System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a natural-language instruction from a user; analysis means including a generation AI for analyzing the natural-language instruction; means for generating an operation script for automatically reflecting a mathematical expression or a setting in spreadsheet software based on a result analyzed by the analysis means; and means for applying the operation script to the spreadsheet software.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] This invention aims to reduce the burden on many users who find spreadsheet software difficult to use. Complex tasks such as entering and setting formulas, setting conditional formatting, and even generating graphs can be particularly challenging for beginners and users unfamiliar with the software. This can lead to formula errors, increased workload, and reduced efficiency. Furthermore, these tasks often require significant time and effort, as it is not possible to automatically retrieve and update appropriate data from other pages or the Internet. To address these issues, a system is needed that allows users to quickly and accurately operate spreadsheet software using only natural language instructions. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. Specifically, it proposes a system equipped with an analysis means including a generation AI that receives instructions in natural language from a user and analyzes those instructions. Based on the results of the analysis by the analysis means, an operation script is generated for automatically reflecting formulas or settings in the spreadsheet software. This operation script includes a means for applying it to the spreadsheet software. Furthermore, by including a function for setting conditional formatting within the spreadsheet software based on specified conditions and an operation for automatically generating graphs based on specified data, it is possible to provide more versatile support. This allows users to quickly and accurately operate the spreadsheet software by simply instructing complex formulas and settings in natural language.

[0006] "User" refers to a person who uses this system to operate spreadsheet software.

[0007] "Natural language instructions" refer to operation requests made by users to the system in natural languages ​​such as Japanese.

[0008] "Generative AI" refers to artificial intelligence technology that analyzes natural language instructions and automatically generates appropriate spreadsheet software operations.

[0009] "Analysis means" refers to the means for using generative AI to analyze natural language instructions received from a user and process the results.

[0010] "Spreadsheet software" refers to software (e.g., Excel) for data entry, calculation, analysis, etc.

[0011] "Formula" refers to a mathematical expression used to define how data is calculated in spreadsheet software.

[0012] "Settings" refers to operations such as formatting cells and setting conditional formatting within spreadsheet software.

[0013] "Operation script" refers to a series of instructions generated by the analysis means for reflecting formulas and settings in the spreadsheet software.

[0014] "Conditional formatting" refers to a feature in spreadsheet software that allows you to change the formatting of cells based on certain conditions.

[0015] "Generating a graph" refers to the operation of automatically creating a visualized graph based on specified data. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention relates to a system that uses generative AI to automatically generate formulas and settings for spreadsheet software and reflect them in the spreadsheet when the user gives instructions in natural language. This system reduces the burden on the user by simply receiving and analyzing the user's instructions and automatically performing the appropriate operations.

[0038] System Configuration

[0039] The system mainly consists of the following components:

[0040] 1. User input means (terminal):

[0041] Users input instructions in natural language through an on-device interface, which can range from creating formulas to setting conditional formatting and even generating graphs.

[0042] 2. Generative AI model (server):

[0043] The server is equipped with a generation AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generation AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[0044] 3. Analysis result sending method (server):

[0045] The server sends the operation script generated by the generation AI to the terminal. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[0046] 4. Sheet reflection method (terminal):

[0047] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[0048] Program processing and example

[0049] 1. User input (terminal):

[0050] The user enters instructions into the device interface, such as "calculate the total sales data," which is then sent to the server for automatic analysis.

[0051] 2. Parsing the instruction (server):

[0052] The generation AI on the server receives the user's input and analyzes it. Through this analysis, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[0053] 3. Generate operation script (server):

[0054] Based on the analysis results of the generative AI, the server generates an appropriate operation script, which is an instruction for automatically applying the specified formulas and settings to the spreadsheet software.

[0055] 4. Sending and reflecting analysis results (from server to device, device):

[0056] The server sends the generated operation script to the terminal, which then applies it to the spreadsheet software, thereby reflecting the specified formulas and settings on the sheet.

[0057] Specific examples

[0058] Automatic formula generation

[0059] User instruction: "Sum the data in column A"

[0060] System Action:

[0061] 1. The user enters this instruction and sends it from the terminal to the server.

[0062] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[0063] 3. An operation script is generated and sent to the terminal.

[0064] 4. The terminal executes the received script and reflects the formula in the cell.

[0065] Conditional formatting settings

[0066] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[0067] System Action:

[0068] 1. The user's instructions are sent from the device to the server.

[0069] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[0070] 3. The script is sent from the server to the device and executed on the device.

[0071] 4. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[0072] This invention enables users to quickly and accurately perform advanced operations on spreadsheet software using only natural language instructions, allowing even beginners and users unfamiliar with the software to work efficiently.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The user provides input. Specifically, the user types natural language instructions into the device interface, such as "calculate the total sales data."

[0076] Step 2:

[0077] The device prepares the user's instructions to send to the server. The instructions are converted into an appropriate format and forwarded to the server.

[0078] Step 3:

[0079] The server receives the user's instructions, and the received data is analyzed by the generating AI.

[0080] Step 4:

[0081] The generation AI on the server analyzes the user's instructions. As a result of the analysis, for example, in response to an instruction to "calculate the sum of sales data," the formula =SUM(sales data) is generated.

[0082] Step 5:

[0083] The server generates an operation script based on the analysis results of the generation AI. Specifically, a script is generated that applies a formula such as =SUM(A:A) in spreadsheet software.

[0084] Step 6:

[0085] The server sends the generated operation script to the terminal. Check that the script was sent successfully.

[0086] Step 7:

[0087] The terminal receives the operation script from the server, confirms that reception has been completed, and moves on to the next process.

[0088] Step 8:

[0089] The terminal starts the spreadsheet software, and the necessary preparations are made to execute the operation script.

[0090] Step 9:

[0091] The terminal executes the received operation script on the spreadsheet software. For example, the terminal enters the formula =SUM(A:A) into a specified cell.

[0092] Step 10:

[0093] The terminal confirms that the operation script has been executed and that the operation requested by the user has been correctly executed.

[0094] This allows users to intuitively and accurately operate complex spreadsheet software simply by issuing instructions in natural language.

[0095] Example 1

[0096] 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."

[0097] Conventional spreadsheet software requires users to manually create formulas and settings, which requires a great deal of time and effort. Creating specific settings and formulas can be difficult, making it difficult for beginners and users unfamiliar with the software to use. Furthermore, the lack of technology to analyze natural language instructions and automatically reflect them in spreadsheets makes efficient data management and information processing difficult.

[0098] 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.

[0099] In this invention, the server includes: means for receiving instructions in natural language from a user; means for transmitting the instructions in natural language to the server; analysis means including a generation AI for analyzing the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of analysis by the analysis means; means for transmitting the operation script to a terminal; and means for applying the operation script to the spreadsheet software. This makes it possible for a user to simply input instructions in natural language to easily and automatically generate formulas and settings for the spreadsheet software and reflect them in a sheet.

[0100] A "user" is a person or entity that uses the system to provide instructions in natural language.

[0101] A "natural language" is a language that humans use on a daily basis and is not a programming language.

[0102] "Instructions" are words or sentences that indicate the operations that a user performs on a system.

[0103] A "terminal" is a device that is directly operated by a user and includes an input interface.

[0104] A "server" is a remote computer system that analyzes and processes instructions sent by a user.

[0105] "Generative AI" is an artificial intelligence technology that analyzes natural language instructions and automatically generates appropriate formulas and settings.

[0106] An "analysis means" is a component that has the function of analyzing natural language instructions using generative AI.

[0107] An "operation script" is a series of commands that are used to reflect formulas and settings in spreadsheet software.

[0108] "Spreadsheet software" is a software application for performing numerical calculations and managing data.

[0109] "Settings" are configuration options or parameters that change the behavior or appearance of the spreadsheet software.

[0110] A "sheet" refers to a page or tab where data is arranged in a spreadsheet program.

[0111] MODE FOR CARRYING OUT THE INVENTION

[0112] This invention is a system that uses generative AI to automatically generate formulas and settings for spreadsheet software in response to instructions given by the user in natural language, and reflects these in the spreadsheet. This system reduces the burden on the user by simply receiving and analyzing the user's instructions, and automatically performing the appropriate operations.

[0113] System Configuration

[0114] The system consists of four main components:

[0115] 1. User input means (terminal):

[0116] Users input instructions in natural language through an on-device interface, such as "calculate the sum of the sales data" or "if the value in column B is greater than 100, make the background red."

[0117] 2. Generative AI model (server):

[0118] The server is equipped with a generative AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. The generative AI analyzes the natural language instructions and generates the necessary formulas and settings.

[0119] 3. Analysis result sending method (server):

[0120] The server sends the operation script generated by the generation AI to the terminal. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[0121] 4. Sheet reflection method (terminal):

[0122] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[0123] Specific examples

[0124] Below are two examples of how the system works:

[0125] Automatic formula generation

[0126] User instruction: "Sum the data in column A"

[0127] The user inputs this instruction and sends it from the terminal to the server.

[0128] The server's generation AI analyzes the instructions and generates the formula =SUM(A:A).

[0129] The operation script generated as a result of the analysis is sent to the terminal.

[0130] The terminal executes the received script and reflects the formulas in the spreadsheet software.

[0131] Conditional formatting settings

[0132] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[0133] The user's instructions are sent from the terminal to the server.

[0134] The server's generated AI parses the instructions and generates a script that applies the conditional formatting.

[0135] The script is sent from the server to the terminal and executed on the terminal.

[0136] The terminal executes the received script, and if the value of the cell in column B is greater than or equal to 100, the background turns red.

[0137] Prompt Sentence Examples

[0138] Here are some example prompts to input to the AI ​​generator:

[0139] "Calculate the sum of the sales data" -> Generate a formula to calculate the total sales data.

[0140] "If the value in column B is greater than or equal to 100, set the background to red" -> Create a conditional formatting rule to set the background of cells in column B to red if the value is 100 or more.

[0141] The generative AI analyzes these prompts and generates appropriate operation scripts, allowing users to quickly and accurately perform advanced operations on spreadsheet software using only natural language instructions, enabling even beginners to work efficiently.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Step 1:

[0144] User instruction input (terminal)

[0145] The user inputs the desired spreadsheet software operation into the terminal interface in natural language. For example, they might input "calculate the total sales data." When this instruction is input, the terminal treats the instruction as data and prepares to send it to the server.

[0146] Input: User's natural language instructions

[0147] Output: Instruction data in the format to send to the server

[0148] Specific operation: The user enters "Calculate the total sales data" in the text box on the terminal and presses the send button.

[0149] Step 2:

[0150] Sending instructions (from terminal to server)

[0151] The device sends the user's specified data to the server, usually using a communication method such as an HTTP request.

[0152] Input: User's natural language instructions

[0153] Output: Data received by the server

[0154] Specific operation: The device sends an HTTP request, and the server's API endpoint accepts this request.

[0155] Step 3:

[0156] Parsing instructions (server)

[0157] The generative AI model on the server analyzes the received natural language instructions. This analysis determines the specific formulas and settings. For example, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[0158] Input: User's natural language instructions

[0159] Output: Formulas and settings as analysis results

[0160] Specific operation: The generation AI analyzes the prompt "Calculate the sum of the sales data" and decides to generate the formula =SUM(sales data).

[0161] Step 4:

[0162] Generate operation script (server)

[0163] Based on the analysis results, the server generates an operation script for the spreadsheet software, which includes specific formulas and settings.

[0164] Input: Formulas and settings as analysis results

[0165] Output: Operation script

[0166] Specific operation: The generation AI executes the script generation logic and creates a specific script called =SUM(sales data).

[0167] Step 5:

[0168] Sending operation scripts (from server to terminal)

[0169] The server sends the generated operation script to the terminal. This transmission also uses a communication method such as HTTP response. The terminal caches and saves the received script.

[0170] Input: Operation script

[0171] Output: Received data from the device

[0172] Specific operation: The server sends back the script as an HTTP response, and the terminal receives the response.

[0173] Step 6:

[0174] Execute operation script and reflect sheet (terminal)

[0175] The terminal applies the received operation script to the spreadsheet software and reflects the formulas and settings in the sheet. Specifically, the formula =SUM(sales data) is entered into the specified cell.

[0176] Input: Received operation script

[0177] Output: Reflection of formulas and settings in spreadsheet software

[0178] Specific behavior: The device's spreadsheet software runs the script, and the formula is automatically entered into the cell.

[0179] (Application example 1)

[0180] 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."

[0181] Conventional factory robot operation and production line management / maintenance work often required a lot of human intervention, resulting in inefficiency. Furthermore, it was difficult for workers without specialized knowledge to operate the robots, leading to the risk of operational errors and reduced efficiency. Furthermore, there was a lack of an appropriate system for analyzing data in real time and responding quickly. To solve these problems, an advanced system that can be operated using natural language is needed.

[0182] 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.

[0183] In this invention, the server includes: means for receiving natural language instructions from a user; analysis means including a generation AI for analyzing the natural language instructions; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of the analysis by the analysis means; means for applying the operation script to the spreadsheet software; and means for applying the generation AI to a production line management or maintenance robot, analyzing the natural language instructions, generating an appropriate operation script, and applying it to the robot. This enables workers to efficiently manage production lines and perform maintenance work in a factory simply by issuing instructions in natural language.

[0184] A "means for receiving natural language instructions from a user" is a device or software that provides an interface through which a user can input instructions in natural language using voice or text.

[0185] "Analysis means including generative AI" refers to devices or software that include artificial intelligence technology used to analyze a user's natural language instructions, understand their content, and generate appropriate operation scripts.

[0186] The "means for generating an operation script" is a device or software that automatically generates instructions for reflecting the necessary formulas and settings in the spreadsheet software or robot based on the results of the analysis by the analysis means.

[0187] The "means for applying to spreadsheet software" is an interface or program for reflecting the generated operation script in the spreadsheet software.

[0188] "Means for application to robots for production line management and maintenance" refers to a device or software that analyzes natural language instructions from generative AI for robots that manage production lines and perform maintenance work within factories, generates commands for appropriate operations, and has the robots execute these commands.

[0189] The system that embodies this invention consists of a series of processes in which a user gives instructions in natural language and uses generative AI to reflect the operations in factory robots.

[0190] 1. System Program

[0191] The system's program involves receiving natural language instructions from the user, using generative AI to generate an operation script, and applying it to the robot.

[0192] 2. Program Processing

[0193] The system operates using the following hardware and software:

[0194] Hardware and Software Configuration

[0195] User input device: A device that allows a user to input natural language instructions via voice or text. Examples include smartphones and tablets.

[0196] Server: A computer system that analyzes natural language instructions and generates appropriate operational scripts using a generative AI model, such as GPT-4.

[0197] Speech recognition API: Software that converts user voice input into text. An example is Google Cloud Speech-to-Text.

[0198] Robot control system: A robot system with a control program to execute the generated operation script. An example is the Siemens TIA Portal.

[0199] 3. Data processing and calculation

[0200] Speech Recognition: Converts speech to text on the user's input device. Uses speech recognition APIs to accurately transcribe the user's natural language commands into text.

[0201] Analysis by generative AI: The server receives textual natural language instructions, analyzes them using a generative AI model (GPT-4), and generates an appropriate operation script.

[0202] Generation and application of operation script: The generated operation script is sent to the robot and executed by the robot's control system, which then performs the specified action.

[0203] 4. Specific Examples

[0204] To calculate the sum of sales data:

[0205] User instruction: "Calculate the sum of the sales data"

[0206] Analysis method:

[0207] 1. The user speaks instructions, which are converted into text using a speech recognition API.

[0208] 2. The server's generation AI analyzes the instructions and generates the formula =SUM(sales data).

[0209] 3. An operation script is generated and sent to the terminal.

[0210] 4. The terminal executes the received script and reflects the formulas in the sheet.

[0211] When giving natural language instructions to a robot

[0212] User instruction: "Calculate and display the production total for line A."

[0213] Example prompt sentence:

[0214] "A user wants to calculate and display the total production data for line A. Please generate the appropriate formula."

[0215] Analysis method:

[0216] 1. The user speaks voice commands to the robot.

[0217] 2. The robot converts the speech into text and sends it to the server.

[0218] 3. GPT-4 on the server analyzes and generates the formula =SUM(A line data).

[0219] 4. The generated script is sent to the robot, which then aggregates and displays the production data.

[0220] This system will improve the efficiency of production line management and maintenance work within factories, and will enable operations to be carried out easily using instructions in natural language.

[0221] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0222] Step 1:

[0223] The user inputs voice instructions into the terminal using natural language. The input is a specific instruction such as "Calculate and display the production total for line A." The terminal receives this voice data.

[0224] Input: Voice commands

[0225] Output: Audio data

[0226] Specific operation: The user speaks into the smartphone or tablet to give instructions, and the device picks up the voice through the microphone.

[0227] Step 2:

[0228] The device converts the voice data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[0229] Input: Audio data

[0230] Output: Text data

[0231] Specific operation: The device sends voice data to the voice recognition API and obtains the text data returned by the API.

[0232] Step 3:

[0233] The text data is sent to a generative AI model (e.g., GPT-4), which analyzes the instructions and generates an operation script.

[0234] Input: Text data

[0235] Output: Operation script

[0236] Specific operation: The server supplies text data to GPT-4 and parses the instructions using the prompt: "The user wants to calculate and display the sum of the production data for line A. Please generate an appropriate formula." As a result, an operation script containing the formula =SUM(line A data) is generated.

[0237] Step 4:

[0238] The server sends the generated operation script to the terminal.

[0239] Input: Operation script

[0240] Output: Operation script

[0241] Specific operation: The server uses the network to send the operation script to the terminal. The script is sent to the terminal in its original format.

[0242] Step 5:

[0243] The terminal then sends the received operation script to the robot's control system, which runs on a platform such as the Siemens TIA Portal.

[0244] Input: Operation script

[0245] Output: None (to robot processing)

[0246] Specific operation: The terminal sends the operation script to the robot using a specific network protocol (e.g., HTTP, TCP / IP).

[0247] Step 6:

[0248] The robot's control system parses the received script and performs the specified operations (in this case, totaling and displaying production data).

[0249] Input: Operation script

[0250] Output: Execution result (total production data)

[0251] How it works: The robot's control system analyzes the operation script, retrieves production data from the Siemens TIA Portal database on line A, calculates the total, and displays the result on a display or touch panel.

[0252] Step 7:

[0253] The robot displays the calculation results and provides feedback to the user.

[0254] Input: Execution result (total of production data)

[0255] Output: Displayed results

[0256] Specific operation: The calculation results are displayed in real time on the robot's display and touch panel, allowing the user to check them and give further instructions.

[0257] Through the above processing steps, efficient production line management and maintenance can be achieved within a factory using natural language.

[0258] 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.

[0259] This invention combines a system that uses generative AI to automatically generate formulas and settings for spreadsheet software based on user instructions in natural language, and reflects the results in the spreadsheet, with an emotion engine that recognizes the user's emotions. This system improves the user experience by providing appropriate operations and feedback according to the user's emotional state.

[0260] System Configuration

[0261] The system mainly consists of the following components:

[0262] 1. User input means (terminal):

[0263] Users input instructions in natural language through an on-device interface, which can range from creating formulas to setting conditional formatting and even generating graphs.

[0264] 2. Generative AI model (server):

[0265] The server is equipped with a generation AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generation AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[0266] 3. Emotion engine (server or device):

[0267] The emotion engine analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state. Based on the results of this emotion engine, the generative AI makes further adjustments.

[0268] 4. Analysis result sending method (server):

[0269] The server sends the operation script generated by the generative AI and emotion engine to the device. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[0270] 5. Sheet reflection method (terminal):

[0271] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[0272] Program processing and example

[0273] 1. User input (terminal):

[0274] The user enters instructions into the device interface, such as "calculate the total sales data," which is then sent to the server for automatic analysis.

[0275] 2. Parsing the instruction (server):

[0276] The generation AI on the server receives the user's input and analyzes it. Through this analysis, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[0277] 3. Acquisition and analysis of emotion data (emotion engine):

[0278] An emotion engine on the server or device acquires and analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. For example, if the user is feeling impatient, it will provide simple operating instructions according to the situation.

[0279] 4. Generate operation script (server):

[0280] Based on the analysis results of the generation AI and the emotion engine, the server generates an appropriate operation script, which is adjusted to take into account the user's emotional state.

[0281] 5. Sending and reflecting analysis results (from server to device, device):

[0282] The server sends the generated operation script to the terminal, which then applies it to the spreadsheet software, thereby reflecting the specified formulas and settings on the sheet.

[0283] Specific examples

[0284] Automatic generation of mathematical formulas and emotional response

[0285] User instruction: "Sum the data in column A"

[0286] System Action:

[0287] 1. The user enters this instruction and sends it from the terminal to the server.

[0288] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[0289] 3. If the emotion engine determines that the user is feeling anxious or stressed, it simplifies the analysis results to make them easier for the user to understand.

[0290] 4. An operation script is generated and sent to the terminal.

[0291] 5. The terminal executes the received script and reflects the formula in the cell.

[0292] Conditional formatting and sentiment support

[0293] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[0294] System Action:

[0295] 1. The user's instructions are sent from the device to the server.

[0296] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[0297] 3. If the emotion engine judges the user to be relaxed, it will present multiple options and allow the user to choose.

[0298] 4. The script is sent from the server to the device and executed on the device.

[0299] 5. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[0300] This invention allows users to quickly and accurately perform advanced operations on spreadsheet software simply by issuing instructions in natural language, and through the emotion engine, it is possible to realize flexible operation responses according to the user's emotional state, allowing even beginners and users unfamiliar with the software to work efficiently.

[0301] The processing flow will be explained below.

[0302] Step 1:

[0303] The user provides input. Specifically, the user types natural language instructions into the device interface, such as "calculate the total sales data."

[0304] Step 2:

[0305] The device prepares the user's instructions to send to the server. The instructions are converted into an appropriate format and forwarded to the server.

[0306] Step 3:

[0307] The server receives the user's instructions, and the received data is analyzed by the generating AI.

[0308] Step 4:

[0309] The generation AI on the server analyzes the user's instructions. As a result of the analysis, the formula =SUM(sales data) is generated in response to the instruction "Calculate the sum of the sales data."

[0310] Step 5:

[0311] The emotion engine analyzes the user's current emotional state, obtaining emotional data based on the user's tone of voice, facial expressions, typing speed, etc.

[0312] Step 6:

[0313] The emotion engine provides the analysis results to the generative AI, which adjusts to provide simple feedback if the user is feeling stressed.

[0314] Step 7:

[0315] The server generates an operation script based on the analysis results of the generation AI and the emotion engine. For example, a script is generated to apply the formula =SUM(A:A) in spreadsheet software.

[0316] Step 8:

[0317] The server sends the generated operation script to the terminal. Check that the script was sent successfully.

[0318] Step 9:

[0319] The terminal receives the operation script from the server, confirms that reception has been completed, and moves on to the next process.

[0320] Step 10:

[0321] The terminal starts the spreadsheet software and makes the necessary preparations to execute the operation script.

[0322] Step 11:

[0323] The terminal executes the received operation script on the spreadsheet software. For example, the terminal enters the formula =SUM(A:A) into a specified cell.

[0324] Step 12:

[0325] The terminal confirms that the operation script has been executed and that the operation requested by the user has been correctly executed.

[0326] Example 2

[0327] 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."

[0328] Operating conventional spreadsheet software is often difficult for users who are not familiar with technology. Furthermore, operations are performed without considering the user's emotional state, which can result in a poor user experience. Specifically, there is a need for a system that simplifies operations using natural language instructions while flexibly responding to the user's emotional state.

[0329] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving instructions in natural language from a user; analysis means including a generation AI for analyzing the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in the spreadsheet software based on the analysis result by the analysis means; means for applying the operation script to the spreadsheet software; means including an emotion engine for evaluating the emotional state of the user; and means for adjusting the operation script based on the evaluation result of the emotion engine. This enables the user to perform advanced operations on the spreadsheet software simply by issuing instructions in natural language, and also enables flexible operation responses according to the user's emotional state.

[0330] A "user" is an entity that utilizes the system to input natural language instructions.

[0331] "Natural language instructions" are requests or commands for operations given by the user using everyday language.

[0332] A "terminal" is a device used by a user to access the system, including a personal computer or smartphone.

[0333] "Generative AI" is artificial intelligence that analyzes the user's natural language instructions and automatically generates specific operating instructions such as formulas and settings.

[0334] "Analysis means" includes generative AI, a function that analyzes the user's natural language instructions and generates appropriate formulas and settings.

[0335] An "operation script" is a series of instructions for applying the formulas and settings generated by the analysis means to the spreadsheet software.

[0336] "Spreadsheet software" refers to software used to calculate formulas, organize information, and visualize it, and includes Microsoft Excel and Google Sheets.

[0337] The "emotion engine" is an engine that evaluates the user's emotional state based on their tone of voice, facial expression, input speed, etc.

[0338] "Emotional state" refers to the user's emotional state analyzed by the emotion engine, and includes excitement, impatience, relaxation, etc.

[0339] The "system" refers to the entire technical setup, including a series of components, that receives natural language instructions from the user, parses them, and reflects them in the spreadsheet software.

[0340] The "server" is a central processing unit that receives user instructions, analyzes them using a generative AI model and emotion engine, generates an operation script, and sends it back to the terminal.

[0341] This invention combines a system that uses generative AI to automatically generate formulas and settings for spreadsheet software and reflects them in the spreadsheet when the user gives instructions in natural language, with an emotion engine that recognizes the user's emotions. The system aims to improve the user experience by providing appropriate operations and feedback according to the user's emotional state.

[0342] System Configuration

[0343] The system mainly consists of the following components:

[0344] 1. User input means (terminal):

[0345] Users input instructions in natural language through an interface on their device, which typically uses a personal computer (PC) or smartphone. These instructions range from creating mathematical formulas to setting conditional formatting and even generating graphs.

[0346] 2. Generative AI model (server):

[0347] The server is equipped with a generative AI (e.g., GPT-3) that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generative AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[0348] 3. Emotion engine (server or device):

[0349] The emotion engine (e.g., Affdex) analyzes emotion data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state. Based on the results of this emotion engine, the generative AI makes further adjustments.

[0350] 4. Analysis result sending method (server):

[0351] The server sends the operation script generated by the generative AI and emotion engine to the device. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[0352] 5. Sheet reflection method (terminal):

[0353] The terminal operates spreadsheet software (for example, Microsoft Excel or Google Sheets) based on the received operation script, and reflects formulas and settings in the sheet.

[0354] Examples of specific examples and prompts

[0355] Example 1: Automatic generation of mathematical expressions and emotional response

[0356] User instruction: "Sum the data in column A"

[0357] Specific system actions:

[0358] 1. The user enters this instruction and sends it from the terminal to the server.

[0359] 2. The server's generation AI analyzes the instructions and generates the formula =SUM(A:A).

[0360] 3. If the emotion engine assesses that the user is feeling anxious or stressed, it will simplify the analysis results based on that assessment and adjust them to make them easier for the user to understand.

[0361] 4. An operation script is generated and sent to the terminal.

[0362] 5. The terminal executes the received script and reflects the formula in the cell.

[0363] Example 2: Conditional formatting and emotional response

[0364] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[0365] Specific system actions:

[0366] 1. The user's instructions are sent from the device to the server.

[0367] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[0368] 3. If the emotion engine assesses that the user is relaxed, it will present multiple options based on that assessment and adjust them so that the user can choose.

[0369] 4. The script is sent from the server to the device and executed on the device.

[0370] 5. If the value of a cell in column B is greater than or equal to 100, the background will automatically be set to red.

[0371] Prompt Sentence Examples

[0372] Prompt 1: "Calculate the sum of the data in column A."

[0373] Prompt 2: "If the value in column B is greater than or equal to 100, make the background red."

[0374] This invention allows users to quickly and accurately perform advanced operations on spreadsheet software simply by issuing instructions in natural language, and also enables flexible operation responses according to the user's emotional state through an emotion engine, allowing even beginners and users unfamiliar with the software to work efficiently.

[0375] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0376] Step 1:

[0377] User prompt input:

[0378] The user inputs instructions in natural language through the terminal interface, for example, "Calculate the sum of the data in column A." The input data is a string of natural language characters, which is the starting point for the system's processing.

[0379] Input: User's natural language instructions

[0380] Output: Natural language string

[0381] Step 2:

[0382] Instructions sent to the server:

[0383] The device sends the user's natural language instructions to the server, which receives this data as an HTTP request.

[0384] Input: Natural language string

[0385] Output: HTTP request to the server

[0386] Step 3:

[0387] Parsing instructions:

[0388] The server passes the received natural language instructions to a generative AI model (e.g., GPT-3) for analysis. The generative AI model analyzes the natural language and generates appropriate spreadsheet formulas and settings. For example, the instruction "Calculate the sum of the data in column A" is converted into the formula =SUM(A:A).

[0389] Input: HTTP request to the server

[0390] Output: Formula or setting

[0391] Step 4:

[0392] Emotion data acquisition and analysis:

[0393] The emotion engine acquires and analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. The emotion engine evaluates the user's emotional state based on this data. For example, if the user is feeling impatient, that data is reflected in the generating AI.

[0394] Input: User emotional data (tone of voice, facial expressions, typing speed, etc.)

[0395] Output: Emotional state assessment result

[0396] Step 5:

[0397] Generate operation script:

[0398] The generative AI model generates operation scripts based on the results of instruction analysis and the evaluation of emotional data. For example, if the emotion engine recognizes the user's impatience, the generated formulas and spreadsheet settings will be kept simple.

[0399] Input: Formula or setting, emotional state evaluation result

[0400] Output: Operation script

[0401] Step 6:

[0402] Sending analysis results:

[0403] The server sends the generated operation script to the terminal, usually in JSON format as an HTTP response.

[0404] Input: Operation script

[0405] Output: HTTP response to the device

[0406] Step 7:

[0407] Reflecting the operation script:

[0408] The device applies the received operation script to spreadsheet software (e.g., Microsoft Excel or Google Sheets). The spreadsheet software automatically opens and the formulas and settings are reflected in the specified sheet.

[0409] Input: Action script as HTTP response

[0410] Output: Formulas and settings reflected in spreadsheet software

[0411] (Application example 2)

[0412] 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."

[0413] In recent years, many users have been using spreadsheet software to manage and analyze business data. However, these operations often require specialized knowledge and are cumbersome for average users. Furthermore, the user's emotional state can affect the operation, making efficient operation particularly difficult under stressful or impatient circumstances. Therefore, there is a need to develop a system that can appropriately perform complex spreadsheet operations using simple natural language instructions and provide flexible feedback according to the user's emotional state.

[0414] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving instructions in natural language from a user; analysis means including a generation AI that analyzes the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the analysis result by the analysis means; means including an emotion engine that analyzes the user's emotional state; means for the generation AI to adjust the operation script based on the result of the emotion engine; and means for applying the operation script to the spreadsheet software. This allows the user to easily operate the spreadsheet software in natural language and further enables the user to receive appropriate feedback according to their emotional state.

[0415] A "user" is a person who operates the system and inputs natural language instructions.

[0416] A "natural language" is a language that people use in their daily lives, and is not a formal programming language.

[0417] "Generative AI" is artificial intelligence that analyzes the user's natural language instructions and automatically generates the necessary formulas and settings.

[0418] "Analysis means" refers to a means for analyzing input natural language instructions, and includes generative AI.

[0419] An "operation script" is a program that contains a series of commands to automatically reflect formulas and settings in spreadsheet software.

[0420] "Spreadsheet software" is software that stores data and performs calculations and creates graphs.

[0421] An "emotion engine" is a system that analyzes a user's emotional state based on their tone of voice, facial expression, input speed, etc.

[0422] "Feedback" refers to responses or guidance to the user, including content that is tailored based on emotional state.

[0423] The "adjustment means" is a means by which the generation AI adjusts the operation script based on the analysis results of the emotion engine.

[0424] The "application means" is a means for applying the generated operation script to the spreadsheet software.

[0425] This invention is a system that uses a generative AI to automatically generate formulas and settings for spreadsheet software in response to instructions given by the user in natural language, and also provides flexible feedback according to the user's emotional state. Specific examples are described below.

[0426] System configuration

[0427] 1. User input means (terminal)

[0428] The user inputs natural language instructions through an interface on the device, such as "calculate the sum of the sales data."

[0429] 2. Analysis method (generative AI model, server)

[0430] The server is equipped with a generative AI that analyzes the user's natural language instructions. The generative AI uses an artificial intelligence model such as OpenAI to analyze the input instructions and automatically generate the necessary formulas and settings. For example, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[0431] 3. Emotion engine (server or terminal)

[0432] The emotion engine analyzes emotion data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state, using emotion recognition services from Microsoft Azure or Google Cloud, for example.

[0433] 4. Coordination means (server)

[0434] Based on the results of the emotion engine, the generative AI adjusts the operation script, simplifying the steps and providing detailed guidance if the user is feeling impatient.

[0435] 5. Application means (terminal)

[0436] The operation script generated on the server is sent to the terminal and applied to spreadsheet software, such as Excel or Google Sheets, automatically reflecting formulas.

[0437] Program processing

[0438] When the server receives a natural language instruction from the user, it uses an analysis means to analyze the content of the instruction. Next, it uses an emotion engine to analyze the user's emotional state, and the generation AI adjusts the operation script based on the results. The adjusted operation script is sent from the server to the terminal and applied to the spreadsheet software on the terminal.

[0439] Possible generative AI models to use include OpenAI's GPT-3.

[0440] For sentiment analysis, you can use Microsoft Azure's sentiment analysis API or Google Cloud's emotion recognition API.

[0441] Microsoft Excel and Google Sheets are used as spreadsheet software.

[0442] Specific examples

[0443] Automatic generation of mathematical formulas and emotional response

[0444] User instruction: "Sum the data in column A"

[0445] System Action:

[0446] 1. The user enters this instruction and sends it from the terminal to the server.

[0447] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[0448] 3. If the emotion engine determines that the user is feeling anxious or stressed, it simplifies the analysis results to make them easier for the user to understand.

[0449] 4. An operation script is generated and sent to the terminal.

[0450] 5. The terminal executes the received script and reflects the formula in the cell.

[0451] Conditional formatting and sentiment support

[0452] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[0453] System Action:

[0454] 1. The user's instructions are sent from the device to the server.

[0455] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[0456] 3. If the emotion engine judges the user to be relaxed, it will present multiple options and allow the user to choose.

[0457] 4. The script is sent from the server to the device and executed on the device.

[0458] 5. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[0459] Example prompt sentence:

[0460] "Enter today's sales data"

[0461] "Calculate this week's sales totals"

[0462] Check if sales targets are being met

[0463] Show me the sales graph

[0464] "Tell me your lowest sales days"

[0465] In this way, store staff can receive flexible, emotional feedback while efficiently managing and analyzing data.

[0466] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0467] Step 1:

[0468] User Input

[0469] The user inputs instructions in natural language through the interface on the terminal.

[0470] Input: Natural language instructions (e.g., "Calculate the sum of the sales data")

[0471] Output: Text data with natural language instructions

[0472] Step 2:

[0473] Sending natural language instructions

[0474] The terminal transmits the natural language instructions entered by the user to the server.

[0475] Input: Text data with natural language instructions

[0476] Output: Sends instruction data to the server

[0477] Step 3:

[0478] Parsing instructions

[0479] The server analyzes the received natural language instructions using an analysis method (generative AI model), such as OpenAI's GPT-3.

[0480] Input: Text data with natural language instructions

[0481] Data processing: Generative AI models analyze natural language and convert it into appropriate formulas and settings.

[0482] Output: Text data of formulas and settings (e.g. =SUM(sales data))

[0483] Step 4:

[0484] Acquiring emotional state

[0485] The emotion engine collects data such as the user's tone of voice, facial expressions, and typing speed to analyze their emotional state.

[0486] Input: User voice data, facial expression data, and typing speed data

[0487] Data calculation: Analysis using a sentiment analysis engine (e.g., Microsoft Azure's sentiment recognition API)

[0488] Output: Emotional state data (e.g., anxious, relaxed, etc.)

[0489] Step 5:

[0490] Generate and adjust operation scripts

[0491] The server generates an operation script based on the analyzed formulas, settings, and emotional state data, and makes adjustments as needed.

[0492] Input: Text data for formulas and settings, emotional state data

[0493] Data processing: Adjustments based on emotional state (e.g., simplifying procedures if you are in a hurry)

[0494] Output: Adjusted operation script

[0495] Step 6:

[0496] Sending an Operation Script

[0497] The server transmits the generated operation script to the terminal.

[0498] Input: Adjusted operation script

[0499] Output: Sends script data to the terminal

[0500] Step 7:

[0501] Applying a script

[0502] The terminal then applies the received operation script to spreadsheet software, such as Microsoft Excel or Google Sheets.

[0503] Input: Adjusted operation script

[0504] Data calculation: Reflect formulas and settings in spreadsheet software

[0505] Output: Formulas and settings reflected in the spreadsheet software (e.g. =SUM(A:A) is entered in the cell)

[0506] 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.

[0507] 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.

[0508] 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.

[0509] [Second embodiment]

[0510] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0511] 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.

[0512] 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).

[0513] 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.

[0514] 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.

[0515] 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).

[0516] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0517] 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.

[0518] 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.

[0519] 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.

[0520] 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.

[0521] 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."

[0522] This invention relates to a system that uses generative AI to automatically generate formulas and settings for spreadsheet software and reflect them in the spreadsheet when the user gives instructions in natural language. This system reduces the burden on the user by simply receiving and analyzing the user's instructions and automatically performing the appropriate operations.

[0523] System Configuration

[0524] The system mainly consists of the following components:

[0525] 1. User input means (terminal):

[0526] Users input instructions in natural language through an on-device interface, which can range from creating formulas to setting conditional formatting and even generating graphs.

[0527] 2. Generative AI model (server):

[0528] The server is equipped with a generation AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generation AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[0529] 3. Analysis result sending method (server):

[0530] The server sends the operation script generated by the generation AI to the terminal. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[0531] 4. Sheet reflection method (terminal):

[0532] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[0533] Program processing and example

[0534] 1. User input (terminal):

[0535] The user enters instructions into the device interface, such as "calculate the total sales data," which is then sent to the server for automatic analysis.

[0536] 2. Parsing the instruction (server):

[0537] The generation AI on the server receives the user's input and analyzes it. Through this analysis, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[0538] 3. Generate operation script (server):

[0539] Based on the analysis results of the generative AI, the server generates an appropriate operation script, which is an instruction for automatically applying the specified formulas and settings to the spreadsheet software.

[0540] 4. Sending and reflecting analysis results (from server to device, device):

[0541] The server sends the generated operation script to the terminal, which then applies it to the spreadsheet software, thereby reflecting the specified formulas and settings on the sheet.

[0542] Specific examples

[0543] Automatic formula generation

[0544] User instruction: "Sum the data in column A"

[0545] System Action:

[0546] 1. The user enters this instruction and sends it from the terminal to the server.

[0547] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[0548] 3. An operation script is generated and sent to the terminal.

[0549] 4. The terminal executes the received script and reflects the formula in the cell.

[0550] Conditional formatting settings

[0551] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[0552] System Action:

[0553] 1. The user's instructions are sent from the device to the server.

[0554] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[0555] 3. The script is sent from the server to the device and executed on the device.

[0556] 4. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[0557] This invention enables users to quickly and accurately perform advanced operations on spreadsheet software using only natural language instructions, allowing even beginners and users unfamiliar with the software to work efficiently.

[0558] The processing flow will be explained below.

[0559] Step 1:

[0560] The user provides input. Specifically, the user types natural language instructions into the device interface, such as "calculate the total sales data."

[0561] Step 2:

[0562] The device prepares the user's instructions to send to the server. The instructions are converted into an appropriate format and forwarded to the server.

[0563] Step 3:

[0564] The server receives the user's instructions, and the received data is analyzed by the generating AI.

[0565] Step 4:

[0566] The generation AI on the server analyzes the user's instructions. As a result of the analysis, for example, in response to an instruction to "calculate the sum of sales data," the formula =SUM(sales data) is generated.

[0567] Step 5:

[0568] The server generates an operation script based on the analysis results of the generation AI. Specifically, a script is generated that applies a formula such as =SUM(A:A) in spreadsheet software.

[0569] Step 6:

[0570] The server sends the generated operation script to the terminal. Check that the script was sent successfully.

[0571] Step 7:

[0572] The terminal receives the operation script from the server, confirms that reception has been completed, and moves on to the next process.

[0573] Step 8:

[0574] The terminal starts the spreadsheet software, and the necessary preparations are made to execute the operation script.

[0575] Step 9:

[0576] The terminal executes the received operation script on the spreadsheet software. For example, the terminal enters the formula =SUM(A:A) into a specified cell.

[0577] Step 10:

[0578] The terminal confirms that the operation script has been executed and that the operation requested by the user has been correctly executed.

[0579] This allows users to intuitively and accurately operate complex spreadsheet software simply by issuing instructions in natural language.

[0580] Example 1

[0581] 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."

[0582] Conventional spreadsheet software requires users to manually create formulas and settings, which requires a great deal of time and effort. Creating specific settings and formulas can be difficult, making it difficult for beginners and users unfamiliar with the software to use. Furthermore, the lack of technology to analyze natural language instructions and automatically reflect them in spreadsheets makes efficient data management and information processing difficult.

[0583] 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.

[0584] In this invention, the server includes: means for receiving instructions in natural language from a user; means for transmitting the instructions in natural language to the server; analysis means including a generation AI for analyzing the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of analysis by the analysis means; means for transmitting the operation script to a terminal; and means for applying the operation script to the spreadsheet software. This makes it possible for a user to simply input instructions in natural language to easily and automatically generate formulas and settings for the spreadsheet software and reflect them in a sheet.

[0585] A "user" is a person or entity that uses the system to provide instructions in natural language.

[0586] A "natural language" is a language that humans use on a daily basis and is not a programming language.

[0587] "Instructions" are words or sentences that indicate the operations that a user performs on a system.

[0588] A "terminal" is a device that is directly operated by a user and includes an input interface.

[0589] A "server" is a remote computer system that analyzes and processes instructions sent by a user.

[0590] "Generative AI" is an artificial intelligence technology that analyzes natural language instructions and automatically generates appropriate formulas and settings.

[0591] An "analysis means" is a component that has the function of analyzing natural language instructions using generative AI.

[0592] An "operation script" is a series of commands that are used to reflect formulas and settings in spreadsheet software.

[0593] "Spreadsheet software" is a software application for performing numerical calculations and managing data.

[0594] "Settings" are configuration options or parameters that change the behavior or appearance of the spreadsheet software.

[0595] A "sheet" refers to a page or tab where data is arranged in a spreadsheet program.

[0596] MODE FOR CARRYING OUT THE INVENTION

[0597] This invention is a system that uses generative AI to automatically generate formulas and settings for spreadsheet software in response to instructions given by the user in natural language, and reflects these in the spreadsheet. This system reduces the burden on the user by simply receiving and analyzing the user's instructions, and automatically performing the appropriate operations.

[0598] System Configuration

[0599] The system consists of four main components:

[0600] 1. User input means (terminal):

[0601] Users input instructions in natural language through an on-device interface, such as "calculate the sum of the sales data" or "if the value in column B is greater than 100, make the background red."

[0602] 2. Generative AI model (server):

[0603] The server is equipped with a generative AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. The generative AI analyzes the natural language instructions and generates the necessary formulas and settings.

[0604] 3. Analysis result sending method (server):

[0605] The server sends the operation script generated by the generation AI to the terminal. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[0606] 4. Sheet reflection method (terminal):

[0607] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[0608] Specific examples

[0609] Below are two examples of how the system works:

[0610] Automatic formula generation

[0611] User instruction: "Sum the data in column A"

[0612] The user inputs this instruction and sends it from the terminal to the server.

[0613] The server's generation AI analyzes the instructions and generates the formula =SUM(A:A).

[0614] The operation script generated as a result of the analysis is sent to the terminal.

[0615] The terminal executes the received script and reflects the formulas in the spreadsheet software.

[0616] Conditional formatting settings

[0617] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[0618] The user's instructions are sent from the terminal to the server.

[0619] The server's generated AI parses the instructions and generates a script that applies the conditional formatting.

[0620] The script is sent from the server to the terminal and executed on the terminal.

[0621] The terminal executes the received script, and if the value of the cell in column B is greater than or equal to 100, the background turns red.

[0622] Prompt Sentence Examples

[0623] Here are some example prompts to input to the AI ​​generator:

[0624] "Calculate the sum of the sales data" -> Generate a formula to calculate the total sales data.

[0625] "If the value in column B is greater than or equal to 100, set the background to red" -> Create a conditional formatting rule to set the background of cells in column B to red if the value is 100 or more.

[0626] The generative AI analyzes these prompts and generates appropriate operation scripts, allowing users to quickly and accurately perform advanced operations on spreadsheet software using only natural language instructions, enabling even beginners to work efficiently.

[0627] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0628] Step 1:

[0629] User instruction input (terminal)

[0630] The user inputs the desired spreadsheet software operation into the terminal interface in natural language. For example, they might input "calculate the total sales data." When this instruction is input, the terminal treats the instruction as data and prepares to send it to the server.

[0631] Input: User's natural language instructions

[0632] Output: Instruction data in the format to send to the server

[0633] Specific operation: The user enters "Calculate the total sales data" in the text box on the terminal and presses the send button.

[0634] Step 2:

[0635] Sending instructions (from terminal to server)

[0636] The device sends the user's specified data to the server, usually using a communication method such as an HTTP request.

[0637] Input: User's natural language instructions

[0638] Output: Data received by the server

[0639] Specific operation: The device sends an HTTP request, and the server's API endpoint accepts this request.

[0640] Step 3:

[0641] Parsing instructions (server)

[0642] The generative AI model on the server analyzes the received natural language instructions. This analysis determines the specific formulas and settings. For example, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[0643] Input: User's natural language instructions

[0644] Output: Formulas and settings as analysis results

[0645] Specific operation: The generation AI analyzes the prompt "Calculate the sum of the sales data" and decides to generate the formula =SUM(sales data).

[0646] Step 4:

[0647] Generate operation script (server)

[0648] Based on the analysis results, the server generates an operation script for the spreadsheet software, which includes specific formulas and settings.

[0649] Input: Formulas and settings as analysis results

[0650] Output: Operation script

[0651] Specific operation: The generation AI executes the script generation logic and creates a specific script called =SUM(sales data).

[0652] Step 5:

[0653] Sending operation scripts (from server to terminal)

[0654] The server sends the generated operation script to the terminal. This transmission also uses a communication method such as HTTP response. The terminal caches and saves the received script.

[0655] Input: Operation script

[0656] Output: Received data from the device

[0657] Specific operation: The server sends back the script as an HTTP response, and the terminal receives the response.

[0658] Step 6:

[0659] Execute operation script and reflect sheet (terminal)

[0660] The terminal applies the received operation script to the spreadsheet software and reflects the formulas and settings in the sheet. Specifically, the formula =SUM(sales data) is entered into the specified cell.

[0661] Input: Received operation script

[0662] Output: Reflection of formulas and settings in spreadsheet software

[0663] Specific behavior: The device's spreadsheet software runs the script, and the formula is automatically entered into the cell.

[0664] (Application example 1)

[0665] 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."

[0666] Conventional factory robot operation and production line management / maintenance work often required a lot of human intervention, resulting in inefficiency. Furthermore, it was difficult for workers without specialized knowledge to operate the robots, leading to the risk of operational errors and reduced efficiency. Furthermore, there was a lack of an appropriate system for analyzing data in real time and responding quickly. To solve these problems, an advanced system that can be operated using natural language is needed.

[0667] 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.

[0668] In this invention, the server includes: means for receiving natural language instructions from a user; analysis means including a generation AI for analyzing the natural language instructions; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of the analysis by the analysis means; means for applying the operation script to the spreadsheet software; and means for applying the generation AI to a production line management or maintenance robot, analyzing the natural language instructions, generating an appropriate operation script, and applying it to the robot. This enables workers to efficiently manage production lines and perform maintenance work in a factory simply by issuing instructions in natural language.

[0669] A "means for receiving natural language instructions from a user" is a device or software that provides an interface through which a user can input instructions in natural language using voice or text.

[0670] "Analysis means including generative AI" refers to devices or software that include artificial intelligence technology used to analyze a user's natural language instructions, understand their content, and generate appropriate operation scripts.

[0671] The "means for generating an operation script" is a device or software that automatically generates instructions for reflecting the necessary formulas and settings in the spreadsheet software or robot based on the results of the analysis by the analysis means.

[0672] The "means for applying to spreadsheet software" is an interface or program for reflecting the generated operation script in the spreadsheet software.

[0673] "Means for application to robots for production line management and maintenance" refers to a device or software that analyzes natural language instructions from generative AI for robots that manage production lines and perform maintenance work within factories, generates commands for appropriate operations, and has the robots execute these commands.

[0674] The system that embodies this invention consists of a series of processes in which a user gives instructions in natural language and uses generative AI to reflect the operations in factory robots.

[0675] 1. System Program

[0676] The system's program involves receiving natural language instructions from the user, using generative AI to generate an operation script, and applying it to the robot.

[0677] 2. Program Processing

[0678] The system operates using the following hardware and software:

[0679] Hardware and Software Configuration

[0680] User input device: A device that allows a user to input natural language instructions via voice or text. Examples include smartphones and tablets.

[0681] Server: A computer system that analyzes natural language instructions and generates appropriate operational scripts using a generative AI model, such as GPT-4.

[0682] Speech recognition API: Software that converts user voice input into text. An example is Google Cloud Speech-to-Text.

[0683] Robot control system: A robot system with a control program to execute the generated operation script. An example is the Siemens TIA Portal.

[0684] 3. Data processing and calculation

[0685] Speech Recognition: Converts speech to text on the user's input device. Uses speech recognition APIs to accurately transcribe the user's natural language commands into text.

[0686] Analysis by generative AI: The server receives textual natural language instructions, analyzes them using a generative AI model (GPT-4), and generates an appropriate operation script.

[0687] Generation and application of operation script: The generated operation script is sent to the robot and executed by the robot's control system, which then performs the specified action.

[0688] 4. Specific Examples

[0689] To calculate the sum of sales data:

[0690] User instruction: "Calculate the sum of the sales data"

[0691] Analysis method:

[0692] 1. The user speaks instructions, which are converted into text using a speech recognition API.

[0693] 2. The server's generation AI analyzes the instructions and generates the formula =SUM(sales data).

[0694] 3. An operation script is generated and sent to the terminal.

[0695] 4. The terminal executes the received script and reflects the formulas in the sheet.

[0696] When giving natural language instructions to a robot

[0697] User instruction: "Calculate and display the production total for line A."

[0698] Example prompt sentence:

[0699] "A user wants to calculate and display the total production data for line A. Please generate the appropriate formula."

[0700] Analysis method:

[0701] 1. The user speaks voice commands to the robot.

[0702] 2. The robot converts the speech into text and sends it to the server.

[0703] 3. GPT-4 on the server analyzes and generates the formula =SUM(A line data).

[0704] 4. The generated script is sent to the robot, which then aggregates and displays the production data.

[0705] This system will improve the efficiency of production line management and maintenance work within factories, and will enable operations to be carried out easily using instructions in natural language.

[0706] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0707] Step 1:

[0708] The user inputs voice instructions into the terminal using natural language. The input is a specific instruction such as "Calculate and display the production total for line A." The terminal receives this voice data.

[0709] Input: Voice commands

[0710] Output: Audio data

[0711] Specific operation: The user speaks into the smartphone or tablet to give instructions, and the device picks up the voice through the microphone.

[0712] Step 2:

[0713] The device converts the voice data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[0714] Input: Audio data

[0715] Output: Text data

[0716] Specific operation: The device sends voice data to the voice recognition API and obtains the text data returned by the API.

[0717] Step 3:

[0718] The text data is sent to a generative AI model (e.g., GPT-4), which analyzes the instructions and generates an operation script.

[0719] Input: Text data

[0720] Output: Operation script

[0721] Specific operation: The server supplies text data to GPT-4 and parses the instructions using the prompt: "The user wants to calculate and display the sum of the production data for line A. Please generate an appropriate formula." As a result, an operation script containing the formula =SUM(line A data) is generated.

[0722] Step 4:

[0723] The server sends the generated operation script to the terminal.

[0724] Input: Operation script

[0725] Output: Operation script

[0726] Specific operation: The server uses the network to send the operation script to the terminal. The script is sent to the terminal in its original format.

[0727] Step 5:

[0728] The terminal then sends the received operation script to the robot's control system, which runs on a platform such as the Siemens TIA Portal.

[0729] Input: Operation script

[0730] Output: None (to robot processing)

[0731] Specific operation: The terminal sends the operation script to the robot using a specific network protocol (e.g., HTTP, TCP / IP).

[0732] Step 6:

[0733] The robot's control system parses the received script and performs the specified operations (in this case, totaling and displaying production data).

[0734] Input: Operation script

[0735] Output: Execution result (total production data)

[0736] How it works: The robot's control system analyzes the operation script, retrieves production data from the Siemens TIA Portal database on line A, calculates the total, and displays the result on a display or touch panel.

[0737] Step 7:

[0738] The robot displays the calculation results and provides feedback to the user.

[0739] Input: Execution result (total of production data)

[0740] Output: Displayed results

[0741] Specific operation: The calculation results are displayed in real time on the robot's display and touch panel, allowing the user to check them and give further instructions.

[0742] Through the above processing steps, efficient production line management and maintenance can be achieved within a factory using natural language.

[0743] 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.

[0744] This invention combines a system that uses generative AI to automatically generate formulas and settings for spreadsheet software based on user instructions in natural language, and reflects the results in the spreadsheet, with an emotion engine that recognizes the user's emotions. This system improves the user experience by providing appropriate operations and feedback according to the user's emotional state.

[0745] System Configuration

[0746] The system mainly consists of the following components:

[0747] 1. User input means (terminal):

[0748] Users input instructions in natural language through an on-device interface, which can range from creating formulas to setting conditional formatting and even generating graphs.

[0749] 2. Generative AI model (server):

[0750] The server is equipped with a generation AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generation AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[0751] 3. Emotion engine (server or device):

[0752] The emotion engine analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state. Based on the results of this emotion engine, the generative AI makes further adjustments.

[0753] 4. Analysis result sending method (server):

[0754] The server sends the operation script generated by the generative AI and emotion engine to the device. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[0755] 5. Sheet reflection method (terminal):

[0756] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[0757] Program processing and example

[0758] 1. User input (terminal):

[0759] The user enters instructions into the device interface, such as "calculate the total sales data," which is then sent to the server for automatic analysis.

[0760] 2. Parsing the instruction (server):

[0761] The generation AI on the server receives the user's input and analyzes it. Through this analysis, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[0762] 3. Acquisition and analysis of emotion data (emotion engine):

[0763] An emotion engine on the server or device acquires and analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. For example, if the user is feeling impatient, it will provide simple operating instructions according to the situation.

[0764] 4. Generate operation script (server):

[0765] Based on the analysis results of the generation AI and the emotion engine, the server generates an appropriate operation script, which is adjusted to take into account the user's emotional state.

[0766] 5. Sending and reflecting analysis results (from server to device, device):

[0767] The server sends the generated operation script to the terminal, which then applies it to the spreadsheet software, thereby reflecting the specified formulas and settings on the sheet.

[0768] Specific examples

[0769] Automatic generation of mathematical formulas and emotional response

[0770] User instruction: "Sum the data in column A"

[0771] System Action:

[0772] 1. The user enters this instruction and sends it from the terminal to the server.

[0773] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[0774] 3. If the emotion engine determines that the user is feeling anxious or stressed, it simplifies the analysis results to make them easier for the user to understand.

[0775] 4. An operation script is generated and sent to the terminal.

[0776] 5. The terminal executes the received script and reflects the formula in the cell.

[0777] Conditional formatting and sentiment support

[0778] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[0779] System Action:

[0780] 1. The user's instructions are sent from the device to the server.

[0781] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[0782] 3. If the emotion engine judges the user to be relaxed, it will present multiple options and allow the user to choose.

[0783] 4. The script is sent from the server to the device and executed on the device.

[0784] 5. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[0785] This invention allows users to quickly and accurately perform advanced operations on spreadsheet software simply by issuing instructions in natural language, and through the emotion engine, it is possible to realize flexible operation responses according to the user's emotional state, allowing even beginners and users unfamiliar with the software to work efficiently.

[0786] The processing flow will be explained below.

[0787] Step 1:

[0788] The user provides input. Specifically, the user types natural language instructions into the device interface, such as "calculate the total sales data."

[0789] Step 2:

[0790] The device prepares the user's instructions to send to the server. The instructions are converted into an appropriate format and forwarded to the server.

[0791] Step 3:

[0792] The server receives the user's instructions, and the received data is analyzed by the generating AI.

[0793] Step 4:

[0794] The generation AI on the server analyzes the user's instructions. As a result of the analysis, the formula =SUM(sales data) is generated in response to the instruction "Calculate the sum of the sales data."

[0795] Step 5:

[0796] The emotion engine analyzes the user's current emotional state, obtaining emotional data based on the user's tone of voice, facial expressions, typing speed, etc.

[0797] Step 6:

[0798] The emotion engine provides the analysis results to the generative AI, which adjusts to provide simple feedback if the user is feeling stressed.

[0799] Step 7:

[0800] The server generates an operation script based on the analysis results of the generation AI and the emotion engine. For example, a script is generated to apply the formula =SUM(A:A) in spreadsheet software.

[0801] Step 8:

[0802] The server sends the generated operation script to the terminal. Check that the script was sent successfully.

[0803] Step 9:

[0804] The terminal receives the operation script from the server, confirms that reception has been completed, and moves on to the next process.

[0805] Step 10:

[0806] The terminal starts the spreadsheet software and makes the necessary preparations to execute the operation script.

[0807] Step 11:

[0808] The terminal executes the received operation script on the spreadsheet software. For example, the terminal enters the formula =SUM(A:A) into a specified cell.

[0809] Step 12:

[0810] The terminal confirms that the operation script has been executed and that the operation requested by the user has been correctly executed.

[0811] Example 2

[0812] 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."

[0813] Operating conventional spreadsheet software is often difficult for users who are not familiar with technology. Furthermore, operations are performed without considering the user's emotional state, which can result in a poor user experience. Specifically, there is a need for a system that simplifies operations using natural language instructions while flexibly responding to the user's emotional state.

[0814] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving instructions in natural language from a user; analysis means including a generation AI for analyzing the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in the spreadsheet software based on the analysis result by the analysis means; means for applying the operation script to the spreadsheet software; means including an emotion engine for evaluating the emotional state of the user; and means for adjusting the operation script based on the evaluation result of the emotion engine. This enables the user to perform advanced operations on the spreadsheet software simply by issuing instructions in natural language, and also enables flexible operation responses according to the user's emotional state.

[0815] A "user" is an entity that utilizes the system to input natural language instructions.

[0816] "Natural language instructions" are requests or commands for operations given by the user using everyday language.

[0817] A "terminal" is a device used by a user to access the system, including a personal computer or smartphone.

[0818] "Generative AI" is artificial intelligence that analyzes the user's natural language instructions and automatically generates specific operating instructions such as formulas and settings.

[0819] "Analysis means" includes generative AI, a function that analyzes the user's natural language instructions and generates appropriate formulas and settings.

[0820] An "operation script" is a series of instructions for applying the formulas and settings generated by the analysis means to the spreadsheet software.

[0821] "Spreadsheet software" refers to software used to calculate formulas, organize information, and visualize it, and includes Microsoft Excel and Google Sheets.

[0822] The "emotion engine" is an engine that evaluates the user's emotional state based on their tone of voice, facial expression, input speed, etc.

[0823] "Emotional state" refers to the user's emotional state analyzed by the emotion engine, and includes excitement, impatience, relaxation, etc.

[0824] The "system" refers to the entire technical setup, including a series of components, that receives natural language instructions from the user, parses them, and reflects them in the spreadsheet software.

[0825] The "server" is a central processing unit that receives user instructions, analyzes them using a generative AI model and emotion engine, generates an operation script, and sends it back to the terminal.

[0826] This invention combines a system that uses generative AI to automatically generate formulas and settings for spreadsheet software and reflects them in the spreadsheet when the user gives instructions in natural language, with an emotion engine that recognizes the user's emotions. The system aims to improve the user experience by providing appropriate operations and feedback according to the user's emotional state.

[0827] System Configuration

[0828] The system mainly consists of the following components:

[0829] 1. User input means (terminal):

[0830] Users input instructions in natural language through an interface on their device, which typically uses a personal computer (PC) or smartphone. These instructions range from creating mathematical formulas to setting conditional formatting and even generating graphs.

[0831] 2. Generative AI model (server):

[0832] The server is equipped with a generative AI (e.g., GPT-3) that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generative AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[0833] 3. Emotion engine (server or device):

[0834] The emotion engine (e.g., Affdex) analyzes emotion data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state. Based on the results of this emotion engine, the generative AI makes further adjustments.

[0835] 4. Analysis result sending method (server):

[0836] The server sends the operation script generated by the generative AI and emotion engine to the device. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[0837] 5. Sheet reflection method (terminal):

[0838] The terminal operates spreadsheet software (for example, Microsoft Excel or Google Sheets) based on the received operation script, and reflects formulas and settings in the sheet.

[0839] Examples of specific examples and prompts

[0840] Example 1: Automatic generation of mathematical expressions and emotional response

[0841] User instruction: "Sum the data in column A"

[0842] Specific system actions:

[0843] 1. The user enters this instruction and sends it from the terminal to the server.

[0844] 2. The server's generation AI analyzes the instructions and generates the formula =SUM(A:A).

[0845] 3. If the emotion engine assesses that the user is feeling anxious or stressed, it will simplify the analysis results based on that assessment and adjust them to make them easier for the user to understand.

[0846] 4. An operation script is generated and sent to the terminal.

[0847] 5. The terminal executes the received script and reflects the formula in the cell.

[0848] Example 2: Conditional formatting and emotional response

[0849] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[0850] Specific system actions:

[0851] 1. The user's instructions are sent from the device to the server.

[0852] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[0853] 3. If the emotion engine assesses that the user is relaxed, it will present multiple options based on that assessment and adjust them so that the user can choose.

[0854] 4. The script is sent from the server to the device and executed on the device.

[0855] 5. If the value of a cell in column B is greater than or equal to 100, the background will automatically be set to red.

[0856] Prompt Sentence Examples

[0857] Prompt 1: "Calculate the sum of the data in column A."

[0858] Prompt 2: "If the value in column B is greater than or equal to 100, make the background red."

[0859] This invention allows users to quickly and accurately perform advanced operations on spreadsheet software simply by issuing instructions in natural language, and also enables flexible operation responses according to the user's emotional state through an emotion engine, allowing even beginners and users unfamiliar with the software to work efficiently.

[0860] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0861] Step 1:

[0862] User prompt input:

[0863] The user inputs instructions in natural language through the terminal interface, for example, "Calculate the sum of the data in column A." The input data is a string of natural language characters, which is the starting point for the system's processing.

[0864] Input: User's natural language instructions

[0865] Output: Natural language string

[0866] Step 2:

[0867] Instructions sent to the server:

[0868] The device sends the user's natural language instructions to the server, which receives this data as an HTTP request.

[0869] Input: Natural language string

[0870] Output: HTTP request to the server

[0871] Step 3:

[0872] Parsing instructions:

[0873] The server passes the received natural language instructions to a generative AI model (e.g., GPT-3) for analysis. The generative AI model analyzes the natural language and generates appropriate spreadsheet formulas and settings. For example, the instruction "Calculate the sum of the data in column A" is converted into the formula =SUM(A:A).

[0874] Input: HTTP request to the server

[0875] Output: Formula or setting

[0876] Step 4:

[0877] Emotion data acquisition and analysis:

[0878] The emotion engine acquires and analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. The emotion engine evaluates the user's emotional state based on this data. For example, if the user is feeling impatient, that data is reflected in the generating AI.

[0879] Input: User emotional data (tone of voice, facial expressions, typing speed, etc.)

[0880] Output: Emotional state assessment result

[0881] Step 5:

[0882] Generate operation script:

[0883] The generative AI model generates operation scripts based on the results of instruction analysis and the evaluation of emotional data. For example, if the emotion engine recognizes the user's impatience, the generated formulas and spreadsheet settings will be kept simple.

[0884] Input: Formula or setting, emotional state evaluation result

[0885] Output: Operation script

[0886] Step 6:

[0887] Sending analysis results:

[0888] The server sends the generated operation script to the terminal, usually in JSON format as an HTTP response.

[0889] Input: Operation script

[0890] Output: HTTP response to the device

[0891] Step 7:

[0892] Reflecting the operation script:

[0893] The device applies the received operation script to spreadsheet software (e.g., Microsoft Excel or Google Sheets). The spreadsheet software automatically opens and the formulas and settings are reflected in the specified sheet.

[0894] Input: Action script as HTTP response

[0895] Output: Formulas and settings reflected in spreadsheet software

[0896] (Application example 2)

[0897] 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."

[0898] In recent years, many users have been using spreadsheet software to manage and analyze business data. However, these operations often require specialized knowledge and are cumbersome for average users. Furthermore, the user's emotional state can affect the operation, making efficient operation particularly difficult under stressful or impatient circumstances. Therefore, there is a need to develop a system that can appropriately perform complex spreadsheet operations using simple natural language instructions and provide flexible feedback according to the user's emotional state.

[0899] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving instructions in natural language from a user; analysis means including a generation AI that analyzes the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the analysis result by the analysis means; means including an emotion engine that analyzes the user's emotional state; means for the generation AI to adjust the operation script based on the result of the emotion engine; and means for applying the operation script to the spreadsheet software. This allows the user to easily operate the spreadsheet software in natural language and further enables the user to receive appropriate feedback according to their emotional state.

[0900] A "user" is a person who operates the system and inputs natural language instructions.

[0901] A "natural language" is a language that people use in their daily lives, and is not a formal programming language.

[0902] "Generative AI" is artificial intelligence that analyzes the user's natural language instructions and automatically generates the necessary formulas and settings.

[0903] "Analysis means" refers to a means for analyzing input natural language instructions, and includes generative AI.

[0904] An "operation script" is a program that contains a series of commands to automatically reflect formulas and settings in spreadsheet software.

[0905] "Spreadsheet software" is software that stores data and performs calculations and creates graphs.

[0906] An "emotion engine" is a system that analyzes a user's emotional state based on their tone of voice, facial expression, input speed, etc.

[0907] "Feedback" refers to responses or guidance to the user, including content that is tailored based on emotional state.

[0908] The "adjustment means" is a means by which the generation AI adjusts the operation script based on the analysis results of the emotion engine.

[0909] The "application means" is a means for applying the generated operation script to the spreadsheet software.

[0910] This invention is a system that uses a generative AI to automatically generate formulas and settings for spreadsheet software in response to instructions given by the user in natural language, and also provides flexible feedback according to the user's emotional state. Specific examples are described below.

[0911] System configuration

[0912] 1. User input means (terminal)

[0913] The user inputs natural language instructions through an interface on the device, such as "calculate the sum of the sales data."

[0914] 2. Analysis method (generative AI model, server)

[0915] The server is equipped with a generative AI that analyzes the user's natural language instructions. The generative AI uses an artificial intelligence model such as OpenAI to analyze the input instructions and automatically generate the necessary formulas and settings. For example, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[0916] 3. Emotion engine (server or terminal)

[0917] The emotion engine analyzes emotion data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state, using emotion recognition services from Microsoft Azure or Google Cloud, for example.

[0918] 4. Coordination means (server)

[0919] Based on the results of the emotion engine, the generative AI adjusts the operation script, simplifying the steps and providing detailed guidance if the user is feeling impatient.

[0920] 5. Application means (terminal)

[0921] The operation script generated on the server is sent to the terminal and applied to spreadsheet software, such as Excel or Google Sheets, automatically reflecting formulas.

[0922] Program processing

[0923] When the server receives a natural language instruction from the user, it uses an analysis means to analyze the content of the instruction. Next, it uses an emotion engine to analyze the user's emotional state, and the generation AI adjusts the operation script based on the results. The adjusted operation script is sent from the server to the terminal and applied to the spreadsheet software on the terminal.

[0924] Possible generative AI models to use include OpenAI's GPT-3.

[0925] For sentiment analysis, you can use Microsoft Azure's sentiment analysis API or Google Cloud's emotion recognition API.

[0926] Microsoft Excel and Google Sheets are used as spreadsheet software.

[0927] Specific examples

[0928] Automatic generation of mathematical formulas and emotional response

[0929] User instruction: "Sum the data in column A"

[0930] System Action:

[0931] 1. The user enters this instruction and sends it from the terminal to the server.

[0932] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[0933] 3. If the emotion engine determines that the user is feeling anxious or stressed, it simplifies the analysis results to make them easier for the user to understand.

[0934] 4. An operation script is generated and sent to the terminal.

[0935] 5. The terminal executes the received script and reflects the formula in the cell.

[0936] Conditional formatting and sentiment support

[0937] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[0938] System Action:

[0939] 1. The user's instructions are sent from the device to the server.

[0940] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[0941] 3. If the emotion engine judges the user to be relaxed, it will present multiple options and allow the user to choose.

[0942] 4. The script is sent from the server to the device and executed on the device.

[0943] 5. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[0944] Example prompt sentence:

[0945] "Enter today's sales data"

[0946] "Calculate this week's sales totals"

[0947] Check if sales targets are being met

[0948] Show me the sales graph

[0949] "Tell me your lowest sales days"

[0950] In this way, store staff can receive flexible, emotional feedback while efficiently managing and analyzing data.

[0951] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0952] Step 1:

[0953] User Input

[0954] The user inputs instructions in natural language through the interface on the terminal.

[0955] Input: Natural language instructions (e.g., "Calculate the sum of the sales data")

[0956] Output: Text data with natural language instructions

[0957] Step 2:

[0958] Sending natural language instructions

[0959] The terminal transmits the natural language instructions entered by the user to the server.

[0960] Input: Text data with natural language instructions

[0961] Output: Sends instruction data to the server

[0962] Step 3:

[0963] Parsing instructions

[0964] The server analyzes the received natural language instructions using an analysis method (generative AI model), such as OpenAI's GPT-3.

[0965] Input: Text data with natural language instructions

[0966] Data processing: Generative AI models analyze natural language and convert it into appropriate formulas and settings.

[0967] Output: Text data of formulas and settings (e.g. =SUM(sales data))

[0968] Step 4:

[0969] Acquiring emotional state

[0970] The emotion engine collects data such as the user's tone of voice, facial expressions, and typing speed to analyze their emotional state.

[0971] Input: User voice data, facial expression data, and typing speed data

[0972] Data calculation: Analysis using a sentiment analysis engine (e.g., Microsoft Azure's sentiment recognition API)

[0973] Output: Emotional state data (e.g., anxious, relaxed, etc.)

[0974] Step 5:

[0975] Generate and adjust operation scripts

[0976] The server generates an operation script based on the analyzed formulas, settings, and emotional state data, and makes adjustments as needed.

[0977] Input: Text data for formulas and settings, emotional state data

[0978] Data processing: Adjustments based on emotional state (e.g., simplifying procedures if you are in a hurry)

[0979] Output: Adjusted operation script

[0980] Step 6:

[0981] Sending an Operation Script

[0982] The server transmits the generated operation script to the terminal.

[0983] Input: Adjusted operation script

[0984] Output: Sends script data to the terminal

[0985] Step 7:

[0986] Applying a script

[0987] The terminal then applies the received operation script to spreadsheet software, such as Microsoft Excel or Google Sheets.

[0988] Input: Adjusted operation script

[0989] Data calculation: Reflect formulas and settings in spreadsheet software

[0990] Output: Formulas and settings reflected in the spreadsheet software (e.g. =SUM(A:A) is entered in the cell)

[0991] 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.

[0992] 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.

[0993] 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.

[0994] [Third embodiment]

[0995] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0996] 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.

[0997] 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).

[0998] 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.

[0999] 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.

[1000] 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).

[1001] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1002] 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.

[1003] 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.

[1004] 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.

[1005] 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.

[1006] 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."

[1007] This invention relates to a system that uses generative AI to automatically generate formulas and settings for spreadsheet software and reflect them in the spreadsheet when the user gives instructions in natural language. This system reduces the burden on the user by simply receiving and analyzing the user's instructions and automatically performing the appropriate operations.

[1008] System Configuration

[1009] The system mainly consists of the following components:

[1010] 1. User input means (terminal):

[1011] Users input instructions in natural language through an on-device interface, which can range from creating formulas to setting conditional formatting and even generating graphs.

[1012] 2. Generative AI model (server):

[1013] The server is equipped with a generation AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generation AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[1014] 3. Analysis result sending method (server):

[1015] The server sends the operation script generated by the generation AI to the terminal. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[1016] 4. Sheet reflection method (terminal):

[1017] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[1018] Program processing and example

[1019] 1. User input (terminal):

[1020] The user enters instructions into the device interface, such as "calculate the total sales data," which is then sent to the server for automatic analysis.

[1021] 2. Parsing the instruction (server):

[1022] The generation AI on the server receives the user's input and analyzes it. Through this analysis, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[1023] 3. Generate operation script (server):

[1024] Based on the analysis results of the generative AI, the server generates an appropriate operation script, which is an instruction for automatically applying the specified formulas and settings to the spreadsheet software.

[1025] 4. Sending and reflecting analysis results (from server to device, device):

[1026] The server sends the generated operation script to the terminal, which then applies it to the spreadsheet software, thereby reflecting the specified formulas and settings on the sheet.

[1027] Specific examples

[1028] Automatic formula generation

[1029] User instruction: "Sum the data in column A"

[1030] System Action:

[1031] 1. The user enters this instruction and sends it from the terminal to the server.

[1032] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[1033] 3. An operation script is generated and sent to the terminal.

[1034] 4. The terminal executes the received script and reflects the formula in the cell.

[1035] Conditional formatting settings

[1036] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[1037] System Action:

[1038] 1. The user's instructions are sent from the device to the server.

[1039] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[1040] 3. The script is sent from the server to the device and executed on the device.

[1041] 4. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[1042] This invention enables users to quickly and accurately perform advanced operations on spreadsheet software using only natural language instructions, allowing even beginners and users unfamiliar with the software to work efficiently.

[1043] The processing flow will be explained below.

[1044] Step 1:

[1045] The user provides input. Specifically, the user types natural language instructions into the device interface, such as "calculate the total sales data."

[1046] Step 2:

[1047] The device prepares the user's instructions to send to the server. The instructions are converted into an appropriate format and forwarded to the server.

[1048] Step 3:

[1049] The server receives the user's instructions, and the received data is analyzed by the generating AI.

[1050] Step 4:

[1051] The generation AI on the server analyzes the user's instructions. As a result of the analysis, for example, in response to an instruction to "calculate the sum of sales data," the formula =SUM(sales data) is generated.

[1052] Step 5:

[1053] The server generates an operation script based on the analysis results of the generation AI. Specifically, a script is generated that applies a formula such as =SUM(A:A) in spreadsheet software.

[1054] Step 6:

[1055] The server sends the generated operation script to the terminal. Check that the script was sent successfully.

[1056] Step 7:

[1057] The terminal receives the operation script from the server, confirms that reception has been completed, and moves on to the next process.

[1058] Step 8:

[1059] The terminal starts the spreadsheet software, and the necessary preparations are made to execute the operation script.

[1060] Step 9:

[1061] The terminal executes the received operation script on the spreadsheet software. For example, the terminal enters the formula =SUM(A:A) into a specified cell.

[1062] Step 10:

[1063] The terminal confirms that the operation script has been executed and that the operation requested by the user has been correctly executed.

[1064] This allows users to intuitively and accurately operate complex spreadsheet software simply by issuing instructions in natural language.

[1065] Example 1

[1066] 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."

[1067] Conventional spreadsheet software requires users to manually create formulas and settings, which requires a great deal of time and effort. Creating specific settings and formulas can be difficult, making it difficult for beginners and users unfamiliar with the software to use. Furthermore, the lack of technology to analyze natural language instructions and automatically reflect them in spreadsheets makes efficient data management and information processing difficult.

[1068] 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.

[1069] In this invention, the server includes: means for receiving instructions in natural language from a user; means for transmitting the instructions in natural language to the server; analysis means including a generation AI for analyzing the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of analysis by the analysis means; means for transmitting the operation script to a terminal; and means for applying the operation script to the spreadsheet software. This makes it possible for a user to simply input instructions in natural language to easily and automatically generate formulas and settings for the spreadsheet software and reflect them in a sheet.

[1070] A "user" is a person or entity that uses the system to provide instructions in natural language.

[1071] A "natural language" is a language that humans use on a daily basis and is not a programming language.

[1072] "Instructions" are words or sentences that indicate the operations that a user performs on a system.

[1073] A "terminal" is a device that is directly operated by a user and includes an input interface.

[1074] A "server" is a remote computer system that analyzes and processes instructions sent by a user.

[1075] "Generative AI" is an artificial intelligence technology that analyzes natural language instructions and automatically generates appropriate formulas and settings.

[1076] An "analysis means" is a component that has the function of analyzing natural language instructions using generative AI.

[1077] An "operation script" is a series of commands that are used to reflect formulas and settings in spreadsheet software.

[1078] "Spreadsheet software" is a software application for performing numerical calculations and managing data.

[1079] "Settings" are configuration options or parameters that change the behavior or appearance of the spreadsheet software.

[1080] A "sheet" refers to a page or tab where data is arranged in a spreadsheet program.

[1081] MODE FOR CARRYING OUT THE INVENTION

[1082] This invention is a system that uses generative AI to automatically generate formulas and settings for spreadsheet software in response to instructions given by the user in natural language, and reflects these in the spreadsheet. This system reduces the burden on the user by simply receiving and analyzing the user's instructions, and automatically performing the appropriate operations.

[1083] System Configuration

[1084] The system consists of four main components:

[1085] 1. User input means (terminal):

[1086] Users input instructions in natural language through an on-device interface, such as "calculate the sum of the sales data" or "if the value in column B is greater than 100, make the background red."

[1087] 2. Generative AI model (server):

[1088] The server is equipped with a generative AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. The generative AI analyzes the natural language instructions and generates the necessary formulas and settings.

[1089] 3. Analysis result sending method (server):

[1090] The server sends the operation script generated by the generation AI to the terminal. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[1091] 4. Sheet reflection method (terminal):

[1092] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[1093] Specific examples

[1094] Below are two examples of how the system works:

[1095] Automatic formula generation

[1096] User instruction: "Sum the data in column A"

[1097] The user inputs this instruction and sends it from the terminal to the server.

[1098] The server's generation AI analyzes the instructions and generates the formula =SUM(A:A).

[1099] The operation script generated as a result of the analysis is sent to the terminal.

[1100] The terminal executes the received script and reflects the formulas in the spreadsheet software.

[1101] Conditional formatting settings

[1102] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[1103] The user's instructions are sent from the terminal to the server.

[1104] The server's generated AI parses the instructions and generates a script that applies the conditional formatting.

[1105] The script is sent from the server to the terminal and executed on the terminal.

[1106] The terminal executes the received script, and if the value of the cell in column B is greater than or equal to 100, the background turns red.

[1107] Prompt Sentence Examples

[1108] Here are some example prompts to input to the AI ​​generator:

[1109] "Calculate the sum of the sales data" -> Generate a formula to calculate the total sales data.

[1110] "If the value in column B is greater than or equal to 100, set the background to red" -> Create a conditional formatting rule to set the background of cells in column B to red if the value is 100 or more.

[1111] The generative AI analyzes these prompts and generates appropriate operation scripts, allowing users to quickly and accurately perform advanced operations on spreadsheet software using only natural language instructions, enabling even beginners to work efficiently.

[1112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1113] Step 1:

[1114] User instruction input (terminal)

[1115] The user inputs the desired spreadsheet software operation into the terminal interface in natural language. For example, they might input "calculate the total sales data." When this instruction is input, the terminal treats the instruction as data and prepares to send it to the server.

[1116] Input: User's natural language instructions

[1117] Output: Instruction data in the format to send to the server

[1118] Specific operation: The user enters "Calculate the total sales data" in the text box on the terminal and presses the send button.

[1119] Step 2:

[1120] Sending instructions (from terminal to server)

[1121] The device sends the user's specified data to the server, usually using a communication method such as an HTTP request.

[1122] Input: User's natural language instructions

[1123] Output: Data received by the server

[1124] Specific operation: The device sends an HTTP request, and the server's API endpoint accepts this request.

[1125] Step 3:

[1126] Parsing instructions (server)

[1127] The generative AI model on the server analyzes the received natural language instructions. This analysis determines the specific formulas and settings. For example, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[1128] Input: User's natural language instructions

[1129] Output: Formulas and settings as analysis results

[1130] Specific operation: The generation AI analyzes the prompt "Calculate the sum of the sales data" and decides to generate the formula =SUM(sales data).

[1131] Step 4:

[1132] Generate operation script (server)

[1133] Based on the analysis results, the server generates an operation script for the spreadsheet software, which includes specific formulas and settings.

[1134] Input: Formulas and settings as analysis results

[1135] Output: Operation script

[1136] Specific operation: The generation AI executes the script generation logic and creates a specific script called =SUM(sales data).

[1137] Step 5:

[1138] Sending operation scripts (from server to terminal)

[1139] The server sends the generated operation script to the terminal. This transmission also uses a communication method such as HTTP response. The terminal caches and saves the received script.

[1140] Input: Operation script

[1141] Output: Received data from the device

[1142] Specific operation: The server sends back the script as an HTTP response, and the terminal receives the response.

[1143] Step 6:

[1144] Execute operation script and reflect sheet (terminal)

[1145] The terminal applies the received operation script to the spreadsheet software and reflects the formulas and settings in the sheet. Specifically, the formula =SUM(sales data) is entered into the specified cell.

[1146] Input: Received operation script

[1147] Output: Reflection of formulas and settings in spreadsheet software

[1148] Specific behavior: The device's spreadsheet software runs the script, and the formula is automatically entered into the cell.

[1149] (Application example 1)

[1150] 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."

[1151] Conventional factory robot operation and production line management / maintenance work often required a lot of human intervention, resulting in inefficiency. Furthermore, it was difficult for workers without specialized knowledge to operate the robots, leading to the risk of operational errors and reduced efficiency. Furthermore, there was a lack of an appropriate system for analyzing data in real time and responding quickly. To solve these problems, an advanced system that can be operated using natural language is needed.

[1152] 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.

[1153] In this invention, the server includes: means for receiving natural language instructions from a user; analysis means including a generation AI for analyzing the natural language instructions; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of the analysis by the analysis means; means for applying the operation script to the spreadsheet software; and means for applying the generation AI to a production line management or maintenance robot, analyzing the natural language instructions, generating an appropriate operation script, and applying it to the robot. This enables workers to efficiently manage production lines and perform maintenance work in a factory simply by issuing instructions in natural language.

[1154] A "means for receiving natural language instructions from a user" is a device or software that provides an interface through which a user can input instructions in natural language using voice or text.

[1155] "Analysis means including generative AI" refers to devices or software that include artificial intelligence technology used to analyze a user's natural language instructions, understand their content, and generate appropriate operation scripts.

[1156] The "means for generating an operation script" is a device or software that automatically generates instructions for reflecting the necessary formulas and settings in the spreadsheet software or robot based on the results of the analysis by the analysis means.

[1157] The "means for applying to spreadsheet software" is an interface or program for reflecting the generated operation script in the spreadsheet software.

[1158] "Means for application to robots for production line management and maintenance" refers to a device or software that analyzes natural language instructions from generative AI for robots that manage production lines and perform maintenance work within factories, generates commands for appropriate operations, and has the robots execute these commands.

[1159] The system that embodies this invention consists of a series of processes in which a user gives instructions in natural language and uses generative AI to reflect the operations in factory robots.

[1160] 1. System Program

[1161] The system's program involves receiving natural language instructions from the user, using generative AI to generate an operation script, and applying it to the robot.

[1162] 2. Program Processing

[1163] The system operates using the following hardware and software:

[1164] Hardware and Software Configuration

[1165] User input device: A device that allows a user to input natural language instructions via voice or text. Examples include smartphones and tablets.

[1166] Server: A computer system that analyzes natural language instructions and generates appropriate operational scripts using a generative AI model, such as GPT-4.

[1167] Speech recognition API: Software that converts user voice input into text. An example is Google Cloud Speech-to-Text.

[1168] Robot control system: A robot system with a control program to execute the generated operation script. An example is the Siemens TIA Portal.

[1169] 3. Data processing and calculation

[1170] Speech Recognition: Converts speech to text on the user's input device. Uses speech recognition APIs to accurately transcribe the user's natural language commands into text.

[1171] Analysis by generative AI: The server receives textual natural language instructions, analyzes them using a generative AI model (GPT-4), and generates an appropriate operation script.

[1172] Generation and application of operation script: The generated operation script is sent to the robot and executed by the robot's control system, which then performs the specified action.

[1173] 4. Specific Examples

[1174] To calculate the sum of sales data:

[1175] User instruction: "Calculate the sum of the sales data"

[1176] Analysis method:

[1177] 1. The user speaks instructions, which are converted into text using a speech recognition API.

[1178] 2. The server's generation AI analyzes the instructions and generates the formula =SUM(sales data).

[1179] 3. An operation script is generated and sent to the terminal.

[1180] 4. The terminal executes the received script and reflects the formulas in the sheet.

[1181] When giving natural language instructions to a robot

[1182] User instruction: "Calculate and display the production total for line A."

[1183] Example prompt sentence:

[1184] "A user wants to calculate and display the total production data for line A. Please generate the appropriate formula."

[1185] Analysis method:

[1186] 1. The user speaks voice commands to the robot.

[1187] 2. The robot converts the speech into text and sends it to the server.

[1188] 3. GPT-4 on the server analyzes and generates the formula =SUM(A line data).

[1189] 4. The generated script is sent to the robot, which then aggregates and displays the production data.

[1190] This system will improve the efficiency of production line management and maintenance work within factories, and will enable operations to be carried out easily using instructions in natural language.

[1191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1192] Step 1:

[1193] The user inputs voice instructions into the terminal using natural language. The input is a specific instruction such as "Calculate and display the production total for line A." The terminal receives this voice data.

[1194] Input: Voice commands

[1195] Output: Audio data

[1196] Specific operation: The user speaks into the smartphone or tablet to give instructions, and the device picks up the voice through the microphone.

[1197] Step 2:

[1198] The device converts the voice data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[1199] Input: Audio data

[1200] Output: Text data

[1201] Specific operation: The device sends voice data to the voice recognition API and obtains the text data returned by the API.

[1202] Step 3:

[1203] The text data is sent to a generative AI model (e.g., GPT-4), which analyzes the instructions and generates an operation script.

[1204] Input: Text data

[1205] Output: Operation script

[1206] Specific operation: The server supplies text data to GPT-4 and parses the instructions using the prompt: "The user wants to calculate and display the sum of the production data for line A. Please generate an appropriate formula." As a result, an operation script containing the formula =SUM(line A data) is generated.

[1207] Step 4:

[1208] The server sends the generated operation script to the terminal.

[1209] Input: Operation script

[1210] Output: Operation script

[1211] Specific operation: The server uses the network to send the operation script to the terminal. The script is sent to the terminal in its original format.

[1212] Step 5:

[1213] The terminal then sends the received operation script to the robot's control system, which runs on a platform such as the Siemens TIA Portal.

[1214] Input: Operation script

[1215] Output: None (to robot processing)

[1216] Specific operation: The terminal sends the operation script to the robot using a specific network protocol (e.g., HTTP, TCP / IP).

[1217] Step 6:

[1218] The robot's control system parses the received script and performs the specified operations (in this case, totaling and displaying production data).

[1219] Input: Operation script

[1220] Output: Execution result (total production data)

[1221] How it works: The robot's control system analyzes the operation script, retrieves production data from the Siemens TIA Portal database on line A, calculates the total, and displays the result on a display or touch panel.

[1222] Step 7:

[1223] The robot displays the calculation results and provides feedback to the user.

[1224] Input: Execution result (total of production data)

[1225] Output: Displayed results

[1226] Specific operation: The calculation results are displayed in real time on the robot's display and touch panel, allowing the user to check them and give further instructions.

[1227] Through the above processing steps, efficient production line management and maintenance can be achieved within a factory using natural language.

[1228] 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.

[1229] This invention combines a system that uses generative AI to automatically generate formulas and settings for spreadsheet software based on user instructions in natural language, and reflects the results in the spreadsheet, with an emotion engine that recognizes the user's emotions. This system improves the user experience by providing appropriate operations and feedback according to the user's emotional state.

[1230] System Configuration

[1231] The system mainly consists of the following components:

[1232] 1. User input means (terminal):

[1233] Users input instructions in natural language through an on-device interface, which can range from creating formulas to setting conditional formatting and even generating graphs.

[1234] 2. Generative AI model (server):

[1235] The server is equipped with a generation AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generation AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[1236] 3. Emotion engine (server or device):

[1237] The emotion engine analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state. Based on the results of this emotion engine, the generative AI makes further adjustments.

[1238] 4. Analysis result sending method (server):

[1239] The server sends the operation script generated by the generative AI and emotion engine to the device. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[1240] 5. Sheet reflection method (terminal):

[1241] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[1242] Program processing and example

[1243] 1. User input (terminal):

[1244] The user enters instructions into the device interface, such as "calculate the total sales data," which is then sent to the server for automatic analysis.

[1245] 2. Parsing the instruction (server):

[1246] The generation AI on the server receives the user's input and analyzes it. Through this analysis, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[1247] 3. Acquisition and analysis of emotion data (emotion engine):

[1248] An emotion engine on the server or device acquires and analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. For example, if the user is feeling impatient, it will provide simple operating instructions according to the situation.

[1249] 4. Generate operation script (server):

[1250] Based on the analysis results of the generation AI and the emotion engine, the server generates an appropriate operation script, which is adjusted to take into account the user's emotional state.

[1251] 5. Sending and reflecting analysis results (from server to device, device):

[1252] The server sends the generated operation script to the terminal, which then applies it to the spreadsheet software, thereby reflecting the specified formulas and settings on the sheet.

[1253] Specific examples

[1254] Automatic generation of mathematical formulas and emotional response

[1255] User instruction: "Sum the data in column A"

[1256] System Action:

[1257] 1. The user enters this instruction and sends it from the terminal to the server.

[1258] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[1259] 3. If the emotion engine determines that the user is feeling anxious or stressed, it simplifies the analysis results to make them easier for the user to understand.

[1260] 4. An operation script is generated and sent to the terminal.

[1261] 5. The terminal executes the received script and reflects the formula in the cell.

[1262] Conditional formatting and sentiment support

[1263] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[1264] System Action:

[1265] 1. The user's instructions are sent from the device to the server.

[1266] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[1267] 3. If the emotion engine judges the user to be relaxed, it will present multiple options and allow the user to choose.

[1268] 4. The script is sent from the server to the device and executed on the device.

[1269] 5. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[1270] This invention allows users to quickly and accurately perform advanced operations on spreadsheet software simply by issuing instructions in natural language, and through the emotion engine, it is possible to realize flexible operation responses according to the user's emotional state, allowing even beginners and users unfamiliar with the software to work efficiently.

[1271] The processing flow will be explained below.

[1272] Step 1:

[1273] The user provides input. Specifically, the user types natural language instructions into the device interface, such as "calculate the total sales data."

[1274] Step 2:

[1275] The device prepares the user's instructions to send to the server. The instructions are converted into an appropriate format and forwarded to the server.

[1276] Step 3:

[1277] The server receives the user's instructions, and the received data is analyzed by the generating AI.

[1278] Step 4:

[1279] The generation AI on the server analyzes the user's instructions. As a result of the analysis, the formula =SUM(sales data) is generated in response to the instruction "Calculate the sum of the sales data."

[1280] Step 5:

[1281] The emotion engine analyzes the user's current emotional state, obtaining emotional data based on the user's tone of voice, facial expressions, typing speed, etc.

[1282] Step 6:

[1283] The emotion engine provides the analysis results to the generative AI, which adjusts to provide simple feedback if the user is feeling stressed.

[1284] Step 7:

[1285] The server generates an operation script based on the analysis results of the generation AI and the emotion engine. For example, a script is generated to apply the formula =SUM(A:A) in spreadsheet software.

[1286] Step 8:

[1287] The server sends the generated operation script to the terminal. Check that the script was sent successfully.

[1288] Step 9:

[1289] The terminal receives the operation script from the server, confirms that reception has been completed, and moves on to the next process.

[1290] Step 10:

[1291] The terminal starts the spreadsheet software and makes the necessary preparations to execute the operation script.

[1292] Step 11:

[1293] The terminal executes the received operation script on the spreadsheet software. For example, the terminal enters the formula =SUM(A:A) into a specified cell.

[1294] Step 12:

[1295] The terminal confirms that the operation script has been executed and that the operation requested by the user has been correctly executed.

[1296] Example 2

[1297] 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."

[1298] Operating conventional spreadsheet software is often difficult for users who are not familiar with technology. Furthermore, operations are performed without considering the user's emotional state, which can result in a poor user experience. Specifically, there is a need for a system that simplifies operations using natural language instructions while flexibly responding to the user's emotional state.

[1299] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving instructions in natural language from a user; analysis means including a generation AI for analyzing the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in the spreadsheet software based on the analysis result by the analysis means; means for applying the operation script to the spreadsheet software; means including an emotion engine for evaluating the emotional state of the user; and means for adjusting the operation script based on the evaluation result of the emotion engine. This enables the user to perform advanced operations on the spreadsheet software simply by issuing instructions in natural language, and also enables flexible operation responses according to the user's emotional state.

[1300] A "user" is an entity that utilizes the system to input natural language instructions.

[1301] "Natural language instructions" are requests or commands for operations given by the user using everyday language.

[1302] A "terminal" is a device used by a user to access the system, including a personal computer or smartphone.

[1303] "Generative AI" is artificial intelligence that analyzes the user's natural language instructions and automatically generates specific operating instructions such as formulas and settings.

[1304] "Analysis means" includes generative AI, a function that analyzes the user's natural language instructions and generates appropriate formulas and settings.

[1305] An "operation script" is a series of instructions for applying the formulas and settings generated by the analysis means to the spreadsheet software.

[1306] "Spreadsheet software" refers to software used to calculate formulas, organize information, and visualize it, and includes Microsoft Excel and Google Sheets.

[1307] The "emotion engine" is an engine that evaluates the user's emotional state based on their tone of voice, facial expression, input speed, etc.

[1308] "Emotional state" refers to the user's emotional state analyzed by the emotion engine, and includes excitement, impatience, relaxation, etc.

[1309] The "system" refers to the entire technical setup, including a series of components, that receives natural language instructions from the user, parses them, and reflects them in the spreadsheet software.

[1310] The "server" is a central processing unit that receives user instructions, analyzes them using a generative AI model and emotion engine, generates an operation script, and sends it back to the terminal.

[1311] This invention combines a system that uses generative AI to automatically generate formulas and settings for spreadsheet software and reflects them in the spreadsheet when the user gives instructions in natural language, with an emotion engine that recognizes the user's emotions. The system aims to improve the user experience by providing appropriate operations and feedback according to the user's emotional state.

[1312] System Configuration

[1313] The system mainly consists of the following components:

[1314] 1. User input means (terminal):

[1315] Users input instructions in natural language through an interface on their device, which typically uses a personal computer (PC) or smartphone. These instructions range from creating mathematical formulas to setting conditional formatting and even generating graphs.

[1316] 2. Generative AI model (server):

[1317] The server is equipped with a generative AI (e.g., GPT-3) that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generative AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[1318] 3. Emotion engine (server or device):

[1319] The emotion engine (e.g., Affdex) analyzes emotion data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state. Based on the results of this emotion engine, the generative AI makes further adjustments.

[1320] 4. Analysis result sending method (server):

[1321] The server sends the operation script generated by the generative AI and emotion engine to the device. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[1322] 5. Sheet reflection method (terminal):

[1323] The terminal operates spreadsheet software (for example, Microsoft Excel or Google Sheets) based on the received operation script, and reflects formulas and settings in the sheet.

[1324] Examples of specific examples and prompts

[1325] Example 1: Automatic generation of mathematical expressions and emotional response

[1326] User instruction: "Sum the data in column A"

[1327] Specific system actions:

[1328] 1. The user enters this instruction and sends it from the terminal to the server.

[1329] 2. The server's generation AI analyzes the instructions and generates the formula =SUM(A:A).

[1330] 3. If the emotion engine assesses that the user is feeling anxious or stressed, it will simplify the analysis results based on that assessment and adjust them to make them easier for the user to understand.

[1331] 4. An operation script is generated and sent to the terminal.

[1332] 5. The terminal executes the received script and reflects the formula in the cell.

[1333] Example 2: Conditional formatting and emotional response

[1334] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[1335] Specific system actions:

[1336] 1. The user's instructions are sent from the device to the server.

[1337] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[1338] 3. If the emotion engine assesses that the user is relaxed, it will present multiple options based on that assessment and adjust them so that the user can choose.

[1339] 4. The script is sent from the server to the device and executed on the device.

[1340] 5. If the value of a cell in column B is greater than or equal to 100, the background will automatically be set to red.

[1341] Prompt Sentence Examples

[1342] Prompt 1: "Calculate the sum of the data in column A."

[1343] Prompt 2: "If the value in column B is greater than or equal to 100, make the background red."

[1344] This invention allows users to quickly and accurately perform advanced operations on spreadsheet software simply by issuing instructions in natural language, and also enables flexible operation responses according to the user's emotional state through an emotion engine, allowing even beginners and users unfamiliar with the software to work efficiently.

[1345] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1346] Step 1:

[1347] User prompt input:

[1348] The user inputs instructions in natural language through the terminal interface, for example, "Calculate the sum of the data in column A." The input data is a string of natural language characters, which is the starting point for the system's processing.

[1349] Input: User's natural language instructions

[1350] Output: Natural language string

[1351] Step 2:

[1352] Instructions sent to the server:

[1353] The device sends the user's natural language instructions to the server, which receives this data as an HTTP request.

[1354] Input: Natural language string

[1355] Output: HTTP request to the server

[1356] Step 3:

[1357] Parsing instructions:

[1358] The server passes the received natural language instructions to a generative AI model (e.g., GPT-3) for analysis. The generative AI model analyzes the natural language and generates appropriate spreadsheet formulas and settings. For example, the instruction "Calculate the sum of the data in column A" is converted into the formula =SUM(A:A).

[1359] Input: HTTP request to the server

[1360] Output: Formula or setting

[1361] Step 4:

[1362] Emotion data acquisition and analysis:

[1363] The emotion engine acquires and analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. The emotion engine evaluates the user's emotional state based on this data. For example, if the user is feeling impatient, that data is reflected in the generating AI.

[1364] Input: User emotional data (tone of voice, facial expressions, typing speed, etc.)

[1365] Output: Emotional state assessment result

[1366] Step 5:

[1367] Generate operation script:

[1368] The generative AI model generates operation scripts based on the results of instruction analysis and the evaluation of emotional data. For example, if the emotion engine recognizes the user's impatience, the generated formulas and spreadsheet settings will be kept simple.

[1369] Input: Formula or setting, emotional state evaluation result

[1370] Output: Operation script

[1371] Step 6:

[1372] Sending analysis results:

[1373] The server sends the generated operation script to the terminal, usually in JSON format as an HTTP response.

[1374] Input: Operation script

[1375] Output: HTTP response to the device

[1376] Step 7:

[1377] Reflecting the operation script:

[1378] The device applies the received operation script to spreadsheet software (e.g., Microsoft Excel or Google Sheets). The spreadsheet software automatically opens and the formulas and settings are reflected in the specified sheet.

[1379] Input: Action script as HTTP response

[1380] Output: Formulas and settings reflected in spreadsheet software

[1381] (Application example 2)

[1382] 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."

[1383] In recent years, many users have been using spreadsheet software to manage and analyze business data. However, these operations often require specialized knowledge and are cumbersome for average users. Furthermore, the user's emotional state can affect the operation, making efficient operation particularly difficult under stressful or impatient circumstances. Therefore, there is a need to develop a system that can appropriately perform complex spreadsheet operations using simple natural language instructions and provide flexible feedback according to the user's emotional state.

[1384] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving instructions in natural language from a user; analysis means including a generation AI that analyzes the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the analysis result by the analysis means; means including an emotion engine that analyzes the user's emotional state; means for the generation AI to adjust the operation script based on the result of the emotion engine; and means for applying the operation script to the spreadsheet software. This allows the user to easily operate the spreadsheet software in natural language and further enables the user to receive appropriate feedback according to their emotional state.

[1385] A "user" is a person who operates the system and inputs natural language instructions.

[1386] A "natural language" is a language that people use in their daily lives, and is not a formal programming language.

[1387] "Generative AI" is artificial intelligence that analyzes the user's natural language instructions and automatically generates the necessary formulas and settings.

[1388] "Analysis means" refers to a means for analyzing input natural language instructions, and includes generative AI.

[1389] An "operation script" is a program that contains a series of commands to automatically reflect formulas and settings in spreadsheet software.

[1390] "Spreadsheet software" is software that stores data and performs calculations and creates graphs.

[1391] An "emotion engine" is a system that analyzes a user's emotional state based on their tone of voice, facial expression, input speed, etc.

[1392] "Feedback" refers to responses or guidance to the user, including content that is tailored based on emotional state.

[1393] The "adjustment means" is a means by which the generation AI adjusts the operation script based on the analysis results of the emotion engine.

[1394] The "application means" is a means for applying the generated operation script to the spreadsheet software.

[1395] This invention is a system that uses a generative AI to automatically generate formulas and settings for spreadsheet software in response to instructions given by the user in natural language, and also provides flexible feedback according to the user's emotional state. Specific examples are described below.

[1396] System configuration

[1397] 1. User input means (terminal)

[1398] The user inputs natural language instructions through an interface on the device, such as "calculate the sum of the sales data."

[1399] 2. Analysis method (generative AI model, server)

[1400] The server is equipped with a generative AI that analyzes the user's natural language instructions. The generative AI uses an artificial intelligence model such as OpenAI to analyze the input instructions and automatically generate the necessary formulas and settings. For example, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[1401] 3. Emotion engine (server or terminal)

[1402] The emotion engine analyzes emotion data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state, using emotion recognition services from Microsoft Azure or Google Cloud, for example.

[1403] 4. Coordination means (server)

[1404] Based on the results of the emotion engine, the generative AI adjusts the operation script, simplifying the steps and providing detailed guidance if the user is feeling impatient.

[1405] 5. Application means (terminal)

[1406] The operation script generated on the server is sent to the terminal and applied to spreadsheet software, such as Excel or Google Sheets, automatically reflecting formulas.

[1407] Program processing

[1408] When the server receives a natural language instruction from the user, it uses an analysis means to analyze the content of the instruction. Next, it uses an emotion engine to analyze the user's emotional state, and the generation AI adjusts the operation script based on the results. The adjusted operation script is sent from the server to the terminal and applied to the spreadsheet software on the terminal.

[1409] Possible generative AI models to use include OpenAI's GPT-3.

[1410] For sentiment analysis, you can use Microsoft Azure's sentiment analysis API or Google Cloud's emotion recognition API.

[1411] Microsoft Excel and Google Sheets are used as spreadsheet software.

[1412] Specific examples

[1413] Automatic generation of mathematical formulas and emotional response

[1414] User instruction: "Sum the data in column A"

[1415] System Action:

[1416] 1. The user enters this instruction and sends it from the terminal to the server.

[1417] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[1418] 3. If the emotion engine determines that the user is feeling anxious or stressed, it simplifies the analysis results to make them easier for the user to understand.

[1419] 4. An operation script is generated and sent to the terminal.

[1420] 5. The terminal executes the received script and reflects the formula in the cell.

[1421] Conditional formatting and sentiment support

[1422] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[1423] System Action:

[1424] 1. The user's instructions are sent from the device to the server.

[1425] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[1426] 3. If the emotion engine judges the user to be relaxed, it will present multiple options and allow the user to choose.

[1427] 4. The script is sent from the server to the device and executed on the device.

[1428] 5. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[1429] Example prompt sentence:

[1430] "Enter today's sales data"

[1431] "Calculate this week's sales totals"

[1432] Check if sales targets are being met

[1433] Show me the sales graph

[1434] "Tell me your lowest sales days"

[1435] In this way, store staff can receive flexible, emotional feedback while efficiently managing and analyzing data.

[1436] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1437] Step 1:

[1438] User Input

[1439] The user inputs instructions in natural language through the interface on the terminal.

[1440] Input: Natural language instructions (e.g., "Calculate the sum of the sales data")

[1441] Output: Text data with natural language instructions

[1442] Step 2:

[1443] Sending natural language instructions

[1444] The terminal transmits the natural language instructions entered by the user to the server.

[1445] Input: Text data with natural language instructions

[1446] Output: Sends instruction data to the server

[1447] Step 3:

[1448] Parsing instructions

[1449] The server analyzes the received natural language instructions using an analysis method (generative AI model), such as OpenAI's GPT-3.

[1450] Input: Text data with natural language instructions

[1451] Data processing: Generative AI models analyze natural language and convert it into appropriate formulas and settings.

[1452] Output: Text data of formulas and settings (e.g. =SUM(sales data))

[1453] Step 4:

[1454] Acquiring emotional state

[1455] The emotion engine collects data such as the user's tone of voice, facial expressions, and typing speed to analyze their emotional state.

[1456] Input: User voice data, facial expression data, and typing speed data

[1457] Data calculation: Analysis using a sentiment analysis engine (e.g., Microsoft Azure's sentiment recognition API)

[1458] Output: Emotional state data (e.g., anxious, relaxed, etc.)

[1459] Step 5:

[1460] Generate and adjust operation scripts

[1461] The server generates an operation script based on the analyzed formulas, settings, and emotional state data, and makes adjustments as needed.

[1462] Input: Text data for formulas and settings, emotional state data

[1463] Data processing: Adjustments based on emotional state (e.g., simplifying procedures if you are in a hurry)

[1464] Output: Adjusted operation script

[1465] Step 6:

[1466] Sending an Operation Script

[1467] The server transmits the generated operation script to the terminal.

[1468] Input: Adjusted operation script

[1469] Output: Sends script data to the terminal

[1470] Step 7:

[1471] Applying a script

[1472] The terminal then applies the received operation script to spreadsheet software, such as Microsoft Excel or Google Sheets.

[1473] Input: Adjusted operation script

[1474] Data calculation: Reflect formulas and settings in spreadsheet software

[1475] Output: Formulas and settings reflected in the spreadsheet software (e.g. =SUM(A:A) is entered in the cell)

[1476] 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.

[1477] 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.

[1478] 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.

[1479] [Fourth embodiment]

[1480] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1481] 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.

[1482] 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).

[1483] 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.

[1484] 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.

[1485] 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).

[1486] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1487] 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.

[1488] 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.

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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."

[1493] This invention relates to a system that uses generative AI to automatically generate formulas and settings for spreadsheet software and reflect them in the spreadsheet when the user gives instructions in natural language. This system reduces the burden on the user by simply receiving and analyzing the user's instructions and automatically performing the appropriate operations.

[1494] System Configuration

[1495] The system mainly consists of the following components:

[1496] 1. User input means (terminal):

[1497] Users input instructions in natural language through an on-device interface, which can range from creating formulas to setting conditional formatting and even generating graphs.

[1498] 2. Generative AI model (server):

[1499] The server is equipped with a generation AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generation AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[1500] 3. Analysis result sending method (server):

[1501] The server sends the operation script generated by the generation AI to the terminal. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[1502] 4. Sheet reflection method (terminal):

[1503] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[1504] Program processing and example

[1505] 1. User input (terminal):

[1506] The user enters instructions into the device interface, such as "calculate the total sales data," which is then sent to the server for automatic analysis.

[1507] 2. Parsing the instruction (server):

[1508] The generation AI on the server receives the user's input and analyzes it. Through this analysis, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[1509] 3. Generate operation script (server):

[1510] Based on the analysis results of the generative AI, the server generates an appropriate operation script, which is an instruction for automatically applying the specified formulas and settings to the spreadsheet software.

[1511] 4. Sending and reflecting analysis results (from server to device, device):

[1512] The server sends the generated operation script to the terminal, which then applies it to the spreadsheet software, thereby reflecting the specified formulas and settings on the sheet.

[1513] Specific examples

[1514] Automatic formula generation

[1515] User instruction: "Sum the data in column A"

[1516] System Action:

[1517] 1. The user enters this instruction and sends it from the terminal to the server.

[1518] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[1519] 3. An operation script is generated and sent to the terminal.

[1520] 4. The terminal executes the received script and reflects the formula in the cell.

[1521] Conditional formatting settings

[1522] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[1523] System Action:

[1524] 1. The user's instructions are sent from the device to the server.

[1525] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[1526] 3. The script is sent from the server to the device and executed on the device.

[1527] 4. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[1528] This invention enables users to quickly and accurately perform advanced operations on spreadsheet software using only natural language instructions, allowing even beginners and users unfamiliar with the software to work efficiently.

[1529] The processing flow will be explained below.

[1530] Step 1:

[1531] The user provides input. Specifically, the user types natural language instructions into the device interface, such as "calculate the total sales data."

[1532] Step 2:

[1533] The device prepares the user's instructions to send to the server. The instructions are converted into an appropriate format and forwarded to the server.

[1534] Step 3:

[1535] The server receives the user's instructions, and the received data is analyzed by the generating AI.

[1536] Step 4:

[1537] The generation AI on the server analyzes the user's instructions. As a result of the analysis, for example, in response to an instruction to "calculate the sum of sales data," the formula =SUM(sales data) is generated.

[1538] Step 5:

[1539] The server generates an operation script based on the analysis results of the generation AI. Specifically, a script is generated that applies a formula such as =SUM(A:A) in spreadsheet software.

[1540] Step 6:

[1541] The server sends the generated operation script to the terminal. Check that the script was sent successfully.

[1542] Step 7:

[1543] The terminal receives the operation script from the server, confirms that reception has been completed, and moves on to the next process.

[1544] Step 8:

[1545] The terminal starts the spreadsheet software, and the necessary preparations are made to execute the operation script.

[1546] Step 9:

[1547] The terminal executes the received operation script on the spreadsheet software. For example, the terminal enters the formula =SUM(A:A) into a specified cell.

[1548] Step 10:

[1549] The terminal confirms that the operation script has been executed and that the operation requested by the user has been correctly executed.

[1550] This allows users to intuitively and accurately operate complex spreadsheet software simply by issuing instructions in natural language.

[1551] Example 1

[1552] 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."

[1553] Conventional spreadsheet software requires users to manually create formulas and settings, which requires a great deal of time and effort. Creating specific settings and formulas can be difficult, making it difficult for beginners and users unfamiliar with the software to use. Furthermore, the lack of technology to analyze natural language instructions and automatically reflect them in spreadsheets makes efficient data management and information processing difficult.

[1554] 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.

[1555] In this invention, the server includes: means for receiving instructions in natural language from a user; means for transmitting the instructions in natural language to the server; analysis means including a generation AI for analyzing the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of analysis by the analysis means; means for transmitting the operation script to a terminal; and means for applying the operation script to the spreadsheet software. This makes it possible for a user to simply input instructions in natural language to easily and automatically generate formulas and settings for the spreadsheet software and reflect them in a sheet.

[1556] A "user" is a person or entity that uses the system to provide instructions in natural language.

[1557] A "natural language" is a language that humans use on a daily basis and is not a programming language.

[1558] "Instructions" are words or sentences that indicate the operations that a user performs on a system.

[1559] A "terminal" is a device that is directly operated by a user and includes an input interface.

[1560] A "server" is a remote computer system that analyzes and processes instructions sent by a user.

[1561] "Generative AI" is an artificial intelligence technology that analyzes natural language instructions and automatically generates appropriate formulas and settings.

[1562] An "analysis means" is a component that has the function of analyzing natural language instructions using generative AI.

[1563] An "operation script" is a series of commands that are used to reflect formulas and settings in spreadsheet software.

[1564] "Spreadsheet software" is a software application for performing numerical calculations and managing data.

[1565] "Settings" are configuration options or parameters that change the behavior or appearance of the spreadsheet software.

[1566] A "sheet" refers to a page or tab where data is arranged in a spreadsheet program.

[1567] MODE FOR CARRYING OUT THE INVENTION

[1568] This invention is a system that uses generative AI to automatically generate formulas and settings for spreadsheet software in response to instructions given by the user in natural language, and reflects these in the spreadsheet. This system reduces the burden on the user by simply receiving and analyzing the user's instructions, and automatically performing the appropriate operations.

[1569] System Configuration

[1570] The system consists of four main components:

[1571] 1. User input means (terminal):

[1572] Users input instructions in natural language through an on-device interface, such as "calculate the sum of the sales data" or "if the value in column B is greater than 100, make the background red."

[1573] 2. Generative AI model (server):

[1574] The server is equipped with a generative AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. The generative AI analyzes the natural language instructions and generates the necessary formulas and settings.

[1575] 3. Analysis result sending method (server):

[1576] The server sends the operation script generated by the generation AI to the terminal. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[1577] 4. Sheet reflection method (terminal):

[1578] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[1579] Specific examples

[1580] Below are two examples of how the system works:

[1581] Automatic formula generation

[1582] User instruction: "Sum the data in column A"

[1583] The user inputs this instruction and sends it from the terminal to the server.

[1584] The server's generation AI analyzes the instructions and generates the formula =SUM(A:A).

[1585] The operation script generated as a result of the analysis is sent to the terminal.

[1586] The terminal executes the received script and reflects the formulas in the spreadsheet software.

[1587] Conditional formatting settings

[1588] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[1589] The user's instructions are sent from the terminal to the server.

[1590] The server's generated AI parses the instructions and generates a script that applies the conditional formatting.

[1591] The script is sent from the server to the terminal and executed on the terminal.

[1592] The terminal executes the received script, and if the value of the cell in column B is greater than or equal to 100, the background turns red.

[1593] Prompt Sentence Examples

[1594] Here are some example prompts to input to the AI ​​generator:

[1595] "Calculate the sum of the sales data" -> Generate a formula to calculate the total sales data.

[1596] "If the value in column B is greater than or equal to 100, set the background to red" -> Create a conditional formatting rule to set the background of cells in column B to red if the value is 100 or more.

[1597] The generative AI analyzes these prompts and generates appropriate operation scripts, allowing users to quickly and accurately perform advanced operations on spreadsheet software using only natural language instructions, enabling even beginners to work efficiently.

[1598] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1599] Step 1:

[1600] User instruction input (terminal)

[1601] The user inputs the desired spreadsheet software operation into the terminal interface in natural language. For example, they might input "calculate the total sales data." When this instruction is input, the terminal treats the instruction as data and prepares to send it to the server.

[1602] Input: User's natural language instructions

[1603] Output: Instruction data in the format to send to the server

[1604] Specific operation: The user enters "Calculate the total sales data" in the text box on the terminal and presses the send button.

[1605] Step 2:

[1606] Sending instructions (from terminal to server)

[1607] The device sends the user's specified data to the server, usually using a communication method such as an HTTP request.

[1608] Input: User's natural language instructions

[1609] Output: Data received by the server

[1610] Specific operation: The device sends an HTTP request, and the server's API endpoint accepts this request.

[1611] Step 3:

[1612] Parsing instructions (server)

[1613] The generative AI model on the server analyzes the received natural language instructions. This analysis determines the specific formulas and settings. For example, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[1614] Input: User's natural language instructions

[1615] Output: Formulas and settings as analysis results

[1616] Specific operation: The generation AI analyzes the prompt "Calculate the sum of the sales data" and decides to generate the formula =SUM(sales data).

[1617] Step 4:

[1618] Generate operation script (server)

[1619] Based on the analysis results, the server generates an operation script for the spreadsheet software, which includes specific formulas and settings.

[1620] Input: Formulas and settings as analysis results

[1621] Output: Operation script

[1622] Specific operation: The generation AI executes the script generation logic and creates a specific script called =SUM(sales data).

[1623] Step 5:

[1624] Sending operation scripts (from server to terminal)

[1625] The server sends the generated operation script to the terminal. This transmission also uses a communication method such as HTTP response. The terminal caches and saves the received script.

[1626] Input: Operation script

[1627] Output: Received data from the device

[1628] Specific operation: The server sends back the script as an HTTP response, and the terminal receives the response.

[1629] Step 6:

[1630] Execute operation script and reflect sheet (terminal)

[1631] The terminal applies the received operation script to the spreadsheet software and reflects the formulas and settings in the sheet. Specifically, the formula =SUM(sales data) is entered into the specified cell.

[1632] Input: Received operation script

[1633] Output: Reflection of formulas and settings in spreadsheet software

[1634] Specific behavior: The device's spreadsheet software runs the script, and the formula is automatically entered into the cell.

[1635] (Application example 1)

[1636] 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."

[1637] Conventional factory robot operation and production line management / maintenance work often required a lot of human intervention, resulting in inefficiency. Furthermore, it was difficult for workers without specialized knowledge to operate the robots, leading to the risk of operational errors and reduced efficiency. Furthermore, there was a lack of an appropriate system for analyzing data in real time and responding quickly. To solve these problems, an advanced system that can be operated using natural language is needed.

[1638] 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.

[1639] In this invention, the server includes: means for receiving natural language instructions from a user; analysis means including a generation AI for analyzing the natural language instructions; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of the analysis by the analysis means; means for applying the operation script to the spreadsheet software; and means for applying the generation AI to a production line management or maintenance robot, analyzing the natural language instructions, generating an appropriate operation script, and applying it to the robot. This enables workers to efficiently manage production lines and perform maintenance work in a factory simply by issuing instructions in natural language.

[1640] A "means for receiving natural language instructions from a user" is a device or software that provides an interface through which a user can input instructions in natural language using voice or text.

[1641] "Analysis means including generative AI" refers to devices or software that include artificial intelligence technology used to analyze a user's natural language instructions, understand their content, and generate appropriate operation scripts.

[1642] The "means for generating an operation script" is a device or software that automatically generates instructions for reflecting the necessary formulas and settings in the spreadsheet software or robot based on the results of the analysis by the analysis means.

[1643] The "means for applying to spreadsheet software" is an interface or program for reflecting the generated operation script in the spreadsheet software.

[1644] "Means for application to robots for production line management and maintenance" refers to a device or software that analyzes natural language instructions from generative AI for robots that manage production lines and perform maintenance work within factories, generates commands for appropriate operations, and has the robots execute these commands.

[1645] The system that embodies this invention consists of a series of processes in which a user gives instructions in natural language and uses generative AI to reflect the operations in factory robots.

[1646] 1. System Program

[1647] The system's program involves receiving natural language instructions from the user, using generative AI to generate an operation script, and applying it to the robot.

[1648] 2. Program Processing

[1649] The system operates using the following hardware and software:

[1650] Hardware and Software Configuration

[1651] User input device: A device that allows a user to input natural language instructions via voice or text. Examples include smartphones and tablets.

[1652] Server: A computer system that analyzes natural language instructions and generates appropriate operational scripts using a generative AI model, such as GPT-4.

[1653] Speech recognition API: Software that converts user voice input into text. An example is Google Cloud Speech-to-Text.

[1654] Robot control system: A robot system with a control program to execute the generated operation script. An example is the Siemens TIA Portal.

[1655] 3. Data processing and calculation

[1656] Speech Recognition: Converts speech to text on the user's input device. Uses speech recognition APIs to accurately transcribe the user's natural language commands into text.

[1657] Analysis by generative AI: The server receives textual natural language instructions, analyzes them using a generative AI model (GPT-4), and generates an appropriate operation script.

[1658] Generation and application of operation script: The generated operation script is sent to the robot and executed by the robot's control system, which then performs the specified action.

[1659] 4. Specific Examples

[1660] To calculate the sum of sales data:

[1661] User instruction: "Calculate the sum of the sales data"

[1662] Analysis method:

[1663] 1. The user speaks instructions, which are converted into text using a speech recognition API.

[1664] 2. The server's generation AI analyzes the instructions and generates the formula =SUM(sales data).

[1665] 3. An operation script is generated and sent to the terminal.

[1666] 4. The terminal executes the received script and reflects the formulas in the sheet.

[1667] When giving natural language instructions to a robot

[1668] User instruction: "Calculate and display the production total for line A."

[1669] Example prompt sentence:

[1670] "A user wants to calculate and display the total production data for line A. Please generate the appropriate formula."

[1671] Analysis method:

[1672] 1. The user speaks voice commands to the robot.

[1673] 2. The robot converts the speech into text and sends it to the server.

[1674] 3. GPT-4 on the server analyzes and generates the formula =SUM(A line data).

[1675] 4. The generated script is sent to the robot, which then aggregates and displays the production data.

[1676] This system will improve the efficiency of production line management and maintenance work within factories, and will enable operations to be carried out easily using instructions in natural language.

[1677] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1678] Step 1:

[1679] The user inputs voice instructions into the terminal using natural language. The input is a specific instruction such as "Calculate and display the production total for line A." The terminal receives this voice data.

[1680] Input: Voice commands

[1681] Output: Audio data

[1682] Specific operation: The user speaks into the smartphone or tablet to give instructions, and the device picks up the voice through the microphone.

[1683] Step 2:

[1684] The device converts the voice data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[1685] Input: Audio data

[1686] Output: Text data

[1687] Specific operation: The device sends voice data to the voice recognition API and obtains the text data returned by the API.

[1688] Step 3:

[1689] The text data is sent to a generative AI model (e.g., GPT-4), which analyzes the instructions and generates an operation script.

[1690] Input: Text data

[1691] Output: Operation script

[1692] Specific operation: The server supplies text data to GPT-4 and parses the instructions using the prompt: "The user wants to calculate and display the sum of the production data for line A. Please generate an appropriate formula." As a result, an operation script containing the formula =SUM(line A data) is generated.

[1693] Step 4:

[1694] The server sends the generated operation script to the terminal.

[1695] Input: Operation script

[1696] Output: Operation script

[1697] Specific operation: The server uses the network to send the operation script to the terminal. The script is sent to the terminal in its original format.

[1698] Step 5:

[1699] The terminal then sends the received operation script to the robot's control system, which runs on a platform such as the Siemens TIA Portal.

[1700] Input: Operation script

[1701] Output: None (to robot processing)

[1702] Specific operation: The terminal sends the operation script to the robot using a specific network protocol (e.g., HTTP, TCP / IP).

[1703] Step 6:

[1704] The robot's control system parses the received script and performs the specified operations (in this case, totaling and displaying production data).

[1705] Input: Operation script

[1706] Output: Execution result (total production data)

[1707] How it works: The robot's control system analyzes the operation script, retrieves production data from the Siemens TIA Portal database on line A, calculates the total, and displays the result on a display or touch panel.

[1708] Step 7:

[1709] The robot displays the calculation results and provides feedback to the user.

[1710] Input: Execution result (total of production data)

[1711] Output: Displayed results

[1712] Specific operation: The calculation results are displayed in real time on the robot's display and touch panel, allowing the user to check them and give further instructions.

[1713] Through the above processing steps, efficient production line management and maintenance can be achieved within a factory using natural language.

[1714] 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.

[1715] This invention combines a system that uses generative AI to automatically generate formulas and settings for spreadsheet software based on user instructions in natural language, and reflects the results in the spreadsheet, with an emotion engine that recognizes the user's emotions. This system improves the user experience by providing appropriate operations and feedback according to the user's emotional state.

[1716] System Configuration

[1717] The system mainly consists of the following components:

[1718] 1. User input means (terminal):

[1719] Users input instructions in natural language through an on-device interface, which can range from creating formulas to setting conditional formatting and even generating graphs.

[1720] 2. Generative AI model (server):

[1721] The server is equipped with a generation AI that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generation AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[1722] 3. Emotion engine (server or device):

[1723] The emotion engine analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state. Based on the results of this emotion engine, the generative AI makes further adjustments.

[1724] 4. Analysis result sending method (server):

[1725] The server sends the operation script generated by the generative AI and emotion engine to the device. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[1726] 5. Sheet reflection method (terminal):

[1727] The terminal operates the spreadsheet software based on the received operation script, and reflects the formulas and settings on the sheet.

[1728] Program processing and example

[1729] 1. User input (terminal):

[1730] The user enters instructions into the device interface, such as "calculate the total sales data," which is then sent to the server for automatic analysis.

[1731] 2. Parsing the instruction (server):

[1732] The generation AI on the server receives the user's input and analyzes it. Through this analysis, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[1733] 3. Acquisition and analysis of emotion data (emotion engine):

[1734] An emotion engine on the server or device acquires and analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. For example, if the user is feeling impatient, it will provide simple operating instructions according to the situation.

[1735] 4. Generate operation script (server):

[1736] Based on the analysis results of the generation AI and the emotion engine, the server generates an appropriate operation script, which is adjusted to take into account the user's emotional state.

[1737] 5. Sending and reflecting analysis results (from server to device, device):

[1738] The server sends the generated operation script to the terminal, which then applies it to the spreadsheet software, thereby reflecting the specified formulas and settings on the sheet.

[1739] Specific examples

[1740] Automatic generation of mathematical formulas and emotional response

[1741] User instruction: "Sum the data in column A"

[1742] System Action:

[1743] 1. The user enters this instruction and sends it from the terminal to the server.

[1744] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[1745] 3. If the emotion engine determines that the user is feeling anxious or stressed, it simplifies the analysis results to make them easier for the user to understand.

[1746] 4. An operation script is generated and sent to the terminal.

[1747] 5. The terminal executes the received script and reflects the formula in the cell.

[1748] Conditional formatting and sentiment support

[1749] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[1750] System Action:

[1751] 1. The user's instructions are sent from the device to the server.

[1752] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[1753] 3. If the emotion engine judges the user to be relaxed, it will present multiple options and allow the user to choose.

[1754] 4. The script is sent from the server to the device and executed on the device.

[1755] 5. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[1756] This invention allows users to quickly and accurately perform advanced operations on spreadsheet software simply by issuing instructions in natural language, and through the emotion engine, it is possible to realize flexible operation responses according to the user's emotional state, allowing even beginners and users unfamiliar with the software to work efficiently.

[1757] The processing flow will be explained below.

[1758] Step 1:

[1759] The user provides input. Specifically, the user types natural language instructions into the device interface, such as "calculate the total sales data."

[1760] Step 2:

[1761] The device prepares the user's instructions to send to the server. The instructions are converted into an appropriate format and forwarded to the server.

[1762] Step 3:

[1763] The server receives the user's instructions, and the received data is analyzed by the generating AI.

[1764] Step 4:

[1765] The generation AI on the server analyzes the user's instructions. As a result of the analysis, the formula =SUM(sales data) is generated in response to the instruction "Calculate the sum of the sales data."

[1766] Step 5:

[1767] The emotion engine analyzes the user's current emotional state, obtaining emotional data based on the user's tone of voice, facial expressions, typing speed, etc.

[1768] Step 6:

[1769] The emotion engine provides the analysis results to the generative AI, which adjusts to provide simple feedback if the user is feeling stressed.

[1770] Step 7:

[1771] The server generates an operation script based on the analysis results of the generation AI and the emotion engine. For example, a script is generated to apply the formula =SUM(A:A) in spreadsheet software.

[1772] Step 8:

[1773] The server sends the generated operation script to the terminal. Check that the script was sent successfully.

[1774] Step 9:

[1775] The terminal receives the operation script from the server, confirms that reception has been completed, and moves on to the next process.

[1776] Step 10:

[1777] The terminal starts the spreadsheet software and makes the necessary preparations to execute the operation script.

[1778] Step 11:

[1779] The terminal executes the received operation script on the spreadsheet software. For example, the terminal enters the formula =SUM(A:A) into a specified cell.

[1780] Step 12:

[1781] The terminal confirms that the operation script has been executed and that the operation requested by the user has been correctly executed.

[1782] Example 2

[1783] 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."

[1784] Operating conventional spreadsheet software is often difficult for users who are not familiar with technology. Furthermore, operations are performed without considering the user's emotional state, which can result in a poor user experience. Specifically, there is a need for a system that simplifies operations using natural language instructions while flexibly responding to the user's emotional state.

[1785] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving instructions in natural language from a user; analysis means including a generation AI for analyzing the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in the spreadsheet software based on the analysis result by the analysis means; means for applying the operation script to the spreadsheet software; means including an emotion engine for evaluating the emotional state of the user; and means for adjusting the operation script based on the evaluation result of the emotion engine. This enables the user to perform advanced operations on the spreadsheet software simply by issuing instructions in natural language, and also enables flexible operation responses according to the user's emotional state.

[1786] A "user" is an entity that utilizes the system to input natural language instructions.

[1787] "Natural language instructions" are requests or commands for operations given by the user using everyday language.

[1788] A "terminal" is a device used by a user to access the system, including a personal computer or smartphone.

[1789] "Generative AI" is artificial intelligence that analyzes the user's natural language instructions and automatically generates specific operating instructions such as formulas and settings.

[1790] "Analysis means" includes generative AI, a function that analyzes the user's natural language instructions and generates appropriate formulas and settings.

[1791] An "operation script" is a series of instructions for applying the formulas and settings generated by the analysis means to the spreadsheet software.

[1792] "Spreadsheet software" refers to software used to calculate formulas, organize information, and visualize it, and includes Microsoft Excel and Google Sheets.

[1793] The "emotion engine" is an engine that evaluates the user's emotional state based on their tone of voice, facial expression, input speed, etc.

[1794] "Emotional state" refers to the user's emotional state analyzed by the emotion engine, and includes excitement, impatience, relaxation, etc.

[1795] The "system" refers to the entire technical setup, including a series of components, that receives natural language instructions from the user, parses them, and reflects them in the spreadsheet software.

[1796] The "server" is a central processing unit that receives user instructions, analyzes them using a generative AI model and emotion engine, generates an operation script, and sends it back to the terminal.

[1797] This invention combines a system that uses generative AI to automatically generate formulas and settings for spreadsheet software and reflects them in the spreadsheet when the user gives instructions in natural language, with an emotion engine that recognizes the user's emotions. The system aims to improve the user experience by providing appropriate operations and feedback according to the user's emotional state.

[1798] System Configuration

[1799] The system mainly consists of the following components:

[1800] 1. User input means (terminal):

[1801] Users input instructions in natural language through an interface on their device, which typically uses a personal computer (PC) or smartphone. These instructions range from creating mathematical formulas to setting conditional formatting and even generating graphs.

[1802] 2. Generative AI model (server):

[1803] The server is equipped with a generative AI (e.g., GPT-3) that analyzes the user's natural language instructions and automatically generates appropriate spreadsheet software operations. This generative AI analyzes the input instructions and generates the necessary formulas, settings, and scripts.

[1804] 3. Emotion engine (server or device):

[1805] The emotion engine (e.g., Affdex) analyzes emotion data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state. Based on the results of this emotion engine, the generative AI makes further adjustments.

[1806] 4. Analysis result sending method (server):

[1807] The server sends the operation script generated by the generative AI and emotion engine to the device. This script is a series of instructions for reflecting formulas and settings in the spreadsheet software.

[1808] 5. Sheet reflection method (terminal):

[1809] The terminal operates spreadsheet software (for example, Microsoft Excel or Google Sheets) based on the received operation script, and reflects formulas and settings in the sheet.

[1810] Examples of specific examples and prompts

[1811] Example 1: Automatic generation of mathematical expressions and emotional response

[1812] User instruction: "Sum the data in column A"

[1813] Specific system actions:

[1814] 1. The user enters this instruction and sends it from the terminal to the server.

[1815] 2. The server's generation AI analyzes the instructions and generates the formula =SUM(A:A).

[1816] 3. If the emotion engine assesses that the user is feeling anxious or stressed, it will simplify the analysis results based on that assessment and adjust them to make them easier for the user to understand.

[1817] 4. An operation script is generated and sent to the terminal.

[1818] 5. The terminal executes the received script and reflects the formula in the cell.

[1819] Example 2: Conditional formatting and emotional response

[1820] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[1821] Specific system actions:

[1822] 1. The user's instructions are sent from the device to the server.

[1823] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[1824] 3. If the emotion engine assesses that the user is relaxed, it will present multiple options based on that assessment and adjust them so that the user can choose.

[1825] 4. The script is sent from the server to the device and executed on the device.

[1826] 5. If the value of a cell in column B is greater than or equal to 100, the background will automatically be set to red.

[1827] Prompt Sentence Examples

[1828] Prompt 1: "Calculate the sum of the data in column A."

[1829] Prompt 2: "If the value in column B is greater than or equal to 100, make the background red."

[1830] This invention allows users to quickly and accurately perform advanced operations on spreadsheet software simply by issuing instructions in natural language, and also enables flexible operation responses according to the user's emotional state through an emotion engine, allowing even beginners and users unfamiliar with the software to work efficiently.

[1831] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1832] Step 1:

[1833] User prompt input:

[1834] The user inputs instructions in natural language through the terminal interface, for example, "Calculate the sum of the data in column A." The input data is a string of natural language characters, which is the starting point for the system's processing.

[1835] Input: User's natural language instructions

[1836] Output: Natural language string

[1837] Step 2:

[1838] Instructions sent to the server:

[1839] The device sends the user's natural language instructions to the server, which receives this data as an HTTP request.

[1840] Input: Natural language string

[1841] Output: HTTP request to the server

[1842] Step 3:

[1843] Parsing instructions:

[1844] The server passes the received natural language instructions to a generative AI model (e.g., GPT-3) for analysis. The generative AI model analyzes the natural language and generates appropriate spreadsheet formulas and settings. For example, the instruction "Calculate the sum of the data in column A" is converted into the formula =SUM(A:A).

[1845] Input: HTTP request to the server

[1846] Output: Formula or setting

[1847] Step 4:

[1848] Emotion data acquisition and analysis:

[1849] The emotion engine acquires and analyzes emotional data from the user's tone of voice, facial expressions, typing speed, etc. The emotion engine evaluates the user's emotional state based on this data. For example, if the user is feeling impatient, that data is reflected in the generating AI.

[1850] Input: User emotional data (tone of voice, facial expressions, typing speed, etc.)

[1851] Output: Emotional state assessment result

[1852] Step 5:

[1853] Generate operation script:

[1854] The generative AI model generates operation scripts based on the results of instruction analysis and the evaluation of emotional data. For example, if the emotion engine recognizes the user's impatience, the generated formulas and spreadsheet settings will be kept simple.

[1855] Input: Formula or setting, emotional state evaluation result

[1856] Output: Operation script

[1857] Step 6:

[1858] Sending analysis results:

[1859] The server sends the generated operation script to the terminal, usually in JSON format as an HTTP response.

[1860] Input: Operation script

[1861] Output: HTTP response to the device

[1862] Step 7:

[1863] Reflecting the operation script:

[1864] The device applies the received operation script to spreadsheet software (e.g., Microsoft Excel or Google Sheets). The spreadsheet software automatically opens and the formulas and settings are reflected in the specified sheet.

[1865] Input: Action script as HTTP response

[1866] Output: Formulas and settings reflected in spreadsheet software

[1867] (Application example 2)

[1868] 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."

[1869] In recent years, many users have been using spreadsheet software to manage and analyze business data. However, these operations often require specialized knowledge and are cumbersome for average users. Furthermore, the user's emotional state can affect the operation, making efficient operation particularly difficult under stressful or impatient circumstances. Therefore, there is a need to develop a system that can appropriately perform complex spreadsheet operations using simple natural language instructions and provide flexible feedback according to the user's emotional state.

[1870] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving instructions in natural language from a user; analysis means including a generation AI that analyzes the instructions in natural language; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the analysis result by the analysis means; means including an emotion engine that analyzes the user's emotional state; means for the generation AI to adjust the operation script based on the result of the emotion engine; and means for applying the operation script to the spreadsheet software. This allows the user to easily operate the spreadsheet software in natural language and further enables the user to receive appropriate feedback according to their emotional state.

[1871] A "user" is a person who operates the system and inputs natural language instructions.

[1872] A "natural language" is a language that people use in their daily lives, and is not a formal programming language.

[1873] "Generative AI" is artificial intelligence that analyzes the user's natural language instructions and automatically generates the necessary formulas and settings.

[1874] "Analysis means" refers to a means for analyzing input natural language instructions, and includes generative AI.

[1875] An "operation script" is a program that contains a series of commands to automatically reflect formulas and settings in spreadsheet software.

[1876] "Spreadsheet software" is software that stores data and performs calculations and creates graphs.

[1877] An "emotion engine" is a system that analyzes a user's emotional state based on their tone of voice, facial expression, input speed, etc.

[1878] "Feedback" refers to responses or guidance to the user, including content that is tailored based on emotional state.

[1879] The "adjustment means" is a means by which the generation AI adjusts the operation script based on the analysis results of the emotion engine.

[1880] The "application means" is a means for applying the generated operation script to the spreadsheet software.

[1881] This invention is a system that uses a generative AI to automatically generate formulas and settings for spreadsheet software in response to instructions given by the user in natural language, and also provides flexible feedback according to the user's emotional state. Specific examples are described below.

[1882] System configuration

[1883] 1. User input means (terminal)

[1884] The user inputs natural language instructions through an interface on the device, such as "calculate the sum of the sales data."

[1885] 2. Analysis method (generative AI model, server)

[1886] The server is equipped with a generative AI that analyzes the user's natural language instructions. The generative AI uses an artificial intelligence model such as OpenAI to analyze the input instructions and automatically generate the necessary formulas and settings. For example, the instruction "Calculate the sum of the sales data" is converted into the formula =SUM(sales data).

[1887] 3. Emotion engine (server or terminal)

[1888] The emotion engine analyzes emotion data from the user's tone of voice, facial expressions, typing speed, etc. to assess the user's emotional state, using emotion recognition services from Microsoft Azure or Google Cloud, for example.

[1889] 4. Coordination means (server)

[1890] Based on the results of the emotion engine, the generative AI adjusts the operation script, simplifying the steps and providing detailed guidance if the user is feeling impatient.

[1891] 5. Application means (terminal)

[1892] The operation script generated on the server is sent to the terminal and applied to spreadsheet software, such as Excel or Google Sheets, automatically reflecting formulas.

[1893] Program processing

[1894] When the server receives a natural language instruction from the user, it uses an analysis means to analyze the content of the instruction. Next, it uses an emotion engine to analyze the user's emotional state, and the generation AI adjusts the operation script based on the results. The adjusted operation script is sent from the server to the terminal and applied to the spreadsheet software on the terminal.

[1895] Possible generative AI models to use include OpenAI's GPT-3.

[1896] For sentiment analysis, you can use Microsoft Azure's sentiment analysis API or Google Cloud's emotion recognition API.

[1897] Microsoft Excel and Google Sheets are used as spreadsheet software.

[1898] Specific examples

[1899] Automatic generation of mathematical formulas and emotional response

[1900] User instruction: "Sum the data in column A"

[1901] System Action:

[1902] 1. The user enters this instruction and sends it from the terminal to the server.

[1903] 2. The generating AI analyzes the instructions and generates the formula =SUM(A:A).

[1904] 3. If the emotion engine determines that the user is feeling anxious or stressed, it simplifies the analysis results to make them easier for the user to understand.

[1905] 4. An operation script is generated and sent to the terminal.

[1906] 5. The terminal executes the received script and reflects the formula in the cell.

[1907] Conditional formatting and sentiment support

[1908] User instruction: "If the value in column B is greater than or equal to 100, make the background red."

[1909] System Action:

[1910] 1. The user's instructions are sent from the device to the server.

[1911] 2. The generation AI analyzes the instructions and generates a script that applies conditional formatting.

[1912] 3. If the emotion engine judges the user to be relaxed, it will present multiple options and allow the user to choose.

[1913] 4. The script is sent from the server to the device and executed on the device.

[1914] 5. If the value of a cell in column B is greater than or equal to 100, the background will turn red.

[1915] Example prompt sentence:

[1916] "Enter today's sales data"

[1917] "Calculate this week's sales totals"

[1918] Check if sales targets are being met

[1919] Show me the sales graph

[1920] "Tell me your lowest sales days"

[1921] In this way, store staff can receive flexible, emotional feedback while efficiently managing and analyzing data.

[1922] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1923] Step 1:

[1924] User Input

[1925] The user inputs instructions in natural language through the interface on the terminal.

[1926] Input: Natural language instructions (e.g., "Calculate the sum of the sales data")

[1927] Output: Text data with natural language instructions

[1928] Step 2:

[1929] Sending natural language instructions

[1930] The terminal transmits the natural language instructions entered by the user to the server.

[1931] Input: Text data with natural language instructions

[1932] Output: Sends instruction data to the server

[1933] Step 3:

[1934] Parsing instructions

[1935] The server analyzes the received natural language instructions using an analysis method (generative AI model), such as OpenAI's GPT-3.

[1936] Input: Text data with natural language instructions

[1937] Data processing: Generative AI models analyze natural language and convert it into appropriate formulas and settings.

[1938] Output: Text data of formulas and settings (e.g. =SUM(sales data))

[1939] Step 4:

[1940] Acquiring emotional state

[1941] The emotion engine collects data such as the user's tone of voice, facial expressions, and typing speed to analyze their emotional state.

[1942] Input: User voice data, facial expression data, and typing speed data

[1943] Data calculation: Analysis using a sentiment analysis engine (e.g., Microsoft Azure's sentiment recognition API)

[1944] Output: Emotional state data (e.g., anxious, relaxed, etc.)

[1945] Step 5:

[1946] Generate and adjust operation scripts

[1947] The server generates an operation script based on the analyzed formulas, settings, and emotional state data, and makes adjustments as needed.

[1948] Input: Text data for formulas and settings, emotional state data

[1949] Data processing: Adjustments based on emotional state (e.g., simplifying procedures if you are in a hurry)

[1950] Output: Adjusted operation script

[1951] Step 6:

[1952] Sending an Operation Script

[1953] The server transmits the generated operation script to the terminal.

[1954] Input: Adjusted operation script

[1955] Output: Sends script data to the terminal

[1956] Step 7:

[1957] Applying a script

[1958] The terminal then applies the received operation script to spreadsheet software, such as Microsoft Excel or Google Sheets.

[1959] Input: Adjusted operation script

[1960] Data calculation: Reflect formulas and settings in spreadsheet software

[1961] Output: Formulas and settings reflected in the spreadsheet software (e.g. =SUM(A:A) is entered in the cell)

[1962] 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.

[1963] 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.

[1964] 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.

[1965] 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.

[1966] 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.

[1967] 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.

[1968] 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).

[1969] 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.

[1970] 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."

[1971] 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.

[1972] 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).

[1973] 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.

[1974] 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.

[1975] 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.

[1976] 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.

[1977] 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.

[1978] 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.

[1979] 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.

[1980] 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.

[1981] 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.

[1982] 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.

[1983] The following is further disclosed regarding the above embodiment.

[1984] (Claim 1)

[1985] a means for receiving natural language instructions from a user;

[1986] an analysis means including a generation AI that analyzes the natural language instruction;

[1987] means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of analysis by said analysis means;

[1988] means for applying the operation script to the spreadsheet software;

[1989] A system including:

[1990] (Claim 2)

[1991] 2. The system of claim 1, wherein the analyzing means sets conditional formatting in spreadsheet software based on specified conditions.

[1992] (Claim 3)

[1993] 2. The system according to claim 1, wherein the analysis means includes an operation for automatically generating a graph based on specified data.

[1994] "Example 1"

[1995] (Claim 1)

[1996] a means for receiving natural language instructions from a user;

[1997] means for transmitting the natural language instruction to a server;

[1998] an analysis means including a generation AI that analyzes the natural language instruction;

[1999] means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of analysis by said analysis means;

[2000] means for transmitting the operation script to a terminal;

[2001] means for applying the operation script to the spreadsheet software;

[2002] A system including:

[2003] (Claim 2)

[2004] 2. The system of claim 1, wherein the analyzing means sets conditional formatting in spreadsheet software based on specified conditions.

[2005] (Claim 3)

[2006] 2. The system according to claim 1, wherein the analysis means includes an operation for automatically generating a graph based on specified data.

[2007] "Application Example 1"

[2008] (Claim 1)

[2009] a means for receiving natural language instructions from a user;

[2010] an analysis means including a generation AI that analyzes the natural language instruction;

[2011] means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of analysis by said analysis means;

[2012] means for applying the operation script to the spreadsheet software;

[2013] A means for applying the generative AI to a robot for managing or maintaining a production line, analyzing natural language instructions, generating an appropriate operation script, and applying it to the robot;

[2014] A system including:

[2015] (Claim 2)

[2016] 2. The system of claim 1, wherein the analyzing means sets conditional formatting in spreadsheet software based on specified conditions.

[2017] (Claim 3)

[2018] 2. The system according to claim 1, wherein the analysis means includes an operation for automatically generating a graph based on specified data.

[2019] "Example 2: Combining Emotion Engines"

[2020] (Claim 1)

[2021] a means for receiving natural language instructions from a user;

[2022] an analysis means including a generation AI that analyzes the natural language instruction;

[2023] means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of analysis by said analysis means;

[2024] means for applying the operation script to the spreadsheet software;

[2025] means for evaluating an emotional state of a user, the emotional engine comprising:

[2026] means for adjusting the operation script based on the evaluation result of the emotion engine;

[2027] A system including:

[2028] (Claim 2)

[2029] 2. The system of claim 1, wherein the analyzing means sets conditional formatting in spreadsheet software based on specified conditions.

[2030] (Claim 3)

[2031] 2. The system according to claim 1, wherein the analysis means includes an operation for automatically generating a graph based on specified data.

[2032] "Application example 2 when combining emotion engines"

[2033] (Claim 1)

[2034] a means for receiving natural language instructions from a user;

[2035] an analysis means including a generation AI that analyzes the natural language instruction;

[2036] means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of analysis by said analysis means;

[2037] means including an emotion engine for analyzing an emotional state of a user;

[2038] A means for the generation AI to adjust an operation script based on the result of the emotion engine;

[2039] means for applying the operation script to the spreadsheet software;

[2040] A system including:

[2041] (Claim 2)

[2042] 2. The system of claim 1, wherein the analyzing means sets conditional formatting in spreadsheet software based on specified conditions.

[2043] (Claim 3)

[2044] 2. The system according to claim 1, wherein the analysis means includes an operation for automatically generating a graph based on specified data.

[2045] (Claim 4)

[2046] 10. The system of claim 1, wherein the emotion engine includes functionality to provide feedback based on the user's emotional state. [Explanation of symbols]

[2047] 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 receiving natural language instructions from a user; an analysis means including a generation AI that analyzes the natural language instruction; means for generating an operation script for automatically reflecting formulas or settings in spreadsheet software based on the results of analysis by said analysis means; means for applying the operation script to the spreadsheet software; A system including:

2. 2. The system of claim 1, wherein the analyzing means sets conditional formatting in spreadsheet software based on specified conditions.

3. 2. The system according to claim 1, wherein said analysis means includes an operation for automatically generating a graph based on designated data.

Images