key statistics and graphs.

[1035] Step 5:

[1036] Based on the analysis results, the generative model automatically generates materials in the specified format (e.g., presentation, report).

[1037] Step 6:

[1038] The server transmits the generated materials to the user's terminal.

[1039] Step 7:

[1040] The terminal allows the user to display or download the material.

[1041] Shorter analysis time

[1042] Step 1:

[1043] The user uploads data (e.g., customer data) for analysis from their device.

[1044] Step 2:

[1045] The device sends the data to the server.

[1046] Step 3:

[1047] The server receives the data and passes it to the generative model.

[1048] Step 4:

[1049] Generative models analyze the data and extract trends and insights.

[1050] Step 5:

[1051] The generative model generates the analysis results in the form of reports and dashboards.

[1052] Step 6:

[1053] The server sends the generated results to the user's terminal.

[1054] Step 7:

[1055] The terminal displays the results to the user and provides interactivity where necessary.

[1056] The above steps enable efficient information search, document creation, and data analysis, greatly improving the user's work efficiency.

[1057] Example 1

[1058] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1059] In the past, the processes of information search, document creation, and data analysis required separate tasks, significantly reducing user efficiency. Furthermore, the need to use multiple tools and platforms made it difficult to centrally manage information, which required time and effort.

[1060] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1061] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple information sources using a generative AI model, means for analyzing a dataset uploaded from a terminal using the generative AI model and automatically generating materials, means for analyzing marketing data using the generative AI model and extracting trends and insights, means for analyzing the search query and collecting information from specific information sources, means for integrating the collected information and sending it to the terminal, means for analyzing the dataset and integrating the analysis results into a specified format, and means for compiling the analysis results into an interactive dashboard or a detailed report. This allows users to integrate information search, document creation, and data analysis within a single system, significantly improving work efficiency.

[1062] A "generative AI model" is an artificial intelligence algorithm that analyzes natural language queries and datasets entered by users and generates appropriate responses or analytical results.

[1063] A "search query" refers to a question or keyword that a user enters to search for specific information.

[1064] "Sources" refer to multiple databases or systems that contain information relevant to a search query, such as email systems, word processing tools, and intranets.

[1065] A "dataset" refers to a set of data provided by a user for a specific analysis or document creation, and examples include Excel files and CSV files.

[1066] "Integration" refers to the process of bringing together information obtained from different sources and data formats and making it easy for users to use.

[1067] "Documents" refers to documents such as reports and presentations created using generative AI models.

[1068] "Insights" refers to useful insights and understanding gained through data analysis, and is information that is useful for business decision-making.

[1069] A "dashboard" refers to an interface for visually displaying the results of data analysis, including graphs and charts.

[1070] This invention is a system for improving business efficiency using a generative AI model. Specifically, it aims to automate the processes of information search, document creation, and data analysis, thereby improving the business efficiency of users. Specific embodiments for implementing this invention are described below.

[1071] Efficient information search

[1072] A user enters a search query into their device. For example, they might type "latest marketing report." The device then sends this search query to a server. The server then passes the received search query to a generative AI model (e.g., GPT-4) for analysis. The generative AI model analyzes the search query and identifies relevant information sources (e.g., email system, word processing tool, company intranet). The server then collects and integrates the necessary information from the identified information sources. The integrated information is then sent from the server to the user's device, allowing the user to quickly access the information they need from a single interface.

[1073] Specific examples

[1074] When a user searches for "latest marketing reports," the server gathers relevant documents from Gmail, Google Docs, and your intranet, consolidates them, and displays them on the user's device.

[1075] Example prompts

[1076] "Find the latest marketing reports!"

[1077] Improving the efficiency of document creation

[1078] A user uploads a dataset from their device to create a document. For example, they upload "New Product Sales Data.xlsx." The device sends the dataset to a server. The server passes the dataset to a generative AI model (e.g., OpenAI Codex) and requests data analysis. The generative AI model analyzes the dataset and automatically generates key statistics and graphs. The generated statistics and graphs are integrated into a specified format (e.g., PowerPoint presentation) and sent to the user's device. The user can obtain high-quality documents in a short amount of time.

[1079] Specific examples

[1080] When a user uploads new product sales data (an Excel file), the server passes it through a generative AI model, which automatically graphs sales trends and key indicators, and the resulting PowerPoint presentation is instantly delivered to the user's device.

[1081] Prompt example

[1082] "Analyze sales data for new products and create presentation materials!"

[1083] Shorter analysis time

[1084] The user uploads marketing data from their device. For example, they upload "CustomerData.csv". The device sends the marketing data to the server. The server passes the received data to a generative AI model (e.g., BERT) for data analysis. The generative AI model analyzes the data and extracts trends and insights. The extracted information is compiled into interactive dashboards and detailed reports, which are then sent from the server to the user's device. The user can quickly grasp the current market situation and trends.

[1085] Specific examples

[1086] Users upload customer data for a specific market, and the server analyzes the data to extract customer purchasing patterns and regional sales trends. These results are displayed on the user's device as an interactive dashboard.

[1087] Prompt example

[1088] "Analyze customer data for a specific market and create a report highlighting key trends!"

[1089] This system utilizes generative AI models to streamline the processes of information search, document creation, and data analysis, significantly improving user work efficiency. This implementation frees users from the hassle of using multiple tools and platforms, allowing them to manage and use all information through a single interface.

[1090] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1091] Efficient information search

[1092] Step 1:

[1093] A user enters a search query into a device.

[1094] Input: Search query (e.g. "latest marketing report")

[1095] Action: Enter keywords in the search field

[1096] Output: The search query entered by the user

[1097] Step 2:

[1098] The terminal transmits the entered search query to the server.

[1099] Input: Search query

[1100] What it does: Creates an HTTP request and sends it to the server. The query is packaged in JSON format.

[1101] Output: The search query sent (received on the server side)

[1102] Step 3:

[1103] The server passes the search query to the generative AI model.

[1104] Input: Received search query

[1105] How it works: Passing a query to a generative AI model and requesting analysis

[1106] Output: The search query sent to the generative AI model

[1107] Step 4:

[1108] A generative AI model analyzes search queries.

[1109] Input: Search query passed by the server

[1110] How it works: Analyzes the query content and identifies relevant sources of information (e.g., company intranet, email system, word processing tool)

[1111] Output: List of relevant sources

[1112] Step 5:

[1113] The server identifies relevant data sources and collects the information.

[1114] Input: List of relevant sources

[1115] Operation: Calls the API of each information source and collects relevant information

[1116] Output: Information collected from each data source

[1117] Step 6:

[1118] The server aggregates the collected information.

[1119] Input: Collected information

[1120] What it does: Consolidates information into a single response dataset

[1121] Output: A consolidated response dataset

[1122] Step 7:

[1123] The server sends the integrated information to the user's terminal.

[1124] Input: Consolidated response dataset

[1125] Behavior: Creates an HTTP response and sends it to the user's device.

[1126] Output: The aggregated information sent to the user's device

[1127] Step 8:

[1128] The terminal displays the integrated information to the user.

[1129] Input: Received consolidated information

[1130] What it does: Parses JSON-formatted data and displays it visually (e.g., in a web browser)

[1131] Output: Consolidated information displayed to the user

[1132] Improving the efficiency of document creation

[1133] Step 1:

[1134] The user uploads a dataset from the terminal to create a document.

[1135] Input: File (e.g. "New Product Sales Data.xlsx")

[1136] Action: Select a dataset from the file selection dialog

[1137] Output: Selected files

[1138] Step 2:

[1139] The device sends the data set to the server.

[1140] Input: File (dataset)

[1141] What it does: Sends a file via an HTTP POST request, with the data encoded in multipart format.

[1142] Output: The file sent

[1143] Step 3:

[1144] The server passes the dataset to the generative AI model.

[1145] Input: The received dataset

[1146] What it does: Pass a dataset to a generative AI model and make a request to analyze it

[1147] Output: The dataset sent to the generative AI model

[1148] Step 4:

[1149] A generative AI model analyzes the dataset.

[1150] Input: Dataset passed from the server

[1151] What it does: Analyzes data and generates key statistics and graphs

[1152] Output: Analyzed statistics and graphs

[1153] Step 5:

[1154] The server integrates the analysis results into the specified format (e.g. PowerPoint).

[1155] Input: Analyzed statistics and graphs

[1156] Action: Integrates into a specified document format and creates a document (e.g., PowerPoint slides)

[1157] Output: Generated documentation file

[1158] Step 6:

[1159] The server transmits the generated materials to the user's terminal.

[1160] Input: Generated document file

[1161] Action: Sends a document file in the HTTP response

[1162] Output: The file sent to the user's device

[1163] Step 7:

[1164] The terminal displays the material to the user.

[1165] Input: Received document file

[1166] Behavior: Generates a download link and provides it to the user

[1167] Output: A file of the displayed material that can be downloaded by the user.

[1168] Shorter analysis time

[1169] Step 1:

[1170] The user uploads marketing data from the device.

[1171] Input: File (e.g. "CustomerData.csv")

[1172] Action: Select data from file selection dialog

[1173] Output: Selected files

[1174] Step 2:

[1175] The device sends the marketing data to the server.

[1176] Input: File (Marketing Data)

[1177] What it does: Sends a file via an HTTP POST request, with the data encoded in multipart format.

[1178] Output: The file sent

[1179] Step 3:

[1180] The server passes the data to the generative AI model.

[1181] Input: Received file

[1182] Action: Pass a file to the generative AI model and request analysis

[1183] Output: The file sent to the generative AI model

[1184] Step 4:

[1185] Generative AI models analyze the data and extract trends and insights.

[1186] Input: File passed from the server

[1187] Action: Analyze data and extract trends and insights

[1188] Output: Analyzed trends and insights

[1189] Step 5:

[1190] The server compiles the analysis results into interactive dashboards and detailed reports.

[1191] Input: Analyzed trends and insights

[1192] How it works: Generate interactive dashboards and detailed reports

[1193] Output: Generated dashboards and reports

[1194] Step 6:

[1195] The server sends the results to the user's terminal.

[1196] Input: Generated dashboards and reports

[1197] Action: Send the result in an HTTP response

[1198] Output: Dashboards and reports sent to the user's device

[1199] Step 7:

[1200] The terminal displays the results to the user.

[1201] Input: Incoming dashboards and reports

[1202] Action: Visually displays a dashboard or report (e.g., in a web browser)

[1203] Output: The results displayed in a form that the user can interact with.

[1204] (Application example 1)

[1205] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1206] In logistics centers, quickly collecting and integrating information from multiple data sources is challenging when searching for necessary information in real time. Uploading data sets for document creation and manually compiling analytical and statistical information is time-consuming and labor-intensive. Analyzing marketing data quickly and effectively to extract important trends and insights is also a challenge. To streamline on-site operations, it is necessary to process this information in real time and display it on visual devices such as smart glasses, thereby improving efficiency.

[1207] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1208] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model to automatically create materials, means for analyzing marketing data using a generative model to extract trends and insights, means for converting real-time voice input into text data and processing it as the specified search query, and means for outputting related information based on the search query to a visual device for displaying it, thereby enabling logistics center staff to quickly and centrally obtain information through the smart glasses to create materials and analyze data.

[1209] A "generative model" is an algorithm that analyzes data or queries entered by a user and automatically generates related information or data.

[1210] A "specified search query" is a search request entered by a user into a server to obtain the information desired.

[1211] "Data Source" refers to multiple databases or information resources that are referenced to obtain information.

[1212] "Means of integration" refers to a method of consolidating information obtained from multiple data sources into one and providing it in a centralized manner.

[1213] A "dataset" is a set of data uploaded by a user for analysis or documentation purposes.

[1214] "Material creation means" refers to a method for automatically generating materials in a specified format by analyzing and processing the uploaded dataset.

[1215] "Marketing data" refers to data used for market research and consumer behavior analysis.

[1216] A "trend" is a specific tendency or tendency found in data.

[1217] "Insights" refers to insights and findings revealed through data analysis.

[1218] "Real-time voice input" is a technology that instantly processes the voice spoken by the user as digital data.

[1219] "Text data" refers to voice input converted into text information.

[1220] A "visual device" is a tool for visually presenting information to a user, and specifically includes smart glasses.

[1221] This invention is a system for improving operational efficiency in logistics centers, specifically, a method for using generative AI models to perform information retrieval, document creation, and data analysis in real time, and providing information to visual devices such as smart glasses.

[1222] Hardware and software used

[1223] Hardware: Smart glasses (e.g., Google Glass)

[1224] Software: Generative AI models (e.g., GPT-4), database systems (e.g., MySQL, PostgreSQL), real-time speech recognition (e.g., Google Speech-to-Text API)

[1225] Processing flow and system operation

[1226] 1. Voice to Text

[1227] The user speaks into the microphone of the smart glasses to input voice commands. The voice commands (e.g., "Show me the latest inventory list") are captured by the microphone and converted into text data in real time using the Google Speech-to-Text API.

[1228] 2. Search query analysis and data collection

[1229] The text search query is analyzed by a generative AI model (GPT-4), which understands the query and generates appropriate SQL queries to gather relevant information from multiple data sources (e.g., corporate databases, inventory management systems, etc.). The generated SQL queries are then executed in a database system to extract the relevant data.

[1230] 3. Data integration and documentation

[1231] The extracted data is integrated with a generative AI model to automatically generate documents and reports in the specified format. For example, sales data and inventory data can be automatically graphed and compiled into a detailed report.

[1232] 4. Real-time display

[1233] The generated information and materials are displayed in real time on the smart glasses' display, allowing users to quickly access the information they need without using their hands.

[1234] Example prompt

[1235] Below are some examples of prompts that can be used with this system:

[1236] "View the latest inventory list"

[1237] I'd like to check the delivery schedule.

[1238] "Please prepare yesterday's shipping report."

[1239] This invention allows staff at logistics centers to use voice input to efficiently perform complex information searches, data analysis, document creation, etc. By implementing this system, work efficiency is improved and work can be carried out quickly and accurately.

[1240] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1241] Step 1:

[1242] The user speaks into the microphone in the smart glasses, for example, saying, "Show me the latest inventory list." The microphone in the smart glasses captures the voice and sends it in real time to the Google Speech-to-Text API.

[1243] Input: User voice input

[1244] Output: Audio data

[1245] Step 2:

[1246] The server uses the Google Speech-to-Text API to convert the voice data into text data. For example, the voice input "Show me the latest inventory list" is converted into text data "Show me the latest inventory list."

[1247] Input: Audio data

[1248] Output: Text data

[1249] Step 3:

[1250] The server passes the text data to a generative AI model (GPT-4) for analysis, which uses natural language understanding to analyze the search query and generate the SQL queries needed to retrieve information from relevant data sources.

[1251] Input: Text data

[1252] Output: Generated SQL query

[1253] Step 4:

[1254] The server sends an SQL query to a database system (e.g., MySQL, PostgreSQL) to extract the required data. For example, an SQL query to get the "latest inventory list" is executed, and the relevant data is extracted from the inventory management system.

[1255] Input: SQL query

[1256] Output: Data extracted from the database

[1257] Step 5:

[1258] The server integrates the extracted data with a generative AI model and automatically generates documents in the specified format (e.g., list format, table format). For example, an inventory list can be compiled in a table format.

[1259] Input: Extracted data

[1260] Output: Automatically generated materials

[1261] Step 6:

[1262] The server sends the automatically generated information to the smart glasses and displays it in real time, allowing the user to check the information displayed on the smart glasses' display.

[1263] Input: Auto-generated material

[1264] Output: Information displayed on the smart glasses

[1265] This allows users to use voice input to quickly and efficiently perform complex information searches, data analysis, and document creation.

[1266] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1267] This invention provides a system that combines a generative model and an emotion engine to recognize user emotions and automatically adjust business processes. Specific examples include improving the efficiency of information search, document creation, and shortening analysis time, as well as presenting and editing data according to the user's emotions.

[1268] Efficient information search

[1269] The server receives the search query entered by the user and passes it to the generative model. The generative model analyzes the query and collects information from relevant data sources (e.g., email systems, word processing tools, company intranets). In parallel, the emotion engine analyzes the user's emotions and adjusts the order and display format of the search results, allowing the user to retrieve information more appropriately.

[1270] Specific examples

[1271] When a user searches for "latest marketing reports," the server gathers relevant documents from Gmail, Google Docs, and the intranet. If the emotion engine determines that the user's stress level is high, it prioritizes the most concise and important information.

[1272] Improving the efficiency of document creation

[1273] When a user uploads a dataset to create a document, the server passes it to a generative model. The generative model analyzes the data and automatically creates key statistics and graphs. In addition, an emotion engine analyzes the user's emotions and adjusts the tone and style of the document. This allows users to create high-quality documents without spending a lot of time.

[1274] Specific examples

[1275] When a user uploads sales data (Excel file) for a new product, the server analyzes it and automatically graphs sales trends and key indicators. If the user is nervous about preparing a presentation, the emotion engine generates presentation materials using simple language and plenty of visual support.

[1276] Shorter analysis time

[1277] When a user provides marketing data for analysis, the server passes it to the generative model. The generative model analyzes the data and extracts trends and insights. The emotion engine analyzes the user's emotions and adjusts the presentation method and interface of the analysis results as needed. This allows users to quickly understand the current market situation and trends, and work at an appropriate stress level.

[1278] Specific examples

[1279] Users upload customer data for a specific market, and the server analyzes it to extract purchasing patterns by age group and sales trends by region. If the emotion engine determines that the user is calm, it will provide an interactive dashboard with detailed data, but if it determines that the user is anxious, it will provide a concise report highlighting only the key points.

[1280] By combining a generative model with an emotion engine, this system enables flexible responses according to the user's emotional state, significantly improving work efficiency and user satisfaction.

[1281] The processing flow will be explained below.

[1282] Efficient information search

[1283] Step 1:

[1284] A user enters a search query into the search bar.

[1285] Step 2:

[1286] The terminal transmits the entered search query to the server.

[1287] Step 3:

[1288] The server passes the received search query to the generative model.

[1289] Step 4:

[1290] A generative model parses the search query and generates requests to relevant data sources (e.g., email system, word processing tool, company intranet).

[1291] Step 5:

[1292] The server sends a request to each data source via an API.

[1293] Step 6:

[1294] Each data source responds with relevant data in response to a request.

[1295] Step 7:

[1296] The server receives the collected data, analyzes it with a generative model, and integrates it.

[1297] Step 8:

[1298] The emotion engine analyzes the user's emotions and adjusts the order and display format of search results.

[1299] Step 9:

[1300] The server sends the adjusted search results to the device.

[1301] Step 10:

[1302] The terminal displays the results to the user.

[1303] Improving the efficiency of document creation

[1304] Step 1:

[1305] The user uploads a dataset (e.g., an Excel file) from their device to create a document.

[1306] Step 2:

[1307] The device sends the data set to the server.

[1308] Step 3:

[1309] The server receives the data and passes it to the generative model.

[1310] Step 4:

[1311] A generative model analyzes the dataset and produces key statistics and graphs.

[1312] Step 5:

[1313] Based on the analysis results, the generative model automatically generates materials in the specified format (e.g., presentation, report).

[1314] Step 6:

[1315] The emotion engine analyzes the user's emotions and adjusts the tone and style of the material.

[1316] Step 7:

[1317] The server transmits the generated materials to the terminal.

[1318] Step 8:

[1319] The terminal allows the user to display or download the material.

[1320] Shorter analysis time

[1321] Step 1:

[1322] The user uploads data (e.g., customer data) for analysis from their device.

[1323] Step 2:

[1324] The device sends the data to the server.

[1325] Step 3:

[1326] The server receives the data and passes it to the generative model.

[1327] Step 4:

[1328] Generative models analyze the data and extract trends and insights.

[1329] Step 5:

[1330] The generative model generates the analysis results in the form of reports and dashboards.

[1331] Step 6:

[1332] The emotion engine analyzes the user's emotions and adjusts the way the analysis results are presented and the interface.

[1333] Step 7:

[1334] The server transmits the generated results to the terminal.

[1335] Step 8:

[1336] The terminal displays the results to the user and provides interactivity where necessary.

[1337] These steps allow for efficient information search, document creation, and data analysis, and enable flexible responses to the user's emotional state.

[1338] Example 2

[1339] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1340] In conventional systems, even when a user enters a search query, the results are not optimized according to the user's emotional state, making information acquisition and document creation inefficient. Furthermore, analyzing large amounts of data takes time, and the system does not provide an interface that responds to the user's emotions, resulting in problems such as reduced work efficiency and user satisfaction.

[1341] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1342] In this invention, the server includes means for extracting and integrating data related to a search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model and automatically creating materials, means for analyzing marketing data using a generative model and extracting trends and insights, and means for adjusting search results, materials, and analysis results using an emotion engine that analyzes the user's emotional state. This enables flexible responses according to the user's emotional state, making it possible to significantly improve business efficiency and user satisfaction.

[1343] A "generative model" is a means of analyzing user input and generating or extracting relevant data using machine learning algorithms.

[1344] An "emotion engine" is a means of analyzing a user's emotional state and adjusting the display order and format of data based on the results.

[1345] A "search query" is the text or keywords that a user enters to obtain information.

[1346] "Data sources" are various sources for collecting information, including, for example, email systems, word processing tools, and company intranets.

[1347] A "dataset" is a collection of data that is the subject of document creation or data analysis, and includes, for example, data in spreadsheet format.

[1348] A "trend" is a temporal fluctuation or tendency obtained as a result of data analysis.

[1349] "Insight" refers to useful knowledge and insight gained through data analysis.

[1350] "User emotional state" refers to the psychological state of the user when searching for information, creating materials, or analyzing data, and includes stress, tension, calmness, etc.

[1351] "Adjustment" refers to changing the way information is presented or the format of the display based on the user's emotional state.

[1352] "Interface" refers to the means or display screen through which a user interacts with a system.

[1353] This invention provides a system that combines a generative model and an emotion engine to recognize user emotions and automatically adjust business processes. Specifically, it presents and edits data according to the user's emotions, improving the efficiency of information search, document creation, and shortening analysis time.

[1354] Efficient information search

[1355] When a user enters a search query (e.g., "latest marketing report"), the device sends this search query to the server. The server uses a generative model to analyze the query and collects information from related data sources (e.g., email system, word processing tool, company intranet). At the same time, the emotion engine analyzes the user's emotions and adjusts the order and display format of the search results. This allows the user to efficiently obtain optimized information. For example, when a user searches for "latest marketing report," the server collects related documents from the email system and word processing tool, and if the emotion engine determines that the user's stress level is high, it prioritizes displaying the most concise and important information.

[1356] Improving the efficiency of document creation

[1357] When a user uploads a dataset (e.g., an Excel file) from their device to create a presentation, the server passes the dataset to a generative model. The generative model analyzes the data and automatically creates key statistical information and graphs. Furthermore, an emotion engine analyzes the user's emotions and adjusts the tone and style of the presentation. This allows users to create high-quality presentations in a short amount of time. For example, when a user uploads sales data for a new product, the server analyzes it and automatically graphs sales trends and key indicators. If the emotion engine determines that the user is nervous about preparing a presentation, it generates presentation materials that use simple language and plenty of visual support elements.

[1358] Shorter analysis time

[1359] When a user uploads marketing data (e.g., customer data) from their device for analysis, the server passes the data to a generative model. The generative model analyzes the data and extracts trends and insights. The emotion engine analyzes the user's emotions and adjusts the presentation of the analysis results as needed. This allows users to quickly understand the current market situation and trends and work with an appropriate stress level. For example, when a user uploads customer data for a specific market, the server analyzes it and extracts purchasing patterns by age group and sales trends by region. If the emotion engine determines that the user is calm, it will provide an interactive dashboard with detailed data, but if it determines that the user is anxious, it will provide a concise report that highlights only the key points.

[1360] This invention allows for flexible responses according to the user's emotional state by combining a generative model and an emotion engine, thereby significantly improving business efficiency and user satisfaction.

[1361] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1362] Efficient information search

[1363] Step 1:

[1364] A user enters a search query into a device. This query is in text format (e.g., "latest marketing reports"), and this query triggers the start of an information search.

[1365] Step 2:

[1366] The device sends the entered search query to the server, which analyzes it on the server side.

[1367] Step 3:

[1368] The server passes the received query to the generative model for analysis. The generative model uses natural language understanding to analyze the query and extract the necessary information from relevant data sources (e.g., email systems, document creation tools, company intranets). The output is a list of relevant documents.

[1369] Step 4:

[1370] The server sends the user's input information and facial recognition data to the emotion engine, which analyzes the user's emotional state. The emotion engine evaluates the user's stress level and emotional state, and the results of this evaluation influence subsequent steps.

[1371] Step 5:

[1372] The server adjusts the presentation order and display format of the collected information based on the analysis results of the emotion engine. For example, if the user's stress level is high, the server will prioritize the most concise and important information. This process results in an ergonomic presentation of information.

[1373] Step 6:

[1374] The terminal receives the adjusted search results sent from the server and displays them to the user, with the output being displayed as an optimized list of information for the user to view.

[1375] Improving the efficiency of document creation

[1376] Step 1:

[1377] The user uploads a data set to the terminal for document creation, usually in the form of a spreadsheet (e.g., Excel file).

[1378] Step 2:

[1379] The device sends the uploaded dataset to the server, where the data is passed to the server in its raw format.

[1380] Step 3:

[1381] The server passes the dataset to a generative model for analysis. The generative model analyzes the data and automatically creates key statistics and graphs. The output is generated as a first draft of the document.

[1382] Step 4:

[1383] The server sends the user's emotional state to the emotion engine for analysis. The emotion engine evaluates the user's emotional state, such as stress or tension. The evaluation results are reflected in the content and format of the document.

[1384] Step 5:

[1385] The server adjusts the tone and style of the materials based on the analysis results of the emotion engine. For example, if the user is nervous, the server will create materials that use simple language and plenty of visual support. This results in user-friendly materials.

[1386] Step 6:

[1387] The terminal displays the adjusted material to the user, and the output is provided in a format that can be used for presentations or reports.

[1388] Shorter analysis time

[1389] Step 1:

[1390] The user provides marketing data to the device, typically in the form of a database or spreadsheet (e.g., customer data).

[1391] Step 2:

[1392] The device sends the provided marketing data to the server, which passes the data to the server in its raw form.

[1393] Step 3:

[1394] The server passes the data to a generative model for analysis. The generative model analyzes the data and extracts trends and insights. The output is generated as a list or graph of the analysis results.

[1395] Step 4:

[1396] The server sends the user's emotional state to the emotion engine for analysis, which evaluates the user's emotional state and influences how the results are presented.

[1397] Step 5:

[1398] The server adjusts the presentation of the analysis results based on the emotion engine's analysis: if the user is deemed calm, detailed data is displayed, but if the user is deemed anxious, a concise report highlighting only the main points is created, providing information in a format that is optimal for the user.

[1399] Step 6:

[1400] The terminal receives the adjusted analysis results sent from the server and displays them to the user, providing the output as reports and graphs of the optimized analysis results.

[1401] (Application example 2)

[1402] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1403] Conventional information search systems and document creation systems provide uniform results without considering the user's emotional state, resulting in problems such as reduced user satisfaction and reduced work efficiency. Furthermore, they lacked the flexibility to respond to user emotions and lacked a system to reduce user stress. As a result, there was concern that the user experience would deteriorate and the utilization rate of content distribution services would decline.

[1404] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1405] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model and automatically creating materials, means for analyzing marketing data using a generative model and extracting trends and insights, means for analyzing user emotions using an emotion engine and adjusting the data presentation method accordingly, and means for suggesting content based on the user's emotional state using the emotion engine, thereby enabling the presentation of appropriate content and materials according to the user's emotional state.

[1406] A "generative model" is a type of artificial intelligence that analyzes user input or datasets and generates relevant information based on them.

[1407] The "emotion engine" is a part of artificial intelligence that analyzes a user's facial expressions, voice, vital signs, etc. to identify the user's emotional state.

[1408] "Data Source" means a system or device that contains the raw data that provides the information.

[1409] A "search query" is a phrase or keyword that a user enters to search for specific information.

[1410] "Uploading" is the act of a user sending data from a local device to a server or cloud storage.

[1411] A "dataset" is a collection of data collected for the purposes of statistical analysis or machine learning.

[1412] A "trend" is the tendency or movement of data or events over a specific period of time.

[1413] "Insights" refers to insights and findings gained from data analysis and research.

[1414] "Content suggestion" refers to suggesting information or entertainment that a user is looking for.

[1415] In this invention, the server, the terminal, and the user work closely together to realize an emotion-adaptive content suggestion system.

[1416] System Program

[1417] The server collects information from various data sources (email systems, document creation tools, intranets, etc.) and passes it to the generative model for analysis. The server also uses an emotion engine to analyze the user's emotions and adjust the way data is presented accordingly. The emotion engine analyzes the user's emotions in real time using a camera, microphone, and vital signs sensors.

[1418] Hardware and Software

[1419] Hardware:

[1420] Camera (acquiring video data for emotion analysis)

[1421] Microphone (audio data acquisition)

[1422] Vital sensors (monitoring heart rate and stress levels)

[1423] software:

[1424] OpenCV: Analyze camera images using image processing library

[1425] TensorFlow and Keras: Implementing generative models used in natural language processing and image / audio data analysis

[1426] scikit-learn: Used for data preprocessing and scaling

[1427] Specific example explanation

[1428] Efficient information search

[1429] When a user searches for "latest marketing reports," the server gathers relevant information from each data source. A generative model uses natural language understanding to parse the query and extract the relevant information. An emotion engine analyzes the user's stress level and prioritizes concise, important information if the stress level is high.

[1430] Improving the efficiency of document creation

[1431] When users upload sales data for new products, the server passes the data through a generative model that automatically generates key statistics and graphs. The emotion engine provides presentation materials with plain language and ample visual support for users who are nervous about preparing a presentation.

[1432] Shorter analysis time

[1433] Users provide marketing data, and the server uses generative models to analyze the data and extract trends and insights. The emotion engine analyzes the user's calmness level and provides an interactive dashboard with detailed information if they are calm, or a concise report highlighting the key points if they are anxious.

[1434] Prompt Sentence Examples

[1435] "Generate a list of movies to recommend when the user is in a happy state."

[1436] "Generate content that has a relaxing effect that is perfect for when the user is feeling stressed."

[1437] This combines the generative AI model with the emotion engine to provide flexible data that responds to the user's emotional state.

[1438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1439] Step 1:

[1440] The user device collects real-time data from the user using a camera, microphone, and vital sensors. Specifically, the camera captures the user's facial expressions, the microphone collects voice data, and the vital sensors measure heart rate and stress level. The input is the user's facial expression data, voice data, and heart rate data, which are then sent to the server.

[1441] Step 2:

[1442] The server uses an emotion engine to analyze the user's emotional state. It uses camera data (facial expressions), microphone data (audio), and vital data (heart rate, etc.) as input. Specifically, it uses OpenCV to extract facial features, and TensorFlow and Keras to analyze audio and vital data. The output is the user's emotional state (e.g., joy, sadness, stress).

[1443] Step 3:

[1444] A user searches for information or uploads data. In this case, the user inputs a search query or a dataset. For example, a user might input "latest marketing report" as a search query or upload sales data. The input is a search query or a dataset.

[1445] Step 4:

[1446] The server uses the generative model to analyze user input (search query or dataset). Specifically, it uses natural language understanding to parse the search query and extract information from relevant data sources (e.g., email systems, word processing tools, intranets, etc.). It also analyzes uploaded datasets (e.g., Excel files) and automatically generates key statistics and graphs. The output is a list of relevant information or an automatically generated resource.

[1447] Step 5:

[1448] The server adjusts the display order and presentation format of the data based on the user's emotional state. Specifically, based on the output of the emotion engine (user's emotional state), it makes adjustments such as prioritizing concise information when the stress level is high. The inputs are the output of the emotion engine and the output of the generative model, and the output is the adjusted information or materials.

[1449] Step 6:

[1450] The server uses an emotion engine to suggest content based on the user's emotional state. Specifically, the emotion engine analyzes the user's current emotions and uses a generative model to suggest appropriate content (movies, music, articles, etc.). The inputs are the output of the emotion engine and a content database, and the output is a list of recommended content.

[1451] Step 7:

[1452] The user's device presents the adjusted information and recommended content sent from the server to the user. Specifically, the generated materials and recommended content are displayed on a device such as a smartphone or head-mounted display. The input is data from the server, and the output is information displayed in a form that the user can see.

[1453] This series of processes enables users to receive the most appropriate data and content according to their emotional state.

[1454] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1455] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1456] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1457] [Fourth embodiment]

[1458] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1459] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1460] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1461] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1462] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1463] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1464] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1465] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1466] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1467] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1468] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1469] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1470] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1471] This invention is a system for improving business efficiency by utilizing generative models. Specific examples include improving the efficiency of information search, document creation, and shortening analysis time. Specific embodiments of this system are described below.

[1472] Efficient information search

[1473] The server receives the search query entered by the user and passes it to the generative model. The generative model analyzes the query and collects information from relevant data sources (e.g., email systems, word processing tools, company intranets). The collected information is integrated and sent to the user's device. This allows the user to quickly access the information they need from a single interface.

[1474] Specific examples

[1475] When a user searches for "latest marketing reports," the server gathers relevant documents from Gmail, Google Docs, and the intranet and displays them on the device, allowing users to get the information they need in one place without having to use multiple tools.

[1476] Improving the efficiency of document creation

[1477] When a user uploads a dataset for document creation, the server passes it to a generative model. The generative model analyzes the data and automatically creates key statistics and graphs. These analysis results are integrated into the specified format (e.g., presentation, report) and sent to the user's device. Users can obtain high-quality documents in a short time.

[1478] Specific examples

[1479] When a user uploads new product sales data (an Excel file), the server analyzes it and automatically graphs sales trends and key indicators, generating a PowerPoint presentation that is instantly delivered to the user's device.

[1480] Shorter analysis time

[1481] When users provide marketing data for analysis, the server passes it to the generative model, which analyzes the data and extracts trends and insights. The analysis results are generated as interactive dashboards and detailed reports and sent to the user's device, allowing users to quickly understand the current market situation and trends.

[1482] Specific examples

[1483] Users can upload customer data for a specific market, and the server analyzes it to extract purchasing patterns by age group and sales trends by region. The results are displayed on the device as an interactive dashboard, allowing users to perform detailed data analysis.

[1484] This system integrates the processes of information search, document creation, and data analysis around a generative model, significantly improving users' work efficiency.

[1485] The processing flow will be explained below.

[1486] Efficient information search

[1487] Step 1:

[1488] A user enters a search query into the search bar.

[1489] Step 2:

[1490] The terminal transmits the entered search query to the server.

[1491] Step 3:

[1492] The server passes the received search query to the generative model.

[1493] Step 4:

[1494] A generative model parses the search query and generates requests to relevant data sources (e.g., email system, word processing tool, company intranet).

[1495] Step 5:

[1496] The server sends a request to each data source via an API.

[1497] Step 6:

[1498] Each data source responds with relevant data in response to a request.

[1499] Step 7:

[1500] The server receives the collected data, analyzes it with a generative model, and integrates it.

[1501] Step 8:

[1502] The server sends the integrated search results to the terminal.

[1503] Step 9:

[1504] The terminal displays the results to the user.

[1505] Improving the efficiency of document creation

[1506] Step 1:

[1507] The user uploads a dataset (e.g., an Excel file) from their device to create a document.

[1508] Step 2:

[1509] The device sends the data set to the server.

[1510] Step 3:

[1511] The server receives the data and passes it to the generative model.

[1512] Step 4:

[1513] A generative model analyzes the dataset and produces key statistics and graphs.

[1514] Step 5:

[1515] Based on the analysis results, the generative model automatically generates materials in the specified format (e.g., presentation, report).

[1516] Step 6:

[1517] The server transmits the generated materials to the user's terminal.

[1518] Step 7:

[1519] The terminal allows the user to display or download the material.

[1520] Shorter analysis time

[1521] Step 1:

[1522] The user uploads data (e.g., customer data) for analysis from their device.

[1523] Step 2:

[1524] The device sends the data to the server.

[1525] Step 3:

[1526] The server receives the data and passes it to the generative model.

[1527] Step 4:

[1528] Generative models analyze the data and extract trends and insights.

[1529] Step 5:

[1530] The generative model generates the analysis results in the form of reports and dashboards.

[1531] Step 6:

[1532] The server sends the generated results to the user's terminal.

[1533] Step 7:

[1534] The terminal displays the results to the user and provides interactivity where necessary.

[1535] The above steps enable efficient information search, document creation, and data analysis, greatly improving the user's work efficiency.

[1536] Example 1

[1537] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1538] In the past, the processes of information search, document creation, and data analysis required separate tasks, significantly reducing user efficiency. Furthermore, the need to use multiple tools and platforms made it difficult to centrally manage information, which required time and effort.

[1539] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1540] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple information sources using a generative AI model, means for analyzing a dataset uploaded from a terminal using the generative AI model and automatically generating materials, means for analyzing marketing data using the generative AI model and extracting trends and insights, means for analyzing the search query and collecting information from specific information sources, means for integrating the collected information and sending it to the terminal, means for analyzing the dataset and integrating the analysis results into a specified format, and means for compiling the analysis results into an interactive dashboard or a detailed report. This allows users to integrate information search, document creation, and data analysis within a single system, significantly improving work efficiency.

[1541] A "generative AI model" is an artificial intelligence algorithm that analyzes natural language queries and datasets entered by users and generates appropriate responses or analytical results.

[1542] A "search query" refers to a question or keyword that a user enters to search for specific information.

[1543] "Sources" refer to multiple databases or systems that contain information relevant to a search query, such as email systems, word processing tools, and intranets.

[1544] A "dataset" refers to a set of data provided by a user for a specific analysis or document creation, and examples include Excel files and CSV files.

[1545] "Integration" refers to the process of bringing together information obtained from different sources and data formats and making it easy for users to use.

[1546] "Documents" refers to documents such as reports and presentations created using generative AI models.

[1547] "Insights" refers to useful insights and understanding gained through data analysis, and is information that is useful for business decision-making.

[1548] A "dashboard" refers to an interface for visually displaying the results of data analysis, including graphs and charts.

[1549] This invention is a system for improving business efficiency using a generative AI model. Specifically, it aims to automate the processes of information search, document creation, and data analysis, thereby improving the business efficiency of users. Specific embodiments for implementing this invention are described below.

[1550] Efficient information search

[1551] A user enters a search query into their device. For example, they might type "latest marketing report." The device then sends this search query to a server. The server then passes the received search query to a generative AI model (e.g., GPT-4) for analysis. The generative AI model analyzes the search query and identifies relevant information sources (e.g., email system, word processing tool, company intranet). The server then collects and integrates the necessary information from the identified information sources. The integrated information is then sent from the server to the user's device, allowing the user to quickly access the information they need from a single interface.

[1552] Specific examples

[1553] When a user searches for "latest marketing reports," the server gathers relevant documents from Gmail, Google Docs, and your intranet, consolidates them, and displays them on the user's device.

[1554] Prompt example

[1555] "Find the latest marketing reports!"

[1556] Improving the efficiency of document creation

[1557] A user uploads a dataset from their device to create a document. For example, they upload "New Product Sales Data.xlsx." The device sends the dataset to a server. The server passes the dataset to a generative AI model (e.g., OpenAI Codex) and requests data analysis. The generative AI model analyzes the dataset and automatically generates key statistics and graphs. The generated statistics and graphs are integrated into a specified format (e.g., PowerPoint presentation) and sent to the user's device. The user can obtain high-quality documents in a short amount of time.

[1558] Specific examples

[1559] When a user uploads new product sales data (an Excel file), the server passes it through a generative AI model, which automatically graphs sales trends and key indicators, and the resulting PowerPoint presentation is instantly delivered to the user's device.

[1560] Prompt example

[1561] "Analyze sales data for new products and create presentation materials!"

[1562] Shorter analysis time

[1563] The user uploads marketing data from their device. For example, they upload "CustomerData.csv". The device sends the marketing data to the server. The server passes the received data to a generative AI model (e.g., BERT) for data analysis. The generative AI model analyzes the data and extracts trends and insights. The extracted information is compiled into interactive dashboards and detailed reports, which are then sent from the server to the user's device. The user can quickly grasp the current market situation and trends.

[1564] Specific examples

[1565] Users upload customer data for a specific market, and the server analyzes the data to extract customer purchasing patterns and regional sales trends. These results are displayed on the user's device as an interactive dashboard.

[1566] Prompt example

[1567] "Analyze customer data for a specific market and create a report highlighting key trends!"

[1568] This system utilizes generative AI models to streamline the processes of information search, document creation, and data analysis, significantly improving user work efficiency. This implementation frees users from the hassle of using multiple tools and platforms, allowing them to manage and use all information through a single interface.

[1569] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1570] Efficient information search

[1571] Step 1:

[1572] A user enters a search query into a device.

[1573] Input: Search query (e.g. "latest marketing report")

[1574] Action: Enter keywords in the search field

[1575] Output: The search query entered by the user

[1576] Step 2:

[1577] The terminal transmits the entered search query to the server.

[1578] Input: Search query

[1579] What it does: Creates an HTTP request and sends it to the server. The query is packaged in JSON format.

[1580] Output: The search query sent (received on the server side)

[1581] Step 3:

[1582] The server passes the search query to the generative AI model.

[1583] Input: Received search query

[1584] How it works: Passing a query to a generative AI model and requesting analysis

[1585] Output: The search query sent to the generative AI model

[1586] Step 4:

[1587] A generative AI model analyzes search queries.

[1588] Input: Search query passed by the server

[1589] How it works: Analyzes the query content and identifies relevant sources of information (e.g., company intranet, email system, word processing tool)

[1590] Output: List of relevant sources

[1591] Step 5:

[1592] The server identifies relevant data sources and collects the information.

[1593] Input: List of relevant sources

[1594] Operation: Calls the API of each information source and collects relevant information

[1595] Output: Information collected from each data source

[1596] Step 6:

[1597] The server aggregates the collected information.

[1598] Input: Collected information

[1599] What it does: Consolidates information into a single response dataset

[1600] Output: A consolidated response dataset

[1601] Step 7:

[1602] The server sends the integrated information to the user's terminal.

[1603] Input: Consolidated response dataset

[1604] Behavior: Creates an HTTP response and sends it to the user's device.

[1605] Output: The aggregated information sent to the user's device

[1606] Step 8:

[1607] The terminal displays the integrated information to the user.

[1608] Input: Received consolidated information

[1609] What it does: Parses JSON-formatted data and displays it visually (e.g., in a web browser)

[1610] Output: Consolidated information displayed to the user

[1611] Improving the efficiency of document creation

[1612] Step 1:

[1613] The user uploads a dataset from the terminal to create a document.

[1614] Input: File (e.g. "New Product Sales Data.xlsx")

[1615] Action: Select a dataset from the file selection dialog

[1616] Output: Selected files

[1617] Step 2:

[1618] The device sends the data set to the server.

[1619] Input: File (dataset)

[1620] What it does: Sends a file via an HTTP POST request, with the data encoded in multipart format.

[1621] Output: The file sent

[1622] Step 3:

[1623] The server passes the dataset to the generative AI model.

[1624] Input: The received dataset

[1625] What it does: Pass a dataset to a generative AI model and make a request to analyze it

[1626] Output: The dataset sent to the generative AI model

[1627] Step 4:

[1628] A generative AI model analyzes the dataset.

[1629] Input: Dataset passed from the server

[1630] What it does: Analyzes data and generates key statistics and graphs

[1631] Output: Analyzed statistics and graphs

[1632] Step 5:

[1633] The server integrates the analysis results into the specified format (e.g. PowerPoint).

[1634] Input: Analyzed statistics and graphs

[1635] Action: Integrates into a specified document format and creates a document (e.g., PowerPoint slides)

[1636] Output: Generated documentation file

[1637] Step 6:

[1638] The server transmits the generated materials to the user's terminal.

[1639] Input: Generated document file

[1640] Action: Sends a document file in the HTTP response

[1641] Output: The file sent to the user's device

[1642] Step 7:

[1643] The terminal displays the material to the user.

[1644] Input: Received document file

[1645] Behavior: Generates a download link and provides it to the user

[1646] Output: A file of the displayed material that can be downloaded by the user.

[1647] Shorter analysis time

[1648] Step 1:

[1649] The user uploads marketing data from the device.

[1650] Input: File (e.g. "CustomerData.csv")

[1651] Action: Select data from file selection dialog

[1652] Output: Selected files

[1653] Step 2:

[1654] The device sends the marketing data to the server.

[1655] Input: File (Marketing Data)

[1656] What it does: Sends a file via an HTTP POST request, with the data encoded in multipart format.

[1657] Output: The file sent

[1658] Step 3:

[1659] The server passes the data to the generative AI model.

[1660] Input: Received file

[1661] Action: Pass a file to the generative AI model and request analysis

[1662] Output: The file sent to the generative AI model

[1663] Step 4:

[1664] Generative AI models analyze the data and extract trends and insights.

[1665] Input: File passed from the server

[1666] Action: Analyze data and extract trends and insights

[1667] Output: Analyzed trends and insights

[1668] Step 5:

[1669] The server compiles the analysis results into interactive dashboards and detailed reports.

[1670] Input: Analyzed trends and insights

[1671] How it works: Generate interactive dashboards and detailed reports

[1672] Output: Generated dashboards and reports

[1673] Step 6:

[1674] The server sends the results to the user's terminal.

[1675] Input: Generated dashboards and reports

[1676] Action: Send the result in an HTTP response

[1677] Output: Dashboards and reports sent to the user's device

[1678] Step 7:

[1679] The terminal displays the results to the user.

[1680] Input: Incoming dashboards and reports

[1681] Action: Visually displays a dashboard or report (e.g., in a web browser)

[1682] Output: The results displayed in a form that the user can interact with.

[1683] (Application example 1)

[1684] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1685] In logistics centers, quickly collecting and integrating information from multiple data sources is challenging when searching for necessary information in real time. Uploading data sets for document creation and manually compiling analytical and statistical information is time-consuming and labor-intensive. Analyzing marketing data quickly and effectively to extract important trends and insights is also a challenge. To streamline on-site operations, it is necessary to process this information in real time and display it on visual devices such as smart glasses, thereby improving efficiency.

[1686] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1687] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model to automatically create materials, means for analyzing marketing data using a generative model to extract trends and insights, means for converting real-time voice input into text data and processing it as the specified search query, and means for outputting related information based on the search query to a visual device for displaying it, thereby enabling logistics center staff to quickly and centrally obtain information through the smart glasses to create materials and analyze data.

[1688] A "generative model" is an algorithm that analyzes data or queries entered by a user and automatically generates related information or data.

[1689] A "specified search query" is a search request entered by a user into a server to obtain the information desired.

[1690] "Data Source" refers to multiple databases or information resources that are referenced to obtain information.

[1691] "Means of integration" refers to a method of consolidating information obtained from multiple data sources into one and providing it in a centralized manner.

[1692] A "dataset" is a set of data uploaded by a user for analysis or documentation purposes.

[1693] "Material creation means" refers to a method for automatically generating materials in a specified format by analyzing and processing the uploaded dataset.

[1694] "Marketing data" refers to data used for market research and consumer behavior analysis.

[1695] A "trend" is a specific tendency or tendency found in data.

[1696] "Insights" refers to insights and findings revealed through data analysis.

[1697] "Real-time voice input" is a technology that instantly processes the voice spoken by the user as digital data.

[1698] "Text data" refers to voice input converted into text information.

[1699] A "visual device" is a tool for visually presenting information to a user, and specifically includes smart glasses.

[1700] This invention is a system for improving operational efficiency in logistics centers, specifically, a method for using generative AI models to perform information retrieval, document creation, and data analysis in real time, and providing information to visual devices such as smart glasses.

[1701] Hardware and software used

[1702] Hardware: Smart glasses (e.g., Google Glass)

[1703] Software: Generative AI models (e.g., GPT-4), database systems (e.g., MySQL, PostgreSQL), real-time speech recognition (e.g., Google Speech-to-Text API)

[1704] Processing flow and system operation

[1705] 1. Voice to Text

[1706] The user speaks into the microphone of the smart glasses to input voice commands. The voice commands (e.g., "Show me the latest inventory list") are captured by the microphone and converted into text data in real time using the Google Speech-to-Text API.

[1707] 2. Search query analysis and data collection

[1708] The text search query is analyzed by a generative AI model (GPT-4), which understands the query and generates appropriate SQL queries to gather relevant information from multiple data sources (e.g., corporate databases, inventory management systems, etc.). The generated SQL queries are then executed in a database system to extract the relevant data.

[1709] 3. Data integration and documentation

[1710] The extracted data is integrated with a generative AI model to automatically generate documents and reports in the specified format. For example, sales data and inventory data can be automatically graphed and compiled into a detailed report.

[1711] 4. Real-time display

[1712] The generated information and materials are displayed in real time on the smart glasses' display, allowing users to quickly access the information they need without using their hands.

[1713] Example prompt

[1714] Below are some examples of prompts that can be used with this system:

[1715] "View the latest inventory list"

[1716] I'd like to check the delivery schedule.

[1717] "Please prepare yesterday's shipping report."

[1718] This invention allows staff at logistics centers to use voice input to efficiently perform complex information searches, data analysis, document creation, etc. By implementing this system, work efficiency is improved and work can be carried out quickly and accurately.

[1719] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1720] Step 1:

[1721] The user speaks into the microphone in the smart glasses, for example, saying, "Show me the latest inventory list." The microphone in the smart glasses captures the voice and sends it in real time to the Google Speech-to-Text API.

[1722] Input: User voice input

[1723] Output: Audio data

[1724] Step 2:

[1725] The server uses the Google Speech-to-Text API to convert the voice data into text data. For example, the voice input "Show me the latest inventory list" is converted into text data "Show me the latest inventory list."

[1726] Input: Audio data

[1727] Output: Text data

[1728] Step 3:

[1729] The server passes the text data to a generative AI model (GPT-4) for analysis, which uses natural language understanding to analyze the search query and generate the SQL queries needed to retrieve information from relevant data sources.

[1730] Input: Text data

[1731] Output: Generated SQL query

[1732] Step 4:

[1733] The server sends an SQL query to a database system (e.g., MySQL, PostgreSQL) to extract the required data. For example, an SQL query to get the "latest inventory list" is executed, and the relevant data is extracted from the inventory management system.

[1734] Input: SQL query

[1735] Output: Data extracted from the database

[1736] Step 5:

[1737] The server integrates the extracted data with a generative AI model and automatically generates documents in the specified format (e.g., list format, table format). For example, an inventory list can be compiled in a table format.

[1738] Input: Extracted data

[1739] Output: Automatically generated materials

[1740] Step 6:

[1741] The server sends the automatically generated information to the smart glasses and displays it in real time, allowing the user to check the information displayed on the smart glasses' display.

[1742] Input: Auto-generated material

[1743] Output: Information displayed on the smart glasses

[1744] This allows users to use voice input to quickly and efficiently perform complex information searches, data analysis, and document creation.

[1745] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1746] This invention provides a system that combines a generative model and an emotion engine to recognize user emotions and automatically adjust business processes. Specific examples include improving the efficiency of information search, document creation, and shortening analysis time, as well as presenting and editing data according to the user's emotions.

[1747] Efficient information search

[1748] The server receives the search query entered by the user and passes it to the generative model. The generative model analyzes the query and collects information from relevant data sources (e.g., email systems, word processing tools, company intranets). In parallel, the emotion engine analyzes the user's emotions and adjusts the order and display format of the search results, allowing the user to retrieve information more appropriately.

[1749] Specific examples

[1750] When a user searches for "latest marketing reports," the server gathers relevant documents from Gmail, Google Docs, and the intranet. If the emotion engine determines that the user's stress level is high, it prioritizes the most concise and important information.

[1751] Improving the efficiency of document creation

[1752] When a user uploads a dataset to create a document, the server passes it to a generative model. The generative model analyzes the data and automatically creates key statistics and graphs. In addition, an emotion engine analyzes the user's emotions and adjusts the tone and style of the document. This allows users to create high-quality documents without spending a lot of time.

[1753] Specific examples

[1754] When a user uploads sales data (Excel file) for a new product, the server analyzes it and automatically graphs sales trends and key indicators. If the user is nervous about preparing a presentation, the emotion engine generates presentation materials using simple language and plenty of visual support.

[1755] Shorter analysis time

[1756] When a user provides marketing data for analysis, the server passes it to the generative model. The generative model analyzes the data and extracts trends and insights. The emotion engine analyzes the user's emotions and adjusts the presentation method and interface of the analysis results as needed. This allows users to quickly understand the current market situation and trends, and work at an appropriate stress level.

[1757] Specific examples

[1758] Users upload customer data for a specific market, and the server analyzes it to extract purchasing patterns by age group and sales trends by region. If the emotion engine determines that the user is calm, it will provide an interactive dashboard with detailed data, but if it determines that the user is anxious, it will provide a concise report highlighting only the key points.

[1759] By combining a generative model with an emotion engine, this system enables flexible responses according to the user's emotional state, significantly improving work efficiency and user satisfaction.

[1760] The processing flow will be explained below.

[1761] Efficient information search

[1762] Step 1:

[1763] A user enters a search query into the search bar.

[1764] Step 2:

[1765] The terminal transmits the entered search query to the server.

[1766] Step 3:

[1767] The server passes the received search query to the generative model.

[1768] Step 4:

[1769] A generative model parses the search query and generates requests to relevant data sources (e.g., email system, word processing tool, company intranet).

[1770] Step 5:

[1771] The server sends a request to each data source via an API.

[1772] Step 6:

[1773] Each data source responds with relevant data in response to a request.

[1774] Step 7:

[1775] The server receives the collected data, analyzes it with a generative model, and integrates it.

[1776] Step 8:

[1777] The emotion engine analyzes the user's emotions and adjusts the order and display format of search results.

[1778] Step 9:

[1779] The server sends the adjusted search results to the device.

[1780] Step 10:

[1781] The terminal displays the results to the user.

[1782] Improving the efficiency of document creation

[1783] Step 1:

[1784] The user uploads a dataset (e.g., an Excel file) from their device to create a document.

[1785] Step 2:

[1786] The device sends the data set to the server.

[1787] Step 3:

[1788] The server receives the data and passes it to the generative model.

[1789] Step 4:

[1790] A generative model analyzes the dataset and produces key statistics and graphs.

[1791] Step 5:

[1792] Based on the analysis results, the generative model automatically generates materials in the specified format (e.g., presentation, report).

[1793] Step 6:

[1794] The emotion engine analyzes the user's emotions and adjusts the tone and style of the material.

[1795] Step 7:

[1796] The server transmits the generated materials to the terminal.

[1797] Step 8:

[1798] The terminal allows the user to display or download the material.

[1799] Shorter analysis time

[1800] Step 1:

[1801] The user uploads data (e.g., customer data) for analysis from their device.

[1802] Step 2:

[1803] The device sends the data to the server.

[1804] Step 3:

[1805] The server receives the data and passes it to the generative model.

[1806] Step 4:

[1807] Generative models analyze the data and extract trends and insights.

[1808] Step 5:

[1809] The generative model generates the analysis results in the form of reports and dashboards.

[1810] Step 6:

[1811] The emotion engine analyzes the user's emotions and adjusts the way the analysis results are presented and the interface.

[1812] Step 7:

[1813] The server transmits the generated results to the terminal.

[1814] Step 8:

[1815] The terminal displays the results to the user and provides interactivity where necessary.

[1816] These steps allow for efficient information search, document creation, and data analysis, and enable flexible responses to the user's emotional state.

[1817] Example 2

[1818] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1819] In conventional systems, even when a user enters a search query, the results are not optimized according to the user's emotional state, making information acquisition and document creation inefficient. Furthermore, analyzing large amounts of data takes time, and the system does not provide an interface that responds to the user's emotions, resulting in problems such as reduced work efficiency and user satisfaction.

[1820] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1821] In this invention, the server includes means for extracting and integrating data related to a search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model and automatically creating materials, means for analyzing marketing data using a generative model and extracting trends and insights, and means for adjusting search results, materials, and analysis results using an emotion engine that analyzes the user's emotional state. This enables flexible responses according to the user's emotional state, making it possible to significantly improve business efficiency and user satisfaction.

[1822] A "generative model" is a means of analyzing user input and generating or extracting relevant data using machine learning algorithms.

[1823] An "emotion engine" is a means of analyzing a user's emotional state and adjusting the display order and format of data based on the results.

[1824] A "search query" is the text or keywords that a user enters to obtain information.

[1825] "Data sources" are various sources for collecting information, including, for example, email systems, word processing tools, and company intranets.

[1826] A "dataset" is a collection of data that is the subject of document creation or data analysis, and includes, for example, data in spreadsheet format.

[1827] A "trend" is a temporal fluctuation or tendency obtained as a result of data analysis.

[1828] "Insight" refers to useful knowledge and insight gained through data analysis.

[1829] "User emotional state" refers to the psychological state of the user when searching for information, creating materials, or analyzing data, and includes stress, tension, calmness, etc.

[1830] "Adjustment" refers to changing the way information is presented or the format of the display based on the user's emotional state.

[1831] "Interface" refers to the means or display screen through which a user interacts with a system.

[1832] This invention provides a system that combines a generative model and an emotion engine to recognize user emotions and automatically adjust business processes. Specifically, it presents and edits data according to the user's emotions, improving the efficiency of information search, document creation, and shortening analysis time.

[1833] Efficient information search

[1834] When a user enters a search query (e.g., "latest marketing report"), the device sends this search query to the server. The server uses a generative model to analyze the query and collects information from related data sources (e.g., email system, word processing tool, company intranet). At the same time, the emotion engine analyzes the user's emotions and adjusts the order and display format of the search results. This allows the user to efficiently obtain optimized information. For example, when a user searches for "latest marketing report," the server collects related documents from the email system and word processing tool, and if the emotion engine determines that the user's stress level is high, it prioritizes displaying the most concise and important information.

[1835] Improving the efficiency of document creation

[1836] When a user uploads a dataset (e.g., an Excel file) from their device to create a presentation, the server passes the dataset to a generative model. The generative model analyzes the data and automatically creates key statistical information and graphs. Furthermore, an emotion engine analyzes the user's emotions and adjusts the tone and style of the presentation. This allows users to create high-quality presentations in a short amount of time. For example, when a user uploads sales data for a new product, the server analyzes it and automatically graphs sales trends and key indicators. If the emotion engine determines that the user is nervous about preparing a presentation, it generates presentation materials that use simple language and plenty of visual support elements.

[1837] Shorter analysis time

[1838] When a user uploads marketing data (e.g., customer data) from their device for analysis, the server passes the data to a generative model. The generative model analyzes the data and extracts trends and insights. The emotion engine analyzes the user's emotions and adjusts the presentation of the analysis results as needed. This allows users to quickly understand the current market situation and trends and work with an appropriate stress level. For example, when a user uploads customer data for a specific market, the server analyzes it and extracts purchasing patterns by age group and sales trends by region. If the emotion engine determines that the user is calm, it will provide an interactive dashboard with detailed data, but if it determines that the user is anxious, it will provide a concise report that highlights only the key points.

[1839] This invention allows for flexible responses according to the user's emotional state by combining a generative model and an emotion engine, thereby significantly improving business efficiency and user satisfaction.

[1840] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1841] Efficient information search

[1842] Step 1:

[1843] A user enters a search query into a device. This query is in text format (e.g., "latest marketing reports"), and this query triggers the start of an information search.

[1844] Step 2:

[1845] The device sends the entered search query to the server, which analyzes it on the server side.

[1846] Step 3:

[1847] The server passes the received query to the generative model for analysis. The generative model uses natural language understanding to analyze the query and extract the necessary information from relevant data sources (e.g., email systems, document creation tools, company intranets). The output is a list of relevant documents.

[1848] Step 4:

[1849] The server sends the user's input information and facial recognition data to the emotion engine, which analyzes the user's emotional state. The emotion engine evaluates the user's stress level and emotional state, and the results of this evaluation influence subsequent steps.

[1850] Step 5:

[1851] The server adjusts the presentation order and display format of the collected information based on the analysis results of the emotion engine. For example, if the user's stress level is high, the server will prioritize the most concise and important information. This process results in an ergonomic presentation of information.

[1852] Step 6:

[1853] The terminal receives the adjusted search results sent from the server and displays them to the user, with the output being displayed as an optimized list of information for the user to view.

[1854] Improving the efficiency of document creation

[1855] Step 1:

[1856] The user uploads a data set to the terminal for document creation, usually in the form of a spreadsheet (e.g., Excel file).

[1857] Step 2:

[1858] The device sends the uploaded dataset to the server, where the data is passed to the server in its raw format.

[1859] Step 3:

[1860] The server passes the dataset to a generative model for analysis. The generative model analyzes the data and automatically creates key statistics and graphs. The output is generated as a first draft of the document.

[1861] Step 4:

[1862] The server sends the user's emotional state to the emotion engine for analysis. The emotion engine evaluates the user's emotional state, such as stress or tension. The evaluation results are reflected in the content and format of the document.

[1863] Step 5:

[1864] The server adjusts the tone and style of the materials based on the analysis results of the emotion engine. For example, if the user is nervous, the server will create materials that use simple language and plenty of visual support. This results in user-friendly materials.

[1865] Step 6:

[1866] The terminal displays the adjusted material to the user, and the output is provided in a format that can be used for presentations or reports.

[1867] Shorter analysis time

[1868] Step 1:

[1869] The user provides marketing data to the device, typically in the form of a database or spreadsheet (e.g., customer data).

[1870] Step 2:

[1871] The device sends the provided marketing data to the server, which passes the data to the server in its raw form.

[1872] Step 3:

[1873] The server passes the data to a generative model for analysis. The generative model analyzes the data and extracts trends and insights. The output is generated as a list or graph of the analysis results.

[1874] Step 4:

[1875] The server sends the user's emotional state to the emotion engine for analysis, which evaluates the user's emotional state and influences how the results are presented.

[1876] Step 5:

[1877] The server adjusts the presentation of the analysis results based on the emotion engine's analysis: if the user is deemed calm, detailed data is displayed, but if the user is deemed anxious, a concise report highlighting only the main points is created, providing information in a format that is optimal for the user.

[1878] Step 6:

[1879] The terminal receives the adjusted analysis results sent from the server and displays them to the user, providing the output as reports and graphs of the optimized analysis results.

[1880] (Application example 2)

[1881] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1882] Conventional information search systems and document creation systems provide uniform results without considering the user's emotional state, resulting in problems such as reduced user satisfaction and reduced work efficiency. Furthermore, they lacked the flexibility to respond to user emotions and lacked a system to reduce user stress. As a result, there was concern that the user experience would deteriorate and the utilization rate of content distribution services would decline.

[1883] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1884] In this invention, the server includes means for extracting and integrating data related to a specified search query from multiple data sources using a generative model, means for analyzing uploaded datasets using a generative model and automatically creating materials, means for analyzing marketing data using a generative model and extracting trends and insights, means for analyzing user emotions using an emotion engine and adjusting the data presentation method accordingly, and means for suggesting content based on the user's emotional state using the emotion engine, thereby enabling the presentation of appropriate content and materials according to the user's emotional state.

[1885] A "generative model" is a type of artificial intelligence that analyzes user input or datasets and generates relevant information based on them.

[1886] The "emotion engine" is a part of artificial intelligence that analyzes a user's facial expressions, voice, vital signs, etc. to identify the user's emotional state.

[1887] "Data Source" means a system or device that contains the raw data that provides the information.

[1888] A "search query" is a phrase or keyword that a user enters to search for specific information.

[1889] "Uploading" is the act of a user sending data from a local device to a server or cloud storage.

[1890] A "dataset" is a collection of data collected for the purposes of statistical analysis or machine learning.

[1891] A "trend" is the tendency or movement of data or events over a specific period of time.

[1892] "Insights" refers to insights and findings gained from data analysis and research.

[1893] "Content suggestion" refers to suggesting information or entertainment that a user is looking for.

[1894] In this invention, the server, the terminal, and the user work closely together to realize an emotion-adaptive content suggestion system.

[1895] System Program

[1896] The server collects information from various data sources (email systems, document creation tools, intranets, etc.) and passes it to the generative model for analysis. The server also uses an emotion engine to analyze the user's emotions and adjust the way data is presented accordingly. The emotion engine analyzes the user's emotions in real time using a camera, microphone, and vital signs sensors.

[1897] Hardware and Software

[1898] Hardware:

[1899] Camera (acquiring video data for emotion analysis)

[1900] Microphone (audio data acquisition)

[1901] Vital sensors (monitoring heart rate and stress levels)

[1902] software:

[1903] OpenCV: Analyze camera images using image processing library

[1904] TensorFlow and Keras: Implementing generative models used in natural language processing and image / audio data analysis

[1905] scikit-learn: Used for data preprocessing and scaling

[1906] Specific example explanation

[1907] Efficient information search

[1908] When a user searches for "latest marketing reports," the server gathers relevant information from each data source. A generative model uses natural language understanding to parse the query and extract the relevant information. An emotion engine analyzes the user's stress level and prioritizes concise, important information if the stress level is high.

[1909] Improving the efficiency of document creation

[1910] When users upload sales data for new products, the server passes the data through a generative model that automatically generates key statistics and graphs. The emotion engine provides presentation materials with plain language and ample visual support for users who are nervous about preparing a presentation.

[1911] Shorter analysis time

[1912] Users provide marketing data, and the server uses generative models to analyze the data and extract trends and insights. The emotion engine analyzes the user's calmness level and provides an interactive dashboard with detailed information if they are calm, or a concise report highlighting the key points if they are anxious.

[1913] Prompt Sentence Examples

[1914] "Generate a list of movies to recommend when the user is in a happy state."

[1915] "Generate content that has a relaxing effect that is perfect for when the user is feeling stressed."

[1916] This combines the generative AI model with the emotion engine to provide flexible data that responds to the user's emotional state.

[1917] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1918] Step 1:

[1919] The user device collects real-time data from the user using a camera, microphone, and vital sensors. Specifically, the camera captures the user's facial expressions, the microphone collects voice data, and the vital sensors measure heart rate and stress level. The input is the user's facial expression data, voice data, and heart rate data, which are then sent to the server.

[1920] Step 2:

[1921] The server uses an emotion engine to analyze the user's emotional state. It uses camera data (facial expressions), microphone data (audio), and vital data (heart rate, etc.) as input. Specifically, it uses OpenCV to extract facial features, and TensorFlow and Keras to analyze audio and vital data. The output is the user's emotional state (e.g., joy, sadness, stress).

[1922] Step 3:

[1923] A user searches for information or uploads data. In this case, the user inputs a search query or a dataset. For example, a user might input "latest marketing report" as a search query or upload sales data. The input is a search query or a dataset.

[1924] Step 4:

[1925] The server uses the generative model to analyze user input (search query or dataset). Specifically, it uses natural language understanding to parse the search query and extract information from relevant data sources (e.g., email systems, word processing tools, intranets, etc.). It also analyzes uploaded datasets (e.g., Excel files) and automatically generates key statistics and graphs. The output is a list of relevant information or an automatically generated resource.

[1926] Step 5:

[1927] The server adjusts the display order and presentation format of the data based on the user's emotional state. Specifically, based on the output of the emotion engine (user's emotional state), it makes adjustments such as prioritizing concise information when the stress level is high. The inputs are the output of the emotion engine and the output of the generative model, and the output is the adjusted information or materials.

[1928] Step 6:

[1929] The server uses an emotion engine to suggest content based on the user's emotional state. Specifically, the emotion engine analyzes the user's current emotions and uses a generative model to suggest appropriate content (movies, music, articles, etc.). The inputs are the output of the emotion engine and a content database, and the output is a list of recommended content.

[1930] Step 7:

[1931] The user's device presents the adjusted information and recommended content sent from the server to the user. Specifically, the generated materials and recommended content are displayed on a device such as a smartphone or head-mounted display. The input is data from the server, and the output is information displayed in a form that the user can see.

[1932] This series of processes enables users to receive the most appropriate data and content according to their emotional state.

[1933] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1934] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1935] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1936] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1937] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1938] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1939] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1940] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1941] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1942] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1943] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1944] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1945] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1946] 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.

[1947] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1948] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1949] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1950] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1951] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1952] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1953] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1954] The following is further disclosed regarding the above embodiment.

[1955] (Claim 1)

[1956] a means for utilizing a generative model to extract and integrate data relevant to a specified search query from multiple data sources;

[1957] A means of analyzing uploaded datasets using generative models and automatically generating materials;

[1958] A means of analyzing marketing data using generative models to extract trends and insights;

[1959] A system including:

[1960] (Claim 2)

[1961] 10. The system of claim 1, wherein the generative model utilizes natural language understanding to parse search queries and retrieve relevant data.

[1962] (Claim 3)

[1963] 2. The system of claim 1, wherein the generative model analyzes spreadsheet data and automatically generates materials in a specified format.

[1964] "Example 1"

[1965] (Claim 1)

[1966] a means for utilizing a generative AI model to extract and integrate data relevant to a specified search query from multiple sources; and

[1967] A means to analyze datasets uploaded from devices using generative AI models and automatically generate materials;

[1968] A means to analyze marketing data using generative AI models to extract trends and insights;

[1969] A means of analyzing search queries and collecting information from specific sources;

[1970] means for aggregating and transmitting the collected information to a terminal;

[1971] A means for analyzing the dataset and synthesizing the results of the analysis into a specified format;

[1972] A means to synthesize analytical results into interactive dashboards and detailed reports,

[1973] A system including:

[1974] (Claim 2)

[1975] 10. The system of claim 1, wherein the generative AI model utilizes natural language understanding to parse search queries and retrieve relevant data.

[1976] (Claim 3)

[1977] The system of claim 1, wherein the generative AI model analyzes data from a spreadsheet software and automatically generates materials in a specified format.

[1978] "Application Example 1"

[1979] (Claim 1)

[1980] a means for utilizing a generative model to extract and integrate data relevant to a specified search query from multiple data sources;

[1981] A means of analyzing uploaded datasets using generative models and automatically generating materials;

[1982] A means of analyzing marketing data using generative models to extract trends and insights;

[1983] means for converting real-time voice input into text data for processing as a specified search query;

[1984] means for outputting to a visual device for displaying relevant information based on the search query;

[1985] A system including:

[1986] (Claim 2)

[1987] 10. The system of claim 1, wherein the generative model utilizes natural language understanding to parse search queries and retrieve relevant data.

[1988] (Claim 3)

[1989] 2. The system of claim 1, wherein the generative model analyzes spreadsheet data and automatically generates materials in a specified format.

[1990] "Example 2: Combining Emotion Engines"

[1991] (Claim 1)

[1992] a means for utilizing a generative model to extract and integrate data relevant to a specified search query from multiple data sources;

[1993] A means of analyzing uploaded datasets using generative models and automatically generating materials;

[1994] A means of analyzing marketing data using generative models to extract trends and insights;

[1995] A means of adjusting search results, materials, and analysis results using an emotion engine that analyzes the user's emotional state;

[1996] A system including:

[1997] (Claim 2)

[1998] 10. The system of claim 1, wherein the generative model utilizes natural language understanding to parse search queries and retrieve relevant data.

[1999] (Claim 3)

[2000] 2. The system of claim 1, wherein the generative model analyzes spreadsheet data and automatically generates materials in a specified format.

[2001] (Claim 4)

[2002] 10. The system of claim 1, wherein the emotional engine adjusts the display order and format of the data based on the emotional state of the user.

[2003] "Application example 2 when combining emotion engines"

[2004] (Claim 1)

[2005] a means for utilizing a generative model to extract and integrate data relevant to a specified search query from multiple data sources;

[2006] A means of analyzing uploaded datasets using generative models and automatically generating materials;

[2007] A means of analyzing marketing data using generative models to extract trends and insights;

[2008] a means for analyzing user emotions using an emotion engine and adjusting the presentation of data accordingly;

[2009] means for suggesting content based on a user's emotional state using an emotion engine;

[2010] A system including:

[2011] (Claim 2)

[2012] 10. The system of claim 1, wherein the generative model and emotion engine utilize natural language understanding to analyze the search query, retrieve relevant data, and adjust the presentation order and format depending on the user's emotional state.

[2013] (Claim 3)

[2014] 2. The system of claim 1, wherein the generative model analyzes spreadsheet data and automatically generates materials in a specified format based on the user's emotional state. [Explanation of symbols]

[2015] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for utilizing a generative model to extract and integrate data relevant to a specified search query from multiple data sources; A means of analyzing uploaded datasets using generative models and automatically generating materials; A means of analyzing marketing data using generative models to extract trends and insights; A system including:

2. The system of claim 1 , wherein the generative model utilizes natural language understanding to parse search queries and retrieve relevant data.

3. The system of claim 1 , wherein the generative model analyzes spreadsheet data and automatically generates materials in a specified format.

Images