system

Abstract

We provide the system. [Solution] A means of analyzing instructions input in natural language, Means for generating appropriate operations for a data processing program based on the above instructions, Means for executing the generated operation on a data processing program, A means for presenting the execution result to the user via a visual display device, A means of obtaining instructions using speech recognition technology, Means for updating the program operation via an intermediary device, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When using spreadsheet software, many users need to perform advanced function settings and complex setting operations, which results in the problem of reduced work efficiency. In particular, users with little experience or limited technical knowledge spend a lot of time on such operations. Also, input errors and setting errors are likely to occur, and there is a risk of impairing the accuracy of the work. There is a need to solve such problems and provide an environment in which users can use spreadsheet software more intuitively and efficiently.

Means for Solving the Problems

[0005] This invention provides a system that analyzes instructions entered in natural language and automatically generates appropriate operations on spreadsheet data based on those instructions. Specifically, it uses a large-scale language model to analyze natural language instructions entered by the user, converts them into structured data, and then executes appropriate operations on spreadsheet software. Furthermore, by presenting the results of the executed operations to the user, spreadsheet operations become possible through an intuitive interface, thereby improving work efficiency and reducing errors.

[0006] "Natural language" refers to the language that humans use on a daily basis to communicate through speaking and writing.

[0007] "Analysis" is the process of breaking down an object and revealing its composition and structure.

[0008] An "instruction" is a command or guidance to cause someone to perform a specific action or task.

[0009] "Spreadsheet data" refers to data in a table format, consisting of rows and columns, used for managing and calculating numerical and textual data.

[0010] "Operation" refers to a specific action taken to make a device or system function for a particular purpose.

[0011] "Generation" is the process of creating something new.

[0012] "Execution" is the process of acting according to a plan or instructions.

[0013] "Result" refers to the conclusion or state obtained after some operation or process.

[0014] A "user" is someone who uses a system or service.

[0015] "Presentation" is the act of showing information or objects to someone. [Brief explanation of the drawing]

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [[ID=二十九]] [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [[ID=三十三]] [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] [[ID=三十七]]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0018] First, let's explain the terminology used in the following explanation.

[0019] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0020] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] The system of the present invention analyzes instructions input in natural language and generates and executes appropriate operations on spreadsheet software based on those instructions.

[0038] At the initial stage of the system, the user inputs instructions for the spreadsheet software in natural language using a dedicated interface. These instructions should describe in detail the operations the user intends to perform, such as setting specific functions or changing cell formatting.

[0039] Next, the terminal sends the input natural language instruction to the server. The server then starts a process to analyze the received instruction. This analysis uses natural language processing techniques to break down the instruction into specific elements. For example, it extracts information such as which column or row the operation is performed on and what criteria to use.

[0040] Subsequently, the server evaluates the elements generated from the analysis results through a large-scale language model and generates the necessary spreadsheet software operations. This creates spreadsheet software functions and configuration methods optimized for the user's instructions. At this stage, the server prepares to execute the generated operations using a spreadsheet API.

[0041] Furthermore, the server executes operations set up in the spreadsheet software via the spreadsheet API. For example, it automatically applies conditional formatting such as "gray out rows where column A is 'Completed'."

[0042] After processing is complete, the server sends the operation results to the terminal, which visually displays the results to the user. This allows the user to see how their instructions were carried out and, if they are not satisfied with the results, to enter new instructions.

[0043] Thus, the present invention provides a means for users to intuitively and efficiently operate spreadsheet software without having to learn complex functions or settings. This not only improves work efficiency but also enhances the user experience.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user enters the operation they want to perform on the spreadsheet software in natural language. The instructions entered in the text boxes on the interface become the initial data.

[0047] Step 2:

[0048] The terminal receives the input natural language data and prepares to send that data to the server as a digital message. The crucial point here is to format the data in a way that the server can interpret.

[0049] Step 3:

[0050] The server passes the message received from the terminal to the parsing module. This module uses natural language processing techniques to convert the text into structured data. Specifically, it extracts elements such as the columns and cells to be manipulated and the conditions to be applied.

[0051] Step 4:

[0052] The server uses a generative AI model to generate operations to be executed in spreadsheet software based on the elements obtained from the analysis. In this process, for example, a large-scale language model derives how to apply conditional formatting and functions.

[0053] Step 5:

[0054] The server sends the generated operations to the spreadsheet API. This API receives the operation instructions and applies the settings to the spreadsheet software in real time. Operations based on the user's intent are executed here.

[0055] Step 6:

[0056] The server collects the status of the execution results and generates success or error messages. This information is configured to allow the user to check the results of the operation through a feedback module.

[0057] Step 7:

[0058] The terminal displays feedback information received from the server to the user. The results are displayed in visual or text format, which the user reviews and enters additional instructions if necessary.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] Operating current spreadsheet programs requires specialized knowledge, and setting conditional formatting and using certain functions, in particular, can often be complex for the average user. Therefore, there is a need for a system that allows users to intuitively operate spreadsheet programs using natural language.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for analyzing instructions input in natural language and breaking down the instruction content into specific elements, means for generating appropriate operations for a spreadsheet program using a generative artificial intelligence model, and means for communicating via an interface to execute the generated operations on a spreadsheet application program. This makes it possible for users to intuitively and efficiently operate a spreadsheet program in natural language without having to learn complex operations.

[0064] "Natural language" refers to the words and sentences that humans use in everyday life, and is the form used when giving instructions to a system.

[0065] A "generative artificial intelligence model" is an algorithm that uses large datasets to understand natural language and generate appropriate responses and actions.

[0066] A "spreadsheet application program" is software intended for organizing, calculating, and visualizing data, and generally allows for spreadsheet calculations and graph creation.

[0067] "Communicating via an interface" refers to protocols and connection methods used to exchange data between information systems and devices.

[0068] This invention provides a system for users to intuitively operate spreadsheet software. This system analyzes instructions entered in natural language and generates and executes appropriate operations on the spreadsheet program based on those instructions.

[0069] Users input information in natural language through a dedicated interface. For example, they can enter instructions such as, "Calculate the total for each month in the sales data sheet." The terminal receives these instructions and immediately sends them to the server.

[0070] The server uses a generative artificial intelligence model to analyze the instructions it receives. This model is a large-scale language model that breaks down natural language instructions into specific elements, creating a foundation for generating appropriate operations. During the analysis process, elements such as which data range to manipulate and what calculations to perform are clarified.

[0071] Next, the server generates specific operations based on the instructions using spreadsheet application programs, such as the Google® Sheets API. These operations are performed in concrete forms, such as applying the SUM function to a specific range of cells to calculate the sum.

[0072] After processing is complete, the server sends the results back to the terminal, which visually displays the results to the user. This allows the user to verify that the specified operation was performed correctly. Finally, if the user is not satisfied, they can re-enter new instructions.

[0073] This system eliminates the need for users to learn complex spreadsheet programs, allowing them to easily instruct and perform complex calculations using everyday language. A concrete example of a prompt might be, "Sort column B of the sales record sheet by product name."

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] Users input instructions using natural language through a dedicated interface. For example, they might input instructions such as, "Sort column A of the expense report sheet in chronological order." This input is processed as text data on the terminal.

[0077] Step 2:

[0078] The terminal sends natural language instructions received from the user to the server. This transmission process involves transferring the entered text data to the server over the network.

[0079] Step 3:

[0080] The server uses a generative AI model to analyze the received text instructions. This model converts the instructions into structured data and analyzes what operations are needed on which sheets and columns. As a result of the analysis, specific elements such as sorting column A by date are extracted. This output is stored as an entity in database format.

[0081] Step 4:

[0082] The server generates API calls for spreadsheet applications based on the parsed structured data. Specifically, it generates API requests for sorting operations. At this stage, necessary data processing is performed, and the output as an API request is prepared.

[0083] Step 5:

[0084] The server executes the generated API request against the spreadsheet application. This operation applies the sorting functionality that should be performed on the selected sheet and columns. The response from the application returns the status of whether the operation was successful or not.

[0085] Step 6:

[0086] After processing is complete, the server sends the final operation result to the terminal. Based on the received information, the terminal visually displays the result to the user. The user can verify on the screen that the sorting results have been performed correctly. This output serves as result confirmation for the user.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] In data management operations, there is a particular need to provide an environment that can be operated intuitively, especially by employees who are unfamiliar with technology. Traditional methods require users to learn complex operations, leading to decreased work efficiency and operational errors. A new method is needed to solve this problem.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations for a data processing program, and means for acquiring instructions using speech recognition technology. This enables users to easily perform data management operations using voice instructions, improving the efficiency and accuracy of operations.

[0092] "Instructions entered in natural language" refer to instructions that are formalized in the language that users use on a daily basis.

[0093] "Means of analysis" refers to a function that interprets the instructions in the input natural language and converts its content into a specific structure.

[0094] "Appropriate operation of the data processing program" refers to the process of automatically making necessary changes or updates to the data management software based on the analysis results.

[0095] "Speech recognition technology" is a technology that analyzes spoken words as digital information and obtains them as text information.

[0096] A "visual display device" is a device used to present information to a user visually, and smart glasses are an example of such a device.

[0097] A "knowledge model" is a neural network model built on linguistic data that highly analyzes input sentences and phrases and converts them into structured data.

[0098] "Conditional display" refers to a setting that makes visual changes based on specific conditions being met.

[0099] A "transit device" is a device or system that mediates the transmission and reception of data, and is used when operations are updated via a network.

[0100] A system for carrying out this invention includes a terminal connected to a visual display device (e.g., smart glasses) used by a user. The user gives voice instructions through the visual display device, and voice recognition technology captures these instructions and converts them into digital signals. The converted voice data is transmitted by the terminal to a server.

[0101] The server analyzes the received audio data using a large-scale knowledge model (e.g., BERT) and converts natural language instructions into structured data. Based on the analyzed data, the server generates the necessary operations for a data processing program (e.g., a spreadsheet application). The generated data operations are then executed on the data processing program via an intermediary device.

[0102] Because the results are presented to the user via a visual display device, the user can visually and intuitively confirm the results of data processing. For example, a store staff member can instruct the smart glasses to "update today's sales," and the sales data will be updated in real time. In such demonstrations, an example of a prompt message might be "reduce the chocolate inventory by 10."

[0103] This significantly improves operational efficiency, allowing users to easily manage data without having to learn complex operations.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The user gives voice instructions via a visual display device. Voice recognition technology captures these voice instructions and converts them into digital signals. The input to this process is the user's voice instructions, and the output is digitized voice data. This operation involves voice capture using a voice sensor and digital conversion by a voice signal processing chip.

[0107] Step 2:

[0108] The terminal sends digitized audio data to the server. The input here is the digitized audio data, and the output is the signal indicating successful transmission to the server. Specifically, this involves transferring audio data over a network using a communication module.

[0109] Step 3:

[0110] The server analyzes the audio data using a knowledge model. This analysis converts natural language instructions from the audio data into structured data. The input to this step is the received audio data, and the output is structured instruction data. The operation here involves audio decoding and text analysis processing by the AI ​​model.

[0111] Step 4:

[0112] The server generates operations for a data processing program based on the structured data it analyzes. The input is structured instruction data, and the output is program operation instructions. The operation includes script generation and macro setting based on the analysis results.

[0113] Step 5:

[0114] The generated program operation instructions are executed on the data processing program via an intermediary device. The input for this step is the operation instruction, and the output is an execution completion signal. Specific operations include database updates and calculations using APIs.

[0115] Step 6:

[0116] The server presents the execution results to the user via a visual display device. The input for this step is the execution result data, and the output is visual feedback to the user. Specifically, the result is displayed using a display device.

[0117] Step 7:

[0118] The user reviews the visual results and provides further verbal instructions if needed. The input for this step is visual feedback, and the output is new verbal instructions. This process involves visual evaluation of the results and generation of new instructions.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] This invention provides a system that allows users to control spreadsheet software using natural language and further recognizes user emotions to adjust the operation content and feedback.

[0121] When using the system, users input the operations they want to perform on the spreadsheet software using natural language. For example, they might give instructions such as "gray out rows where column A is marked 'Completed'." These natural language instructions are first received by the terminal and then sent to the server.

[0122] The server utilizes a large-scale language model to analyze the input natural language. This ensures that the instructions are appropriately converted into structured data, clearly defining the necessary operations. Following this analysis, an operation generation system generates operations in spreadsheet software based on the instructions. The generated operations are then ready for execution via a spreadsheet API.

[0123] Next, an emotion engine that recognizes the user's emotions kicks in. The server extracts emotions from the input and user actions, and then fine-tunes the operation based on the results. For example, if the user is expressing dissatisfaction, the operation is adjusted to provide more detailed feedback or additional help information. In this way, the feedback module provides information in accordance with the user's emotions.

[0124] Ultimately, the device presents the user with the results of the operation and feedback adjusted by the emotion engine. The user reviews the results and continues working if the operation was as intended. If they are not satisfied with the results or if further adjustments are needed, they can enter new instructions.

[0125] Through this method, the present invention enables smooth spreadsheet operations that appropriately reflect the user's instructions and emotions. This system not only supports efficient work but also significantly improves the user experience.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] Users input instructions for operating the spreadsheet software in natural language. This input is made in text boxes on a dedicated interface and recorded as a document that accurately conveys the user's intent.

[0129] Step 2:

[0130] The terminal receives natural language instructions and sends that data to the server. During this process, the input data is converted to an appropriate format, making it ready for processing on the server.

[0131] Step 3:

[0132] The server passes the received natural language data to the analysis module, which then analyzes the instructions. A large-scale language model structures the text into data, extracting elements such as the target of the operation and the conditions.

[0133] Step 4:

[0134] The server uses an emotion engine to extract emotional information from user input. This emotional information indicates how the user is feeling and is reflected in the system's response.

[0135] Step 5:

[0136] The server generates appropriate operations for spreadsheet software based on analysis results and emotional information. The generating AI model fine-tunes the operations, especially based on emotional information, to produce the optimal result for the user.

[0137] Step 6:

[0138] The server sends the generated operations to the spreadsheet API, which then executes the operations on the spreadsheet software. This includes, for example, applying conditional formatting and updating cell data.

[0139] Step 7:

[0140] The server sends the execution results and adjusted feedback to the terminal. The results include not only success or failure information, but also explanations and support information that take the user's feelings into consideration.

[0141] Step 8:

[0142] The terminal displays the results and feedback received from the server to the user. Visual feedback shows how the operation was performed, allowing the user to decide on the next steps as needed.

[0143] This system process enables users to operate spreadsheet software in an efficient and emotionally resonant way.

[0144] (Example 2)

[0145] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0146] Traditional spreadsheet software has limitations in terms of complexity and learning curve because users cannot input instructions in natural language. Furthermore, the lack of systems that provide real-time feedback that takes user emotions into account limits the potential for improving the user experience.

[0147] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0148] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations on digital data, and means for recognizing the user's emotions and adjusting the operation content and feedback accordingly. This makes it possible for the user to give instructions in natural language and receive appropriate operations and feedback according to their emotions.

[0149] "Natural language" refers to the language that humans use on a daily basis, and its purpose is to be converted into a format that machines can understand.

[0150] An "analysis tool" is a device that analyzes input information, extracts meaning and intent, and converts it into a format that can be used for subsequent processing.

[0151] "Digital data" is a general term for information stored in digital format, and it is the subject to which specific operations are performed.

[0152] An "operation generation means" is a device that has the function of automatically constructing specific processing procedures based on analyzed information and making them executable.

[0153] "Emotion recognition" refers to technology that estimates a user's emotional state based on their input and actions.

[0154] "Feedback" refers to the information output from a system that provides users with operational results and additional information to improve the user experience.

[0155] This invention provides a system that automatically performs operations on digital data by receiving instructions entered by the user in natural language. The aim of this system is to provide the user with a more intuitive operating environment, achieve efficient data processing, and improve the user experience by recognizing the user's emotions and adjusting the feedback accordingly.

[0156] The following hardware and software are used to implement this system. Natural language instructions are entered via a user-operated terminal, such as a personal computer or mobile device. The terminal transmits the input data to a server via a network. The server uses a large-scale language model known as a generative AI model to analyze the natural language instructions and convert them into structured data. Based on this analysis, it generates appropriate digital data operations.

[0157] As a concrete example, a user-inputted prompt might be, "Gray out rows where column A is marked 'Completed'." This instruction is received by the terminal and sent to the server. On the server, a generating AI model analyzes the instruction and generates an operation to apply conditional formatting to the relevant rows to gray them out. In this process, a spreadsheet API or similar tool would be used.

[0158] Furthermore, emotion recognition software installed on the server analyzes the user's emotions based on their input and operation history, and adjusts the feedback module accordingly. This allows for the provision of user-specific information, such as providing additional explanations if the user indicates discomfort.

[0159] Ultimately, the device displays feedback to the user that is tailored to the results of the actions performed and the user's emotions. The user can review the results, verify that they are the intended outcome, and then provide further instructions if necessary. Thus, this system is characterized by providing flexible operation in response to user instructions via natural language and returning responses that take the user's emotions into consideration.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The user inputs the desired action in natural language. For example, they might enter a prompt such as, "Gray out rows where column A is marked 'Completed'." The terminal receives the input natural language instruction.

[0163] Step 2:

[0164] The terminal sends the input instructions to the server. Here, the input text data is processed to be sent to the server as an HTTP request, and the request is output.

[0165] Step 3:

[0166] The server analyzes the received natural language instructions using a generative AI model. Here, natural language processing is performed to convert the instructions into structured data that a machine can understand. This process yields the converted data as output.

[0167] Step 4:

[0168] The server generates specific operations on the digital data based on the parsed instructions. It uses the spreadsheet API to construct instructions for applying conditional formatting to specified cells. At this stage, specific operation instructions are output.

[0169] Step 5:

[0170] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's input and interaction history, and extracts the emotional state from the obtained data. Based on these results, feedback and adjustments to subsequent actions are made.

[0171] Step 6:

[0172] The server fine-tunes the actions and feedback based on the recognized emotions. It determines whether additional comments or explanations are needed, adjusts the actions accordingly, and then outputs the feedback.

[0173] Step 7:

[0174] The terminal displays the user the operation results sent from the server and the adjusted feedback. Specifically, the updated status of the spreadsheet is displayed on the screen, and feedback is indicated through pop-up messages or other means.

[0175] Step 8:

[0176] The user reviews the results and determines if the operation was performed as intended. If the results are not as intended or if additional changes are needed, they can enter new instructions to request the next action.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0179] Conventional data management systems do not fully utilize natural language operation instructions, making it difficult for users to operate them intuitively and efficiently. Furthermore, the lack of feedback and operation adjustments that respond to user emotions results in a limited user experience, which is a significant challenge.

[0180] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0181] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations on a data processing structure based on the instructions, and means for recognizing the user's emotions from the input information. This enables the user to intuitively give instructions in natural language and receive optimal operations and feedback that correspond to their emotions based on those instructions.

[0182] "Natural language" refers to the language that humans use in everyday life, enabling intuitive input of instructions into a system.

[0183] "Means of analysis" refers to techniques that understand natural language instructions and convert them into appropriately structured data.

[0184] "Data processing structure" refers to the target dataset or database, which is the object of the operation.

[0185] "Means for generating operations" refers to techniques for designing specific actions to be performed on data based on instructions in analyzed natural language.

[0186] "Means of recognizing emotions" refers to technologies that determine a user's emotional state from their input and actions.

[0187] "Means of adjusting feedback" refers to methods of optimizing the information and responses presented to the user in accordance with the perceived emotions.

[0188] "Execution result" refers to the final output of operations performed on the data processing structure based on the instructions.

[0189] A "user" refers to an entity that uses this system to send instructions in natural language and receive feedback.

[0190] The system to realize this application combines a large-scale language model for natural language processing with an analysis engine for recognizing emotions. Specifically, the user inputs instructions in natural language via a terminal. For example, they might give a specific instruction such as, "We're running low on milk, please add it to the shopping list."

[0191] The terminal receives this instruction and forwards it to the server. The server uses a large-scale language model as an analysis tool to analyze the input natural language and convert the instruction into structured data. For example, a generative AI model such as OpenAI's GPT-4® is used for this purpose. Next, the operation generation tool designs a data processing structure, such as an operation on an inventory management list, based on the analysis results.

[0192] Furthermore, the server uses an emotion analysis engine as a means of recognizing emotions. It employs technologies such as Microsoft's Emotion API to infer emotions from the user's voice and facial expressions. Then, through mechanisms to adjust feedback, it provides appropriate responses, additional advice, and feedback to the user based on their emotions.

[0193] Ultimately, the user is presented with feedback that reflects the results and their emotions. This allows the user to confirm whether the action was performed as intended and to provide additional instructions if necessary.

[0194] For example, if a user says, "The weather is nice, so I want to go for a walk," the server analyzes this information and provides the most appropriate feedback. An example of a prompt would be, "User said: 'The weather is nice, so I want to go for a walk.' What task should the robot perform based on this statement?" This would be input to the language model.

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The user inputs natural language instructions via the terminal. The input data includes specific phrases such as "We're running low on milk, please add it to the shopping list." This instruction is used as input for the next process. The terminal receives this voice or text input and prepares to send it to the server as digital data.

[0198] Step 2:

[0199] The terminal transfers the input instruction data to the server. The server's role here is to receive this transferred data. After receiving the data, the server prepares to use a large-scale language model to analyze the input. The output at this step is the instruction data itself to be analyzed.

[0200] Step 3:

[0201] The server uses a large-scale language model to parse the received natural language instructions. This analysis converts the natural language instructions into structured data. The model interprets the meaning of the instructions and generates operation instructions for the data processing structure based on this interpretation. The input to this step is natural language instruction data, and the output is the parsed structured data.

[0202] Step 4:

[0203] The server uses the generated structured data to create operations. Specifically, it designs concrete actions such as "add milk to the list" in the inventory management list. The input in this step is the structured data that was the output in step 3, and the output is the operation instruction.

[0204] Step 5:

[0205] The server determines the user's emotions using means of emotion recognition. Inputs include natural language indications such as tone and related metadata. An emotion analysis engine is used here to generate data about the user's current emotional state. The output is the emotion recognition result.

[0206] Step 6:

[0207] The server fine-tunes feedback and instructions based on the results of emotion recognition. This adjustment process involves designing additional, gentle, and reassuring feedback if the user is experiencing stress or anxiety. The input is emotional state data, and the output is the adjusted feedback message.

[0208] Step 7:

[0209] The server sends the execution results and adjusted feedback back to the terminal. The terminal then presents these results to the user, either visually or audibly. This may include messages such as, "Milk has been added to the list," or "Is there anything else I can help you with?" The output is the final result and feedback presented to the user.

[0210] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0211] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search)<url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0212] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0213] [Second Embodiment]

[0214] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0215] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0216] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0217] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0218] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0219] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0220] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0221] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0222] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0223] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0224] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0225] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0226] The system of the present invention analyzes instructions input in natural language and generates and executes appropriate operations on spreadsheet software based on those instructions.

[0227] At the initial stage of the system, the user inputs instructions for the spreadsheet software in natural language using a dedicated interface. These instructions should describe in detail the operations the user intends to perform, such as setting specific functions or changing cell formatting.

[0228] Next, the terminal sends the input natural language instruction to the server. The server then starts a process to analyze the received instruction. This analysis uses natural language processing techniques to break down the instruction into specific elements. For example, it extracts information such as which column or row the operation is performed on and what criteria to use.

[0229] Subsequently, the server evaluates the elements generated from the analysis results through a large-scale language model and generates the necessary spreadsheet software operations. This creates spreadsheet software functions and configuration methods optimized for the user's instructions. At this stage, the server prepares to execute the generated operations using a spreadsheet API.

[0230] Furthermore, the server executes operations set up in the spreadsheet software via the spreadsheet API. For example, it automatically applies conditional formatting such as "gray out rows where column A is 'Completed'."

[0231] After processing is complete, the server sends the operation results to the terminal, which visually displays the results to the user. This allows the user to see how their instructions were carried out and, if they are not satisfied with the results, to enter new instructions.

[0232] Thus, the present invention provides a means for users to intuitively and efficiently operate spreadsheet software without having to learn complex functions or settings. This not only improves work efficiency but also enhances the user experience.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The user enters the operation they want to perform on the spreadsheet software in natural language. The instructions entered in the text boxes on the interface become the initial data.

[0236] Step 2:

[0237] The terminal receives the input natural language data and prepares to send that data to the server as a digital message. The crucial point here is to format the data in a way that the server can interpret.

[0238] Step 3:

[0239] The server passes the message received from the terminal to the parsing module. This module uses natural language processing techniques to convert the text into structured data. Specifically, it extracts elements such as the columns and cells to be manipulated and the conditions to be applied.

[0240] Step 4:

[0241] The server uses a generative AI model to generate operations to be executed in spreadsheet software based on the elements obtained from the analysis. In this process, for example, a large-scale language model derives how to apply conditional formatting and functions.

[0242] Step 5:

[0243] The server sends the generated operations to the spreadsheet API. This API receives the operation instructions and applies the settings to the spreadsheet software in real time. Operations based on the user's intent are executed here.

[0244] Step 6:

[0245] The server collects the status of the execution results and generates success or error messages. This information is configured to allow the user to check the results of the operation through a feedback module.

[0246] Step 7:

[0247] The terminal displays feedback information received from the server to the user. The results are displayed in visual or text format, which the user reviews and enters additional instructions if necessary.

[0248] (Example 1)

[0249] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0250] Operating current spreadsheet programs requires specialized knowledge, and setting conditional formatting and using certain functions, in particular, can often be complex for the average user. Therefore, there is a need for a system that allows users to intuitively operate spreadsheet programs using natural language.

[0251] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0252] In this invention, the server includes means for analyzing instructions input in natural language and breaking down the instruction content into specific elements, means for generating appropriate operations for a spreadsheet program using a generative artificial intelligence model, and means for communicating via an interface to execute the generated operations on a spreadsheet application program. This makes it possible for users to intuitively and efficiently operate a spreadsheet program in natural language without having to learn complex operations.

[0253] "Natural language" refers to the words and sentences that humans use in everyday life, and is the form used when giving instructions to a system.

[0254] A "generative artificial intelligence model" is an algorithm that uses large datasets to understand natural language and generate appropriate responses and actions.

[0255] A "spreadsheet application program" is software intended for organizing, calculating, and visualizing data, and generally allows for spreadsheet calculations and graph creation.

[0256] "Communicating via an interface" refers to protocols and connection methods used to exchange data between information systems and devices.

[0257] This invention provides a system for users to intuitively operate spreadsheet software. This system analyzes instructions entered in natural language and generates and executes appropriate operations on the spreadsheet program based on those instructions.

[0258] Users input information in natural language through a dedicated interface. For example, they can enter instructions such as, "Calculate the total for each month in the sales data sheet." The terminal receives these instructions and immediately sends them to the server.

[0259] The server uses a generative artificial intelligence model to analyze the instructions it receives. This model is a large-scale language model that breaks down natural language instructions into specific elements, creating a foundation for generating appropriate operations. During the analysis process, elements such as which data range to manipulate and what calculations to perform are clarified.

[0260] Next, the server generates specific operations based on the instructions using spreadsheet application programs, such as the API of Google Sheets. These operations are performed in concrete forms, such as applying the SUM function to a specific range of cells to calculate the sum.

[0261] After processing is complete, the server sends the results back to the terminal, which visually displays the results to the user. This allows the user to verify that the specified operation was performed correctly. Finally, if the user is not satisfied, they can re-enter new instructions.

[0262] This system eliminates the need for users to learn complex spreadsheet programs, allowing them to easily instruct and perform complex calculations using everyday language. A concrete example of a prompt might be, "Sort column B of the sales record sheet by product name."

[0263] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0264] Step 1:

[0265] Users input instructions using natural language through a dedicated interface. For example, they might input instructions such as, "Sort column A of the expense report sheet in chronological order." This input is processed as text data on the terminal.

[0266] Step 2:

[0267] The terminal sends natural language instructions received from the user to the server. This transmission process involves transferring the entered text data to the server over the network.

[0268] Step 3:

[0269] The server uses a generative AI model to analyze the received text instructions. This model converts the instructions into structured data and analyzes what operations are needed on which sheets and columns. As a result of the analysis, specific elements such as sorting column A by date are extracted. This output is stored as an entity in database format.

[0270] Step 4:

[0271] The server generates API calls for spreadsheet applications based on the parsed structured data. Specifically, it generates API requests for sorting operations. At this stage, necessary data processing is performed, and the output as an API request is prepared.

[0272] Step 5:

[0273] The server executes the generated API request against the spreadsheet application. This operation applies the sorting functionality that should be performed on the selected sheet and columns. The response from the application returns the status of whether the operation was successful or not.

[0274] Step 6:

[0275] After processing is complete, the server sends the final operation result to the terminal. Based on the received information, the terminal visually displays the result to the user. The user can verify on the screen that the sorting results have been performed correctly. This output serves as result confirmation for the user.

[0276] (Application Example 1)

[0277] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0278] In data management operations, there is a particular need to provide an environment that can be operated intuitively, especially by employees who are unfamiliar with technology. Traditional methods require users to learn complex operations, leading to decreased work efficiency and operational errors. A new method is needed to solve this problem.

[0279] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0280] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations for a data processing program, and means for acquiring instructions using speech recognition technology. This enables users to easily perform data management operations using voice instructions, improving the efficiency and accuracy of operations.

[0281] The "instructions input in natural language" refers to instructions formalized in the language commonly used by users.

[0282] The "means for analysis" is a function that interprets the input instructions in natural language and converts the content into a specific structure.

[0283] The "appropriate operation on the data processing program" is a process that automatically makes necessary changes and updates to the data management software based on the analysis results.

[0284] The "speech recognition technology" is a technology that analyzes spoken words as digital information and obtains them as character information.

[0285] The "visual display device" is a device used to visually present information to the user, and examples include smart glasses.

[0286] The "knowledge model" is a neural network model constructed based on language data, which highly analyzes the input sentences and phrases and converts them into structured data.

[0287] The "conditional display" refers to a setting that makes visual changes based on specific conditions being met.

[0288] The "intermediate device" refers to a device or system that mediates the transmission and reception of data and is used when operations are updated via a network.

[0289] The system for implementing this invention includes a terminal connected to a visual display device (e.g., smart glasses) used by the user. The user gives voice instructions through the visual display device, and the speech recognition technology captures the instructions and converts them into digital signals. The converted voice data is sent by the terminal to the server.

[0290] The server analyzes the received audio data using a large-scale knowledge model (e.g., BERT) and converts natural language instructions into structured data. Based on the analyzed data, the server generates the necessary operations for a data processing program (e.g., a spreadsheet application). The generated data operations are then executed on the data processing program via an intermediary device.

[0291] Because the results are presented to the user via a visual display device, the user can visually and intuitively confirm the results of data processing. For example, a store staff member can instruct the smart glasses to "update today's sales," and the sales data will be updated in real time. In such demonstrations, an example of a prompt message might be "reduce the chocolate inventory by 10."

[0292] This significantly improves operational efficiency, allowing users to easily manage data without having to learn complex operations.

[0293] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0294] Step 1:

[0295] The user gives voice instructions via a visual display device. Voice recognition technology captures these voice instructions and converts them into digital signals. The input to this process is the user's voice instructions, and the output is digitized voice data. This operation involves voice capture using a voice sensor and digital conversion by a voice signal processing chip.

[0296] Step 2:

[0297] The terminal sends digitized audio data to the server. The input here is the digitized audio data, and the output is the signal indicating successful transmission to the server. Specifically, this involves transferring audio data over a network using a communication module.

[0298] Step 3:

[0299] The server analyzes the voice data using the knowledge model. Through this analysis, the natural language instructions in the voice data are converted into structured data. The input of this step is the received voice data, and the output is the structured instruction data. The operations here involve voice decoding and text analysis processing by the AI model.

[0300] Step 4:

[0301] Based on the structured data analyzed by the server, operations on the data processing program are generated. The input is the structured instruction data, and the output is the program operation instruction. The operations include script generation and macro setting according to the analysis results.

[0302] Step 5:

[0303] Execute the generated program operation instruction on the data processing program via the via device. The input of this step is the operation instruction, and the output is the execution completion signal. Specific operations include database update and calculation processing using the API.

[0304] Step 6:

[0305] The server presents the execution result to the user via the visual display device. The input of this step is the execution result data, and the output is the visual feedback to the user. Specific operations include result display using the display device.

[0306] Step 7:

[0307] The user checks the visual result and gives new instructions in voice again if new instructions are needed. The input of this step is the visual feedback, and the output is the new voice instruction. This operation includes visual evaluation of the result and generation of new instructions.

[0308] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0309] This invention provides a system that allows users to control spreadsheet software using natural language and further recognizes user emotions to adjust the operation content and feedback.

[0310] When using the system, users input the operations they want to perform on the spreadsheet software using natural language. For example, they might give instructions such as "gray out rows where column A is marked 'Completed'." These natural language instructions are first received by the terminal and then sent to the server.

[0311] The server utilizes a large-scale language model to analyze the input natural language. This ensures that the instructions are appropriately converted into structured data, clearly defining the necessary operations. Following this analysis, an operation generation system generates operations in spreadsheet software based on the instructions. The generated operations are then ready for execution via a spreadsheet API.

[0312] Next, an emotion engine that recognizes the user's emotions kicks in. The server extracts emotions from the input and user actions, and then fine-tunes the operation based on the results. For example, if the user is expressing dissatisfaction, the operation is adjusted to provide more detailed feedback or additional help information. In this way, the feedback module provides information in accordance with the user's emotions.

[0313] Ultimately, the device presents the user with the results of the operation and feedback adjusted by the emotion engine. The user reviews the results and continues working if the operation was as intended. If they are not satisfied with the results or if further adjustments are needed, they can enter new instructions.

[0314] Through this method, the present invention enables smooth spreadsheet operations that appropriately reflect the user's instructions and emotions. This system not only supports efficient work but also significantly improves the user experience.

[0315] The following describes the processing flow.

[0316] Step 1:

[0317] Users input instructions for operating the spreadsheet software in natural language. This input is made in text boxes on a dedicated interface and recorded as a document that accurately conveys the user's intent.

[0318] Step 2:

[0319] The terminal receives natural language instructions and sends that data to the server. During this process, the input data is converted to an appropriate format, making it ready for processing on the server.

[0320] Step 3:

[0321] The server passes the received natural language data to the analysis module, which then analyzes the instructions. A large-scale language model structures the text into data, extracting elements such as the target of the operation and the conditions.

[0322] Step 4:

[0323] The server uses an emotion engine to extract emotional information from user input. This emotional information indicates how the user is feeling and is reflected in the system's response.

[0324] Step 5:

[0325] The server generates appropriate operations for spreadsheet software based on analysis results and emotional information. The generating AI model fine-tunes the operations, especially based on emotional information, to produce the optimal result for the user.

[0326] Step 6:

[0327] The server sends the generated operations to the spreadsheet API, which then executes the operations on the spreadsheet software. This includes, for example, applying conditional formatting and updating cell data.

[0328] Step 7:

[0329] The server sends the execution results and adjusted feedback to the terminal. The results include not only success or failure information, but also explanations and support information that take the user's feelings into consideration.

[0330] Step 8:

[0331] The terminal displays the results and feedback received from the server to the user. Visual feedback shows how the operation was performed, allowing the user to decide on the next steps as needed.

[0332] This system process enables users to operate spreadsheet software in an efficient and emotionally resonant way.

[0333] (Example 2)

[0334] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0335] Traditional spreadsheet software has limitations in terms of complexity and learning curve because users cannot input instructions in natural language. Furthermore, the lack of systems that provide real-time feedback that takes user emotions into account limits the potential for improving the user experience.

[0336] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0337] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations on digital data, and means for recognizing the user's emotions and adjusting the operation content and feedback accordingly. This makes it possible for the user to give instructions in natural language and receive appropriate operations and feedback according to their emotions.

[0338] "Natural language" refers to the language that humans use on a daily basis, and its purpose is to be converted into a format that machines can understand.

[0339] An "analysis tool" is a device that analyzes input information, extracts meaning and intent, and converts it into a format that can be used for subsequent processing.

[0340] "Digital data" is a general term for information stored in digital format, and it is the subject to which specific operations are performed.

[0341] An "operation generation means" is a device that has the function of automatically constructing specific processing procedures based on analyzed information and making them executable.

[0342] "Emotion recognition" refers to technology that estimates a user's emotional state based on their input and actions.

[0343] "Feedback" refers to the information output from a system that provides users with operational results and additional information to improve the user experience.

[0344] This invention provides a system that automatically performs operations on digital data by receiving instructions entered by the user in natural language. The aim of this system is to provide the user with a more intuitive operating environment, achieve efficient data processing, and improve the user experience by recognizing the user's emotions and adjusting the feedback accordingly.

[0345] The following hardware and software are used to implement this system. Natural language instructions are entered via a user-operated terminal, such as a personal computer or mobile device. The terminal transmits the input data to a server via a network. The server uses a large-scale language model known as a generative AI model to analyze the natural language instructions and convert them into structured data. Based on this analysis, it generates appropriate digital data operations.

[0346] As a concrete example, a user-inputted prompt might be, "Gray out rows where column A is marked 'Completed'." This instruction is received by the terminal and sent to the server. On the server, a generating AI model analyzes the instruction and generates an operation to apply conditional formatting to the relevant rows to gray them out. In this process, a spreadsheet API or similar tool would be used.

[0347] Furthermore, emotion recognition software installed on the server analyzes the user's emotions based on their input and operation history, and adjusts the feedback module accordingly. This allows for the provision of user-specific information, such as providing additional explanations if the user indicates discomfort.

[0348] Ultimately, the device displays feedback to the user that is tailored to the results of the actions performed and the user's emotions. The user can review the results, verify that they are the intended outcome, and then provide further instructions if necessary. Thus, this system is characterized by providing flexible operation in response to user instructions via natural language and returning responses that take the user's emotions into consideration.

[0349] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0350] Step 1:

[0351] The user inputs the desired action in natural language. For example, they might enter a prompt such as, "Gray out rows where column A is marked 'Completed'." The terminal receives the input natural language instruction.

[0352] Step 2:

[0353] The terminal sends the input instructions to the server. Here, the input text data is processed to be sent to the server as an HTTP request, and the request is output.

[0354] Step 3:

[0355] The server analyzes the received natural language instructions using a generative AI model. Here, natural language processing is performed to convert the instructions into structured data that a machine can understand. This process yields the converted data as output.

[0356] Step 4:

[0357] The server generates specific operations on the digital data based on the parsed instructions. It uses the spreadsheet API to construct instructions for applying conditional formatting to specified cells. At this stage, specific operation instructions are output.

[0358] Step 5:

[0359] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's input and interaction history, and extracts the emotional state from the obtained data. Based on these results, feedback and adjustments to subsequent actions are made.

[0360] Step 6:

[0361] The server fine-tunes the actions and feedback based on the recognized emotions. It determines whether additional comments or explanations are needed, adjusts the actions accordingly, and then outputs the feedback.

[0362] Step 7:

[0363] The terminal displays the user the operation results sent from the server and the adjusted feedback. Specifically, the updated status of the spreadsheet is displayed on the screen, and feedback is indicated through pop-up messages or other means.

[0364] Step 8:

[0365] The user reviews the results and determines if the operation was performed as intended. If the results are not as intended or if additional changes are needed, they can enter new instructions to request the next action.

[0366] (Application Example 2)

[0367] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0368] Conventional data management systems do not fully utilize natural language operation instructions, making it difficult for users to operate them intuitively and efficiently. Furthermore, the lack of feedback and operation adjustments that respond to user emotions results in a limited user experience, which is a significant challenge.

[0369] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0370] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations on a data processing structure based on the instructions, and means for recognizing the user's emotions from the input information. This enables the user to intuitively give instructions in natural language and receive optimal operations and feedback that correspond to their emotions based on those instructions.

[0371] "Natural language" refers to the language that humans use in everyday life, enabling intuitive input of instructions into a system.

[0372] "Means of analysis" refers to techniques that understand natural language instructions and convert them into appropriately structured data.

[0373] "Data processing structure" refers to the target dataset or database, which is the object of the operation.

[0374] "Means for generating operations" refers to techniques for designing specific actions to be performed on data based on instructions in analyzed natural language.

[0375] "Means of recognizing emotions" refers to technologies that determine a user's emotional state from their input and actions.

[0376] "Means of adjusting feedback" refers to methods of optimizing the information and responses presented to the user in accordance with the perceived emotions.

[0377] "Execution result" refers to the final output of operations performed on the data processing structure based on the instructions.

[0378] A "user" refers to an entity that uses this system to send instructions in natural language and receive feedback.

[0379] The system to realize this application combines a large-scale language model for natural language processing with an analysis engine for recognizing emotions. Specifically, the user inputs instructions in natural language via a terminal. For example, they might give a specific instruction such as, "We're running low on milk, please add it to the shopping list."

[0380] The terminal receives this instruction and forwards it to the server. The server uses a large-scale language model as an analysis tool to analyze the input natural language and convert the instruction into structured data. For example, a generative AI model such as OpenAI's GPT-4 is used for this purpose. Next, an operation generation tool designs a data processing structure, such as an operation on an inventory management list, based on the analysis results.

[0381] Furthermore, the server uses an emotion analysis engine as a means of recognizing emotions. Leveraging technologies like Microsoft's Emotion API, it infers emotions from the user's voice and facial expressions. Then, through mechanisms to adjust feedback, it provides appropriate responses, additional advice, and feedback to the user based on their emotions.

[0382] Ultimately, the user is presented with feedback that reflects the results and their emotions. This allows the user to confirm whether the action was performed as intended and to provide additional instructions if necessary.

[0383] For example, if a user says, "The weather is nice, so I want to go for a walk," the server analyzes this information and provides the most appropriate feedback. An example of a prompt would be, "User said: 'The weather is nice, so I want to go for a walk.' What task should the robot perform based on this statement?" This would be input to the language model.

[0384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0385] Step 1:

[0386] The user inputs natural language instructions via the terminal. The input data includes specific phrases such as "We're running low on milk, please add it to the shopping list." This instruction is used as input for the next process. The terminal receives this voice or text input and prepares to send it to the server as digital data.

[0387] Step 2:

[0388] The terminal transfers the input instruction data to the server. The server's role here is to receive this transferred data. After receiving the data, the server prepares to use a large-scale language model to analyze the input. The output at this step is the instruction data itself to be analyzed.

[0389] Step 3:

[0390] The server uses a large-scale language model to parse the received natural language instructions. This analysis converts the natural language instructions into structured data. The model interprets the meaning of the instructions and generates operation instructions for the data processing structure based on this interpretation. The input to this step is natural language instruction data, and the output is the parsed structured data.

[0391] Step 4:

[0392] The server uses the generated structured data to create operations. Specifically, it designs concrete actions such as "add milk to the list" in the inventory management list. The input in this step is the structured data that was the output in step 3, and the output is the operation instruction.

[0393] Step 5:

[0394] The server determines the user's emotions using means of emotion recognition. Inputs include natural language indications such as tone and related metadata. An emotion analysis engine is used here to generate data about the user's current emotional state. The output is the emotion recognition result.

[0395] Step 6:

[0396] The server fine-tunes feedback and instructions based on the results of emotion recognition. This adjustment process involves designing additional, gentle, and reassuring feedback if the user is experiencing stress or anxiety. The input is emotional state data, and the output is the adjusted feedback message.

[0397] Step 7:

[0398] The server sends the execution results and adjusted feedback back to the terminal. The terminal then presents these results to the user, either visually or audibly. This may include messages such as, "Milk has been added to the list," or "Is there anything else I can help you with?" The output is the final result and feedback presented to the user.

[0399] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0400] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0401] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0402] [Third Embodiment]

[0403] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0404] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0405] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0406] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0407] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0408] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0409] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0410] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0411] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0412] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0413] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0414] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0415] The system of the present invention analyzes instructions input in natural language and generates and executes appropriate operations on spreadsheet software based on those instructions.

[0416] At the initial stage of the system, the user inputs instructions for the spreadsheet software in natural language using a dedicated interface. These instructions should describe in detail the operations the user intends to perform, such as setting specific functions or changing cell formatting.

[0417] Next, the terminal sends the input natural language instruction to the server. The server then starts a process to analyze the received instruction. This analysis uses natural language processing techniques to break down the instruction into specific elements. For example, it extracts information such as which column or row the operation is performed on and what criteria to use.

[0418] Subsequently, the server evaluates the elements generated from the analysis results through a large-scale language model and generates the necessary spreadsheet software operations. This creates spreadsheet software functions and configuration methods optimized for the user's instructions. At this stage, the server prepares to execute the generated operations using a spreadsheet API.

[0419] Furthermore, the server executes operations set up in the spreadsheet software via the spreadsheet API. For example, it automatically applies conditional formatting such as "gray out rows where column A is 'Completed'."

[0420] After processing is complete, the server sends the operation results to the terminal, which visually displays the results to the user. This allows the user to see how their instructions were carried out and, if they are not satisfied with the results, to enter new instructions.

[0421] Thus, the present invention provides a means for users to intuitively and efficiently operate spreadsheet software without having to learn complex functions or settings. This not only improves work efficiency but also enhances the user experience.

[0422] The following describes the processing flow.

[0423] Step 1:

[0424] The user enters the operation they want to perform on the spreadsheet software in natural language. The instructions entered in the text boxes on the interface become the initial data.

[0425] Step 2:

[0426] The terminal receives the input natural language data and prepares to send that data to the server as a digital message. The crucial point here is to format the data in a way that the server can interpret.

[0427] Step 3:

[0428] The server passes the message received from the terminal to the parsing module. This module uses natural language processing techniques to convert the text into structured data. Specifically, it extracts elements such as the columns and cells to be manipulated and the conditions to be applied.

[0429] Step 4:

[0430] The server uses a generative AI model to generate operations to be executed in spreadsheet software based on the elements obtained from the analysis. In this process, for example, a large-scale language model derives how to apply conditional formatting and functions.

[0431] Step 5:

[0432] The server sends the generated operations to the spreadsheet API. This API receives the operation instructions and applies the settings to the spreadsheet software in real time. Operations based on the user's intent are executed here.

[0433] Step 6:

[0434] The server collects the status of the execution results and generates success or error messages. This information is configured to allow the user to check the results of the operation through a feedback module.

[0435] Step 7:

[0436] The terminal displays feedback information received from the server to the user. The results are displayed in visual or text format, which the user reviews and enters additional instructions if necessary.

[0437] (Example 1)

[0438] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0439] Operating current spreadsheet programs requires specialized knowledge, and setting conditional formatting and using certain functions, in particular, can often be complex for the average user. Therefore, there is a need for a system that allows users to intuitively operate spreadsheet programs using natural language.

[0440] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0441] In this invention, the server includes means for analyzing instructions input in natural language and breaking down the instruction content into specific elements, means for generating appropriate operations for a spreadsheet program using a generative artificial intelligence model, and means for communicating via an interface to execute the generated operations on a spreadsheet application program. This makes it possible for users to intuitively and efficiently operate a spreadsheet program in natural language without having to learn complex operations.

[0442] "Natural language" refers to the words and sentences that humans use in everyday life, and is the form used when giving instructions to a system.

[0443] A "generative artificial intelligence model" is an algorithm that uses large datasets to understand natural language and generate appropriate responses and actions.

[0444] A "spreadsheet application program" is software intended for organizing, calculating, and visualizing data, and generally allows for spreadsheet calculations and graph creation.

[0445] "Communicating via an interface" refers to protocols and connection methods used to exchange data between information systems and devices.

[0446] This invention provides a system for users to intuitively operate spreadsheet software. This system analyzes instructions entered in natural language and generates and executes appropriate operations on the spreadsheet program based on those instructions.

[0447] Users input information in natural language through a dedicated interface. For example, they can enter instructions such as, "Calculate the total for each month in the sales data sheet." The terminal receives these instructions and immediately sends them to the server.

[0448] The server uses a generative artificial intelligence model to analyze the instructions it receives. This model is a large-scale language model that breaks down natural language instructions into specific elements, creating a foundation for generating appropriate operations. During the analysis process, elements such as which data range to manipulate and what calculations to perform are clarified.

[0449] Next, the server generates specific operations based on the instructions using spreadsheet application programs, such as the API of Google Sheets. These operations are performed in concrete forms, such as applying the SUM function to a specific range of cells to calculate the sum.

[0450] After processing is complete, the server sends the results back to the terminal, which visually displays the results to the user. This allows the user to verify that the specified operation was performed correctly. Finally, if the user is not satisfied, they can re-enter new instructions.

[0451] This system eliminates the need for users to learn complex spreadsheet programs, allowing them to easily instruct and perform complex calculations using everyday language. A concrete example of a prompt might be, "Sort column B of the sales record sheet by product name."

[0452] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0453] Step 1:

[0454] Users input instructions using natural language through a dedicated interface. For example, they might input instructions such as, "Sort column A of the expense report sheet in chronological order." This input is processed as text data on the terminal.

[0455] Step 2:

[0456] The terminal sends natural language instructions received from the user to the server. This transmission process involves transferring the entered text data to the server over the network.

[0457] Step 3:

[0458] The server uses a generative AI model to analyze the received text instructions. This model converts the instructions into structured data and analyzes what operations are needed on which sheets and columns. As a result of the analysis, specific elements such as sorting column A by date are extracted. This output is stored as an entity in database format.

[0459] Step 4:

[0460] The server generates API calls for spreadsheet applications based on the parsed structured data. Specifically, it generates API requests for sorting operations. At this stage, necessary data processing is performed, and the output as an API request is prepared.

[0461] Step 5:

[0462] The server executes the generated API request against the spreadsheet application. This operation applies the sorting functionality that should be performed on the selected sheet and columns. The response from the application returns the status of whether the operation was successful or not.

[0463] Step 6:

[0464] After processing is complete, the server sends the final operation result to the terminal. Based on the received information, the terminal visually displays the result to the user. The user can verify on the screen that the sorting results have been performed correctly. This output serves as result confirmation for the user.

[0465] (Application Example 1)

[0466] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0467] In data management operations, there is a particular need to provide an environment that can be operated intuitively, especially by employees who are unfamiliar with technology. Traditional methods require users to learn complex operations, leading to decreased work efficiency and operational errors. A new method is needed to solve this problem.

[0468] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0469] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations for a data processing program, and means for acquiring instructions using speech recognition technology. This enables users to easily perform data management operations using voice instructions, improving the efficiency and accuracy of operations.

[0470] "Instructions entered in natural language" refer to instructions that are formalized in the language that users use on a daily basis.

[0471] "Means of analysis" refers to a function that interprets the instructions in the input natural language and converts its content into a specific structure.

[0472] "Appropriate operation of the data processing program" refers to the process of automatically making necessary changes or updates to the data management software based on the analysis results.

[0473] "Speech recognition technology" is a technology that analyzes spoken words as digital information and obtains them as text information.

[0474] A "visual display device" is a device used to present information to a user visually, and smart glasses are an example of such a device.

[0475] A "knowledge model" is a neural network model built on linguistic data that highly analyzes input sentences and phrases and converts them into structured data.

[0476] "Conditional display" refers to a setting that makes visual changes based on specific conditions being met.

[0477] A "transit device" is a device or system that mediates the transmission and reception of data, and is used when operations are updated via a network.

[0478] A system for carrying out this invention includes a terminal connected to a visual display device (e.g., smart glasses) used by a user. The user gives voice instructions through the visual display device, and voice recognition technology captures these instructions and converts them into digital signals. The converted voice data is transmitted by the terminal to a server.

[0479] The server analyzes the received audio data using a large-scale knowledge model (e.g., BERT) and converts natural language instructions into structured data. Based on the analyzed data, the server generates the necessary operations for a data processing program (e.g., a spreadsheet application). The generated data operations are then executed on the data processing program via an intermediary device.

[0480] Because the results are presented to the user via a visual display device, the user can visually and intuitively confirm the results of data processing. For example, a store staff member can instruct the smart glasses to "update today's sales," and the sales data will be updated in real time. In such demonstrations, an example of a prompt message might be "reduce the chocolate inventory by 10."

[0481] This significantly improves operational efficiency, allowing users to easily manage data without having to learn complex operations.

[0482] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0483] Step 1:

[0484] The user gives voice instructions via a visual display device. Voice recognition technology captures these voice instructions and converts them into digital signals. The input to this process is the user's voice instructions, and the output is digitized voice data. This operation involves voice capture using a voice sensor and digital conversion by a voice signal processing chip.

[0485] Step 2:

[0486] The terminal sends digitized audio data to the server. The input here is the digitized audio data, and the output is the signal indicating successful transmission to the server. Specifically, this involves transferring audio data over a network using a communication module.

[0487] Step 3:

[0488] The server analyzes the audio data using a knowledge model. This analysis converts natural language instructions from the audio data into structured data. The input to this step is the received audio data, and the output is structured instruction data. The operation here involves audio decoding and text analysis processing by the AI ​​model.

[0489] Step 4:

[0490] The server generates operations for a data processing program based on the structured data it analyzes. The input is structured instruction data, and the output is program operation instructions. The operation includes script generation and macro setting based on the analysis results.

[0491] Step 5:

[0492] The generated program operation instructions are executed on the data processing program via an intermediary device. The input for this step is the operation instruction, and the output is an execution completion signal. Specific operations include database updates and calculations using APIs.

[0493] Step 6:

[0494] The server presents the execution results to the user via a visual display device. The input for this step is the execution result data, and the output is visual feedback to the user. Specifically, the result is displayed using a display device.

[0495] Step 7:

[0496] The user reviews the visual results and provides further verbal instructions if needed. The input for this step is visual feedback, and the output is new verbal instructions. This process involves visual evaluation of the results and generation of new instructions.

[0497] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0498] This invention provides a system that allows users to control spreadsheet software using natural language and further recognizes user emotions to adjust the operation content and feedback.

[0499] When using the system, users input the operations they want to perform on the spreadsheet software using natural language. For example, they might give instructions such as "gray out rows where column A is marked 'Completed'." These natural language instructions are first received by the terminal and then sent to the server.

[0500] The server utilizes a large-scale language model to analyze the input natural language. This ensures that the instructions are appropriately converted into structured data, clearly defining the necessary operations. Following this analysis, an operation generation system generates operations in spreadsheet software based on the instructions. The generated operations are then ready for execution via a spreadsheet API.

[0501] Next, an emotion engine that recognizes the user's emotions kicks in. The server extracts emotions from the input and user actions, and then fine-tunes the operation based on the results. For example, if the user is expressing dissatisfaction, the operation is adjusted to provide more detailed feedback or additional help information. In this way, the feedback module provides information in accordance with the user's emotions.

[0502] Ultimately, the device presents the user with the results of the operation and feedback adjusted by the emotion engine. The user reviews the results and continues working if the operation was as intended. If they are not satisfied with the results or if further adjustments are needed, they can enter new instructions.

[0503] Through this method, the present invention enables smooth spreadsheet operations that appropriately reflect the user's instructions and emotions. This system not only supports efficient work but also significantly improves the user experience.

[0504] The following describes the processing flow.

[0505] Step 1:

[0506] Users input instructions for operating the spreadsheet software in natural language. This input is made in text boxes on a dedicated interface and recorded as a document that accurately conveys the user's intent.

[0507] Step 2:

[0508] The terminal receives natural language instructions and sends that data to the server. During this process, the input data is converted to an appropriate format, making it ready for processing on the server.

[0509] Step 3:

[0510] The server passes the received natural language data to the analysis module, which then analyzes the instructions. A large-scale language model structures the text into data, extracting elements such as the target of the operation and the conditions.

[0511] Step 4:

[0512] The server uses an emotion engine to extract emotional information from user input. This emotional information indicates how the user is feeling and is reflected in the system's response.

[0513] Step 5:

[0514] The server generates appropriate operations for spreadsheet software based on analysis results and emotional information. The generating AI model fine-tunes the operations, especially based on emotional information, to produce the optimal result for the user.

[0515] Step 6:

[0516] The server sends the generated operations to the spreadsheet API, which then executes the operations on the spreadsheet software. This includes, for example, applying conditional formatting and updating cell data.

[0517] Step 7:

[0518] The server sends the execution results and adjusted feedback to the terminal. The results include not only success or failure information, but also explanations and support information that take the user's feelings into consideration.

[0519] Step 8:

[0520] The terminal displays the results and feedback received from the server to the user. Visual feedback shows how the operation was performed, allowing the user to decide on the next steps as needed.

[0521] This system process enables users to operate spreadsheet software in an efficient and emotionally resonant way.

[0522] (Example 2)

[0523] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0524] Traditional spreadsheet software has limitations in terms of complexity and learning curve because users cannot input instructions in natural language. Furthermore, the lack of systems that provide real-time feedback that takes user emotions into account limits the potential for improving the user experience.

[0525] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0526] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations on digital data, and means for recognizing the user's emotions and adjusting the operation content and feedback accordingly. This makes it possible for the user to give instructions in natural language and receive appropriate operations and feedback according to their emotions.

[0527] "Natural language" refers to the language that humans use on a daily basis, and its purpose is to be converted into a format that machines can understand.

[0528] An "analysis tool" is a device that analyzes input information, extracts meaning and intent, and converts it into a format that can be used for subsequent processing.

[0529] "Digital data" is a general term for information stored in digital format, and it is the subject to which specific operations are performed.

[0530] An "operation generation means" is a device that has the function of automatically constructing specific processing procedures based on analyzed information and making them executable.

[0531] "Emotion recognition" refers to technology that estimates a user's emotional state based on their input and actions.

[0532] "Feedback" refers to the information output from a system that provides users with operational results and additional information to improve the user experience.

[0533] This invention provides a system that automatically performs operations on digital data by receiving instructions entered by the user in natural language. The aim of this system is to provide the user with a more intuitive operating environment, achieve efficient data processing, and improve the user experience by recognizing the user's emotions and adjusting the feedback accordingly.

[0534] The following hardware and software are used to implement this system. Natural language instructions are entered via a user-operated terminal, such as a personal computer or mobile device. The terminal transmits the input data to a server via a network. The server uses a large-scale language model known as a generative AI model to analyze the natural language instructions and convert them into structured data. Based on this analysis, it generates appropriate digital data operations.

[0535] As a concrete example, a user-inputted prompt might be, "Gray out rows where column A is marked 'Completed'." This instruction is received by the terminal and sent to the server. On the server, a generating AI model analyzes the instruction and generates an operation to apply conditional formatting to the relevant rows to gray them out. In this process, a spreadsheet API or similar tool would be used.

[0536] Furthermore, emotion recognition software installed on the server analyzes the user's emotions based on their input and operation history, and adjusts the feedback module accordingly. This allows for the provision of user-specific information, such as providing additional explanations if the user indicates discomfort.

[0537] Ultimately, the device displays feedback to the user that is tailored to the results of the actions performed and the user's emotions. The user can review the results, verify that they are the intended outcome, and then provide further instructions if necessary. Thus, this system is characterized by providing flexible operation in response to user instructions via natural language and returning responses that take the user's emotions into consideration.

[0538] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0539] Step 1:

[0540] The user inputs the desired action in natural language. For example, they might enter a prompt such as, "Gray out rows where column A is marked 'Completed'." The terminal receives the input natural language instruction.

[0541] Step 2:

[0542] The terminal sends the input instructions to the server. Here, the input text data is processed to be sent to the server as an HTTP request, and the request is output.

[0543] Step 3:

[0544] The server analyzes the received natural language instructions using a generative AI model. Here, natural language processing is performed to convert the instructions into structured data that a machine can understand. This process yields the converted data as output.

[0545] Step 4:

[0546] The server generates specific operations on the digital data based on the parsed instructions. It uses the spreadsheet API to construct instructions for applying conditional formatting to specified cells. At this stage, specific operation instructions are output.

[0547] Step 5:

[0548] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's input and interaction history, and extracts the emotional state from the obtained data. Based on these results, feedback and adjustments to subsequent actions are made.

[0549] Step 6:

[0550] The server fine-tunes the actions and feedback based on the recognized emotions. It determines whether additional comments or explanations are needed, adjusts the actions accordingly, and then outputs the feedback.

[0551] Step 7:

[0552] The terminal displays the user the operation results sent from the server and the adjusted feedback. Specifically, the updated status of the spreadsheet is displayed on the screen, and feedback is indicated through pop-up messages or other means.

[0553] Step 8:

[0554] The user reviews the results and determines if the operation was performed as intended. If the results are not as intended or if additional changes are needed, they can enter new instructions to request the next action.

[0555] (Application Example 2)

[0556] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0557] Conventional data management systems do not fully utilize natural language operation instructions, making it difficult for users to operate them intuitively and efficiently. Furthermore, the lack of feedback and operation adjustments that respond to user emotions results in a limited user experience, which is a significant challenge.

[0558] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0559] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations on a data processing structure based on the instructions, and means for recognizing the user's emotions from the input information. This enables the user to intuitively give instructions in natural language and receive optimal operations and feedback that correspond to their emotions based on those instructions.

[0560] "Natural language" refers to the language that humans use in everyday life, enabling intuitive input of instructions into a system.

[0561] "Means of analysis" refers to techniques that understand natural language instructions and convert them into appropriately structured data.

[0562] "Data processing structure" refers to the target dataset or database, which is the object of the operation.

[0563] "Means for generating operations" refers to techniques for designing specific actions to be performed on data based on instructions in analyzed natural language.

[0564] "Means of recognizing emotions" refers to technologies that determine a user's emotional state from their input and actions.

[0565] "Means of adjusting feedback" refers to methods of optimizing the information and responses presented to the user in accordance with the perceived emotions.

[0566] "Execution result" refers to the final output of operations performed on the data processing structure based on the instructions.

[0567] A "user" refers to an entity that uses this system to send instructions in natural language and receive feedback.

[0568] The system to realize this application combines a large-scale language model for natural language processing with an analysis engine for recognizing emotions. Specifically, the user inputs instructions in natural language via a terminal. For example, they might give a specific instruction such as, "We're running low on milk, please add it to the shopping list."

[0569] The terminal receives this instruction and forwards it to the server. The server uses a large-scale language model as an analysis tool to analyze the input natural language and convert the instruction into structured data. For example, a generative AI model such as OpenAI's GPT-4 is used for this purpose. Next, an operation generation tool designs a data processing structure, such as an operation on an inventory management list, based on the analysis results.

[0570] Furthermore, the server uses an emotion analysis engine as a means of recognizing emotions. Leveraging technologies like Microsoft's Emotion API, it infers emotions from the user's voice and facial expressions. Then, through mechanisms to adjust feedback, it provides appropriate responses, additional advice, and feedback to the user based on their emotions.

[0571] Ultimately, the user is presented with feedback that reflects the results and their emotions. This allows the user to confirm whether the action was performed as intended and to provide additional instructions if necessary.

[0572] For example, if a user says, "The weather is nice, so I want to go for a walk," the server analyzes this information and provides the most appropriate feedback. An example of a prompt would be, "User said: 'The weather is nice, so I want to go for a walk.' What task should the robot perform based on this statement?" This would be input to the language model.

[0573] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0574] Step 1:

[0575] The user inputs natural language instructions via the terminal. The input data includes specific phrases such as "We're running low on milk, please add it to the shopping list." This instruction is used as input for the next process. The terminal receives this voice or text input and prepares to send it to the server as digital data.

[0576] Step 2:

[0577] The terminal transfers the input instruction data to the server. The server's role here is to receive this transferred data. After receiving the data, the server prepares to use a large-scale language model to analyze the input. The output at this step is the instruction data itself to be analyzed.

[0578] Step 3:

[0579] The server uses a large-scale language model to parse the received natural language instructions. This analysis converts the natural language instructions into structured data. The model interprets the meaning of the instructions and generates operation instructions for the data processing structure based on this interpretation. The input to this step is natural language instruction data, and the output is the parsed structured data.

[0580] Step 4:

[0581] The server uses the generated structured data to create operations. Specifically, it designs concrete actions such as "add milk to the list" in the inventory management list. The input in this step is the structured data that was the output in step 3, and the output is the operation instruction.

[0582] Step 5:

[0583] The server determines the user's emotions using means of emotion recognition. Inputs include natural language indications such as tone and related metadata. An emotion analysis engine is used here to generate data about the user's current emotional state. The output is the emotion recognition result.

[0584] Step 6:

[0585] The server fine-tunes feedback and instructions based on the results of emotion recognition. This adjustment process involves designing additional, gentle, and reassuring feedback if the user is experiencing stress or anxiety. The input is emotional state data, and the output is the adjusted feedback message.

[0586] Step 7:

[0587] The server sends the execution results and adjusted feedback back to the terminal. The terminal then presents these results to the user, either visually or audibly. This may include messages such as, "Milk has been added to the list," or "Is there anything else I can help you with?" The output is the final result and feedback presented to the user.

[0588] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0589] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0590] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0591] [Fourth Embodiment]

[0592] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0593] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0594] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0595] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0596] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0597] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0598] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0599] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0600] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0601] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0602] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0603] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0604] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0605] The system of the present invention analyzes instructions input in natural language and generates and executes appropriate operations on spreadsheet software based on those instructions.

[0606] At the initial stage of the system, the user inputs instructions for the spreadsheet software in natural language using a dedicated interface. These instructions should describe in detail the operations the user intends to perform, such as setting specific functions or changing cell formatting.

[0607] Next, the terminal sends the input natural language instruction to the server. The server then starts a process to analyze the received instruction. This analysis uses natural language processing techniques to break down the instruction into specific elements. For example, it extracts information such as which column or row the operation is performed on and what criteria to use.

[0608] Subsequently, the server evaluates the elements generated from the analysis results through a large-scale language model and generates the necessary spreadsheet software operations. This creates spreadsheet software functions and configuration methods optimized for the user's instructions. At this stage, the server prepares to execute the generated operations using a spreadsheet API.

[0609] Furthermore, the server executes operations set up in the spreadsheet software via the spreadsheet API. For example, it automatically applies conditional formatting such as "gray out rows where column A is 'Completed'."

[0610] After processing is complete, the server sends the operation results to the terminal, which visually displays the results to the user. This allows the user to see how their instructions were carried out and, if they are not satisfied with the results, to enter new instructions.

[0611] Thus, the present invention provides a means for users to intuitively and efficiently operate spreadsheet software without having to learn complex functions or settings. This not only improves work efficiency but also enhances the user experience.

[0612] The following describes the processing flow.

[0613] Step 1:

[0614] The user enters the operation they want to perform on the spreadsheet software in natural language. The instructions entered in the text boxes on the interface become the initial data.

[0615] Step 2:

[0616] The terminal receives the input natural language data and prepares to send that data to the server as a digital message. The crucial point here is to format the data in a way that the server can interpret.

[0617] Step 3:

[0618] The server passes the message received from the terminal to the parsing module. This module uses natural language processing techniques to convert the text into structured data. Specifically, it extracts elements such as the columns and cells to be manipulated and the conditions to be applied.

[0619] Step 4:

[0620] The server uses a generative AI model to generate operations to be executed in spreadsheet software based on the elements obtained from the analysis. In this process, for example, a large-scale language model derives how to apply conditional formatting and functions.

[0621] Step 5:

[0622] The server sends the generated operations to the spreadsheet API. This API receives the operation instructions and applies the settings to the spreadsheet software in real time. Operations based on the user's intent are executed here.

[0623] Step 6:

[0624] The server collects the status of the execution results and generates success or error messages. This information is configured to allow the user to check the results of the operation through a feedback module.

[0625] Step 7:

[0626] The terminal displays feedback information received from the server to the user. The results are displayed in visual or text format, which the user reviews and enters additional instructions if necessary.

[0627] (Example 1)

[0628] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0629] Operating current spreadsheet programs requires specialized knowledge, and setting conditional formatting and using certain functions, in particular, can often be complex for the average user. Therefore, there is a need for a system that allows users to intuitively operate spreadsheet programs using natural language.

[0630] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0631] In this invention, the server includes means for analyzing instructions input in natural language and breaking down the instruction content into specific elements, means for generating appropriate operations for a spreadsheet program using a generative artificial intelligence model, and means for communicating via an interface to execute the generated operations on a spreadsheet application program. This makes it possible for users to intuitively and efficiently operate a spreadsheet program in natural language without having to learn complex operations.

[0632] "Natural language" refers to the words and sentences that humans use in everyday life, and is the form used when giving instructions to a system.

[0633] A "generative artificial intelligence model" is an algorithm that uses large datasets to understand natural language and generate appropriate responses and actions.

[0634] A "spreadsheet application program" is software intended for organizing, calculating, and visualizing data, and generally allows for spreadsheet calculations and graph creation.

[0635] "Communicating via an interface" refers to protocols and connection methods used to exchange data between information systems and devices.

[0636] This invention provides a system for users to intuitively operate spreadsheet software. This system analyzes instructions entered in natural language and generates and executes appropriate operations on the spreadsheet program based on those instructions.

[0637] Users input information in natural language through a dedicated interface. For example, they can enter instructions such as, "Calculate the total for each month in the sales data sheet." The terminal receives these instructions and immediately sends them to the server.

[0638] The server uses a generative artificial intelligence model to analyze the instructions it receives. This model is a large-scale language model that breaks down natural language instructions into specific elements, creating a foundation for generating appropriate operations. During the analysis process, elements such as which data range to manipulate and what calculations to perform are clarified.

[0639] Next, the server generates specific operations based on the instructions using spreadsheet application programs, such as the API of Google Sheets. These operations are performed in concrete forms, such as applying the SUM function to a specific range of cells to calculate the sum.

[0640] After processing is complete, the server sends the results back to the terminal, which visually displays the results to the user. This allows the user to verify that the specified operation was performed correctly. Finally, if the user is not satisfied, they can re-enter new instructions.

[0641] This system eliminates the need for users to learn complex spreadsheet programs, allowing them to easily instruct and perform complex calculations using everyday language. A concrete example of a prompt might be, "Sort column B of the sales record sheet by product name."

[0642] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0643] Step 1:

[0644] Users input instructions using natural language through a dedicated interface. For example, they might input instructions such as, "Sort column A of the expense report sheet in chronological order." This input is processed as text data on the terminal.

[0645] Step 2:

[0646] The terminal sends natural language instructions received from the user to the server. This transmission process involves transferring the entered text data to the server over the network.

[0647] Step 3:

[0648] The server uses a generative AI model to analyze the received text instructions. This model converts the instructions into structured data and analyzes what operations are needed on which sheets and columns. As a result of the analysis, specific elements such as sorting column A by date are extracted. This output is stored as an entity in database format.

[0649] Step 4:

[0650] The server generates API calls for spreadsheet applications based on the parsed structured data. Specifically, it generates API requests for sorting operations. At this stage, necessary data processing is performed, and the output as an API request is prepared.

[0651] Step 5:

[0652] The server executes the generated API request against the spreadsheet application. This operation applies the sorting functionality that should be performed on the selected sheet and columns. The response from the application returns the status of whether the operation was successful or not.

[0653] Step 6:

[0654] After processing is complete, the server sends the final operation result to the terminal. Based on the received information, the terminal visually displays the result to the user. The user can verify on the screen that the sorting results have been performed correctly. This output serves as result confirmation for the user.

[0655] (Application Example 1)

[0656] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0657] In data management operations, there is a particular need to provide an environment that can be operated intuitively, especially by employees who are unfamiliar with technology. Traditional methods require users to learn complex operations, leading to decreased work efficiency and operational errors. A new method is needed to solve this problem.

[0658] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0659] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations for a data processing program, and means for acquiring instructions using speech recognition technology. This enables users to easily perform data management operations using voice instructions, improving the efficiency and accuracy of operations.

[0660] "Instructions entered in natural language" refer to instructions that are formalized in the language that users use on a daily basis.

[0661] "Means of analysis" refers to a function that interprets the instructions in the input natural language and converts its content into a specific structure.

[0662] "Appropriate operation of the data processing program" refers to the process of automatically making necessary changes or updates to the data management software based on the analysis results.

[0663] "Speech recognition technology" is a technology that analyzes spoken words as digital information and obtains them as text information.

[0664] A "visual display device" is a device used to present information to a user visually, and smart glasses are an example of such a device.

[0665] A "knowledge model" is a neural network model built on linguistic data that highly analyzes input sentences and phrases and converts them into structured data.

[0666] "Conditional display" refers to a setting that makes visual changes based on specific conditions being met.

[0667] A "transit device" is a device or system that mediates the transmission and reception of data, and is used when operations are updated via a network.

[0668] A system for carrying out this invention includes a terminal connected to a visual display device (e.g., smart glasses) used by a user. The user gives voice instructions through the visual display device, and voice recognition technology captures these instructions and converts them into digital signals. The converted voice data is transmitted by the terminal to a server.

[0669] The server analyzes the received audio data using a large-scale knowledge model (e.g., BERT) and converts natural language instructions into structured data. Based on the analyzed data, the server generates the necessary operations for a data processing program (e.g., a spreadsheet application). The generated data operations are then executed on the data processing program via an intermediary device.

[0670] Because the results are presented to the user via a visual display device, the user can visually and intuitively confirm the results of data processing. For example, a store staff member can instruct the smart glasses to "update today's sales," and the sales data will be updated in real time. In such demonstrations, an example of a prompt message might be "reduce the chocolate inventory by 10."

[0671] This significantly improves operational efficiency, allowing users to easily manage data without having to learn complex operations.

[0672] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0673] Step 1:

[0674] The user gives voice instructions via a visual display device. Voice recognition technology captures these voice instructions and converts them into digital signals. The input to this process is the user's voice instructions, and the output is digitized voice data. This operation involves voice capture using a voice sensor and digital conversion by a voice signal processing chip.

[0675] Step 2:

[0676] The terminal sends digitized audio data to the server. The input here is the digitized audio data, and the output is the signal indicating successful transmission to the server. Specifically, this involves transferring audio data over a network using a communication module.

[0677] Step 3:

[0678] The server analyzes the audio data using a knowledge model. This analysis converts natural language instructions from the audio data into structured data. The input to this step is the received audio data, and the output is structured instruction data. The operation here involves audio decoding and text analysis processing by the AI ​​model.

[0679] Step 4:

[0680] The server generates operations for a data processing program based on the structured data it analyzes. The input is structured instruction data, and the output is program operation instructions. The operation includes script generation and macro setting based on the analysis results.

[0681] Step 5:

[0682] The generated program operation instructions are executed on the data processing program via an intermediary device. The input for this step is the operation instruction, and the output is an execution completion signal. Specific operations include database updates and calculations using APIs.

[0683] Step 6:

[0684] The server presents the execution results to the user via a visual display device. The input for this step is the execution result data, and the output is visual feedback to the user. Specifically, the result is displayed using a display device.

[0685] Step 7:

[0686] The user reviews the visual results and provides further verbal instructions if needed. The input for this step is visual feedback, and the output is new verbal instructions. This process involves visual evaluation of the results and generation of new instructions.

[0687] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0688] This invention provides a system that allows users to control spreadsheet software using natural language and further recognizes user emotions to adjust the operation content and feedback.

[0689] When using the system, users input the operations they want to perform on the spreadsheet software using natural language. For example, they might give instructions such as "gray out rows where column A is marked 'Completed'." These natural language instructions are first received by the terminal and then sent to the server.

[0690] The server utilizes a large-scale language model to analyze the input natural language. This ensures that the instructions are appropriately converted into structured data, clearly defining the necessary operations. Following this analysis, an operation generation system generates operations in spreadsheet software based on the instructions. The generated operations are then ready for execution via a spreadsheet API.

[0691] Next, an emotion engine that recognizes the user's emotions kicks in. The server extracts emotions from the input and user actions, and then fine-tunes the operation based on the results. For example, if the user is expressing dissatisfaction, the operation is adjusted to provide more detailed feedback or additional help information. In this way, the feedback module provides information in accordance with the user's emotions.

[0692] Ultimately, the device presents the user with the results of the operation and feedback adjusted by the emotion engine. The user reviews the results and continues working if the operation was as intended. If they are not satisfied with the results or if further adjustments are needed, they can enter new instructions.

[0693] Through this method, the present invention enables smooth spreadsheet operations that appropriately reflect the user's instructions and emotions. This system not only supports efficient work but also significantly improves the user experience.

[0694] The following describes the processing flow.

[0695] Step 1:

[0696] Users input instructions for operating the spreadsheet software in natural language. This input is made in text boxes on a dedicated interface and recorded as a document that accurately conveys the user's intent.

[0697] Step 2:

[0698] The terminal receives natural language instructions and sends that data to the server. During this process, the input data is converted to an appropriate format, making it ready for processing on the server.

[0699] Step 3:

[0700] The server passes the received natural language data to the analysis module, which then analyzes the instructions. A large-scale language model structures the text into data, extracting elements such as the target of the operation and the conditions.

[0701] Step 4:

[0702] The server uses an emotion engine to extract emotional information from user input. This emotional information indicates how the user is feeling and is reflected in the system's response.

[0703] Step 5:

[0704] The server generates appropriate operations for spreadsheet software based on analysis results and emotional information. The generating AI model fine-tunes the operations, especially based on emotional information, to produce the optimal result for the user.

[0705] Step 6:

[0706] The server sends the generated operations to the spreadsheet API, which then executes the operations on the spreadsheet software. This includes, for example, applying conditional formatting and updating cell data.

[0707] Step 7:

[0708] The server sends the execution results and adjusted feedback to the terminal. The results include not only success or failure information, but also explanations and support information that take the user's feelings into consideration.

[0709] Step 8:

[0710] The terminal displays the results and feedback received from the server to the user. Visual feedback shows how the operation was performed, allowing the user to decide on the next steps as needed.

[0711] This system process enables users to operate spreadsheet software in an efficient and emotionally resonant way.

[0712] (Example 2)

[0713] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0714] Traditional spreadsheet software has limitations in terms of complexity and learning curve because users cannot input instructions in natural language. Furthermore, the lack of systems that provide real-time feedback that takes user emotions into account limits the potential for improving the user experience.

[0715] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0716] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations on digital data, and means for recognizing the user's emotions and adjusting the operation content and feedback accordingly. This makes it possible for the user to give instructions in natural language and receive appropriate operations and feedback according to their emotions.

[0717] "Natural language" refers to the language that humans use on a daily basis, and its purpose is to be converted into a format that machines can understand.

[0718] An "analysis tool" is a device that analyzes input information, extracts meaning and intent, and converts it into a format that can be used for subsequent processing.

[0719] "Digital data" is a general term for information stored in digital format, and it is the subject to which specific operations are performed.

[0720] An "operation generation means" is a device that has the function of automatically constructing specific processing procedures based on analyzed information and making them executable.

[0721] "Emotion recognition" refers to technology that estimates a user's emotional state based on their input and actions.

[0722] "Feedback" refers to the information output from a system that provides users with operational results and additional information to improve the user experience.

[0723] This invention provides a system that automatically performs operations on digital data by receiving instructions entered by the user in natural language. The aim of this system is to provide the user with a more intuitive operating environment, achieve efficient data processing, and improve the user experience by recognizing the user's emotions and adjusting the feedback accordingly.

[0724] The following hardware and software are used to implement this system. Natural language instructions are entered via a user-operated terminal, such as a personal computer or mobile device. The terminal transmits the input data to a server via a network. The server uses a large-scale language model known as a generative AI model to analyze the natural language instructions and convert them into structured data. Based on this analysis, it generates appropriate digital data operations.

[0725] As a concrete example, a user-inputted prompt might be, "Gray out rows where column A is marked 'Completed'." This instruction is received by the terminal and sent to the server. On the server, a generating AI model analyzes the instruction and generates an operation to apply conditional formatting to the relevant rows to gray them out. In this process, a spreadsheet API or similar tool would be used.

[0726] Furthermore, emotion recognition software installed on the server analyzes the user's emotions based on their input and operation history, and adjusts the feedback module accordingly. This allows for the provision of user-specific information, such as providing additional explanations if the user indicates discomfort.

[0727] Ultimately, the device displays feedback to the user that is tailored to the results of the actions performed and the user's emotions. The user can review the results, verify that they are the intended outcome, and then provide further instructions if necessary. Thus, this system is characterized by providing flexible operation in response to user instructions via natural language and returning responses that take the user's emotions into consideration.

[0728] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0729] Step 1:

[0730] The user inputs the desired action in natural language. For example, they might enter a prompt such as, "Gray out rows where column A is marked 'Completed'." The terminal receives the input natural language instruction.

[0731] Step 2:

[0732] The terminal sends the input instructions to the server. Here, the input text data is processed to be sent to the server as an HTTP request, and the request is output.

[0733] Step 3:

[0734] The server analyzes the received natural language instructions using a generative AI model. Here, natural language processing is performed to convert the instructions into structured data that a machine can understand. This process yields the converted data as output.

[0735] Step 4:

[0736] The server generates specific operations on the digital data based on the parsed instructions. It uses the spreadsheet API to construct instructions for applying conditional formatting to specified cells. At this stage, specific operation instructions are output.

[0737] Step 5:

[0738] The server uses an emotion engine to recognize the user's emotions. It analyzes the user's input and interaction history, and extracts the emotional state from the obtained data. Based on these results, feedback and adjustments to subsequent actions are made.

[0739] Step 6:

[0740] The server fine-tunes the actions and feedback based on the recognized emotions. It determines whether additional comments or explanations are needed, adjusts the actions accordingly, and then outputs the feedback.

[0741] Step 7:

[0742] The terminal displays the user the operation results sent from the server and the adjusted feedback. Specifically, the updated status of the spreadsheet is displayed on the screen, and feedback is indicated through pop-up messages or other means.

[0743] Step 8:

[0744] The user reviews the results and determines if the operation was performed as intended. If the results are not as intended or if additional changes are needed, they can enter new instructions to request the next action.

[0745] (Application Example 2)

[0746] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0747] Conventional data management systems do not fully utilize natural language operation instructions, making it difficult for users to operate them intuitively and efficiently. Furthermore, the lack of feedback and operation adjustments that respond to user emotions results in a limited user experience, which is a significant challenge.

[0748] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0749] In this invention, the server includes means for analyzing instructions input in natural language, means for generating appropriate operations on a data processing structure based on the instructions, and means for recognizing the user's emotions from the input information. This enables the user to intuitively give instructions in natural language and receive optimal operations and feedback that correspond to their emotions based on those instructions.

[0750] "Natural language" refers to the language that humans use in everyday life, enabling intuitive input of instructions into a system.

[0751] "Means of analysis" refers to techniques that understand natural language instructions and convert them into appropriately structured data.

[0752] "Data processing structure" refers to the target dataset or database, which is the object of the operation.

[0753] "Means for generating operations" refers to techniques for designing specific actions to be performed on data based on instructions in analyzed natural language.

[0754] "Means of recognizing emotions" refers to technologies that determine a user's emotional state from their input and actions.

[0755] "Means of adjusting feedback" refers to methods of optimizing the information and responses presented to the user in accordance with the perceived emotions.

[0756] "Execution result" refers to the final output of operations performed on the data processing structure based on the instructions.

[0757] A "user" refers to an entity that uses this system to send instructions in natural language and receive feedback.

[0758] The system to realize this application combines a large-scale language model for natural language processing with an analysis engine for recognizing emotions. Specifically, the user inputs instructions in natural language via a terminal. For example, they might give a specific instruction such as, "We're running low on milk, please add it to the shopping list."

[0759] The terminal receives this instruction and forwards it to the server. The server uses a large-scale language model as an analysis tool to analyze the input natural language and convert the instruction into structured data. For example, a generative AI model such as OpenAI's GPT-4 is used for this purpose. Next, an operation generation tool designs a data processing structure, such as an operation on an inventory management list, based on the analysis results.

[0760] Furthermore, the server uses an emotion analysis engine as a means of recognizing emotions. Leveraging technologies like Microsoft's Emotion API, it infers emotions from the user's voice and facial expressions. Then, through mechanisms to adjust feedback, it provides appropriate responses, additional advice, and feedback to the user based on their emotions.

[0761] Ultimately, the user is presented with feedback that reflects the results and their emotions. This allows the user to confirm whether the action was performed as intended and to provide additional instructions if necessary.

[0762] For example, if a user says, "The weather is nice, so I want to go for a walk," the server analyzes this information and provides the most appropriate feedback. An example of a prompt would be, "User said: 'The weather is nice, so I want to go for a walk.' What task should the robot perform based on this statement?" This would be input to the language model.

[0763] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0764] Step 1:

[0765] The user inputs natural language instructions via the terminal. The input data includes specific phrases such as "We're running low on milk, please add it to the shopping list." This instruction is used as input for the next process. The terminal receives this voice or text input and prepares to send it to the server as digital data.

[0766] Step 2:

[0767] The terminal transfers the input instruction data to the server. The server's role here is to receive this transferred data. After receiving the data, the server prepares to use a large-scale language model to analyze the input. The output at this step is the instruction data itself to be analyzed.

[0768] Step 3:

[0769] The server uses a large-scale language model to parse the received natural language instructions. This analysis converts the natural language instructions into structured data. The model interprets the meaning of the instructions and generates operation instructions for the data processing structure based on this interpretation. The input to this step is natural language instruction data, and the output is the parsed structured data.

[0770] Step 4:

[0771] The server uses the generated structured data to create operations. Specifically, it designs concrete actions such as "add milk to the list" in the inventory management list. The input in this step is the structured data that was the output in step 3, and the output is the operation instruction.

[0772] Step 5:

[0773] The server determines the user's emotions using means of emotion recognition. Inputs include natural language indications such as tone and related metadata. An emotion analysis engine is used here to generate data about the user's current emotional state. The output is the emotion recognition result.

[0774] Step 6:

[0775] The server fine-tunes feedback and instructions based on the results of emotion recognition. This adjustment process involves designing additional, gentle, and reassuring feedback if the user is experiencing stress or anxiety. The input is emotional state data, and the output is the adjusted feedback message.

[0776] Step 7:

[0777] The server sends the execution results and adjusted feedback back to the terminal. The terminal then presents these results to the user, either visually or audibly. This may include messages such as, "Milk has been added to the list," or "Is there anything else I can help you with?" The output is the final result and feedback presented to the user.

[0778] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0779] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0780] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0781] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0782] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0783] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0784] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0785] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0786] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0787] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0788] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0789] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0790] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0791] 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.

[0792] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0793] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0794] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0795] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0796] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0797] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0798] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0799] The following is further disclosed regarding the embodiments described above.

[0800] (Claim 1)

[0801] A means of analyzing instructions input in natural language,

[0802] Means for generating appropriate operations on spreadsheet data based on the above instructions,

[0803] Means for executing the generated operation on a spreadsheet program,

[0804] A means for presenting the execution result to the user,

[0805] A system that includes this.

[0806] (Claim 2)

[0807] The system according to claim 1, characterized in that the analysis means converts natural language instructions into structured data using a large-scale language model.

[0808] (Claim 3)

[0809] The system according to claim 1, characterized in that the operation generation means includes an operation to set conditional formatting.

[0810] "Example 1"

[0811] (Claim 1)

[0812] A means for analyzing instructions input in natural language and breaking down the content of the instructions into specific elements,

[0813] Based on the above instructions, means for generating appropriate operations for a spreadsheet program using a generative artificial intelligence model,

[0814] Means for communicating via an interface in order to execute the generated operation on a spreadsheet application program,

[0815] A means for transmitting the execution result to a terminal and presenting it visually to the user,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, characterized in that the analysis means converts natural language instructions into structured data using a large-scale language model and determines an action based on that data.

[0819] (Claim 3)

[0820] The system according to claim 1, characterized in that the operation generation means performs an operation to set conditional formatting based on the generated analysis elements and prompt statements.

[0821] "Application Example 1"

[0822] (Claim 1)

[0823] A means of analyzing instructions input in natural language,

[0824] Means for generating appropriate operations for a data processing program based on the above instructions,

[0825] Means for executing the generated operation on a data processing program,

[0826] A means for presenting the execution result to the user via a visual display device,

[0827] A means of obtaining instructions using speech recognition technology,

[0828] Means for updating the program operation via an intermediary device,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, characterized in that the analysis means converts natural language instructions into a structured form using a knowledge model.

[0832] (Claim 3)

[0833] The system according to claim 1, characterized in that the operation generation means includes an operation to set a conditional display.

[0834] "Example 2 of combining an emotion engine"

[0835] (Claim 1)

[0836] A means of analyzing instructions input in natural language,

[0837] Means for generating appropriate operations on digital data based on the above instructions,

[0838] Means for performing the generated operation,

[0839] A means of recognizing user emotions and adjusting actions and feedback,

[0840] A means for presenting the aforementioned execution results and feedback after emotion adjustment to the user,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, characterized in that the analysis means converts natural language instructions into structured data using a large-scale language model.

[0844] (Claim 3)

[0845] The system according to claim 1, characterized in that the operation generation means includes an operation to set conditional formatting.

[0846] "Application example 2 when combining with an emotional engine"

[0847] (Claim 1)

[0848] A means of analyzing instructions input in natural language,

[0849] Means for generating appropriate operations on a data processing structure based on the above instructions,

[0850] Means for executing the generated operation on a data management program,

[0851] A means of recognizing the user's emotions from the input information,

[0852] Means for adjusting operations and feedback based on the results of the aforementioned emotion recognition,

[0853] A means for presenting the aforementioned execution results and adjusted feedback to the user,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, characterized in that the analysis means converts natural language instructions into structured data using a large-scale language model.

[0857] (Claim 3)

[0858] The system according to claim 1, characterized in that the operation generating means includes an operation that provides an adaptive reaction. [Explanation of Symbols]

[0859] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing instructions input in natural language, Means for generating appropriate operations for a data processing program based on the above instructions, Means for executing the generated operation on a data processing program, A means for presenting the execution result to the user via a visual display device, A means of obtaining instructions using speech recognition technology, Means for updating the program operation via an intermediary device, A system that includes this.

2. The system according to claim 1, characterized in that the analysis means converts natural language instructions into a structured form using a knowledge model.

3. The system according to claim 1, characterized in that the operation generation means includes an operation to set a conditional display.

Images