System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving input data from a user and executing a calculation process, a means for automatically transmitting the result of the calculation process through a designated communication means, a means for collecting data for business efficiency improvement from a plurality of general sections and proposing further efficiency improvement by using a generation system AI, and a means for generating a fixed calculation program based on the proposal and sharing it among the general sections.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's business environment, data analysis and reporting of the results are important tasks. However, manual data collection, calculation processing, and reporting require a great deal of time and effort, making it necessary to automate and streamline these processes. Furthermore, it is difficult to share and standardize the business efficiency initiatives that each department implements independently. Furthermore, the application of efficiency proposals using generative AI is limited, resulting in a lack of means to further improve business efficiency. It is necessary to resolve these issues and improve business efficiency. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving input data from a user and performing calculations, a means for automatically transmitting the results of the calculations via a specified communication method, a means for collecting business efficiency data from multiple management departments and using generative AI to propose further efficiency improvements, and a means for generating standard calculation programs based on the proposals and sharing them among the management departments. The system also includes triggers for periodically executing calculations based on date and time, and a means for acquiring spreadsheet data and performing multiple calculations on that data. This system centrally manages and automates processes from data collection to reporting, significantly improving business efficiency. Furthermore, the use of generative AI enables continuous business efficiency improvements to be proposed and implemented.

[0006] "User" refers to the entity that operates the system, such as an individual or organization that provides input data and sets triggers.

[0007] "Input data" refers to information such as numbers and text that a user provides to a system, and is the data that is the subject of calculation processing.

[0008] A "computation" is a specific mathematical or logical operation performed on input data, such as calculating the mean or standard deviation.

[0009] "Communication means" refers to means such as email, messaging applications, and social media used to transmit the results of computational processing.

[0010] "Automatic transmission" refers to the function of the system to transmit the results of a computation to a designated recipient via a communication means without requiring manual operation by the user.

[0011] A "governing body" is a department or section within an organization that is responsible for a particular task or project.

[0012] "Business efficiency" refers to reducing work time and costs and improving overall efficiency by reviewing business processes and automating and optimizing them.

[0013] "Generative AI" is a type of artificial intelligence that refers to a system that generates new proposals and solutions based on given data and information.

[0014] A "standard calculation program" refers to a standard calculation procedure or script defined for a specific task or calculation process.

[0015] A "trigger" is a mechanism that automatically starts a system's operation based on a specific time or condition.

[0016] "Spreadsheet data" refers to numerical and text data organized in a tabular format and managed using spreadsheet software (e.g., Google (registered trademark) Sheets or MICROSOFT (registered trademark) EXCEL (registered trademark)). [Brief explanation of the drawings]

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

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

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

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

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

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

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

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

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

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

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0038] This system allows users to input data, automatically performs calculations on that data, and automatically transmits the results. It also includes functions to collect data on business efficiency improvements from each department, use generative AI to propose further efficiency improvements, generate standard calculation programs based on those proposals, and share them among departments.

[0039] Generating a Program

[0040] The program for this system is implemented using Google Apps Script (GAS) and Excel macros. The program is structured as follows:

[0041] 1. Data Collection:

[0042] Users enter the required data into a Google spreadsheet or Excel file.

[0043] The server accesses the specified spreadsheet or Excel file and retrieves data from the specified range.

[0044] 2. Performing the calculation:

[0045] The server performs calculations (e.g., average, standard deviation, etc.) set by the user on the acquired data.

[0046] 3. Formatting and sending the results:

[0047] The server formats the results of the computation and automatically transmits them via the specified communication method (e.g., email, messaging application).

[0048] As a concrete example, consider a spreadsheet where a user has entered sales data into the range "A1:A10." The server retrieves this data, calculates the average sales amount for each cell, and then formats and emails the results to designated recipients as a daily report.

[0049] AI-based efficiency proposals

[0050] Data on business efficiency improvements collected by each department is stored on a central server. Generative AI analyzes this data and makes suggestions for further efficiency improvements. These suggestions may include, for example, methods for automating specific calculation processes or ways to optimize data management.

[0051] Users can receive AI suggestions and generate new scripts and macros based on those suggestions, improving their efficiency and overall business performance.

[0052] Creating and sharing standard programs

[0053] The scripts and macros created based on the generative AI's suggestions are stored on a central server. These standardized programs are shared so that they can be used by other departments. This results in the establishment of standardized, efficient business processes across the company.

[0054] In this way, the present invention provides a system that automates and streamlines the entire business process, from data collection and calculation processing to automatic distribution of results and even AI-based efficiency proposals.By making it possible to share this information with other management departments, it is expected that the business efficiency of the entire organization will be greatly improved.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The user enters the required data into a Google spreadsheet or Excel file. If specifying a range, specify the range (e.g., "A1:A10").

[0058] Step 2:

[0059] Set a trigger that runs the server periodically. This trigger can be set to run every day at 9:00 AM using a GAS or Excel macro script.

[0060] Step 3:

[0061] When the periodic trigger is activated, the server accesses the Google Spreadsheet or Excel file using the SpreadsheetApp.getActiveSpreadsheet() function (for Google Spreadsheets).

[0062] Step 4:

[0063] The server retrieves the specified sheet and range. For example, the getRange("A1:A10") function is used to retrieve the cell data in the specified range "A1:A10".

[0064] Step 5:

[0065] The data retrieved by the server is read as a two-dimensional array. Use the getValues() function to retrieve all cell values ​​in the range as a two-dimensional array.

[0066] Step 6:

[0067] The server performs the calculation. For example, to calculate an average, a for loop is used to sum up each element of an array and calculate the average.

[0068] Step 7:

[0069] The server formats the results appropriately: convert the results (e.g., averages) into strings and format them to fit the report format.

[0070] Step 8:

[0071] The server sends the formatted results via a communication method such as email or a messaging application. The MailApp.sendEmail() function is used to send the results to the specified recipient.

[0072] Step 9:

[0073] The server logs the completion of sending the calculation results. Use the Logger.log() function to record the completion status of the process for subsequent troubleshooting.

[0074] Step 10:

[0075] Users collect data on business efficiency from each department and input it into the generative AI. For example, they can aggregate business efficiency information from each department via Google Forms or Excel sheets.

[0076] Step 11:

[0077] The server uses generative AI to generate suggestions for further efficiency improvements based on the collected data. The AI ​​model performs analysis and proposes effective improvements for specific business processes.

[0078] Step 12:

[0079] The server automatically generates standard calculation programs and scripts based on the generated proposals, thereby providing business efficiency improvements in the form of concrete code.

[0080] Step 13:

[0081] The generated programs and scripts are stored in a central repository by a server, which can be accessed by other departments and used as a common means of efficiency.

[0082] Step 14:

[0083] Users can then apply the generated scripts and programs to their own departments as needed, thereby sharing and standardizing efficiency gains and improving efficiency across the company.

[0084] Example 1

[0085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0086] In the conventional system, users had to manually input data, perform calculations, and manually submit the results, which was time-consuming and labor-intensive. It was also difficult to collect data on the operational efficiency of each department and make recommendations for efficiency improvements based on that data. Furthermore, there was a lack of a way to generate standard calculation programs based on those recommendations and share them among departments. There was a need to solve these problems and improve operational efficiency across the company.

[0087] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0088] In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting business efficiency data from multiple management departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among the management departments, means for using software for data processing and data calculation based on user input data, means for using communication means for formatting and automatically transmitting the calculation results, and means for executing calculation processing set by the user. This enables automatic data processing and immediate delivery of results, and enables company-wide improvement in business efficiency through efficiency proposals by generative AI and the sharing of programs based on those proposals.

[0089] "User" refers to the entity that uses the system to input data and configure the calculation process.

[0090] "Server" refers to a computer system whose role is to receive input data from a user, perform calculations, and automatically transmit the results via a designated communication means.

[0091] "Input data" refers to data such as numbers and strings that users enter into Google Spreadsheets, Excel files, etc.

[0092] "Calculation processing" refers to various arithmetic operations that the server performs based on input data, and specifically includes calculation of average values ​​and standard deviations.

[0093] "Communication means" refers to the method used by the server to transmit the results of computation, including email and messaging applications.

[0094] "Generative AI" refers to an artificial intelligence model that analyzes collected business efficiency data and generates suggestions for further efficiency improvements.

[0095] "Data on improving business efficiency" refers to information collected from each management department to improve the efficiency of overall business operations.

[0096] A "standard program" refers to a calculation program that is generated based on suggestions from generative AI and is used in common by multiple management departments.

[0097] "Data processing" refers to the process of preparing input data in an appropriate format.

[0098] "Data calculation" refers to various calculation processes performed based on data.

[0099] A "trigger" is a trigger that periodically executes a calculation process based on a date or time.

[0100] A "script" is a series of commands used to automate a computation or data collection.

[0101] This system automatically performs calculations based on data entered by the user and automatically transmits the results via a specified communication method. It also includes functions to collect data on business efficiency improvements from each department, use generative AI to propose further efficiency improvements, generate standard calculation programs based on the proposals, and share the results among departments.

[0102] System configuration

[0103] Hardware

[0104] Server: A central computer system that collects data, processes calculations, formats and transmits the results.

[0105] Terminal: The device (computer, tablet, etc.) through which a user enters data.

[0106] software

[0107] Google Apps Script (GAS): A script for manipulating Google Spreadsheets to automate data collection and calculation processes.

[0108] Excel Macro: A program for manipulating Excel files and automating data collection and calculation processes.

[0109] Communication methods: email, messaging applications, etc.

[0110] Program processing

[0111] User operations

[0112] Users enter necessary information such as sales data and inventory data into a Google spreadsheet or Excel file. Specifically, it is assumed that data will be entered into the cell range "A1:A10" in the Google spreadsheet.

[0113] Server Operation

[0114] The server uses Google Apps Script (GAS) or Excel macros to collect the user-entered data from a specified spreadsheet or Excel file. For example, it retrieves data from the cell range "A1:A10."

[0115] The server then performs calculations (e.g., average, standard deviation, etc.) on the collected data as configured by the user. For example, to calculate the average value of the acquired sales data, the server adds up the values ​​of each cell and divides by the number of cells.

[0116] Formatting and sending the calculation results

[0117] The server formats the results of the calculations and makes them easy to understand, such as "Daily Report: Average sales is XX yen." It then automatically sends these results to the user or other recipients via the specified communication method. Specifically, it automatically sends an email containing the results to the specified email address.

[0118] AI-based efficiency proposals

[0119] Server Operation

[0120] Data on business efficiency improvements collected from each department is stored on a central server. A generative AI model on the server analyzes this data and makes suggestions for further improvements to business efficiency. New scripts and macros are then generated based on these suggestions and stored on the central server.

[0121] Prompt Sentence Examples

[0122] The server uses a generative AI model to generate efficiency suggestions using prompt sentences such as the following:

[0123] "Please analyze the operational efficiency data collected by each department and propose ways to automate specific calculation processes. Then, please tell me how to generate a Google Apps Script based on those proposals and share it with other departments."

[0124] Specific examples

[0125] 1. A user enters sales data into a Google spreadsheet

[0126] Action: The user enters sales data into the range "A1:A10".

[0127] 2. The server collects the data

[0128] Operation: The server uses Google Apps Script to read the data in "A1:A10".

[0129] 3. User sets the average calculation

[0130] Operation: The user selects "Calculate the average of sales data" on the program settings screen.

[0131] 4. The server calculates the average

[0132] Operation: The server calculates the average value of the data it retrieves.

[0133] 5. Formatting the calculation results

[0134] Operation: The server formats the calculation result as "Daily report: Average sales is XX yen."

[0135] 6. Send the results to the specified email address

[0136] What it does: The server automatically sends the formatted results to the specified email address.

[0137] 7. Data on operational efficiency is stored on a central server

[0138] Operation: The server periodically collects data from each management department and stores it in a database.

[0139] 8. Generative AI makes efficiency suggestions

[0140] How it works: A generative AI model analyzes data and generates suggestions for automating specific computational tasks.

[0141] 9. Generate and share new scripts

[0142] How it works: The server creates a script based on the suggestions of the generated AI and saves it in a shared folder.

[0143] In this way, the present invention provides an integrated system for automating and streamlining the entire business process, from data collection and calculation processing to automatic distribution of results and even efficiency suggestions using generative AI, which is expected to significantly improve the business efficiency of the entire organization.

[0144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0145] Step 1: Enter your data

[0146] User operations

[0147] The user manually enters the necessary data into a Google spreadsheet or Excel file using the device. Specifically, the sales data is entered into the cell range "A1:A10" in the Google spreadsheet.

[0148] Input: Sales data (cell range A1:A10)

[0149] Output: Input sales data

[0150] Step 2: Collect data

[0151] Server Operation

[0152] The server uses Google Apps Script (GAS) or Excel macros to collect data from the specified spreadsheet or Excel file from the user's device. Specifically, the server reads data from the cell range "A1:A10."

[0153] Input: Entered sales data (cell range A1:A10)

[0154] Output: Collected sales data

[0155] Step 3: Set up the calculation

[0156] User operations

[0157] The user uses the terminal to set the type of calculation processing to be performed on the server. Specifically, on the calculation processing setting screen, the user selects the option "Calculate the average of sales data."

[0158] Input: Calculation settings (e.g., calculating the average value of sales data)

[0159] Output: Setting information for the calculation process

[0160] Step 4: Performing the calculation

[0161] Server Operation

[0162] The server performs the configured calculations on the collected sales data. Specifically, it calculates the average value of the sales data for each cell. The server converts the collected data into a numeric array and sums each element to find the average value.

[0163] Input: Setting information for the calculation process, collected sales data

[0164] Output: Calculation result (average value of sales data)

[0165] Step 5: Formatting the results

[0166] Server Operation

[0167] The server formats the results of the calculations and converts them into a displayable format, such as "Daily report: average sales is XX yen."

[0168] Input: Calculation result (average value of sales data)

[0169] Output: A formatted message of the calculation result

[0170] Step 6: Sending the calculation results

[0171] Server Operation

[0172] The server sends the formatted message containing the calculation result using the specified communication method (e.g., email, messaging app). Specifically, it includes the formatted message in the body of the email and sends it to the specified email address.

[0173] Input: Formatted message of the calculation result

[0174] Output: Message of the calculation result sent

[0175] Step 7: Collect data on operational efficiency

[0176] Server Operation

[0177] The server collects data from each department for the purpose of improving business efficiency and stores it in the central server. Specifically, it collects reports and data tables sent periodically from each department and stores them in a database.

[0178] Input: Business efficiency data provided by each management department

[0179] Output: Business efficiency data stored on a central server

[0180] Step 8: Generative AI proposes efficiency improvements

[0181] How generative AI models work

[0182] The generative AI model analyzes the accumulated operational efficiency data and generates proposals for further operational efficiency improvements. Specifically, it analyzes the data to identify bottlenecks and areas for improvement, and proposes methods for automating specific processes.

[0183] Input: Accumulated business efficiency data

[0184] Output: Efficiency suggestions (e.g., how to automate specific calculation processes)

[0185] Step 9: Generate and share a standard program

[0186] Server Operation

[0187] The server generates new scripts and macros based on the suggestions of the generative AI model and stores them on the central server. Specifically, scripts are created based on the proposed automation methods and saved in a shared folder, making them available to other departments.

[0188] Input: Proposal for efficiency improvement, proposed content of generative AI model

[0189] Output: Generated boilerplate programs, shared scripts and macros

[0190] The above is the specific processing flow of the program for this system. By explaining the operations, inputs, and outputs performed at each processing step, the operation of the entire system becomes easier to understand.

[0191] (Application example 1)

[0192] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0193] In current logistics centers, processing a wide range of data and making proposals for improving operational efficiency is often done manually. This makes it difficult to collect and process data quickly and accurately, hindering efficient business operations. Furthermore, making proposals for improving efficiency requires advanced specialized knowledge, which is rarely shared across the organization. This makes it difficult to standardize operations and improve overall efficiency.

[0194] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0195] In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple management departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among the management departments, means for applying the data collection and calculation processing to inventory management and work analysis at the logistics center, and means for generating new scripts and macros based on the efficiency improvement proposals, and for analyzing and reporting the data. This enables fast and accurate data collection and processing, automatic generation of efficiency improvement proposals, and data analysis and reporting for business efficiency improvements.

[0196] "User" means a person who inputs data or receives results to use the system, or who performs a task.

[0197] "Input data" refers to data provided by a user to a system, and is the information that forms the basis for calculations and analysis.

[0198] "Computational processing" refers to mathematical and statistical manipulations and operations performed on input data.

[0199] "Communication methods" refers to the technologies and methods used to communicate computational results and efficiency suggestions to users and other departments. Examples include email and messaging applications.

[0200] "Multiple administrative functions" refers to the multiple departments or groups within an organization that are responsible for overseeing operations and driving efficiency.

[0201] "Data on business efficiency" refers to data that includes indicators and information for evaluating the efficiency of business processes and tasks.

[0202] "Generative AI" refers to artificial intelligence that analyzes collected data and automatically generates proposals for improving business efficiency based on that data.

[0203] "Proposals" refer to specific guidelines and methods for improving business efficiency and work processes that are automatically created by generative AI.

[0204] A "standard calculation program" refers to a program that performs calculation processing that is standardized based on a proposal and can be used repeatedly.

[0205] "Means for sharing among management departments" refers to methods and techniques for making the generated standard calculation programs available to other management departments.

[0206] A "logistics center" refers to a facility that manages inventory, picks products, and prepares them for shipping.

[0207] "Inventory management" refers to the business process of monitoring and managing the storage status and quantity of goods at a logistics center.

[0208] "Work analysis" refers to the investigation and analysis carried out to evaluate the efficiency and effectiveness of various business processes carried out within a logistics center.

[0209] "Script" refers to program code written to automate specific computations or data manipulations.

[0210] A "macro" is a program or script used to automate a specific task or sequence of actions.

[0211] "Data analysis and reporting" refers to the business process of analyzing collected data and providing the results in the form of a report or report.

[0212]

[0213] This invention is a system that supports inventory management, work analysis, and operational efficiency improvement in logistics centers. The system allows users to input data, performs calculations based on that data, and automatically transmits the results. It also includes a function that uses generative AI to make suggestions for operational efficiency improvement, generates standard calculation programs based on those suggestions, and shares them with other management departments.

[0214] The program for this system is implemented using Google Apps Script (GAS) and other scripting languages. The specific implementation method for the system is explained below.

[0215] Hardware and Software

[0216] The system uses devices such as servers, smartphones, tablets, and robots, and the program runs on Google Apps Script (GAS), spreadsheets, email systems, and generative AI models (e.g., Google Cloud AI).

[0217] Program processing flow

[0218] 1. Data Collection

[0219] The server collects inventory and work data in real time from users' smartphones and robots, and stores this data in a Google spreadsheet.

[0220] 2. Computational Processing

[0221] The server performs calculations on the stored data, specifically calculating the average time and error rate of picking tasks.

[0222] 3. Automatic transmission of results

[0223] The server automatically sends the results of the calculations to the administrator via email or messaging application, allowing the administrator to always be up-to-date on the latest business status.

[0224] 4. Generate efficiency proposals

[0225] The server inputs the collected data into a generative AI model to generate proposals for improving business efficiency. These proposals are then embodied as new scripts or macros that can be shared with other management departments.

[0226] Specific examples

[0227] A logistics center manager uses this system to improve the efficiency of picking work. The input picking data (start time, end time, error rate, etc.) is saved in a spreadsheet, and the server calculates the average time and error rate. The calculation results are automatically sent to the manager, and the generative AI model analyzes the data and makes suggestions for improving efficiency. New scripts and macros are generated based on these suggestions, improving overall work efficiency.

[0228] Example prompt for a generative AI model:

[0229] The following is data on picking operations at a distribution center. Please create a proposal for improving efficiency based on this data. The data includes the start time, end time, and error rate for each picking operation:

[0230] Start time: 08:00, End time: 08:15, Error rate: 2%

[0231] Start time: 08:20, End time: 08:35, Error rate: 1%

[0232] ...

[0233] Use these to generate efficiency suggestions."

[0234] In this way, the present invention can significantly improve overall business efficiency by automating the collection, analysis, and efficiency improvement proposals of real-time data at logistics centers.

[0235] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0236] Step 1: Data collection

[0237] Users use smartphones, tablets, or robots to input inventory information and work performance data for the distribution center. This includes product location, quantity, picking start and end times, and error rates. The input data is saved in real time to a Google spreadsheet. The device collects the data and stores it in a spreadsheet, making it accessible to the server.

[0238] Step 2: Data Acquisition

[0239] The server periodically accesses the Google spreadsheet and retrieves data from the specified range. To retrieve the data, Google Apps Script (GAS) is used to read the data in the specified range (e.g., "A1:D100" in the "Inventory Information" sheet). This data is converted into a database format and used for subsequent calculation processing.

[0240] Step 3: Calculations

[0241] The server then performs calculations on the retrieved data, such as average time, error rate, and inventory fluctuations. For example, to calculate the average time it takes to pick a particular item, the server calculates the difference between the start time and end time and divides it by the total time for all items. The results of this calculation are temporarily stored and used in the next step.

[0242] Step 4: Automatically send calculation results

[0243] The server formats the calculation results and automatically sends them to the administrator via the specified communication method (e.g., email or messaging application). The formatted data is then output in a format that is easy for the administrator to understand (e.g., a table or graph), allowing the administrator to quickly and easily check the data.

[0244] Step 5: Generate efficiency proposals

[0245] The server inputs the collected data and calculation results into a generative AI model to generate business efficiency improvement proposals. The AI ​​model incorporates analytical algorithms based on past data and trends, analyzes the input data, and outputs optimal proposals. These generated proposals are then embodied as new scripts or macros.

[0246] Step 6: Share your efficiency suggestions

[0247] The server stores standardized calculation programs on a central server to share the generated efficiency proposals with other management departments. This allows other departments to use the same efficiency proposals, achieving company-wide business efficiency. The shared programs can also be accessed from other terminals, promoting the standardization of business processes.

[0248] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0249] This system receives input data from users, performs calculations, and automatically transmits the results via a specified communication method. It also uses generative AI to analyze business efficiency data collected from multiple departments, proposes further improvements, generates standard calculation programs based on those proposals, and shares them among departments. It also incorporates an emotion engine that recognizes users' emotions, providing feedback based on emotions and adjusting processing priorities.

[0250] Generating a Program

[0251] The system is programmed using Google Apps Script (GAS) and Excel macros. The system configuration is as follows:

[0252] Data collection

[0253] The user enters the required data into a Google spreadsheet or Excel file. The server accesses the file and retrieves the data from the specified range. For example, it retrieves the range "A1:A10" from the sheet where sales data is entered.

[0254] Calculation execution

[0255] After retrieving the data in the specified range, the server executes the calculations specified by the user. For example, it calculates the average or total value of sales data. This allows the user to perform data analysis efficiently.

[0256] Formatting and sending the calculation results

[0257] The calculation result is formatted and automatically sent via a specified communication means. For example, the calculation result is formatted as the body of an email and sent to a specified recipient.

[0258] Proposals for improving business efficiency

[0259] Data on business efficiency improvements collected from each department is aggregated on a central server. Generative AI analyzes this data and generates proposals for further efficiency improvements. These proposals are presented in the form of specific action plans or scripts.

[0260] Creating and sharing standard programs

[0261] New scripts and macros are automatically generated based on the generated suggestions, and these programs are stored in a central repository and shared for use by other departments, establishing standardized and efficient business processes across the company.

[0262] Emotion engine integration

[0263] Emotion recognition and prioritization

[0264] The emotion engine recognizes the user's emotions in real time and adjusts the priority of computational tasks based on those emotions. For example, if the user is stressed, it will postpone less urgent tasks and prioritize more immediate tasks.

[0265] Providing feedback

[0266] The emotion engine provides appropriate feedback to the user based on the emotions it recognizes. For example, if the user is in an emotionally unstable state, it displays an encouraging message. Furthermore, by incorporating emotional information into the efficiency improvement proposals proposed by the generative AI based on emotion data, more practical suggestions can be made.

[0267] Accumulation and analysis of emotional data

[0268] The emotion engine accumulates and analyzes user emotional data. This data provides important insights for long-term operational efficiency and is reflected in work improvement proposals. For example, if stress levels are high during a particular time period, the engine will propose ways to reduce the workload during that time period.

[0269] Specific examples

[0270] A company's management department inputs daily sales data into a Google spreadsheet. The server retrieves this data at 9:00 AM every day and calculates the average and total sales figures. The calculation results are formatted and automatically emailed to the sales department leader. Sales representatives also enter emotional data using an emotion engine, which is collected on a central server. A generative AI analyzes this data and makes individual business efficiency proposals to each sales representative. Based on these proposals, standard calculation programs are generated and shared among management departments, resulting in business efficiency improvements across the company.

[0271] The processing flow will be explained below.

[0272] Step 1:

[0273] The user enters the required data into a Google spreadsheet or Excel file. For example, when entering sales data, the sales amount is entered into the cell range "A1:A10."

[0274] Step 2:

[0275] Set a trigger that will run the server periodically. If you are using Google Apps Script, use the ScriptApp.newTrigger function to set a periodic trigger that runs every day at 9:00 AM.

[0276] Step 3:

[0277] When the trigger fires, the server accesses the Google Spreadsheet or Excel file. For Google Spreadsheets, it uses the SpreadsheetApp.getActiveSpreadsheet() function.

[0278] Step 4:

[0279] The server retrieves data by specifying the target sheet and range. For example, the getRange("A1:A10") function is used to retrieve data from the range "A1:A10".

[0280] Step 5:

[0281] The data retrieved by the server is read as a two-dimensional array. Use the getValues() function to retrieve the cell data within the range in two-dimensional array format.

[0282] Step 6:

[0283] The server performs the calculation. For example, to calculate the average value of sales data, a for loop is used to sum each element of the array and divide by the total to calculate the average.

[0284] Step 7:

[0285] The server formats the calculation results. The calculation results are converted into a string format, for example, "Average sales: XX yen."

[0286] Step 8:

[0287] The server sends the formatted calculation results via the specified communication method, and then uses the MailApp.sendEmail() function to send an email containing the calculation results to the specified recipient.

[0288] Step 9:

[0289] The server logs the processing status. It uses the Logger.log() function to log that the calculation result has been sent.

[0290] Step 10:

[0291] Users input collected data on business efficiency into generative AI. For example, they can use Google Forms to collect information on business efficiency improvements from the general management department.

[0292] Step 11:

[0293] The server uses generative AI to analyze the accumulated data and generate suggestions for further efficiency improvements. For example, an AI model analyzes the data and suggests optimization measures for a specific business process.

[0294] Step 12:

[0295] The server automatically generates standard calculation programs and scripts based on the generated efficiency improvement proposals, providing specific code for improving business efficiency.

[0296] Step 13:

[0297] The server stores the generated scripts and programs in a central repository and makes them available to other departments, so they are shared across the company as a common means of efficiency.

[0298] Step 14:

[0299] The user inputs emotional data through the emotion engine, which, for example, recognizes emotions through the device's camera or microphone and sends the data to the server.

[0300] Step 15:

[0301] The server uses an emotion engine to analyze the user's emotions in real time and adjusts the priority of calculations based on that. For example, if the user is feeling stressed, the order of calculations will be changed.

[0302] Step 16:

[0303] The server generates feedback based on the user's emotions and provides it to the user. For example, if the user is feeling stressed, it displays an encouraging message.

[0304] Step 17:

[0305] The server accumulates emotional data and performs long-term analysis. This data is reflected in business efficiency proposals using generative AI. For example, if stress tends to be high during certain times of the day, the system will make proposals to reduce the workload during those times.

[0306] Specific examples

[0307] A company's management department inputs daily sales data into a Google spreadsheet. A server retrieves this data at 9:00 AM every day, calculates the average and total sales figures, and automatically sends them by email. Sales representatives also input emotional data using an emotion engine, which is collected on a central server. A generative AI analyzes this data and makes individual proposals for improving business efficiency. Based on these proposals, standard calculation programs are generated and shared among management departments, resulting in company-wide improvements in business efficiency.

[0308] Example 2

[0309] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0310] In modern business operations, a great deal of time and effort is spent on data collection, calculation processing, and proposing and implementing improvements to business efficiency. Furthermore, insufficient information sharing between departments often prevents further efficiency improvements. Furthermore, prioritization of tasks and feedback may be ineffective because users' feelings are not taken into consideration. New methods are needed to solve these issues and realize more productive and efficient business processes.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple departments and proposing further efficiency improvements using a generative AI model, means for generating standard calculation programs based on the proposals and sharing them among departments, means for recognizing user emotions and adjusting processing priorities based on the emotions, and means for accumulating emotion data and reflecting it in long-term business efficiency improvements. This enables data collection, calculation processing, proposing and implementing business efficiency improvements, information sharing, and prioritizing tasks based on emotions.

[0312] A "user" is an entity that uses the system to input data and receives proposals for calculation processing and business efficiency improvements.

[0313] "Input data" refers to information provided by a user to the system, and includes, for example, sales data and data for improving business efficiency.

[0314] "Calculation processing" refers to arithmetic or logical processing performed on input data, including, for example, calculating averages or sums.

[0315] "Communication means" refers to the method used to automatically transmit computational results and efficiency suggestions, including, for example, email.

[0316] A "department" is a section in charge of business within a company, and includes, for example, a sales department and an accounting department.

[0317] "Data on improving business efficiency" is information collected from each department to improve business efficiency.

[0318] A "generative AI model" is an artificial intelligence technology that analyzes provided data and suggests further efficiency improvements.

[0319] A "standard calculation program" is a program that performs consistent calculation processing and is automatically created based on the suggestions of a generative AI model.

[0320] "Emotion recognition" is a technology that grasps a user's emotional state in real time.

[0321] "Emotion data" is information about a user's emotions collected through emotion recognition.

[0322] "Priority adjustment" is the process of reassessing and reordering the importance of work tasks based on perceived emotions.

[0323] "Storage" means storing data for a long period of time and using it for later analysis and recommendations.

[0324] "Long-term business efficiency" refers to efforts to continuously increase business productivity and efficiency by analyzing emotional and business data.

[0325] This system receives input data from users, performs calculations, and automatically transmits the results via a specified communication method. It also has the ability to analyze business efficiency data collected from multiple departments using a generative AI model, propose further efficiency improvements, generate standard calculation programs based on those proposals, and share them among departments. It also incorporates an emotion engine that recognizes user emotions, providing feedback based on emotions and adjusting processing priorities.

[0326] Generating a Program

[0327] The system's programming is implemented using Google Apps Script (GAS) and Excel macros. First, the user enters the necessary data into a Google spreadsheet or Excel file. The server accesses these files and retrieves data from the specified range. For example, it retrieves the range "A1:A10" from the sheet where sales data is entered.

[0328] Calculation execution

[0329] After retrieving the data in the specified range, the server executes the calculations specified by the user. For example, it calculates the average or total value of sales data. This allows the user to perform data analysis efficiently.

[0330] Formatting and sending the calculation results

[0331] The calculation results are formatted and automatically sent via the specified communication method. For example, the calculation results are formatted as the body of an email and sent to the specified recipient. This function is realized using the MailApp class of Google Apps Script.

[0332] Proposals for improving business efficiency

[0333] Business efficiency data collected from each department is aggregated on a central server. A generative AI model (e.g., OpenAI's GPT-3 model) analyzes this data and generates suggestions for further efficiency improvements. The suggestions are presented in the form of specific action plans or scripts.

[0334] Creating and sharing standard programs

[0335] The server automatically generates new scripts and macros based on the generated suggestions. These programs are stored in a central repository and shared for use by other departments, establishing standardized and efficient business processes across the company.

[0336] Emotion engine integration

[0337] Emotion recognition and prioritization

[0338] The emotion engine recognizes the user's emotions in real time and adjusts the priority of computational tasks based on those emotions. For example, if the user is stressed, it will postpone less urgent tasks and prioritize more urgent tasks.

[0339] Providing feedback

[0340] The emotion engine provides appropriate feedback to the user based on the recognized emotion. For example, if the user is in an emotionally unstable state, it displays an encouraging message. In addition, by reflecting emotional information in the efficiency suggestions proposed by the generative AI model based on emotion data, more practical suggestions can be made.

[0341] Accumulation and analysis of emotional data

[0342] The emotion engine accumulates and analyzes user emotional data. This data provides important insights for long-term operational efficiency and is reflected in work improvement proposals. For example, if stress levels are high during a particular time period, the engine will propose ways to reduce the workload during that time period.

[0343] Specific examples

[0344] In a certain company's departments, users enter daily sales data into a Google spreadsheet. The server retrieves this data at 9:00 AM every day and calculates the average and total sales values. The calculation results are formatted and automatically emailed to the sales department leader. Sales representatives also enter emotional data using an emotion engine, which is collected on a central server. A generative AI model analyzes this data and makes individual business efficiency suggestions to each sales representative. Based on these suggestions, standard calculation programs are generated and shared between departments, achieving business efficiency improvements across the company.

[0345] Prompt Sentence Examples

[0346] "Calculate the average and total values ​​based on the following sales data and email the results to me:

[0347] Sales data: 100, 200, 150, 120, 180"

[0348] The above is a specific embodiment for carrying out the present invention, which enables companies to automate data processing and improve business efficiency, and achieve standardization across departments.

[0349] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0350] Step 1:

[0351] Users input the necessary data into a Google Spreadsheet or Excel file. For example, they input daily sales data into cells "A1:A10." This input data becomes the basis for subsequent calculations.

[0352] Step 2:

[0353] At the specified time, for example 9:00 AM, the server accesses the spreadsheet using Google Apps Script and retrieves the data in the specified range. Specifically, it executes "SpreadsheetApp.getActiveSpreadsheet().getRange('A1:A10').getValues();" and stores the data in a variable. The spreadsheet data range is specified as input, and an array of data is obtained as output.

[0354] Step 3:

[0355] The server performs calculations based on the acquired data. For example, it calculates the average and total values ​​of sales data. Specifically, it calculates the average value with "avg = data.reduce((a, b) => a + b, 0) / data.length;" and calculates the total value with "total = data.reduce((a, b) => a + b, 0);". It uses the acquired data array as input and obtains the average and total values ​​as output.

[0356] Step 4:

[0357] The server formats the result of the calculation. Specifically, it converts the average and total values ​​into a single string. For example, "result = 'Average: ' + avg + ', Total: ' + total;". It uses the result of the calculation as input and gets the formatted string as output.

[0358] Step 5:

[0359] The server automatically sends the formatted calculation results to the specified recipient via email. Specifically, it executes the Google Apps Script "MailApp.sendEmail('address@example.com', 'Sales data results', result);". It uses the formatted string and the recipient's email address as input, and obtains the email sending status as output.

[0360] Step 6:

[0361] The server collects data for business efficiency from each department and aggregates it in a central server. For example, the productivity data and working hours of each department are stored in a database. Data from each department is used as input and an integrated data set is obtained as output.

[0362] Step 7:

[0363] The server inputs the collected business data into the generative AI model and generates efficiency improvement proposals. For example, the generative AI model uses a prompt statement such as "Please make business efficiency improvement proposals based on the following data." Using the business data and the prompt statement as input, the generated efficiency proposals are obtained as output.

[0364] Step 8:

[0365] The server automatically generates new scripts and macros based on suggestions from the generative AI model. Specifically, it uses Google Apps Script to create code that implements the proposed efficiency techniques. It uses the generated suggestions as input and obtains the efficiency-improving scripts and macros as output.

[0366] Step 9:

[0367] The server stores the generated scripts and macros in a central repository and shares them with other departments. Specifically, it uploads scripts to cloud storage, uses the generated scripts as input, and obtains a shareable state as output.

[0368] Step 10:

[0369] The device collects the user's emotional data using emotion recognition technology, such as facial recognition technology and emotion analysis software, to analyze the user's facial expressions. It uses the user's real-time video as input and obtains the emotional data as output.

[0370] Step 11:

[0371] The server analyzes the collected emotional data and adjusts the processing priorities. Specifically, if the stress level is high, tasks with low urgency are postponed. It uses emotional data as input and obtains an adjusted list of tasks as output.

[0372] Step 12:

[0373] The server provides emotional feedback to the user, for example, displaying a message such as "You seem to be under a lot of stress. Please take a short break." It uses emotional data as input and gets an appropriate feedback message as output.

[0374] The above is the specific processing flow of this system. These processing steps enable companies to efficiently automate a series of business processes, including data processing, business efficiency, and emotion recognition.

[0375] (Application example 2)

[0376] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0377] Improving work efficiency and reducing staff burdens at logistics centers are important issues in modern logistics operations. However, conventional systems are unable to adequately aggregate and analyze work data or optimize operations while taking into account staff emotions. This can easily lead to problems such as wasted work, incorrect deliveries, and increased staff stress. Furthermore, the inability to make real-time suggestions for improving efficiency poses a major constraint in operations that require rapid response.

[0378] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among departments, and means for analyzing emotional data collected from multiple users and adjusting feedback and calculation processing priorities based on the emotions. This enables efficient collection and analysis of work data at logistics centers and optimization of operations taking into account staff emotions.

[0379] "User" means a person or organization that utilizes the system to input data and receive the results of computations.

[0380] "Input data" refers to various information provided by the user to the system, including numerical data, text data, emotional data, and the like.

[0381] "Computation" refers to the mathematical or logical operations that a system performs on input data.

[0382] "Communication Method" refers to the method or protocol for transmitting the results of a computation to a designated recipient, such as email or notification.

[0383] A "department" refers to a group or section within a company or organization that is responsible for a particular function or task.

[0384] "Data on business efficiency" refers to various information collected to improve business processes and streamline them. This information includes data on working hours, workload, work procedures, etc.

[0385] "Generative AI" refers to artificial intelligence that analyzes collected data, proposes efficiency improvements, and generates new calculation programs.

[0386] A "standard calculation program" refers to a standardized calculation script or program that is automatically generated by generative AI based on suggestions.

[0387] "Emotion data" is information that represents the user's emotional state, including stress level, fatigue level, and the like.

[0388] "Real-time" refers to a state in which processing and analysis are carried out close to the moment data is generated.

[0389] "Suggestions" refer to improvement suggestions and optimization instructions that generative AI makes to improve business efficiency.

[0390] The program for the system that realizes this application example is generated using Google Apps Script (GAS) and a framework for smartphone application development (e.g., React Native).

[0391] System configuration

[0392] Smartphone (ANDROID (registered trademark) or iOS)

[0393] Servers (database servers and application servers)

[0394] Google Apps Script (GAS)

[0395] React Native

[0396] Emotion engine (Emotion API, etc.)

[0397] Generative AI (e.g., OpenAI API)

[0398] Data collection

[0399] Users (logistics center staff) input work data through a smartphone app. This work data includes information such as warehousing, shipping, and inventory confirmation.

[0400] The terminal (smartphone) transmits the data entered by the user to the server in real time.

[0401] Calculation execution

[0402] The server receives the data and uses Google Apps Script (GAS) to retrieve the data in the specified range. For example, extracting data in a specified cell range from a spreadsheet.

[0403] The server performs calculations using GAS, such as calculating the average number of outgoing orders and the total inventory amount.

[0404] Formatting and sending the calculation results

[0405] The server formats the calculation results and stores them in a cloud database.

[0406] The server pushes the formatted results to the user's device in real time.

[0407] Proposals for improving business efficiency

[0408] The server systematically aggregates business efficiency data collected from each department.

[0409] Generative AI on the server (for example, OpenAI's API) generates business efficiency improvement proposals based on the collected data, such as adjusting work shifts or changing inventory management methods.

[0410] Based on the proposals, the server automatically generates new standard calculation programs and stores and shares them in a central repository.

[0411] Emotion engine integration

[0412] The device uses an emotion engine (such as Emotion API) to recognize the user's emotions in real time.

[0413] The server can then use the recognized emotion data to adjust the priority of the user's feedback and computational processes. For example, if the user is under high stress, it can postpone certain processes and send encouraging messages.

[0414] Specific examples

[0415] After completing a shipping task, a logistics center staff member enters the details of the task and their emotional state into a smartphone app. The device sends the input data to a server, which then retrieves a specified range of spreadsheet data and performs calculations based on the data. For example, it calculates the average number of shipping tasks per day and stores the results in a cloud database. The server then pushes the results to the device and uses an emotion engine to analyze the employee's stress level, sending an encouraging message if stress levels are high. Furthermore, the generative AI uses the collected data to make suggestions for efficiency improvements, such as "dividing shifts into morning and afternoon shifts to reduce the number of shipping tasks by 15%."

[0416] Example prompts to input to the generative AI model

[0417] Please provide suggestions for improving the efficiency of shipping operations at a logistics center. The input data is as follows:

[0418] 1. Number of shipping operations: 30

[0419] 2. Stock: 5000 items

[0420] 3. Staff emotional data: High stress level, medium fatigue level

[0421] Examples of suggestions: adjusting work shifts, changing inventory management methods, specific methods to maintain staff motivation, etc.

[0422] This approach improves work efficiency at the logistics center and reduces the burden on staff, optimizing overall operations.

[0423] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0424] Step 1:

[0425] The user inputs work data and emotional data into a smartphone app. At this time, the user inputs specific data about delivery work and inventory checks, and the emotion engine automatically detects the user's current emotional state (such as stress level and fatigue level). Examples of input data include the number of delivery work tasks, inventory volume, and stress level.

[0426] Step 2:

[0427] The device transmits the input task data and emotion data to the server in real time. The smartphone app then transmits the data to the cloud server via an internet connection. The transmitted data includes the task details, inventory information, and the user's emotion data.

[0428] Step 3:

[0429] The server parses the received data and retrieves the data in the specified range using Google Apps Script (GAS). In this step, the data in the required cell range (e.g., A1:D10) is read from the spreadsheet. This allows for consistent retrieval of working data.

[0430] Step 4:

[0431] The server performs calculations on the acquired spreadsheet data. For example, it uses Google Apps Script (GAS) to calculate the number of shipping operations per day, the average inventory amount, and the total amount. This process provides the user with the necessary statistical information.

[0432] Step 5:

[0433] The server formats the results and stores them in a cloud database. The formatting process converts the results into an easy-to-read format and then registers them in the database. At this stage, the results of the calculation are persisted.

[0434] Step 6:

[0435] The server then pushes the formatted results to the user's device in real time. The notification includes the calculation results (e.g., the average number of outgoing shipments), and the user can immediately check the results.

[0436] Step 7:

[0437] Generative AI on the server (for example, OpenAI's API) generates business efficiency improvement proposals based on the collected data, including specific suggestions such as "Review shifts to reduce the workload of shipping work by 15%."

[0438] Step 8:

[0439] The server automatically generates new standard calculation programs based on the suggestions of the generative AI. The generated programs are written as scripts and stored in a central repository. These scripts can then be shared with other departments.

[0440] Step 9:

[0441] The device's emotion engine (such as Emotion API) recognizes the user's emotions in real time and sends the data to the server. Emotion data indicates the user's stress level, fatigue level, etc.

[0442] Step 10:

[0443] The server uses the emotion data to provide feedback to the user and adjust the priority of computational processing. For example, if the user is in a high-stress state, it may lower the priority of stressful tasks or send encouraging messages.

[0444] Step 11:

[0445] The server accumulates emotional and operational data over the long term and reflects it in the generative AI's proposals. This data is used in monthly reports and for specific operational improvement plans.

[0446] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0447] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0448] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0449] [Second embodiment]

[0450] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0451] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0452] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0453] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0454] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0455] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0456] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0457] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0458] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0459] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0460] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0461] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0462] This system allows users to input data, automatically performs calculations on that data, and automatically transmits the results. It also includes functions to collect data on business efficiency improvements from each department, use generative AI to propose further efficiency improvements, generate standard calculation programs based on those proposals, and share them among departments.

[0463] Generating a Program

[0464] The program for this system is implemented using Google Apps Script (GAS) and Excel macros. The program is structured as follows:

[0465] 1. Data Collection:

[0466] Users enter the required data into a Google spreadsheet or Excel file.

[0467] The server accesses the specified spreadsheet or Excel file and retrieves data from the specified range.

[0468] 2. Performing the calculation:

[0469] The server performs calculations (e.g., average, standard deviation, etc.) set by the user on the acquired data.

[0470] 3. Formatting and sending the results:

[0471] The server formats the results of the computation and automatically transmits them via the specified communication method (e.g., email, messaging application).

[0472] As a concrete example, consider a spreadsheet where a user has entered sales data into the range "A1:A10." The server retrieves this data, calculates the average sales amount for each cell, and then formats and emails the results to designated recipients as a daily report.

[0473] AI-based efficiency proposals

[0474] Data on business efficiency improvements collected by each department is stored on a central server. Generative AI analyzes this data and makes suggestions for further efficiency improvements. These suggestions may include, for example, methods for automating specific calculation processes or ways to optimize data management.

[0475] Users can receive AI suggestions and generate new scripts and macros based on those suggestions, improving their efficiency and overall business performance.

[0476] Creating and sharing standard programs

[0477] The scripts and macros created based on the generative AI's suggestions are stored on a central server. These standardized programs are shared so that they can be used by other departments. This results in the establishment of standardized, efficient business processes across the company.

[0478] In this way, the present invention provides a system that automates and streamlines the entire business process, from data collection and calculation processing to automatic distribution of results and even AI-based efficiency proposals.By making it possible to share this information with other management departments, it is expected that the business efficiency of the entire organization will be greatly improved.

[0479] The processing flow will be explained below.

[0480] Step 1:

[0481] The user enters the required data into a Google spreadsheet or Excel file. If specifying a range, specify the range (e.g., "A1:A10").

[0482] Step 2:

[0483] Set a trigger that runs the server periodically. This trigger can be set to run every day at 9:00 AM using a GAS or Excel macro script.

[0484] Step 3:

[0485] When the periodic trigger is activated, the server accesses the Google Spreadsheet or Excel file using the SpreadsheetApp.getActiveSpreadsheet() function (for Google Spreadsheets).

[0486] Step 4:

[0487] The server retrieves the specified sheet and range. For example, use the getRange("A1:A10") function to retrieve the cell data in the specified range "A1:A10".

[0488] Step 5:

[0489] The data retrieved by the server is read as a two-dimensional array. Use the getValues() function to retrieve all cell values ​​in the range as a two-dimensional array.

[0490] Step 6:

[0491] The server performs the calculation. For example, to calculate an average, a for loop is used to sum up each element of an array and calculate the average.

[0492] Step 7:

[0493] The server formats the results appropriately: convert the results (e.g., averages) into strings and format them to fit the report format.

[0494] Step 8:

[0495] The server sends the formatted results via a communication method such as email or a messaging application. The MailApp.sendEmail() function is used to send the results to the specified recipient.

[0496] Step 9:

[0497] The server logs the completion of sending the calculation results. Use the Logger.log() function to record the completion status of the process for subsequent troubleshooting.

[0498] Step 10:

[0499] Users collect data on business efficiency from each department and input it into the generative AI. For example, they can aggregate business efficiency information from each department via Google Forms or Excel sheets.

[0500] Step 11:

[0501] The server uses generative AI to generate suggestions for further efficiency improvements based on the collected data. The AI ​​model performs analysis and proposes effective improvements for specific business processes.

[0502] Step 12:

[0503] The server automatically generates standard calculation programs and scripts based on the generated proposals, thereby providing business efficiency improvements in the form of concrete code.

[0504] Step 13:

[0505] The generated programs and scripts are stored in a central repository by a server, which can be accessed by other departments and used as a common means of efficiency.

[0506] Step 14:

[0507] Users can then apply the generated scripts and programs to their own departments as needed, thereby sharing and standardizing efficiency gains and improving efficiency across the company.

[0508] Example 1

[0509] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0510] In the conventional system, users had to manually input data, perform calculations, and manually submit the results, which was time-consuming and labor-intensive. It was also difficult to collect data on the operational efficiency of each department and make recommendations for efficiency improvements based on that data. Furthermore, there was a lack of a way to generate standard calculation programs based on those recommendations and share them among departments. There was a need to solve these problems and improve operational efficiency across the company.

[0511] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0512] In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting business efficiency data from multiple management departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among the management departments, means for using software for data processing and data calculation based on user input data, means for using communication means for formatting and automatically transmitting the calculation results, and means for executing calculation processing set by the user. This enables automatic data processing and immediate delivery of results, and enables company-wide improvement in business efficiency through efficiency proposals by generative AI and the sharing of programs based on those proposals.

[0513] "User" refers to the entity that uses the system to input data and configure the calculation process.

[0514] "Server" refers to a computer system whose role is to receive input data from a user, perform calculations, and automatically transmit the results via a designated communication means.

[0515] "Input data" refers to data such as numbers and strings that users enter into Google Spreadsheets, Excel files, etc.

[0516] "Calculation processing" refers to various arithmetic operations that the server performs based on input data, and specifically includes calculation of average values ​​and standard deviations.

[0517] "Communication means" refers to the method used by the server to transmit the results of computation, including email and messaging applications.

[0518] "Generative AI" refers to an artificial intelligence model that analyzes collected business efficiency data and generates suggestions for further efficiency improvements.

[0519] "Data on improving business efficiency" refers to information collected from each management department to improve the efficiency of overall business operations.

[0520] A "standard program" refers to a calculation program that is generated based on suggestions from generative AI and is used in common by multiple management departments.

[0521] "Data processing" refers to the process of preparing input data in an appropriate format.

[0522] "Data calculation" refers to various calculation processes performed based on data.

[0523] A "trigger" is a trigger that periodically executes a calculation process based on a date or time.

[0524] A "script" is a series of commands used to automate a computation or data collection.

[0525] This system automatically performs calculations based on data entered by the user and automatically transmits the results via a specified communication method. It also includes functions to collect data on business efficiency improvements from each department, use generative AI to propose further efficiency improvements, generate standard calculation programs based on the proposals, and share the results among departments.

[0526] System configuration

[0527] Hardware

[0528] Server: A central computer system that collects data, processes calculations, formats and transmits the results.

[0529] Terminal: The device (computer, tablet, etc.) through which a user enters data.

[0530] software

[0531] Google Apps Script (GAS): A script for manipulating Google Spreadsheets to automate data collection and calculation processes.

[0532] Excel Macro: A program for manipulating Excel files and automating data collection and calculation processes.

[0533] Communication methods: email, messaging applications, etc.

[0534] Program processing

[0535] User operations

[0536] Users enter necessary information such as sales data and inventory data into a Google spreadsheet or Excel file. Specifically, it is assumed that data will be entered into the cell range "A1:A10" in the Google spreadsheet.

[0537] Server Operation

[0538] The server uses Google Apps Script (GAS) or Excel macros to collect the user-entered data from a specified spreadsheet or Excel file. For example, it retrieves data from the cell range "A1:A10."

[0539] The server then performs calculations (e.g., average, standard deviation, etc.) on the collected data as configured by the user. For example, to calculate the average value of the acquired sales data, the server adds up the values ​​of each cell and divides by the number of cells.

[0540] Formatting and sending the calculation results

[0541] The server formats the results of the calculations and makes them easy to understand, such as "Daily Report: Average sales is XX yen." It then automatically sends these results to the user or other recipients via the specified communication method. Specifically, it automatically sends an email containing the results to the specified email address.

[0542] AI-based efficiency proposals

[0543] Server Operation

[0544] Data on business efficiency improvements collected from each department is stored on a central server. A generative AI model on the server analyzes this data and makes suggestions for further improvements to business efficiency. New scripts and macros are then generated based on these suggestions and stored on the central server.

[0545] Prompt Sentence Examples

[0546] The server uses a generative AI model to generate efficiency suggestions using prompt sentences such as the following:

[0547] "Please analyze the operational efficiency data collected by each department and propose ways to automate specific calculation processes. Then, please tell me how to generate a Google Apps Script based on those proposals and share it with other departments."

[0548] Specific examples

[0549] 1. A user enters sales data into a Google spreadsheet

[0550] Action: The user enters sales data into the range "A1:A10".

[0551] 2. The server collects the data

[0552] Operation: The server uses Google Apps Script to read the data in "A1:A10".

[0553] 3. User sets the average calculation

[0554] Operation: The user selects "Calculate the average of sales data" on the program settings screen.

[0555] 4. The server calculates the average

[0556] Operation: The server calculates the average value of the data it retrieves.

[0557] 5. Formatting the calculation results

[0558] Operation: The server formats the calculation result as "Daily report: Average sales is XX yen."

[0559] 6. Send the results to the specified email address

[0560] What it does: The server automatically sends the formatted results to the specified email address.

[0561] 7. Data on operational efficiency is stored on a central server

[0562] Operation: The server periodically collects data from each management department and stores it in a database.

[0563] 8. Generative AI makes efficiency suggestions

[0564] How it works: A generative AI model analyzes data and generates suggestions for automating specific computational tasks.

[0565] 9. Generate and share new scripts

[0566] How it works: The server creates a script based on the suggestions of the generated AI and saves it in a shared folder.

[0567] In this way, the present invention provides an integrated system for automating and streamlining the entire business process, from data collection and calculation processing to automatic distribution of results and even efficiency suggestions using generative AI, which is expected to significantly improve the business efficiency of the entire organization.

[0568] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0569] Step 1: Enter your data

[0570] User operations

[0571] The user manually enters the necessary data into a Google spreadsheet or Excel file using the device. Specifically, the sales data is entered into the cell range "A1:A10" in the Google spreadsheet.

[0572] Input: Sales data (cell range A1:A10)

[0573] Output: Input sales data

[0574] Step 2: Collect data

[0575] Server Operation

[0576] The server uses Google Apps Script (GAS) or Excel macros to collect data from the specified spreadsheet or Excel file from the user's device. Specifically, the server reads data from the cell range "A1:A10."

[0577] Input: Entered sales data (cell range A1:A10)

[0578] Output: Collected sales data

[0579] Step 3: Set up the calculation

[0580] User operations

[0581] The user uses the terminal to set the type of calculation processing to be performed on the server. Specifically, on the calculation processing setting screen, the user selects the option "Calculate the average of sales data."

[0582] Input: Calculation settings (e.g., calculating the average value of sales data)

[0583] Output: Setting information for the calculation process

[0584] Step 4: Performing the calculation

[0585] Server Operation

[0586] The server performs the configured calculations on the collected sales data. Specifically, it calculates the average value of the sales data for each cell. The server converts the collected data into a numeric array and sums each element to find the average value.

[0587] Input: Setting information for the calculation process, collected sales data

[0588] Output: Calculation result (average value of sales data)

[0589] Step 5: Formatting the results

[0590] Server Operation

[0591] The server formats the results of the calculations and converts them into a displayable format, such as "Daily report: average sales is XX yen."

[0592] Input: Calculation result (average value of sales data)

[0593] Output: A formatted message of the calculation result

[0594] Step 6: Sending the calculation results

[0595] Server Operation

[0596] The server sends the formatted message containing the calculation result using the specified communication method (e.g., email, messaging app). Specifically, it includes the formatted message in the body of the email and sends it to the specified email address.

[0597] Input: Formatted message of the calculation result

[0598] Output: Message of the calculation result sent

[0599] Step 7: Collect data on operational efficiency

[0600] Server Operation

[0601] The server collects data from each department for the purpose of improving business efficiency and stores it in the central server. Specifically, it collects reports and data tables sent periodically from each department and stores them in a database.

[0602] Input: Business efficiency data provided by each management department

[0603] Output: Business efficiency data stored on a central server

[0604] Step 8: Generative AI proposes efficiency improvements

[0605] How generative AI models work

[0606] The generative AI model analyzes the accumulated operational efficiency data and generates proposals for further operational efficiency improvements. Specifically, it analyzes the data to identify bottlenecks and areas for improvement, and proposes methods for automating specific processes.

[0607] Input: Accumulated business efficiency data

[0608] Output: Efficiency suggestions (e.g., how to automate specific calculation processes)

[0609] Step 9: Generate and share a standard program

[0610] Server Operation

[0611] The server generates new scripts and macros based on the suggestions of the generative AI model and stores them on the central server. Specifically, scripts are created based on the proposed automation methods and saved in a shared folder, making them available to other departments.

[0612] Input: Proposal for efficiency improvement, proposed content of generative AI model

[0613] Output: Generated boilerplate programs, shared scripts and macros

[0614] The above is the specific processing flow of the program for this system. By explaining the operations, inputs, and outputs performed at each processing step, the operation of the entire system becomes easier to understand.

[0615] (Application example 1)

[0616] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0617] In current logistics centers, processing a wide range of data and making proposals for improving operational efficiency is often done manually. This makes it difficult to collect and process data quickly and accurately, hindering efficient business operations. Furthermore, making proposals for improving efficiency requires advanced specialized knowledge, which is rarely shared across the organization. This makes it difficult to standardize operations and improve overall efficiency.

[0618] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0619] In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple management departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among the management departments, means for applying the data collection and calculation processing to inventory management and work analysis at the logistics center, and means for generating new scripts and macros based on the efficiency improvement proposals, and for analyzing and reporting the data. This enables fast and accurate data collection and processing, automatic generation of efficiency improvement proposals, and data analysis and reporting for business efficiency improvements.

[0620] "User" means a person who inputs data or receives results to use the system, or who performs a task.

[0621] "Input data" refers to data provided by a user to a system, and is the information that forms the basis for calculations and analysis.

[0622] "Computational processing" refers to mathematical and statistical manipulations and operations performed on input data.

[0623] "Communication methods" refers to the technologies and methods used to communicate computational results and efficiency suggestions to users and other departments. Examples include email and messaging applications.

[0624] "Multiple administrative functions" refers to the multiple departments or groups within an organization that are responsible for overseeing operations and driving efficiency.

[0625] "Data on business efficiency" refers to data that includes indicators and information for evaluating the efficiency of business processes and tasks.

[0626] "Generative AI" refers to artificial intelligence that analyzes collected data and automatically generates proposals for improving business efficiency based on that data.

[0627] "Proposals" refer to specific guidelines and methods for improving business efficiency and work processes that are automatically created by generative AI.

[0628] A "standard calculation program" refers to a program that performs calculation processing that is standardized based on a proposal and can be used repeatedly.

[0629] "Means for sharing among management departments" refers to methods and techniques for making the generated standard calculation programs available to other management departments.

[0630] A "logistics center" refers to a facility that manages inventory, picks products, and prepares them for shipping.

[0631] "Inventory management" refers to the business process of monitoring and managing the storage status and quantity of goods at a logistics center.

[0632] "Work analysis" refers to the investigation and analysis carried out to evaluate the efficiency and effectiveness of various business processes carried out within a logistics center.

[0633] "Script" refers to program code written to automate specific computations or data manipulations.

[0634] A "macro" is a program or script used to automate a specific task or sequence of actions.

[0635] "Data analysis and reporting" refers to the business process of analyzing collected data and providing the results in the form of a report or report.

[0636]

[0637] This invention is a system that supports inventory management, work analysis, and operational efficiency improvement in logistics centers. The system allows users to input data, performs calculations based on that data, and automatically transmits the results. It also includes a function that uses generative AI to make suggestions for operational efficiency improvement, generates standard calculation programs based on those suggestions, and shares them with other management departments.

[0638] The program for this system is implemented using Google Apps Script (GAS) and other scripting languages. The specific implementation method for the system is explained below.

[0639] Hardware and Software

[0640] The system uses devices such as servers, smartphones, tablets, and robots, and the program runs on Google Apps Script (GAS), spreadsheets, email systems, and generative AI models (e.g., Google Cloud AI).

[0641] Program processing flow

[0642] 1. Data Collection

[0643] The server collects inventory and work data in real time from users' smartphones and robots, and stores this data in a Google spreadsheet.

[0644] 2. Computational Processing

[0645] The server performs calculations on the stored data, specifically calculating the average time and error rate of picking tasks.

[0646] 3. Automatic transmission of results

[0647] The server automatically sends the results of the calculations to the administrator via email or messaging application, allowing the administrator to always be up-to-date on the latest business status.

[0648] 4. Generate efficiency proposals

[0649] The server inputs the collected data into a generative AI model to generate proposals for improving business efficiency. These proposals are then embodied as new scripts or macros that can be shared with other management departments.

[0650] Specific examples

[0651] A logistics center manager uses this system to improve the efficiency of picking work. The input picking data (start time, end time, error rate, etc.) is saved in a spreadsheet, and the server calculates the average time and error rate. The calculation results are automatically sent to the manager, and the generative AI model analyzes the data and makes suggestions for improving efficiency. New scripts and macros are generated based on these suggestions, improving overall work efficiency.

[0652] Example prompt for a generative AI model:

[0653] The following is data on picking operations at a distribution center. Please create a proposal for improving efficiency based on this data. The data includes the start time, end time, and error rate for each picking operation:

[0654] Start time: 08:00, End time: 08:15, Error rate: 2%

[0655] Start time: 08:20, End time: 08:35, Error rate: 1%

[0656] ...

[0657] Use these to generate efficiency suggestions."

[0658] In this way, the present invention can significantly improve overall business efficiency by automating the collection, analysis, and efficiency improvement proposals of real-time data at logistics centers.

[0659] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0660] Step 1: Data collection

[0661] Users use smartphones, tablets, or robots to input inventory information and work performance data for the distribution center. This includes product location, quantity, picking start and end times, and error rates. The input data is saved in real time to a Google spreadsheet. The device collects the data and stores it in a spreadsheet, making it accessible to the server.

[0662] Step 2: Data Acquisition

[0663] The server periodically accesses the Google spreadsheet and retrieves data from the specified range. To retrieve the data, Google Apps Script (GAS) is used to read the data in the specified range (e.g., "A1:D100" in the "Inventory Information" sheet). This data is converted into a database format and used for subsequent calculation processing.

[0664] Step 3: Calculations

[0665] The server then performs calculations on the retrieved data, such as average time, error rate, and inventory fluctuations. For example, to calculate the average time it takes to pick a particular item, the server calculates the difference between the start time and end time and divides it by the total time for all items. The results of this calculation are temporarily stored and used in the next step.

[0666] Step 4: Automatically send calculation results

[0667] The server formats the calculation results and automatically sends them to the administrator via the specified communication method (e.g., email or messaging application). The formatted data is then output in a format that is easy for the administrator to understand (e.g., a table or graph), allowing the administrator to quickly and easily check the data.

[0668] Step 5: Generate efficiency proposals

[0669] The server inputs the collected data and calculation results into a generative AI model to generate business efficiency improvement proposals. The AI ​​model incorporates analytical algorithms based on past data and trends, analyzes the input data, and outputs optimal proposals. These generated proposals are then embodied as new scripts or macros.

[0670] Step 6: Share your efficiency suggestions

[0671] The server stores standardized calculation programs on a central server to share the generated efficiency proposals with other management departments. This allows other departments to use the same efficiency proposals, achieving company-wide business efficiency. The shared programs can also be accessed from other terminals, promoting the standardization of business processes.

[0672] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0673] This system receives input data from users, performs calculations, and automatically transmits the results via a specified communication method. It also uses generative AI to analyze business efficiency data collected from multiple departments, proposes further improvements, generates standard calculation programs based on those proposals, and shares them among departments. It also incorporates an emotion engine that recognizes users' emotions, providing feedback based on emotions and adjusting processing priorities.

[0674] Generating a Program

[0675] The system is programmed using Google Apps Script (GAS) and Excel macros. The system configuration is as follows:

[0676] Data collection

[0677] The user enters the required data into a Google spreadsheet or Excel file. The server accesses the file and retrieves the data from the specified range. For example, it retrieves the range "A1:A10" from the sheet where sales data is entered.

[0678] Calculation execution

[0679] After retrieving the data in the specified range, the server executes the calculations specified by the user. For example, it calculates the average or total value of sales data. This allows the user to perform data analysis efficiently.

[0680] Formatting and sending the calculation results

[0681] The calculation result is formatted and automatically sent via a specified communication means. For example, the calculation result is formatted as the body of an email and sent to a specified recipient.

[0682] Proposals for improving business efficiency

[0683] Data on business efficiency improvements collected from each department is aggregated on a central server. Generative AI analyzes this data and generates proposals for further efficiency improvements. These proposals are presented in the form of specific action plans or scripts.

[0684] Creating and sharing standard programs

[0685] New scripts and macros are automatically generated based on the generated suggestions, and these programs are stored in a central repository and shared for use by other departments, establishing standardized and efficient business processes across the company.

[0686] Emotion engine integration

[0687] Emotion recognition and prioritization

[0688] The emotion engine recognizes the user's emotions in real time and adjusts the priority of computational tasks based on those emotions. For example, if the user is stressed, it will postpone less urgent tasks and prioritize more immediate tasks.

[0689] Providing feedback

[0690] The emotion engine provides appropriate feedback to the user based on the emotions it recognizes. For example, if the user is in an emotionally unstable state, it displays an encouraging message. Furthermore, by incorporating emotional information into the efficiency improvement proposals proposed by the generative AI based on emotion data, more practical suggestions can be made.

[0691] Accumulation and analysis of emotional data

[0692] The emotion engine accumulates and analyzes user emotional data. This data provides important insights for long-term operational efficiency and is reflected in work improvement proposals. For example, if stress levels are high during a particular time period, the engine will propose ways to reduce the workload during that time period.

[0693] Specific examples

[0694] A company's management department inputs daily sales data into a Google spreadsheet. The server retrieves this data at 9:00 AM every day and calculates the average and total sales figures. The calculation results are formatted and automatically emailed to the sales department leader. Sales representatives also enter emotional data using an emotion engine, which is collected on a central server. A generative AI analyzes this data and makes individual business efficiency proposals to each sales representative. Based on these proposals, standard calculation programs are generated and shared among management departments, resulting in business efficiency improvements across the company.

[0695] The processing flow will be explained below.

[0696] Step 1:

[0697] The user enters the required data into a Google spreadsheet or Excel file. For example, when entering sales data, the user enters the sales amount into the cell range "A1:A10".

[0698] Step 2:

[0699] Set a trigger that will run the server periodically. If you are using Google Apps Script, use the ScriptApp.newTrigger function to set a periodic trigger that runs "every day at 9:00 AM."

[0700] Step 3:

[0701] When the trigger fires, the server accesses the Google Spreadsheet or Excel file. For Google Spreadsheets, it uses the SpreadsheetApp.getActiveSpreadsheet() function.

[0702] Step 4:

[0703] The server retrieves data by specifying the target sheet and range. For example, the getRange("A1:A10") function is used to retrieve data from the range "A1:A10".

[0704] Step 5:

[0705] The data retrieved by the server is read as a two-dimensional array. Use the getValues() function to retrieve the cell data within the range in two-dimensional array format.

[0706] Step 6:

[0707] The server performs the calculation. For example, to calculate the average value of sales data, a for loop is used to sum each element of the array and divide by the total to calculate the average.

[0708] Step 7:

[0709] The server formats the calculation results. The calculation results are converted into a string format, for example, "Average sales: XX yen."

[0710] Step 8:

[0711] The server sends the formatted calculation results via the specified communication method, and then uses the MailApp.sendEmail() function to send an email containing the calculation results to the specified recipient.

[0712] Step 9:

[0713] The server logs the processing status. It uses the Logger.log() function to log that the calculation result has been sent.

[0714] Step 10:

[0715] Users input collected data on business efficiency into generative AI. For example, they can use Google Forms to collect information on business efficiency improvements from the general management department.

[0716] Step 11:

[0717] The server uses generative AI to analyze the accumulated data and generate suggestions for further efficiency improvements. For example, an AI model analyzes the data and suggests optimization measures for a specific business process.

[0718] Step 12:

[0719] The server automatically generates standard calculation programs and scripts based on the generated efficiency improvement proposals, providing specific code for improving business efficiency.

[0720] Step 13:

[0721] The server stores the generated scripts and programs in a central repository and makes them available to other departments, so they are shared across the company as a common means of efficiency.

[0722] Step 14:

[0723] The user inputs emotional data through the emotion engine, which, for example, recognizes emotions through the device's camera or microphone and sends the data to the server.

[0724] Step 15:

[0725] The server uses an emotion engine to analyze the user's emotions in real time and adjusts the priority of calculations based on that. For example, if the user is feeling stressed, the order of calculations will be changed.

[0726] Step 16:

[0727] The server generates feedback based on the user's emotions and provides it to the user. For example, if the user is feeling stressed, it displays an encouraging message.

[0728] Step 17:

[0729] The server accumulates emotional data and performs long-term analysis. This data is reflected in business efficiency proposals using generative AI. For example, if stress tends to be high during certain times of the day, the system will make proposals to reduce the workload during those times.

[0730] Specific examples

[0731] A company's management department inputs daily sales data into a Google spreadsheet. A server retrieves this data at 9:00 AM every day, calculates the average and total sales figures, and automatically sends them by email. Sales representatives also input emotional data using an emotion engine, which is collected on a central server. A generative AI analyzes this data and makes individual proposals for improving business efficiency. Based on these proposals, standard calculation programs are generated and shared among management departments, resulting in company-wide improvements in business efficiency.

[0732] Example 2

[0733] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0734] In modern business operations, a great deal of time and effort is spent on data collection, calculation processing, and proposing and implementing improvements to business efficiency. Furthermore, insufficient information sharing between departments often prevents further efficiency improvements. Furthermore, prioritization of tasks and feedback may be ineffective because users' feelings are not taken into consideration. New methods are needed to solve these issues and realize more productive and efficient business processes.

[0735] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple departments and proposing further efficiency improvements using a generative AI model, means for generating standard calculation programs based on the proposals and sharing them among departments, means for recognizing user emotions and adjusting processing priorities based on the emotions, and means for accumulating emotion data and reflecting it in long-term business efficiency improvements. This enables data collection, calculation processing, proposing and implementing business efficiency improvements, information sharing, and prioritizing tasks based on emotions.

[0736] A "user" is an entity that uses the system to input data and receives proposals for calculation processing and business efficiency improvements.

[0737] "Input data" refers to information provided by a user to the system, and includes, for example, sales data and data for improving business efficiency.

[0738] "Calculation processing" refers to arithmetic or logical processing performed on input data, including, for example, calculating averages or sums.

[0739] "Communication means" refers to the method used to automatically transmit computational results and efficiency suggestions, including, for example, email.

[0740] A "department" is a section in charge of business within a company, and includes, for example, a sales department and an accounting department.

[0741] "Data on improving business efficiency" is information collected from each department to improve business efficiency.

[0742] A "generative AI model" is an artificial intelligence technology that analyzes provided data and suggests further efficiency improvements.

[0743] A "standard calculation program" is a program that performs consistent calculation processing and is automatically created based on the suggestions of a generative AI model.

[0744] "Emotion recognition" is a technology that grasps a user's emotional state in real time.

[0745] "Emotion data" is information about a user's emotions collected through emotion recognition.

[0746] "Priority adjustment" is the process of reassessing and reordering the importance of work tasks based on perceived emotions.

[0747] "Storage" means storing data for a long period of time and using it for later analysis and recommendations.

[0748] "Long-term business efficiency" refers to efforts to continuously increase business productivity and efficiency by analyzing emotional and business data.

[0749] This system receives input data from users, performs calculations, and automatically transmits the results via a specified communication method. It also has the ability to analyze business efficiency data collected from multiple departments using a generative AI model, propose further efficiency improvements, generate standard calculation programs based on those proposals, and share them among departments. It also incorporates an emotion engine that recognizes user emotions, providing feedback based on emotions and adjusting processing priorities.

[0750] Generating a Program

[0751] The system's programming is implemented using Google Apps Script (GAS) and Excel macros. First, the user enters the necessary data into a Google spreadsheet or Excel file. The server then accesses these files and retrieves data from the specified range. For example, it retrieves the range "A1:A10" from the sheet where sales data is entered.

[0752] Calculation execution

[0753] After retrieving the data in the specified range, the server executes the calculations specified by the user. For example, it calculates the average or total value of sales data. This allows the user to perform data analysis efficiently.

[0754] Formatting and sending the calculation results

[0755] The calculation results are formatted and automatically sent via the specified communication method. For example, the calculation results are formatted as the body of an email and sent to the specified recipient. This function is realized using the MailApp class of Google Apps Script.

[0756] Proposals for improving business efficiency

[0757] Data on operational efficiency improvements collected from each department is aggregated on a central server. A generative AI model (e.g., OpenAI's GPT-3 model) analyzes this data and generates recommendations for further efficiency improvements. These recommendations are presented in the form of specific action plans or scripts.

[0758] Creating and sharing standard programs

[0759] The server automatically generates new scripts and macros based on the generated suggestions. These programs are stored in a central repository and shared for use by other departments, establishing standardized and efficient business processes across the company.

[0760] Emotion engine integration

[0761] Emotion recognition and prioritization

[0762] The emotion engine recognizes the user's emotions in real time and adjusts the priority of computational tasks based on those emotions. For example, if the user is stressed, it will postpone less urgent tasks and prioritize more urgent tasks.

[0763] Providing feedback

[0764] The emotion engine provides appropriate feedback to the user based on the recognized emotion. For example, if the user is in an emotionally unstable state, it displays an encouraging message. In addition, by reflecting emotional information in the efficiency suggestions proposed by the generative AI model based on emotion data, more practical suggestions can be made.

[0765] Accumulation and analysis of emotional data

[0766] The emotion engine accumulates and analyzes user emotional data. This data provides important insights for long-term operational efficiency and is reflected in work improvement proposals. For example, if stress levels are high during a particular time period, the engine will propose ways to reduce the workload during that time period.

[0767] Specific examples

[0768] In a certain company's departments, users enter daily sales data into a Google spreadsheet. The server retrieves this data at 9:00 AM every day and calculates the average and total sales values. The calculation results are formatted and automatically emailed to the sales department leader. Sales representatives also enter emotional data using an emotion engine, which is collected on a central server. A generative AI model analyzes this data and makes individual business efficiency suggestions to each sales representative. Based on these suggestions, standard calculation programs are generated and shared between departments, achieving business efficiency improvements across the company.

[0769] Prompt Sentence Examples

[0770] "Calculate the average and total values ​​based on the following sales data and email the results to me:

[0771] Sales data: 100, 200, 150, 120, 180"

[0772] The above is a specific embodiment for carrying out the present invention, which enables companies to automate data processing and improve business efficiency, and achieve standardization across departments.

[0773] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0774] Step 1:

[0775] Users input the necessary data into a Google Spreadsheet or Excel file. For example, they input daily sales data into cells "A1:A10." This input data becomes the basis for subsequent calculations.

[0776] Step 2:

[0777] At the specified time, for example 9:00 AM, the server accesses the spreadsheet using Google Apps Script and retrieves the data in the specified range. Specifically, it executes "SpreadsheetApp.getActiveSpreadsheet().getRange('A1:A10').getValues();" and stores the data in a variable. The spreadsheet data range is specified as input, and an array of data is obtained as output.

[0778] Step 3:

[0779] The server performs calculations based on the acquired data. For example, it calculates the average and total values ​​of sales data. Specifically, it calculates the average value with "avg = data.reduce((a, b) => a + b, 0) / data.length;" and calculates the total value with "total = data.reduce((a, b) => a + b, 0);". It uses the acquired data array as input and obtains the average and total values ​​as output.

[0780] Step 4:

[0781] The server formats the result of the calculation. Specifically, it converts the average and total values ​​into a single string. For example, "result = 'Average: ' + avg + ', Total: ' + total;". It uses the result of the calculation as input and gets the formatted string as output.

[0782] Step 5:

[0783] The server automatically sends the formatted calculation results to the specified recipient via email. Specifically, it executes the Google Apps Script "MailApp.sendEmail('address@example.com', 'Sales data results', result);". It uses the formatted string and the recipient's email address as input, and obtains the email sending status as output.

[0784] Step 6:

[0785] The server collects data for business efficiency from each department and aggregates it in a central server. For example, the productivity data and working hours of each department are stored in a database. Data from each department is used as input and an integrated data set is obtained as output.

[0786] Step 7:

[0787] The server inputs the collected business data into the generative AI model and generates efficiency improvement proposals. For example, the generative AI model uses a prompt statement such as "Please make business efficiency improvement proposals based on the following data." Using the business data and the prompt statement as input, the generated efficiency proposals are obtained as output.

[0788] Step 8:

[0789] The server automatically generates new scripts and macros based on suggestions from the generative AI model. Specifically, it uses Google Apps Script to create code that implements the proposed efficiency techniques. It uses the generated suggestions as input and obtains the efficiency-improving scripts and macros as output.

[0790] Step 9:

[0791] The server stores the generated scripts and macros in a central repository and shares them with other departments. Specifically, it uploads scripts to cloud storage, uses the generated scripts as input, and obtains a shareable state as output.

[0792] Step 10:

[0793] The device collects the user's emotional data using emotion recognition technology, such as facial recognition technology and emotion analysis software, to analyze the user's facial expressions. It uses the user's real-time video as input and obtains the emotional data as output.

[0794] Step 11:

[0795] The server analyzes the collected emotional data and adjusts the processing priorities. Specifically, if the stress level is high, tasks with low urgency are postponed. It uses emotional data as input and obtains an adjusted list of tasks as output.

[0796] Step 12:

[0797] The server provides emotional feedback to the user, for example, displaying a message such as "You seem to be under a lot of stress. Please take a short break." It uses emotional data as input and gets an appropriate feedback message as output.

[0798] The above is the specific processing flow of this system. These processing steps enable companies to efficiently automate a series of business processes, including data processing, business efficiency, and emotion recognition.

[0799] (Application example 2)

[0800] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0801] Improving work efficiency and reducing staff burdens at logistics centers are important issues in modern logistics operations. However, conventional systems are unable to adequately aggregate and analyze work data or optimize operations while taking into account staff emotions. This can easily lead to problems such as wasted work, incorrect deliveries, and increased staff stress. Furthermore, the inability to make real-time suggestions for improving efficiency poses a major constraint in operations that require rapid response.

[0802] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among departments, and means for analyzing emotional data collected from multiple users and adjusting feedback and calculation processing priorities based on the emotions. This enables efficient collection and analysis of work data at logistics centers and optimization of operations taking into account staff emotions.

[0803] "User" means a person or organization that utilizes the system to input data and receive the results of computations.

[0804] "Input data" refers to various information provided by the user to the system, including numerical data, text data, emotional data, and the like.

[0805] "Computation" refers to the mathematical or logical operations that a system performs on input data.

[0806] "Communication Method" refers to the method or protocol for transmitting the results of a computation to a designated recipient, such as email or notification.

[0807] A "department" refers to a group or section within a company or organization that is responsible for a particular function or task.

[0808] "Data on business efficiency" refers to various information collected to improve business processes and streamline them. This information includes data on working hours, workload, work procedures, etc.

[0809] "Generative AI" refers to artificial intelligence that analyzes collected data, proposes efficiency improvements, and generates new calculation programs.

[0810] A "standard calculation program" refers to a standardized calculation script or program that is automatically generated by generative AI based on suggestions.

[0811] "Emotion data" is information that represents the user's emotional state, including stress level, fatigue level, and the like.

[0812] "Real-time" refers to a state in which processing and analysis are carried out close to the moment data is generated.

[0813] "Suggestions" refer to improvement suggestions and optimization instructions that generative AI makes to improve business efficiency.

[0814] The program for the system that realizes this application example is generated using Google Apps Script (GAS) and a framework for smartphone application development (e.g., React Native).

[0815] System configuration

[0816] Smartphone (Android or iOS)

[0817] Servers (database servers and application servers)

[0818] Google Apps Script (GAS)

[0819] React Native

[0820] Emotion engine (Emotion API, etc.)

[0821] Generative AI (e.g., OpenAI API)

[0822] Data collection

[0823] Users (logistics center staff) input work data through a smartphone app. This work data includes information such as warehousing, shipping, and inventory confirmation.

[0824] The terminal (smartphone) transmits the data entered by the user to the server in real time.

[0825] Calculation execution

[0826] The server receives the data and uses Google Apps Script (GAS) to retrieve the data in the specified range. For example, extracting data in a specified cell range from a spreadsheet.

[0827] The server performs calculations using GAS, such as calculating the average number of outgoing orders and the total inventory amount.

[0828] Formatting and sending the calculation results

[0829] The server formats the calculation results and stores them in a cloud database.

[0830] The server pushes the formatted results to the user's device in real time.

[0831] Proposals for improving business efficiency

[0832] The server systematically aggregates business efficiency data collected from each department.

[0833] Generative AI on the server (for example, OpenAI's API) generates business efficiency improvement proposals based on the collected data, such as adjusting work shifts or changing inventory management methods.

[0834] Based on the proposals, the server automatically generates new standard calculation programs and stores and shares them in a central repository.

[0835] Emotion engine integration

[0836] The device uses an emotion engine (such as Emotion API) to recognize the user's emotions in real time.

[0837] The server can then use the recognized emotion data to adjust the priority of the user's feedback and computational processes. For example, if the user is under high stress, it can postpone certain processes and send encouraging messages.

[0838] Specific examples

[0839] After completing a shipping task, a logistics center staff member enters the details of the task and their emotional state into a smartphone app. The device sends the input data to a server, which then retrieves a specified range of spreadsheet data and performs calculations based on the data. For example, it calculates the average number of shipping tasks per day and stores the results in a cloud database. The server then pushes the results to the device and uses an emotion engine to analyze the employee's stress level, sending an encouraging message if stress levels are high. Furthermore, the generative AI uses the collected data to make suggestions for efficiency improvements, such as "dividing shifts into morning and afternoon shifts to reduce the number of shipping tasks by 15%."

[0840] Example prompts to input to the generative AI model

[0841] Please provide suggestions for improving the efficiency of shipping operations at a logistics center. The input data is as follows:

[0842] 1. Number of shipping operations: 30

[0843] 2. Stock: 5000 items

[0844] 3. Staff emotional data: High stress level, medium fatigue level

[0845] Examples of suggestions: adjusting work shifts, changing inventory management methods, specific methods to maintain staff motivation, etc.

[0846] This approach improves work efficiency at the logistics center and reduces the burden on staff, optimizing overall operations.

[0847] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0848] Step 1:

[0849] The user inputs work data and emotional data into a smartphone app. At this time, the user inputs specific data about delivery work and inventory checks, and the emotion engine automatically detects the user's current emotional state (such as stress level and fatigue level). Examples of input data include the number of delivery work tasks, inventory volume, and stress level.

[0850] Step 2:

[0851] The device transmits the input task data and emotion data to the server in real time. The smartphone app then transmits the data to the cloud server via an internet connection. The transmitted data includes the task details, inventory information, and the user's emotion data.

[0852] Step 3:

[0853] The server parses the received data and retrieves the data in the specified range using Google Apps Script (GAS). In this step, the data in the required cell range (e.g., A1:D10) is read from the spreadsheet. This allows for consistent retrieval of working data.

[0854] Step 4:

[0855] The server performs calculations on the acquired spreadsheet data. For example, it uses Google Apps Script (GAS) to calculate the number of shipping operations per day, the average inventory amount, and the total amount. This process provides the user with the necessary statistical information.

[0856] Step 5:

[0857] The server formats the results and stores them in a cloud database. The formatting process converts the results into an easy-to-read format and then registers them in the database. At this stage, the results of the calculation are persisted.

[0858] Step 6:

[0859] The server then pushes the formatted results to the user's device in real time. The notification includes the calculation results (e.g., the average number of outgoing shipments), and the user can immediately check the results.

[0860] Step 7:

[0861] Generative AI on the server (for example, OpenAI's API) generates business efficiency improvement proposals based on the collected data, including specific suggestions such as "Review shifts to reduce the workload of shipping work by 15%."

[0862] Step 8:

[0863] The server automatically generates new standard calculation programs based on the suggestions of the generative AI. The generated programs are written as scripts and stored in a central repository. These scripts can then be shared with other departments.

[0864] Step 9:

[0865] The device's emotion engine (such as Emotion API) recognizes the user's emotions in real time and sends the data to the server. Emotion data indicates the user's stress level, fatigue level, etc.

[0866] Step 10:

[0867] The server uses the emotion data to provide feedback to the user and adjust the priority of computational processing. For example, if the user is in a high-stress state, it may lower the priority of stressful tasks or send encouraging messages.

[0868] Step 11:

[0869] The server accumulates emotional and operational data over the long term and reflects it in the generative AI's proposals. This data is used in monthly reports and for specific operational improvement plans.

[0870] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0871] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0872] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0873] [Third embodiment]

[0874] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0875] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0876] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0877] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0878] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0879] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0880] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0881] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0882] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0883] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0884] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0885] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0886] This system allows users to input data, automatically performs calculations on that data, and automatically transmits the results. It also includes functions to collect data on business efficiency improvements from each department, use generative AI to propose further efficiency improvements, generate standard calculation programs based on those proposals, and share them among departments.

[0887] Generating a Program

[0888] The program for this system is implemented using Google Apps Script (GAS) and Excel macros. The program is structured as follows:

[0889] 1. Data Collection:

[0890] Users enter the required data into a Google spreadsheet or Excel file.

[0891] The server accesses the specified spreadsheet or Excel file and retrieves data from the specified range.

[0892] 2. Performing the calculation:

[0893] The server performs calculations (e.g., average, standard deviation, etc.) set by the user on the acquired data.

[0894] 3. Formatting and sending the results:

[0895] The server formats the results of the computation and automatically transmits them via the specified communication method (e.g., email, messaging application).

[0896] As a concrete example, consider a spreadsheet where a user has entered sales data into the range "A1:A10." The server retrieves this data, calculates the average sales amount for each cell, and then formats and emails the results to designated recipients as a daily report.

[0897] AI-based efficiency proposals

[0898] Data on business efficiency improvements collected by each department is stored on a central server. Generative AI analyzes this data and makes suggestions for further efficiency improvements. These suggestions may include, for example, methods for automating specific calculation processes or ways to optimize data management.

[0899] Users can receive AI suggestions and generate new scripts and macros based on those suggestions, improving their efficiency and overall business performance.

[0900] Creating and sharing standard programs

[0901] The scripts and macros created based on the generative AI's suggestions are stored on a central server. These standardized programs are shared so that they can be used by other departments. This results in the establishment of standardized, efficient business processes across the company.

[0902] In this way, the present invention provides a system that automates and streamlines the entire business process, from data collection and calculation processing to automatic distribution of results and even AI-based efficiency proposals.By making it possible to share this information with other management departments, it is expected that the business efficiency of the entire organization will be greatly improved.

[0903] The processing flow will be explained below.

[0904] Step 1:

[0905] The user enters the required data into a Google spreadsheet or Excel file. If specifying a range, specify the range (e.g., "A1:A10").

[0906] Step 2:

[0907] Set a trigger that runs the server periodically. This trigger can be set to run every day at 9:00 AM using a GAS or Excel macro script.

[0908] Step 3:

[0909] When the periodic trigger is activated, the server accesses the Google Spreadsheet or Excel file using the SpreadsheetApp.getActiveSpreadsheet() function (for Google Spreadsheets).

[0910] Step 4:

[0911] The server retrieves the specified sheet and range. For example, use the getRange("A1:A10") function to retrieve the cell data in the specified range "A1:A10".

[0912] Step 5:

[0913] The data retrieved by the server is read as a two-dimensional array. Use the getValues() function to retrieve all cell values ​​in the range as a two-dimensional array.

[0914] Step 6:

[0915] The server performs the calculation. For example, to calculate an average, a for loop is used to sum up each element of an array and calculate the average.

[0916] Step 7:

[0917] The server formats the results appropriately: convert the results (e.g., averages) into strings and format them to fit the report format.

[0918] Step 8:

[0919] The server sends the formatted results via a communication method such as email or a messaging application. The MailApp.sendEmail() function is used to send the results to the specified recipient.

[0920] Step 9:

[0921] The server logs the completion of sending the calculation results. Use the Logger.log() function to record the completion status of the process for subsequent troubleshooting.

[0922] Step 10:

[0923] Users collect data on business efficiency from each department and input it into the generative AI. For example, they can aggregate business efficiency information from each department via Google Forms or Excel sheets.

[0924] Step 11:

[0925] The server uses generative AI to generate suggestions for further efficiency improvements based on the collected data. The AI ​​model performs analysis and proposes effective improvements for specific business processes.

[0926] Step 12:

[0927] The server automatically generates standard calculation programs and scripts based on the generated proposals, thereby providing business efficiency improvements in the form of concrete code.

[0928] Step 13:

[0929] The generated programs and scripts are stored in a central repository by a server, which can be accessed by other departments and used as a common means of efficiency.

[0930] Step 14:

[0931] Users can then apply the generated scripts and programs to their own departments as needed, thereby sharing and standardizing efficiency gains and improving efficiency across the company.

[0932] Example 1

[0933] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0934] In the conventional system, users had to manually input data, perform calculations, and manually submit the results, which was time-consuming and labor-intensive. It was also difficult to collect data on the operational efficiency of each department and make recommendations for efficiency improvements based on that data. Furthermore, there was a lack of a way to generate standard calculation programs based on those recommendations and share them among departments. There was a need to solve these problems and improve operational efficiency across the company.

[0935] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0936] In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting business efficiency data from multiple management departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among the management departments, means for using software for data processing and data calculation based on user input data, means for using communication means for formatting and automatically transmitting the calculation results, and means for executing calculation processing set by the user. This enables automatic data processing and immediate delivery of results, and enables company-wide improvement in business efficiency through efficiency proposals by generative AI and the sharing of programs based on those proposals.

[0937] "User" refers to the entity that uses the system to input data and configure the calculation process.

[0938] "Server" refers to a computer system whose role is to receive input data from a user, perform calculations, and automatically transmit the results via a designated communication means.

[0939] "Input data" refers to data such as numbers and strings that users enter into Google Spreadsheets, Excel files, etc.

[0940] "Calculation processing" refers to various arithmetic operations that the server performs based on input data, and specifically includes calculation of average values ​​and standard deviations.

[0941] "Communication means" refers to the method used by the server to transmit the results of computation, including email and messaging applications.

[0942] "Generative AI" refers to an artificial intelligence model that analyzes collected business efficiency data and generates suggestions for further efficiency improvements.

[0943] "Data on improving business efficiency" refers to information collected from each management department to improve the efficiency of overall business operations.

[0944] A "standard program" refers to a calculation program that is generated based on suggestions from generative AI and is used in common by multiple management departments.

[0945] "Data processing" refers to the process of preparing input data in an appropriate format.

[0946] "Data calculation" refers to various calculation processes performed based on data.

[0947] A "trigger" is a trigger that periodically executes a calculation process based on a date or time.

[0948] A "script" is a series of commands used to automate a computation or data collection.

[0949] This system automatically performs calculations based on data entered by the user and automatically transmits the results via a specified communication method. It also includes functions to collect data on business efficiency improvements from each department, use generative AI to propose further efficiency improvements, generate standard calculation programs based on the proposals, and share the results among departments.

[0950] System configuration

[0951] Hardware

[0952] Server: A central computer system that collects data, processes calculations, formats and transmits the results.

[0953] Terminal: The device (computer, tablet, etc.) through which a user enters data.

[0954] software

[0955] Google Apps Script (GAS): A script for manipulating Google Spreadsheets to automate data collection and calculation processes.

[0956] Excel Macro: A program for manipulating Excel files and automating data collection and calculation processes.

[0957] Communication methods: email, messaging applications, etc.

[0958] Program processing

[0959] User operations

[0960] Users enter necessary information such as sales data and inventory data into a Google spreadsheet or Excel file. Specifically, it is assumed that data will be entered into the cell range "A1:A10" in the Google spreadsheet.

[0961] Server Operation

[0962] The server uses Google Apps Script (GAS) or Excel macros to collect the user-entered data from a specified spreadsheet or Excel file. For example, it retrieves data from the cell range "A1:A10."

[0963] The server then performs calculations (e.g., average, standard deviation, etc.) on the collected data as configured by the user. For example, to calculate the average value of the acquired sales data, the server adds up the values ​​of each cell and divides by the number of cells.

[0964] Formatting and sending the calculation results

[0965] The server formats the results of the calculations and makes them easy to understand, such as "Daily Report: Average sales is XX yen." It then automatically sends these results to the user or other recipients via the specified communication method. Specifically, it automatically sends an email containing the results to the specified email address.

[0966] AI-based efficiency proposals

[0967] Server Operation

[0968] Data on business efficiency improvements collected from each department is stored on a central server. A generative AI model on the server analyzes this data and makes suggestions for further improvements to business efficiency. New scripts and macros are then generated based on these suggestions and stored on the central server.

[0969] Prompt Sentence Examples

[0970] The server uses a generative AI model to generate efficiency suggestions using prompt sentences such as the following:

[0971] "Please analyze the operational efficiency data collected by each department and propose ways to automate specific calculation processes. Then, please tell me how to generate a Google Apps Script based on those proposals and share it with other departments."

[0972] Specific examples

[0973] 1. A user enters sales data into a Google spreadsheet

[0974] Action: The user enters sales data into the range "A1:A10".

[0975] 2. The server collects the data

[0976] Operation: The server uses Google Apps Script to read the data in "A1:A10".

[0977] 3. User sets the average calculation

[0978] Operation: The user selects "Calculate the average of sales data" on the program settings screen.

[0979] 4. The server calculates the average

[0980] Operation: The server calculates the average value of the data it retrieves.

[0981] 5. Formatting the calculation results

[0982] Operation: The server formats the calculation result as "Daily report: Average sales is XX yen."

[0983] 6. Send the results to the specified email address

[0984] What it does: The server automatically sends the formatted results to the specified email address.

[0985] 7. Data on operational efficiency is stored on a central server

[0986] Operation: The server periodically collects data from each management department and stores it in a database.

[0987] 8. Generative AI makes efficiency suggestions

[0988] How it works: A generative AI model analyzes data and generates suggestions for automating specific computational tasks.

[0989] 9. Generate and share new scripts

[0990] How it works: The server creates a script based on the suggestions of the generated AI and saves it in a shared folder.

[0991] In this way, the present invention provides an integrated system for automating and streamlining the entire business process, from data collection and calculation processing to automatic distribution of results and even efficiency suggestions using generative AI, which is expected to significantly improve the business efficiency of the entire organization.

[0992] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0993] Step 1: Enter your data

[0994] User operations

[0995] The user manually enters the necessary data into a Google spreadsheet or Excel file using the device. Specifically, the sales data is entered into the cell range "A1:A10" in the Google spreadsheet.

[0996] Input: Sales data (cell range A1:A10)

[0997] Output: Input sales data

[0998] Step 2: Collect data

[0999] Server Operation

[1000] The server uses Google Apps Script (GAS) or Excel macros to collect data from the specified spreadsheet or Excel file from the user's device. Specifically, the server reads data from the cell range "A1:A10."

[1001] Input: Entered sales data (cell range A1:A10)

[1002] Output: Collected sales data

[1003] Step 3: Set up the calculation

[1004] User operations

[1005] The user uses the terminal to set the type of calculation processing to be performed on the server. Specifically, on the calculation processing setting screen, the user selects the option "Calculate the average of sales data."

[1006] Input: Calculation settings (e.g., calculating the average value of sales data)

[1007] Output: Setting information for the calculation process

[1008] Step 4: Performing the calculation

[1009] Server Operation

[1010] The server performs the configured calculations on the collected sales data. Specifically, it calculates the average value of the sales data for each cell. The server converts the collected data into a numeric array and sums each element to find the average value.

[1011] Input: Setting information for the calculation process, collected sales data

[1012] Output: Calculation result (average value of sales data)

[1013] Step 5: Formatting the results

[1014] Server Operation

[1015] The server formats the results of the calculations and converts them into a displayable format, such as "Daily report: average sales is XX yen."

[1016] Input: Calculation result (average value of sales data)

[1017] Output: A formatted message of the calculation result

[1018] Step 6: Sending the calculation results

[1019] Server Operation

[1020] The server sends the formatted message containing the calculation result using the specified communication method (e.g., email, messaging app). Specifically, it includes the formatted message in the body of the email and sends it to the specified email address.

[1021] Input: Formatted message of the calculation result

[1022] Output: Message of the calculation result sent

[1023] Step 7: Collect data on operational efficiency

[1024] Server Operation

[1025] The server collects data from each department for the purpose of improving business efficiency and stores it in the central server. Specifically, it collects reports and data tables sent periodically from each department and stores them in a database.

[1026] Input: Business efficiency data provided by each management department

[1027] Output: Business efficiency data stored on a central server

[1028] Step 8: Generative AI proposes efficiency improvements

[1029] How generative AI models work

[1030] The generative AI model analyzes the accumulated operational efficiency data and generates proposals for further operational efficiency improvements. Specifically, it analyzes the data to identify bottlenecks and areas for improvement, and proposes methods for automating specific processes.

[1031] Input: Accumulated business efficiency data

[1032] Output: Efficiency suggestions (e.g., how to automate specific calculation processes)

[1033] Step 9: Generate and share a standard program

[1034] Server Operation

[1035] The server generates new scripts and macros based on the suggestions of the generative AI model and stores them on the central server. Specifically, scripts are created based on the proposed automation methods and saved in a shared folder, making them available to other departments.

[1036] Input: Proposal for efficiency improvement, proposed content of generative AI model

[1037] Output: Generated boilerplate programs, shared scripts and macros

[1038] The above is the specific processing flow of the program for this system. By explaining the operations, inputs, and outputs performed at each processing step, the operation of the entire system becomes easier to understand.

[1039] (Application example 1)

[1040] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1041] In current logistics centers, processing a wide range of data and making proposals for improving operational efficiency is often done manually. This makes it difficult to collect and process data quickly and accurately, hindering efficient business operations. Furthermore, making proposals for improving efficiency requires advanced specialized knowledge, which is rarely shared across the organization. This makes it difficult to standardize operations and improve overall efficiency.

[1042] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1043] In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple management departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among the management departments, means for applying the data collection and calculation processing to inventory management and work analysis at the logistics center, and means for generating new scripts and macros based on the efficiency improvement proposals, and for analyzing and reporting the data. This enables fast and accurate data collection and processing, automatic generation of efficiency improvement proposals, and data analysis and reporting for business efficiency improvements.

[1044] "User" means a person who inputs data or receives results to use the system, or who performs a task.

[1045] "Input data" refers to data provided by a user to a system, and is the information that forms the basis for calculations and analysis.

[1046] "Computational processing" refers to mathematical and statistical manipulations and operations performed on input data.

[1047] "Communication methods" refers to the technologies and methods used to communicate computational results and efficiency suggestions to users and other departments. Examples include email and messaging applications.

[1048] "Multiple administrative functions" refers to the multiple departments or groups within an organization that are responsible for overseeing operations and driving efficiency.

[1049] "Data on business efficiency" refers to data that includes indicators and information for evaluating the efficiency of business processes and tasks.

[1050] "Generative AI" refers to artificial intelligence that analyzes collected data and automatically generates proposals for improving business efficiency based on that data.

[1051] "Proposals" refer to specific guidelines and methods for improving business efficiency and work processes that are automatically created by generative AI.

[1052] A "standard calculation program" refers to a program that performs calculation processing that is standardized based on a proposal and can be used repeatedly.

[1053] "Means for sharing among management departments" refers to methods and techniques for making the generated standard calculation programs available to other management departments.

[1054] A "logistics center" refers to a facility that manages inventory, picks products, and prepares them for shipping.

[1055] "Inventory management" refers to the business process of monitoring and managing the storage status and quantity of goods at a logistics center.

[1056] "Work analysis" refers to the investigation and analysis carried out to evaluate the efficiency and effectiveness of various business processes carried out within a logistics center.

[1057] "Script" refers to program code written to automate specific computations or data manipulations.

[1058] A "macro" is a program or script used to automate a specific task or sequence of actions.

[1059] "Data analysis and reporting" refers to the business process of analyzing collected data and providing the results in the form of a report or report.

[1060]

[1061] This invention is a system that supports inventory management, work analysis, and operational efficiency improvement in logistics centers. The system allows users to input data, performs calculations based on that data, and automatically transmits the results. It also includes a function that uses generative AI to make suggestions for operational efficiency improvement, generates standard calculation programs based on those suggestions, and shares them with other management departments.

[1062] The program for this system is implemented using Google Apps Script (GAS) and other scripting languages. The specific implementation method for the system is explained below.

[1063] Hardware and Software

[1064] The system uses devices such as servers, smartphones, tablets, and robots, and the program runs on Google Apps Script (GAS), spreadsheets, email systems, and generative AI models (e.g., Google Cloud AI).

[1065] Program processing flow

[1066] 1. Data Collection

[1067] The server collects inventory and work data in real time from users' smartphones and robots, and stores this data in a Google spreadsheet.

[1068] 2. Computational Processing

[1069] The server performs calculations on the stored data, specifically calculating the average time and error rate of picking tasks.

[1070] 3. Automatic transmission of results

[1071] The server automatically sends the results of the calculations to the administrator via email or messaging application, allowing the administrator to always be up-to-date on the latest business status.

[1072] 4. Generate efficiency proposals

[1073] The server inputs the collected data into a generative AI model to generate proposals for improving business efficiency. These proposals are then embodied as new scripts or macros that can be shared with other management departments.

[1074] Specific examples

[1075] A logistics center manager uses this system to improve the efficiency of picking work. The input picking data (start time, end time, error rate, etc.) is saved in a spreadsheet, and the server calculates the average time and error rate. The calculation results are automatically sent to the manager, and the generative AI model analyzes the data and makes suggestions for improving efficiency. New scripts and macros are generated based on these suggestions, improving overall work efficiency.

[1076] Example prompt for a generative AI model:

[1077] The following is data on picking operations at a distribution center. Please create a proposal for improving efficiency based on this data. The data includes the start time, end time, and error rate for each picking operation:

[1078] Start time: 08:00, End time: 08:15, Error rate: 2%

[1079] Start time: 08:20, End time: 08:35, Error rate: 1%

[1080] ...

[1081] Use these to generate efficiency suggestions."

[1082] In this way, the present invention can significantly improve overall business efficiency by automating the collection, analysis, and efficiency improvement proposals of real-time data at logistics centers.

[1083] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1084] Step 1: Data collection

[1085] Users use smartphones, tablets, or robots to input inventory information and work performance data for the distribution center. This includes product location, quantity, picking start and end times, and error rates. The input data is saved in real time to a Google spreadsheet. The device collects the data and stores it in a spreadsheet, making it accessible to the server.

[1086] Step 2: Data Acquisition

[1087] The server periodically accesses the Google spreadsheet and retrieves data from the specified range. To retrieve the data, Google Apps Script (GAS) is used to read the data in the specified range (e.g., "A1:D100" in the "Inventory Information" sheet). This data is converted into a database format and used for subsequent calculation processing.

[1088] Step 3: Calculations

[1089] The server then performs calculations on the retrieved data, such as average time, error rate, and inventory fluctuations. For example, to calculate the average time it takes to pick a particular item, the server calculates the difference between the start time and end time and divides it by the total time for all items. The results of this calculation are temporarily stored and used in the next step.

[1090] Step 4: Automatically send calculation results

[1091] The server formats the calculation results and automatically sends them to the administrator via the specified communication method (e.g., email or messaging application). The formatted data is then output in a format that is easy for the administrator to understand (e.g., a table or graph), allowing the administrator to quickly and easily check the data.

[1092] Step 5: Generate efficiency proposals

[1093] The server inputs the collected data and calculation results into a generative AI model to generate business efficiency improvement proposals. The AI ​​model incorporates analytical algorithms based on past data and trends, analyzes the input data, and outputs optimal proposals. These generated proposals are then embodied as new scripts or macros.

[1094] Step 6: Share your efficiency suggestions

[1095] The server stores standardized calculation programs on a central server to share the generated efficiency proposals with other management departments. This allows other departments to use the same efficiency proposals, achieving company-wide business efficiency. The shared programs can also be accessed from other terminals, promoting the standardization of business processes.

[1096] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1097] This system receives input data from users, performs calculations, and automatically transmits the results via a specified communication method. It also uses generative AI to analyze business efficiency data collected from multiple departments, proposes further improvements, generates standard calculation programs based on those proposals, and shares them among departments. It also incorporates an emotion engine that recognizes users' emotions, providing feedback based on emotions and adjusting processing priorities.

[1098] Generating a Program

[1099] The system is programmed using Google Apps Script (GAS) and Excel macros. The system configuration is as follows:

[1100] Data collection

[1101] The user enters the required data into a Google spreadsheet or Excel file. The server accesses the file and retrieves the data from the specified range. For example, it retrieves the range "A1:A10" from the sheet where sales data is entered.

[1102] Calculation execution

[1103] After retrieving the data in the specified range, the server executes the calculations specified by the user. For example, it calculates the average or total value of sales data. This allows the user to perform data analysis efficiently.

[1104] Formatting and sending the calculation results

[1105] The calculation result is formatted and automatically sent via a specified communication means. For example, the calculation result is formatted as the body of an email and sent to a specified recipient.

[1106] Proposals for improving business efficiency

[1107] Data on business efficiency improvements collected from each department is aggregated on a central server. Generative AI analyzes this data and generates proposals for further efficiency improvements. These proposals are presented in the form of specific action plans or scripts.

[1108] Creating and sharing standard programs

[1109] New scripts and macros are automatically generated based on the generated suggestions, and these programs are stored in a central repository and shared for use by other departments, establishing standardized and efficient business processes across the company.

[1110] Emotion engine integration

[1111] Emotion recognition and prioritization

[1112] The emotion engine recognizes the user's emotions in real time and adjusts the priority of computational tasks based on those emotions. For example, if the user is stressed, it will postpone less urgent tasks and prioritize more immediate tasks.

[1113] Providing feedback

[1114] The emotion engine provides appropriate feedback to the user based on the emotions it recognizes. For example, if the user is in an emotionally unstable state, it displays an encouraging message. Furthermore, by incorporating emotional information into the efficiency improvement proposals proposed by the generative AI based on emotion data, more practical suggestions can be made.

[1115] Accumulation and analysis of emotional data

[1116] The emotion engine accumulates and analyzes user emotional data. This data provides important insights for long-term operational efficiency and is reflected in work improvement proposals. For example, if stress levels are high during a particular time period, the engine will propose ways to reduce the workload during that time period.

[1117] Specific examples

[1118] A company's management department inputs daily sales data into a Google spreadsheet. The server retrieves this data at 9:00 AM every day and calculates the average and total sales figures. The calculation results are formatted and automatically emailed to the sales department leader. Sales representatives also enter emotional data using an emotion engine, which is collected on a central server. A generative AI analyzes this data and makes individual business efficiency proposals to each sales representative. Based on these proposals, standard calculation programs are generated and shared among management departments, resulting in business efficiency improvements across the company.

[1119] The processing flow will be explained below.

[1120] Step 1:

[1121] The user enters the required data into a Google spreadsheet or Excel file. For example, when entering sales data, the user enters the sales amount into the cell range "A1:A10".

[1122] Step 2:

[1123] Set a trigger that will run the server periodically. If you are using Google Apps Script, use the ScriptApp.newTrigger function to set a periodic trigger that runs "every day at 9:00 AM."

[1124] Step 3:

[1125] When the trigger fires, the server accesses the Google Spreadsheet or Excel file. For Google Spreadsheets, it uses the SpreadsheetApp.getActiveSpreadsheet() function.

[1126] Step 4:

[1127] The server retrieves data by specifying the target sheet and range. For example, the getRange("A1:A10") function is used to retrieve data from the range "A1:A10".

[1128] Step 5:

[1129] The data retrieved by the server is read as a two-dimensional array. Use the getValues() function to retrieve the cell data within the range in two-dimensional array format.

[1130] Step 6:

[1131] The server performs the calculation. For example, to calculate the average value of sales data, a for loop is used to sum each element of the array and divide by the total to calculate the average.

[1132] Step 7:

[1133] The server formats the calculation results. The calculation results are converted into a string format, for example, "Average sales: XX yen."

[1134] Step 8:

[1135] The server sends the formatted calculation results via the specified communication method, and then uses the MailApp.sendEmail() function to send an email containing the calculation results to the specified recipient.

[1136] Step 9:

[1137] The server logs the processing status. It uses the Logger.log() function to log that the calculation result has been sent.

[1138] Step 10:

[1139] Users input collected data on business efficiency into generative AI. For example, they can use Google Forms to collect information on business efficiency improvements from the general management department.

[1140] Step 11:

[1141] The server uses generative AI to analyze the accumulated data and generate suggestions for further efficiency improvements. For example, an AI model analyzes the data and suggests optimization measures for a specific business process.

[1142] Step 12:

[1143] The server automatically generates standard calculation programs and scripts based on the generated efficiency improvement proposals, providing specific code for improving business efficiency.

[1144] Step 13:

[1145] The server stores the generated scripts and programs in a central repository and makes them available to other departments, so they are shared across the company as a common means of efficiency.

[1146] Step 14:

[1147] The user inputs emotional data through the emotion engine, which, for example, recognizes emotions through the device's camera or microphone and sends the data to the server.

[1148] Step 15:

[1149] The server uses an emotion engine to analyze the user's emotions in real time and adjusts the priority of calculations based on that. For example, if the user is feeling stressed, the order of calculations will be changed.

[1150] Step 16:

[1151] The server generates feedback based on the user's emotions and provides it to the user. For example, if the user is feeling stressed, it displays an encouraging message.

[1152] Step 17:

[1153] The server accumulates emotional data and performs long-term analysis. This data is reflected in business efficiency proposals using generative AI. For example, if stress tends to be high during certain times of the day, the system will make proposals to reduce the workload during those times.

[1154] Specific examples

[1155] A company's management department inputs daily sales data into a Google spreadsheet. A server retrieves this data at 9:00 AM every day, calculates the average and total sales figures, and automatically sends them by email. Sales representatives also input emotional data using an emotion engine, which is collected on a central server. A generative AI analyzes this data and makes individual proposals for improving business efficiency. Based on these proposals, standard calculation programs are generated and shared among management departments, resulting in company-wide improvements in business efficiency.

[1156] Example 2

[1157] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1158] In modern business operations, a great deal of time and effort is spent on data collection, calculation processing, and proposing and implementing improvements to business efficiency. Furthermore, insufficient information sharing between departments often prevents further efficiency improvements. Furthermore, prioritization of tasks and feedback may be ineffective because users' feelings are not taken into consideration. New methods are needed to solve these issues and realize more productive and efficient business processes.

[1159] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple departments and proposing further efficiency improvements using a generative AI model, means for generating standard calculation programs based on the proposals and sharing them among departments, means for recognizing user emotions and adjusting processing priorities based on the emotions, and means for accumulating emotion data and reflecting it in long-term business efficiency improvements. This enables data collection, calculation processing, proposing and implementing business efficiency improvements, information sharing, and prioritizing tasks based on emotions.

[1160] A "user" is an entity that uses the system to input data and receives proposals for calculation processing and business efficiency improvements.

[1161] "Input data" refers to information provided by a user to the system, and includes, for example, sales data and data for improving business efficiency.

[1162] "Calculation processing" refers to arithmetic or logical processing performed on input data, including, for example, calculating averages or sums.

[1163] "Communication means" refers to the method used to automatically transmit computational results and efficiency suggestions, including, for example, email.

[1164] A "department" is a section in charge of business within a company, and includes, for example, a sales department and an accounting department.

[1165] "Data on improving business efficiency" is information collected from each department to improve business efficiency.

[1166] A "generative AI model" is an artificial intelligence technology that analyzes provided data and suggests further efficiency improvements.

[1167] A "standard calculation program" is a program that performs consistent calculation processing and is automatically created based on the suggestions of a generative AI model.

[1168] "Emotion recognition" is a technology that grasps a user's emotional state in real time.

[1169] "Emotion data" is information about a user's emotions collected through emotion recognition.

[1170] "Priority adjustment" is the process of reassessing and reordering the importance of work tasks based on perceived emotions.

[1171] "Storage" means storing data for a long period of time and using it for later analysis and recommendations.

[1172] "Long-term business efficiency" refers to efforts to continuously increase business productivity and efficiency by analyzing emotional and business data.

[1173] This system receives input data from users, performs calculations, and automatically transmits the results via a specified communication method. It also has the ability to analyze business efficiency data collected from multiple departments using a generative AI model, propose further efficiency improvements, generate standard calculation programs based on those proposals, and share them among departments. It also incorporates an emotion engine that recognizes user emotions, providing feedback based on emotions and adjusting processing priorities.

[1174] Generating a Program

[1175] The system's programming is implemented using Google Apps Script (GAS) and Excel macros. First, the user enters the necessary data into a Google spreadsheet or Excel file. The server then accesses these files and retrieves data from the specified range. For example, it retrieves the range "A1:A10" from the sheet where sales data is entered.

[1176] Calculation execution

[1177] After retrieving the data in the specified range, the server executes the calculations specified by the user. For example, it calculates the average or total value of sales data. This allows the user to perform data analysis efficiently.

[1178] Formatting and sending the calculation results

[1179] The calculation results are formatted and automatically sent via the specified communication method. For example, the calculation results are formatted as the body of an email and sent to the specified recipient. This function is realized using the MailApp class of Google Apps Script.

[1180] Proposals for improving business efficiency

[1181] Data on operational efficiency improvements collected from each department is aggregated on a central server. A generative AI model (e.g., OpenAI's GPT-3 model) analyzes this data and generates recommendations for further efficiency improvements. These recommendations are presented in the form of specific action plans or scripts.

[1182] Creating and sharing standard programs

[1183] The server automatically generates new scripts and macros based on the generated suggestions. These programs are stored in a central repository and shared for use by other departments, establishing standardized and efficient business processes across the company.

[1184] Emotion engine integration

[1185] Emotion recognition and prioritization

[1186] The emotion engine recognizes the user's emotions in real time and adjusts the priority of computational tasks based on those emotions. For example, if the user is stressed, it will postpone less urgent tasks and prioritize more urgent tasks.

[1187] Providing feedback

[1188] The emotion engine provides appropriate feedback to the user based on the recognized emotion. For example, if the user is in an emotionally unstable state, it displays an encouraging message. In addition, by reflecting emotional information in the efficiency suggestions proposed by the generative AI model based on emotion data, more practical suggestions can be made.

[1189] Accumulation and analysis of emotional data

[1190] The emotion engine accumulates and analyzes user emotional data. This data provides important insights for long-term operational efficiency and is reflected in work improvement proposals. For example, if stress levels are high during a particular time period, the engine will propose ways to reduce the workload during that time period.

[1191] Specific examples

[1192] In a certain company's departments, users enter daily sales data into a Google spreadsheet. The server retrieves this data at 9:00 AM every day and calculates the average and total sales values. The calculation results are formatted and automatically emailed to the sales department leader. Sales representatives also enter emotional data using an emotion engine, which is collected on a central server. A generative AI model analyzes this data and makes individual business efficiency suggestions to each sales representative. Based on these suggestions, standard calculation programs are generated and shared between departments, achieving business efficiency improvements across the company.

[1193] Prompt Sentence Examples

[1194] "Calculate the average and total values ​​based on the following sales data and email the results to me:

[1195] Sales data: 100, 200, 150, 120, 180"

[1196] The above is a specific embodiment for carrying out the present invention, which enables companies to automate data processing and improve business efficiency, and achieve standardization across departments.

[1197] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1198] Step 1:

[1199] Users input the necessary data into a Google Spreadsheet or Excel file. For example, they input daily sales data into cells "A1:A10." This input data becomes the basis for subsequent calculations.

[1200] Step 2:

[1201] At the specified time, for example 9:00 AM, the server accesses the spreadsheet using Google Apps Script and retrieves the data in the specified range. Specifically, it executes "SpreadsheetApp.getActiveSpreadsheet().getRange('A1:A10').getValues();" and stores the data in a variable. The spreadsheet data range is specified as input, and an array of data is obtained as output.

[1202] Step 3:

[1203] The server performs calculations based on the acquired data. For example, it calculates the average and total values ​​of sales data. Specifically, it calculates the average value with "avg = data.reduce((a, b) => a + b, 0) / data.length;" and calculates the total value with "total = data.reduce((a, b) => a + b, 0);". It uses the acquired data array as input and obtains the average and total values ​​as output.

[1204] Step 4:

[1205] The server formats the result of the calculation. Specifically, it converts the average and total values ​​into a single string. For example, "result = 'Average: ' + avg + ', Total: ' + total;". It uses the result of the calculation as input and gets the formatted string as output.

[1206] Step 5:

[1207] The server automatically sends the formatted calculation results to the specified recipient via email. Specifically, it executes the Google Apps Script "MailApp.sendEmail('address@example.com', 'Sales data results', result);". It uses the formatted string and the recipient's email address as input, and obtains the email sending status as output.

[1208] Step 6:

[1209] The server collects data for business efficiency from each department and aggregates it in a central server. For example, the productivity data and working hours of each department are stored in a database. Data from each department is used as input and an integrated data set is obtained as output.

[1210] Step 7:

[1211] The server inputs the collected business data into the generative AI model and generates efficiency improvement proposals. For example, the generative AI model uses a prompt statement such as "Please make business efficiency improvement proposals based on the following data." Using the business data and the prompt statement as input, the generated efficiency proposals are obtained as output.

[1212] Step 8:

[1213] The server automatically generates new scripts and macros based on suggestions from the generative AI model. Specifically, it uses Google Apps Script to create code that implements the proposed efficiency techniques. It uses the generated suggestions as input and obtains the efficiency-improving scripts and macros as output.

[1214] Step 9:

[1215] The server stores the generated scripts and macros in a central repository and shares them with other departments. Specifically, it uploads scripts to cloud storage, uses the generated scripts as input, and obtains a shareable state as output.

[1216] Step 10:

[1217] The device collects the user's emotional data using emotion recognition technology, such as facial recognition technology and emotion analysis software, to analyze the user's facial expressions. It uses the user's real-time video as input and obtains the emotional data as output.

[1218] Step 11:

[1219] The server analyzes the collected emotional data and adjusts the processing priorities. Specifically, if the stress level is high, tasks with low urgency are postponed. It uses emotional data as input and obtains an adjusted list of tasks as output.

[1220] Step 12:

[1221] The server provides emotional feedback to the user, for example, displaying a message such as "You seem to be under a lot of stress. Please take a short break." It uses emotional data as input and gets an appropriate feedback message as output.

[1222] The above is the specific processing flow of this system. These processing steps enable companies to efficiently automate a series of business processes, including data processing, business efficiency, and emotion recognition.

[1223] (Application example 2)

[1224] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1225] Improving work efficiency and reducing staff burdens at logistics centers are important issues in modern logistics operations. However, conventional systems are unable to adequately aggregate and analyze work data or optimize operations while taking into account staff emotions. This can easily lead to problems such as wasted work, incorrect deliveries, and increased staff stress. Furthermore, the inability to make real-time suggestions for improving efficiency poses a major constraint in operations that require rapid response.

[1226] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among departments, and means for analyzing emotional data collected from multiple users and adjusting feedback and calculation processing priorities based on the emotions. This enables efficient collection and analysis of work data at logistics centers and optimization of operations taking into account staff emotions.

[1227] "User" means a person or organization that utilizes the system to input data and receive the results of computations.

[1228] "Input data" refers to various information provided by the user to the system, including numerical data, text data, emotional data, and the like.

[1229] "Computation" refers to the mathematical or logical operations that a system performs on input data.

[1230] "Communication Method" refers to the method or protocol for transmitting the results of a computation to a designated recipient, such as email or notification.

[1231] A "department" refers to a group or section within a company or organization that is responsible for a particular function or task.

[1232] "Data on business efficiency" refers to various information collected to improve business processes and streamline them. This information includes data on working hours, workload, work procedures, etc.

[1233] "Generative AI" refers to artificial intelligence that analyzes collected data, proposes efficiency improvements, and generates new calculation programs.

[1234] A "standard calculation program" refers to a standardized calculation script or program that is automatically generated by generative AI based on suggestions.

[1235] "Emotion data" is information that represents the user's emotional state, including stress level, fatigue level, and the like.

[1236] "Real-time" refers to a state in which processing and analysis are carried out close to the moment data is generated.

[1237] "Suggestions" refer to improvement suggestions and optimization instructions that generative AI makes to improve business efficiency.

[1238] The program for the system that realizes this application example is generated using Google Apps Script (GAS) and a framework for smartphone application development (e.g., React Native).

[1239] System configuration

[1240] Smartphone (Android or iOS)

[1241] Servers (database servers and application servers)

[1242] Google Apps Script (GAS)

[1243] React Native

[1244] Emotion engine (Emotion API, etc.)

[1245] Generative AI (e.g., OpenAI API)

[1246] Data collection

[1247] Users (logistics center staff) input work data through a smartphone app. This work data includes information such as warehousing, shipping, and inventory confirmation.

[1248] The terminal (smartphone) transmits the data entered by the user to the server in real time.

[1249] Calculation execution

[1250] The server receives the data and uses Google Apps Script (GAS) to retrieve the data in the specified range. For example, extracting data in a specified cell range from a spreadsheet.

[1251] The server performs calculations using GAS, such as calculating the average number of outgoing orders and the total inventory amount.

[1252] Formatting and sending the calculation results

[1253] The server formats the calculation results and stores them in a cloud database.

[1254] The server pushes the formatted results to the user's device in real time.

[1255] Proposals for improving business efficiency

[1256] The server systematically aggregates business efficiency data collected from each department.

[1257] Generative AI on the server (for example, OpenAI's API) generates business efficiency improvement proposals based on the collected data, such as adjusting work shifts or changing inventory management methods.

[1258] Based on the proposals, the server automatically generates new standard calculation programs and stores and shares them in a central repository.

[1259] Emotion engine integration

[1260] The device uses an emotion engine (such as Emotion API) to recognize the user's emotions in real time.

[1261] The server can then use the recognized emotion data to adjust the priority of the user's feedback and computational processes. For example, if the user is under high stress, it can postpone certain processes and send encouraging messages.

[1262] Specific examples

[1263] After completing a shipping task, a logistics center staff member enters the details of the task and their emotional state into a smartphone app. The device sends the input data to a server, which then retrieves a specified range of spreadsheet data and performs calculations based on the data. For example, it calculates the average number of shipping tasks per day and stores the results in a cloud database. The server then pushes the results to the device and uses an emotion engine to analyze the employee's stress level, sending an encouraging message if stress levels are high. Furthermore, the generative AI uses the collected data to make suggestions for efficiency improvements, such as "dividing shifts into morning and afternoon shifts to reduce the number of shipping tasks by 15%."

[1264] Example prompts to input to the generative AI model

[1265] Please provide suggestions for improving the efficiency of shipping operations at a logistics center. The input data is as follows:

[1266] 1. Number of shipping operations: 30

[1267] 2. Stock: 5000 items

[1268] 3. Staff emotional data: High stress level, medium fatigue level

[1269] Examples of suggestions: adjusting work shifts, changing inventory management methods, specific methods to maintain staff motivation, etc.

[1270] This approach improves work efficiency at the logistics center and reduces the burden on staff, optimizing overall operations.

[1271] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1272] Step 1:

[1273] The user inputs work data and emotional data into a smartphone app. At this time, the user inputs specific data about delivery work and inventory checks, and the emotion engine automatically detects the user's current emotional state (such as stress level and fatigue level). Examples of input data include the number of delivery work tasks, inventory volume, and stress level.

[1274] Step 2:

[1275] The device transmits the input task data and emotion data to the server in real time. The smartphone app then transmits the data to the cloud server via an internet connection. The transmitted data includes the task details, inventory information, and the user's emotion data.

[1276] Step 3:

[1277] The server parses the received data and retrieves the data in the specified range using Google Apps Script (GAS). In this step, the data in the required cell range (e.g., A1:D10) is read from the spreadsheet. This allows for consistent retrieval of working data.

[1278] Step 4:

[1279] The server performs calculations on the acquired spreadsheet data. For example, it uses Google Apps Script (GAS) to calculate the number of shipping operations per day, the average inventory amount, and the total amount. This process provides the user with the necessary statistical information.

[1280] Step 5:

[1281] The server formats the results and stores them in a cloud database. The formatting process converts the results into an easy-to-read format and then registers them in the database. At this stage, the results of the calculation are persisted.

[1282] Step 6:

[1283] The server then pushes the formatted results to the user's device in real time. The notification includes the calculation results (e.g., the average number of outgoing shipments), and the user can immediately check the results.

[1284] Step 7:

[1285] Generative AI on the server (for example, OpenAI's API) generates business efficiency improvement proposals based on the collected data, including specific suggestions such as "Review shifts to reduce the workload of shipping work by 15%."

[1286] Step 8:

[1287] The server automatically generates new standard calculation programs based on the suggestions of the generative AI. The generated programs are written as scripts and stored in a central repository. These scripts can then be shared with other departments.

[1288] Step 9:

[1289] The device's emotion engine (such as Emotion API) recognizes the user's emotions in real time and sends the data to the server. Emotion data indicates the user's stress level, fatigue level, etc.

[1290] Step 10:

[1291] The server uses the emotion data to provide feedback to the user and adjust the priority of computational processing. For example, if the user is in a high-stress state, it may lower the priority of stressful tasks or send encouraging messages.

[1292] Step 11:

[1293] The server accumulates emotional and operational data over the long term and reflects it in the generative AI's proposals. This data is used in monthly reports and for specific operational improvement plans.

[1294] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1295] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1296] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1297] [Fourth embodiment]

[1298] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1299] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1300] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1301] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1302] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1303] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1304] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1305] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1306] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1307] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1308] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1309] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1310] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1311] This system allows users to input data, automatically performs calculations on that data, and automatically transmits the results. It also includes functions to collect data on business efficiency improvements from each department, use generative AI to propose further efficiency improvements, generate standard calculation programs based on those proposals, and share them among departments.

[1312] Generating a Program

[1313] The program for this system is implemented using Google Apps Script (GAS) and Excel macros. The program is structured as follows:

[1314] 1. Data Collection:

[1315] Users enter the required data into a Google spreadsheet or Excel file.

[1316] The server accesses the specified spreadsheet or Excel file and retrieves data from the specified range.

[1317] 2. Performing the calculation:

[1318] The server performs calculations (e.g., average, standard deviation, etc.) set by the user on the acquired data.

[1319] 3. Formatting and sending the results:

[1320] The server formats the results of the computation and automatically transmits them via the specified communication method (e.g., email, messaging application).

[1321] As a concrete example, consider a spreadsheet where a user has entered sales data into the range "A1:A10." The server retrieves this data, calculates the average sales amount for each cell, and then formats and emails the results to designated recipients as a daily report.

[1322] AI-based efficiency proposals

[1323] Data on business efficiency improvements collected by each department is stored on a central server. Generative AI analyzes this data and makes suggestions for further efficiency improvements. These suggestions may include, for example, methods for automating specific calculation processes or ways to optimize data management.

[1324] Users can receive AI suggestions and generate new scripts and macros based on those suggestions, improving their efficiency and overall business performance.

[1325] Creating and sharing standard programs

[1326] The scripts and macros created based on the generative AI's suggestions are stored on a central server. These standardized programs are shared so that they can be used by other departments. This results in the establishment of standardized, efficient business processes across the company.

[1327] In this way, the present invention provides a system that automates and streamlines the entire business process, from data collection and calculation processing to automatic distribution of results and even AI-based efficiency proposals.By making it possible to share this information with other management departments, it is expected that the business efficiency of the entire organization will be greatly improved.

[1328] The processing flow will be explained below.

[1329] Step 1:

[1330] The user enters the required data into a Google spreadsheet or Excel file. If specifying a range, specify the range (e.g., "A1:A10").

[1331] Step 2:

[1332] Set a trigger that runs the server periodically. This trigger can be set to run every day at 9:00 AM using a GAS or Excel macro script.

[1333] Step 3:

[1334] When the periodic trigger is activated, the server accesses the Google Spreadsheet or Excel file using the SpreadsheetApp.getActiveSpreadsheet() function (for Google Spreadsheets).

[1335] Step 4:

[1336] The server retrieves the specified sheet and range. For example, use the getRange("A1:A10") function to retrieve the cell data in the specified range "A1:A10".

[1337] Step 5:

[1338] The data retrieved by the server is read as a two-dimensional array. Use the getValues() function to retrieve all cell values ​​in the range as a two-dimensional array.

[1339] Step 6:

[1340] The server performs the calculation. For example, to calculate an average, a for loop is used to sum up each element of an array and calculate the average.

[1341] Step 7:

[1342] The server formats the results appropriately: convert the results (e.g., averages) into strings and format them to fit the report format.

[1343] Step 8:

[1344] The server sends the formatted results via a communication method such as email or a messaging application. The MailApp.sendEmail() function is used to send the results to the specified recipient.

[1345] Step 9:

[1346] The server logs the completion of sending the calculation results. Use the Logger.log() function to record the completion status of the process for subsequent troubleshooting.

[1347] Step 10:

[1348] Users collect data on business efficiency from each department and input it into the generative AI. For example, they can aggregate business efficiency information from each department via Google Forms or Excel sheets.

[1349] Step 11:

[1350] The server uses generative AI to generate suggestions for further efficiency improvements based on the collected data. The AI ​​model performs analysis and proposes effective improvements for specific business processes.

[1351] Step 12:

[1352] The server automatically generates standard calculation programs and scripts based on the generated proposals, thereby providing business efficiency improvements in the form of concrete code.

[1353] Step 13:

[1354] The generated programs and scripts are stored in a central repository by a server, which can be accessed by other departments and used as a common means of efficiency.

[1355] Step 14:

[1356] Users can then apply the generated scripts and programs to their own departments as needed, thereby sharing and standardizing efficiency gains and improving efficiency across the company.

[1357] Example 1

[1358] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1359] In the conventional system, users had to manually input data, perform calculations, and manually submit the results, which was time-consuming and labor-intensive. It was also difficult to collect data on the operational efficiency of each department and make recommendations for efficiency improvements based on that data. Furthermore, there was a lack of a way to generate standard calculation programs based on those recommendations and share them among departments. There was a need to solve these problems and improve operational efficiency across the company.

[1360] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1361] In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting business efficiency data from multiple management departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among the management departments, means for using software for data processing and data calculation based on user input data, means for using communication means for formatting and automatically transmitting the calculation results, and means for executing calculation processing set by the user. This enables automatic data processing and immediate delivery of results, and enables company-wide improvement in business efficiency through efficiency proposals by generative AI and the sharing of programs based on those proposals.

[1362] "User" refers to the entity that uses the system to input data and configure the calculation process.

[1363] "Server" refers to a computer system whose role is to receive input data from a user, perform calculations, and automatically transmit the results via a designated communication means.

[1364] "Input data" refers to data such as numbers and strings that users enter into Google Spreadsheets, Excel files, etc.

[1365] "Calculation processing" refers to various arithmetic operations that the server performs based on input data, and specifically includes calculation of average values ​​and standard deviations.

[1366] "Communication means" refers to the method used by the server to transmit the results of computation, including email and messaging applications.

[1367] "Generative AI" refers to an artificial intelligence model that analyzes collected business efficiency data and generates suggestions for further efficiency improvements.

[1368] "Data on improving business efficiency" refers to information collected from each management department to improve the efficiency of overall business operations.

[1369] A "standard program" refers to a calculation program that is generated based on suggestions from generative AI and is used in common by multiple management departments.

[1370] "Data processing" refers to the process of preparing input data in an appropriate format.

[1371] "Data calculation" refers to various calculation processes performed based on data.

[1372] A "trigger" is a trigger that periodically executes a calculation process based on a date or time.

[1373] A "script" is a series of commands used to automate a computation or data collection.

[1374] This system automatically performs calculations based on data entered by the user and automatically transmits the results via a specified communication method. It also includes functions to collect data on business efficiency improvements from each department, use generative AI to propose further efficiency improvements, generate standard calculation programs based on the proposals, and share the results among departments.

[1375] System configuration

[1376] Hardware

[1377] Server: A central computer system that collects data, processes calculations, formats and transmits the results.

[1378] Terminal: The device (computer, tablet, etc.) through which a user enters data.

[1379] software

[1380] Google Apps Script (GAS): A script for manipulating Google Spreadsheets to automate data collection and calculation processes.

[1381] Excel Macro: A program for manipulating Excel files and automating data collection and calculation processes.

[1382] Communication methods: email, messaging applications, etc.

[1383] Program processing

[1384] User operations

[1385] Users enter necessary information such as sales data and inventory data into a Google spreadsheet or Excel file. Specifically, it is assumed that data will be entered into the cell range "A1:A10" in the Google spreadsheet.

[1386] Server Operation

[1387] The server uses Google Apps Script (GAS) or Excel macros to collect the user-entered data from a specified spreadsheet or Excel file. For example, it retrieves data from the cell range "A1:A10."

[1388] The server then performs calculations (e.g., average, standard deviation, etc.) on the collected data as configured by the user. For example, to calculate the average value of the acquired sales data, the server adds up the values ​​of each cell and divides by the number of cells.

[1389] Formatting and sending the calculation results

[1390] The server formats the results of the calculations and makes them easy to understand, such as "Daily Report: Average sales is XX yen." It then automatically sends these results to the user or other recipients via the specified communication method. Specifically, it automatically sends an email containing the results to the specified email address.

[1391] AI-based efficiency proposals

[1392] Server Operation

[1393] Data on business efficiency improvements collected from each department is stored on a central server. A generative AI model on the server analyzes this data and makes suggestions for further improvements to business efficiency. New scripts and macros are then generated based on these suggestions and stored on the central server.

[1394] Prompt Sentence Examples

[1395] The server uses a generative AI model to generate efficiency suggestions using prompt sentences such as the following:

[1396] "Please analyze the operational efficiency data collected by each department and propose ways to automate specific calculation processes. Then, please tell me how to generate a Google Apps Script based on those proposals and share it with other departments."

[1397] Specific examples

[1398] 1. A user enters sales data into a Google spreadsheet

[1399] Action: The user enters sales data into the range "A1:A10".

[1400] 2. The server collects the data

[1401] Operation: The server uses Google Apps Script to read the data in "A1:A10".

[1402] 3. User sets the average calculation

[1403] Operation: The user selects "Calculate the average of sales data" on the program settings screen.

[1404] 4. The server calculates the average

[1405] Operation: The server calculates the average value of the data it retrieves.

[1406] 5. Formatting the calculation results

[1407] Operation: The server formats the calculation result as "Daily report: Average sales is XX yen."

[1408] 6. Send the results to the specified email address

[1409] What it does: The server automatically sends the formatted results to the specified email address.

[1410] 7. Data on operational efficiency is stored on a central server

[1411] Operation: The server periodically collects data from each management department and stores it in a database.

[1412] 8. Generative AI makes efficiency suggestions

[1413] How it works: A generative AI model analyzes data and generates suggestions for automating specific computational tasks.

[1414] 9. Generate and share new scripts

[1415] How it works: The server creates a script based on the suggestions of the generated AI and saves it in a shared folder.

[1416] In this way, the present invention provides an integrated system for automating and streamlining the entire business process, from data collection and calculation processing to automatic distribution of results and even efficiency suggestions using generative AI, which is expected to significantly improve the business efficiency of the entire organization.

[1417] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1418] Step 1: Enter your data

[1419] User operations

[1420] The user manually enters the necessary data into a Google spreadsheet or Excel file using the device. Specifically, the sales data is entered into the cell range "A1:A10" in the Google spreadsheet.

[1421] Input: Sales data (cell range A1:A10)

[1422] Output: Input sales data

[1423] Step 2: Collect data

[1424] Server Operation

[1425] The server uses Google Apps Script (GAS) or Excel macros to collect data from the specified spreadsheet or Excel file from the user's device. Specifically, the server reads data from the cell range "A1:A10."

[1426] Input: Entered sales data (cell range A1:A10)

[1427] Output: Collected sales data

[1428] Step 3: Set up the calculation

[1429] User operations

[1430] The user uses the terminal to set the type of calculation processing to be performed on the server. Specifically, on the calculation processing setting screen, the user selects the option "Calculate the average of sales data."

[1431] Input: Calculation settings (e.g., calculating the average value of sales data)

[1432] Output: Setting information for the calculation process

[1433] Step 4: Performing the calculation

[1434] Server Operation

[1435] The server performs the configured calculations on the collected sales data. Specifically, it calculates the average value of the sales data for each cell. The server converts the collected data into a numeric array and sums each element to find the average value.

[1436] Input: Setting information for the calculation process, collected sales data

[1437] Output: Calculation result (average value of sales data)

[1438] Step 5: Formatting the results

[1439] Server Operation

[1440] The server formats the results of the calculations and converts them into a displayable format, such as "Daily report: average sales is XX yen."

[1441] Input: Calculation result (average value of sales data)

[1442] Output: A formatted message of the calculation result

[1443] Step 6: Sending the calculation results

[1444] Server Operation

[1445] The server sends the formatted message containing the calculation result using the specified communication method (e.g., email, messaging app). Specifically, it includes the formatted message in the body of the email and sends it to the specified email address.

[1446] Input: Formatted message of the calculation result

[1447] Output: Message of the calculation result sent

[1448] Step 7: Collect data on operational efficiency

[1449] Server Operation

[1450] The server collects data from each department for the purpose of improving business efficiency and stores it in the central server. Specifically, it collects reports and data tables sent periodically from each department and stores them in a database.

[1451] Input: Business efficiency data provided by each management department

[1452] Output: Business efficiency data stored on a central server

[1453] Step 8: Generative AI proposes efficiency improvements

[1454] How generative AI models work

[1455] The generative AI model analyzes the accumulated operational efficiency data and generates proposals for further operational efficiency improvements. Specifically, it analyzes the data to identify bottlenecks and areas for improvement, and proposes methods for automating specific processes.

[1456] Input: Accumulated business efficiency data

[1457] Output: Efficiency suggestions (e.g., how to automate specific calculation processes)

[1458] Step 9: Generate and share a standard program

[1459] Server Operation

[1460] The server generates new scripts and macros based on the suggestions of the generative AI model and stores them on the central server. Specifically, scripts are created based on the proposed automation methods and saved in a shared folder, making them available to other departments.

[1461] Input: Proposal for efficiency improvement, proposed content of generative AI model

[1462] Output: Generated boilerplate programs, shared scripts and macros

[1463] The above is the specific processing flow of the program for this system. By explaining the operations, inputs, and outputs performed at each processing step, the operation of the entire system becomes easier to understand.

[1464] (Application example 1)

[1465] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1466] In current logistics centers, processing a wide range of data and making proposals for improving operational efficiency is often done manually. This makes it difficult to collect and process data quickly and accurately, hindering efficient business operations. Furthermore, making proposals for improving efficiency requires advanced specialized knowledge, which is rarely shared across the organization. This makes it difficult to standardize operations and improve overall efficiency.

[1467] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1468] In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple management departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among the management departments, means for applying the data collection and calculation processing to inventory management and work analysis at the logistics center, and means for generating new scripts and macros based on the efficiency improvement proposals, and for analyzing and reporting the data. This enables fast and accurate data collection and processing, automatic generation of efficiency improvement proposals, and data analysis and reporting for business efficiency improvements.

[1469] "User" means a person who inputs data or receives results to use the system, or who performs a task.

[1470] "Input data" refers to data provided by a user to a system, and is the information that forms the basis for calculations and analysis.

[1471] "Computational processing" refers to mathematical and statistical manipulations and operations performed on input data.

[1472] "Communication methods" refers to the technologies and methods used to communicate computational results and efficiency suggestions to users and other departments. Examples include email and messaging applications.

[1473] "Multiple administrative functions" refers to the multiple departments or groups within an organization that are responsible for overseeing operations and driving efficiency.

[1474] "Data on business efficiency" refers to data that includes indicators and information for evaluating the efficiency of business processes and tasks.

[1475] "Generative AI" refers to artificial intelligence that analyzes collected data and automatically generates proposals for improving business efficiency based on that data.

[1476] "Proposals" refer to specific guidelines and methods for improving business efficiency and work processes that are automatically created by generative AI.

[1477] A "standard calculation program" refers to a program that performs calculation processing that is standardized based on a proposal and can be used repeatedly.

[1478] "Means for sharing among management departments" refers to methods and techniques for making the generated standard calculation programs available to other management departments.

[1479] A "logistics center" refers to a facility that manages inventory, picks products, and prepares them for shipping.

[1480] "Inventory management" refers to the business process of monitoring and managing the storage status and quantity of goods at a logistics center.

[1481] "Work analysis" refers to the investigation and analysis carried out to evaluate the efficiency and effectiveness of various business processes carried out within a logistics center.

[1482] "Script" refers to program code written to automate specific computations or data manipulations.

[1483] A "macro" is a program or script used to automate a specific task or sequence of actions.

[1484] "Data analysis and reporting" refers to the business process of analyzing collected data and providing the results in the form of a report or report.

[1485]

[1486] This invention is a system that supports inventory management, work analysis, and operational efficiency improvement in logistics centers. The system allows users to input data, performs calculations based on that data, and automatically transmits the results. It also includes a function that uses generative AI to make suggestions for operational efficiency improvement, generates standard calculation programs based on those suggestions, and shares them with other management departments.

[1487] The program for this system is implemented using Google Apps Script (GAS) and other scripting languages. The specific implementation method for the system is explained below.

[1488] Hardware and Software

[1489] The system uses devices such as servers, smartphones, tablets, and robots, and the program runs on Google Apps Script (GAS), spreadsheets, email systems, and generative AI models (e.g., Google Cloud AI).

[1490] Program processing flow

[1491] 1. Data Collection

[1492] The server collects inventory and work data in real time from users' smartphones and robots, and stores this data in a Google spreadsheet.

[1493] 2. Computational Processing

[1494] The server performs calculations on the stored data, specifically calculating the average time and error rate of picking tasks.

[1495] 3. Automatic transmission of results

[1496] The server automatically sends the results of the calculations to the administrator via email or messaging application, allowing the administrator to always be up-to-date on the latest business status.

[1497] 4. Generate efficiency proposals

[1498] The server inputs the collected data into a generative AI model to generate proposals for improving business efficiency. These proposals are then embodied as new scripts or macros that can be shared with other management departments.

[1499] Specific examples

[1500] A logistics center manager uses this system to improve the efficiency of picking work. The input picking data (start time, end time, error rate, etc.) is saved in a spreadsheet, and the server calculates the average time and error rate. The calculation results are automatically sent to the manager, and the generative AI model analyzes the data and makes suggestions for improving efficiency. New scripts and macros are generated based on these suggestions, improving overall work efficiency.

[1501] Example prompt for a generative AI model:

[1502] The following is data on picking operations at a distribution center. Please create a proposal for improving efficiency based on this data. The data includes the start time, end time, and error rate for each picking operation:

[1503] Start time: 08:00, End time: 08:15, Error rate: 2%

[1504] Start time: 08:20, End time: 08:35, Error rate: 1%

[1505] ...

[1506] Use these to generate efficiency suggestions."

[1507] In this way, the present invention can significantly improve overall business efficiency by automating the collection, analysis, and efficiency improvement proposals of real-time data at logistics centers.

[1508] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1509] Step 1: Data collection

[1510] Users use smartphones, tablets, or robots to input inventory information and work performance data for the distribution center. This includes product location, quantity, picking start and end times, and error rates. The input data is saved in real time to a Google spreadsheet. The device collects the data and stores it in a spreadsheet, making it accessible to the server.

[1511] Step 2: Data Acquisition

[1512] The server periodically accesses the Google spreadsheet and retrieves data from the specified range. To retrieve the data, Google Apps Script (GAS) is used to read the data in the specified range (e.g., "A1:D100" in the "Inventory Information" sheet). This data is converted into a database format and used for subsequent calculation processing.

[1513] Step 3: Calculations

[1514] The server then performs calculations on the retrieved data, such as average time, error rate, and inventory fluctuations. For example, to calculate the average time it takes to pick a particular item, the server calculates the difference between the start time and end time and divides it by the total time for all items. The results of this calculation are temporarily stored and used in the next step.

[1515] Step 4: Automatically send calculation results

[1516] The server formats the calculation results and automatically sends them to the administrator via the specified communication method (e.g., email or messaging application). The formatted data is then output in a format that is easy for the administrator to understand (e.g., a table or graph), allowing the administrator to quickly and easily check the data.

[1517] Step 5: Generate efficiency proposals

[1518] The server inputs the collected data and calculation results into a generative AI model to generate business efficiency improvement proposals. The AI ​​model incorporates analytical algorithms based on past data and trends, analyzes the input data, and outputs optimal proposals. These generated proposals are then embodied as new scripts or macros.

[1519] Step 6: Share your efficiency suggestions

[1520] The server stores standardized calculation programs on a central server to share the generated efficiency proposals with other management departments. This allows other departments to use the same efficiency proposals, achieving company-wide business efficiency. The shared programs can also be accessed from other terminals, promoting the standardization of business processes.

[1521] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1522] This system receives input data from users, performs calculations, and automatically transmits the results via a specified communication method. It also uses generative AI to analyze business efficiency data collected from multiple departments, proposes further improvements, generates standard calculation programs based on those proposals, and shares them among departments. It also incorporates an emotion engine that recognizes users' emotions, providing feedback based on emotions and adjusting processing priorities.

[1523] Generating a Program

[1524] The system is programmed using Google Apps Script (GAS) and Excel macros. The system configuration is as follows:

[1525] Data collection

[1526] The user enters the required data into a Google spreadsheet or Excel file. The server accesses the file and retrieves the data from the specified range. For example, it retrieves the range "A1:A10" from the sheet where sales data is entered.

[1527] Calculation execution

[1528] After retrieving the data in the specified range, the server executes the calculations specified by the user. For example, it calculates the average or total value of sales data. This allows the user to perform data analysis efficiently.

[1529] Formatting and sending the calculation results

[1530] The calculation result is formatted and automatically sent via a specified communication means. For example, the calculation result is formatted as the body of an email and sent to a specified recipient.

[1531] Proposals for improving business efficiency

[1532] Data on business efficiency improvements collected from each department is aggregated on a central server. Generative AI analyzes this data and generates proposals for further efficiency improvements. These proposals are presented in the form of specific action plans or scripts.

[1533] Creating and sharing standard programs

[1534] New scripts and macros are automatically generated based on the generated suggestions, and these programs are stored in a central repository and shared for use by other departments, establishing standardized and efficient business processes across the company.

[1535] Emotion engine integration

[1536] Emotion recognition and prioritization

[1537] The emotion engine recognizes the user's emotions in real time and adjusts the priority of computational tasks based on those emotions. For example, if the user is stressed, it will postpone less urgent tasks and prioritize more immediate tasks.

[1538] Providing feedback

[1539] The emotion engine provides appropriate feedback to the user based on the emotions it recognizes. For example, if the user is in an emotionally unstable state, it displays an encouraging message. Furthermore, by incorporating emotional information into the efficiency improvement proposals proposed by the generative AI based on emotion data, more practical suggestions can be made.

[1540] Accumulation and analysis of emotional data

[1541] The emotion engine accumulates and analyzes user emotional data. This data provides important insights for long-term operational efficiency and is reflected in work improvement proposals. For example, if stress levels are high during a particular time period, the engine will propose ways to reduce the workload during that time period.

[1542] Specific examples

[1543] A company's management department inputs daily sales data into a Google spreadsheet. The server retrieves this data at 9:00 AM every day and calculates the average and total sales figures. The calculation results are formatted and automatically emailed to the sales department leader. Sales representatives also enter emotional data using an emotion engine, which is collected on a central server. A generative AI analyzes this data and makes individual business efficiency proposals to each sales representative. Based on these proposals, standard calculation programs are generated and shared among management departments, resulting in business efficiency improvements across the company.

[1544] The processing flow will be explained below.

[1545] Step 1:

[1546] The user enters the required data into a Google spreadsheet or Excel file. For example, when entering sales data, the user enters the sales amount into the cell range "A1:A10".

[1547] Step 2:

[1548] Set a trigger that will run the server periodically. If you are using Google Apps Script, use the ScriptApp.newTrigger function to set a periodic trigger that runs "every day at 9:00 AM."

[1549] Step 3:

[1550] When the trigger fires, the server accesses the Google Spreadsheet or Excel file. For Google Spreadsheets, it uses the SpreadsheetApp.getActiveSpreadsheet() function.

[1551] Step 4:

[1552] The server retrieves data by specifying the target sheet and range. For example, the getRange("A1:A10") function is used to retrieve data from the range "A1:A10".

[1553] Step 5:

[1554] The data retrieved by the server is read as a two-dimensional array. Use the getValues() function to retrieve the cell data within the range in two-dimensional array format.

[1555] Step 6:

[1556] The server performs the calculation. For example, to calculate the average value of sales data, a for loop is used to sum each element of the array and divide by the total to calculate the average.

[1557] Step 7:

[1558] The server formats the calculation results. The calculation results are converted into a string format, for example, "Average sales: XX yen."

[1559] Step 8:

[1560] The server sends the formatted calculation results via the specified communication method, and then uses the MailApp.sendEmail() function to send an email containing the calculation results to the specified recipient.

[1561] Step 9:

[1562] The server logs the processing status. It uses the Logger.log() function to log that the calculation result has been sent.

[1563] Step 10:

[1564] Users input collected data on business efficiency into generative AI. For example, they can use Google Forms to collect information on business efficiency improvements from the general management department.

[1565] Step 11:

[1566] The server uses generative AI to analyze the accumulated data and generate suggestions for further efficiency improvements. For example, an AI model analyzes the data and suggests optimization measures for a specific business process.

[1567] Step 12:

[1568] The server automatically generates standard calculation programs and scripts based on the generated efficiency improvement proposals, providing specific code for improving business efficiency.

[1569] Step 13:

[1570] The server stores the generated scripts and programs in a central repository and makes them available to other departments, so they are shared across the company as a common means of efficiency.

[1571] Step 14:

[1572] The user inputs emotional data through the emotion engine, which, for example, recognizes emotions through the device's camera or microphone and sends the data to the server.

[1573] Step 15:

[1574] The server uses an emotion engine to analyze the user's emotions in real time and adjusts the priority of calculations based on that. For example, if the user is feeling stressed, the order of calculations will be changed.

[1575] Step 16:

[1576] The server generates feedback based on the user's emotions and provides it to the user. For example, if the user is feeling stressed, it displays an encouraging message.

[1577] Step 17:

[1578] The server accumulates emotional data and performs long-term analysis. This data is reflected in business efficiency proposals using generative AI. For example, if stress tends to be high during certain times of the day, the system will make proposals to reduce the workload during those times.

[1579] Specific examples

[1580] A company's management department inputs daily sales data into a Google spreadsheet. A server retrieves this data at 9:00 AM every day, calculates the average and total sales figures, and automatically sends them by email. Sales representatives also input emotional data using an emotion engine, which is collected on a central server. A generative AI analyzes this data and makes individual proposals for improving business efficiency. Based on these proposals, standard calculation programs are generated and shared among management departments, resulting in company-wide improvements in business efficiency.

[1581] Example 2

[1582] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1583] In modern business operations, a great deal of time and effort is spent on data collection, calculation processing, and proposing and implementing improvements to business efficiency. Furthermore, insufficient information sharing between departments often prevents further efficiency improvements. Furthermore, prioritization of tasks and feedback may be ineffective because users' feelings are not taken into consideration. New methods are needed to solve these issues and realize more productive and efficient business processes.

[1584] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple departments and proposing further efficiency improvements using a generative AI model, means for generating standard calculation programs based on the proposals and sharing them among departments, means for recognizing user emotions and adjusting processing priorities based on the emotions, and means for accumulating emotion data and reflecting it in long-term business efficiency improvements. This enables data collection, calculation processing, proposing and implementing business efficiency improvements, information sharing, and prioritizing tasks based on emotions.

[1585] A "user" is an entity that uses the system to input data and receives proposals for calculation processing and business efficiency improvements.

[1586] "Input data" refers to information provided by a user to the system, and includes, for example, sales data and data for improving business efficiency.

[1587] "Calculation processing" refers to arithmetic or logical processing performed on input data, including, for example, calculating averages or sums.

[1588] "Communication means" refers to the method used to automatically transmit computational results and efficiency suggestions, including, for example, email.

[1589] A "department" is a section in charge of business within a company, and includes, for example, a sales department and an accounting department.

[1590] "Data on improving business efficiency" is information collected from each department to improve business efficiency.

[1591] A "generative AI model" is an artificial intelligence technology that analyzes provided data and suggests further efficiency improvements.

[1592] A "standard calculation program" is a program that performs consistent calculation processing and is automatically created based on the suggestions of a generative AI model.

[1593] "Emotion recognition" is a technology that grasps a user's emotional state in real time.

[1594] "Emotion data" is information about a user's emotions collected through emotion recognition.

[1595] "Priority adjustment" is the process of reassessing and reordering the importance of work tasks based on perceived emotions.

[1596] "Storage" means storing data for a long period of time and using it for later analysis and recommendations.

[1597] "Long-term business efficiency" refers to efforts to continuously increase business productivity and efficiency by analyzing emotional and business data.

[1598] This system receives input data from users, performs calculations, and automatically transmits the results via a specified communication method. It also has the ability to analyze business efficiency data collected from multiple departments using a generative AI model, propose further efficiency improvements, generate standard calculation programs based on those proposals, and share them among departments. It also incorporates an emotion engine that recognizes user emotions, providing feedback based on emotions and adjusting processing priorities.

[1599] Generating a Program

[1600] The system's programming is implemented using Google Apps Script (GAS) and Excel macros. First, the user enters the necessary data into a Google spreadsheet or Excel file. The server then accesses these files and retrieves data from the specified range. For example, it retrieves the range "A1:A10" from the sheet where sales data is entered.

[1601] Calculation execution

[1602] After retrieving the data in the specified range, the server executes the calculations specified by the user. For example, it calculates the average or total value of sales data. This allows the user to perform data analysis efficiently.

[1603] Formatting and sending the calculation results

[1604] The calculation results are formatted and automatically sent via the specified communication method. For example, the calculation results are formatted as the body of an email and sent to the specified recipient. This function is realized using the MailApp class of Google Apps Script.

[1605] Proposals for improving business efficiency

[1606] Data on operational efficiency improvements collected from each department is aggregated on a central server. A generative AI model (e.g., OpenAI's GPT-3 model) analyzes this data and generates recommendations for further efficiency improvements. These recommendations are presented in the form of specific action plans or scripts.

[1607] Creating and sharing standard programs

[1608] The server automatically generates new scripts and macros based on the generated suggestions. These programs are stored in a central repository and shared for use by other departments, establishing standardized and efficient business processes across the company.

[1609] Emotion engine integration

[1610] Emotion recognition and prioritization

[1611] The emotion engine recognizes the user's emotions in real time and adjusts the priority of computational tasks based on those emotions. For example, if the user is stressed, it will postpone less urgent tasks and prioritize more urgent tasks.

[1612] Providing feedback

[1613] The emotion engine provides appropriate feedback to the user based on the recognized emotion. For example, if the user is in an emotionally unstable state, it displays an encouraging message. In addition, by reflecting emotional information in the efficiency suggestions proposed by the generative AI model based on emotion data, more practical suggestions can be made.

[1614] Accumulation and analysis of emotional data

[1615] The emotion engine accumulates and analyzes user emotional data. This data provides important insights for long-term operational efficiency and is reflected in work improvement proposals. For example, if stress levels are high during a particular time period, the engine will propose ways to reduce the workload during that time period.

[1616] Specific examples

[1617] In a certain company's departments, users enter daily sales data into a Google spreadsheet. The server retrieves this data at 9:00 AM every day and calculates the average and total sales values. The calculation results are formatted and automatically emailed to the sales department leader. Sales representatives also enter emotional data using an emotion engine, which is collected on a central server. A generative AI model analyzes this data and makes individual business efficiency suggestions to each sales representative. Based on these suggestions, standard calculation programs are generated and shared between departments, achieving business efficiency improvements across the company.

[1618] Prompt Sentence Examples

[1619] "Calculate the average and total values ​​based on the following sales data and email the results to me:

[1620] Sales data: 100, 200, 150, 120, 180"

[1621] The above is a specific embodiment for carrying out the present invention, which enables companies to automate data processing and improve business efficiency, and achieve standardization across departments.

[1622] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1623] Step 1:

[1624] Users input the necessary data into a Google Spreadsheet or Excel file. For example, they input daily sales data into cells "A1:A10." This input data becomes the basis for subsequent calculations.

[1625] Step 2:

[1626] At the specified time, for example 9:00 AM, the server accesses the spreadsheet using Google Apps Script and retrieves the data in the specified range. Specifically, it executes "SpreadsheetApp.getActiveSpreadsheet().getRange('A1:A10').getValues();" and stores the data in a variable. The spreadsheet data range is specified as input, and an array of data is obtained as output.

[1627] Step 3:

[1628] The server performs calculations based on the acquired data. For example, it calculates the average and total values ​​of sales data. Specifically, it calculates the average value with "avg = data.reduce((a, b) => a + b, 0) / data.length;" and calculates the total value with "total = data.reduce((a, b) => a + b, 0);". It uses the acquired data array as input and obtains the average and total values ​​as output.

[1629] Step 4:

[1630] The server formats the result of the calculation. Specifically, it converts the average and total values ​​into a single string. For example, "result = 'Average: ' + avg + ', Total: ' + total;". It uses the result of the calculation as input and gets the formatted string as output.

[1631] Step 5:

[1632] The server automatically sends the formatted calculation results to the specified recipient via email. Specifically, it executes the Google Apps Script "MailApp.sendEmail('address@example.com', 'Sales data results', result);". It uses the formatted string and the recipient's email address as input, and obtains the email sending status as output.

[1633] Step 6:

[1634] The server collects data for business efficiency from each department and aggregates it in a central server. For example, the productivity data and working hours of each department are stored in a database. Data from each department is used as input and an integrated data set is obtained as output.

[1635] Step 7:

[1636] The server inputs the collected business data into the generative AI model and generates efficiency improvement proposals. For example, the generative AI model uses a prompt statement such as "Please make business efficiency improvement proposals based on the following data." Using the business data and the prompt statement as input, the generated efficiency proposals are obtained as output.

[1637] Step 8:

[1638] The server automatically generates new scripts and macros based on suggestions from the generative AI model. Specifically, it uses Google Apps Script to create code that implements the proposed efficiency techniques. It uses the generated suggestions as input and obtains the efficiency-improving scripts and macros as output.

[1639] Step 9:

[1640] The server stores the generated scripts and macros in a central repository and shares them with other departments. Specifically, it uploads scripts to cloud storage, uses the generated scripts as input, and obtains a shareable state as output.

[1641] Step 10:

[1642] The device collects the user's emotional data using emotion recognition technology, such as facial recognition technology and emotion analysis software, to analyze the user's facial expressions. It uses the user's real-time video as input and obtains the emotional data as output.

[1643] Step 11:

[1644] The server analyzes the collected emotional data and adjusts the processing priorities. Specifically, if the stress level is high, tasks with low urgency are postponed. It uses emotional data as input and obtains an adjusted list of tasks as output.

[1645] Step 12:

[1646] The server provides emotional feedback to the user, for example, displaying a message such as "You seem to be under a lot of stress. Please take a short break." It uses emotional data as input and gets an appropriate feedback message as output.

[1647] The above is the specific processing flow of this system. These processing steps enable companies to efficiently automate a series of business processes, including data processing, business efficiency, and emotion recognition.

[1648] (Application example 2)

[1649] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1650] Improving work efficiency and reducing staff burdens at logistics centers are important issues in modern logistics operations. However, conventional systems are unable to adequately aggregate and analyze work data or optimize operations while taking into account staff emotions. This can easily lead to problems such as wasted work, incorrect deliveries, and increased staff stress. Furthermore, the inability to make real-time suggestions for improving efficiency poses a major constraint in operations that require rapid response.

[1651] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input data from a user and executing calculation processing, means for automatically transmitting the results of the calculation processing via a specified communication means, means for collecting data on business efficiency improvements from multiple departments and proposing further efficiency improvements using generative AI, means for generating standard calculation programs based on the proposals and sharing them among departments, and means for analyzing emotional data collected from multiple users and adjusting feedback and calculation processing priorities based on the emotions. This enables efficient collection and analysis of work data at logistics centers and optimization of operations taking into account staff emotions.

[1652] "User" means a person or organization that utilizes the system to input data and receive the results of computations.

[1653] "Input data" refers to various information provided by the user to the system, including numerical data, text data, emotional data, and the like.

[1654] "Computation" refers to the mathematical or logical operations that a system performs on input data.

[1655] "Communication Method" refers to the method or protocol for transmitting the results of a computation to a designated recipient, such as email or notification.

[1656] A "department" refers to a group or section within a company or organization that is responsible for a particular function or task.

[1657] "Data on business efficiency" refers to various information collected to improve business processes and streamline them. This information includes data on working hours, workload, work procedures, etc.

[1658] "Generative AI" refers to artificial intelligence that analyzes collected data, proposes efficiency improvements, and generates new calculation programs.

[1659] A "standard calculation program" refers to a standardized calculation script or program that is automatically generated by generative AI based on suggestions.

[1660] "Emotion data" is information that represents the user's emotional state, including stress level, fatigue level, and the like.

[1661] "Real-time" refers to a state in which processing and analysis are carried out close to the moment data is generated.

[1662] "Suggestions" refer to improvement suggestions and optimization instructions that generative AI makes to improve business efficiency.

[1663] The program for the system that realizes this application example is generated using Google Apps Script (GAS) and a framework for smartphone application development (e.g., React Native).

[1664] System configuration

[1665] Smartphone (Android or iOS)

[1666] Servers (database servers and application servers)

[1667] Google Apps Script (GAS)

[1668] React Native

[1669] Emotion engine (Emotion API, etc.)

[1670] Generative AI (e.g., OpenAI API)

[1671] Data collection

[1672] Users (logistics center staff) input work data through a smartphone app. This work data includes information such as warehousing, shipping, and inventory confirmation.

[1673] The terminal (smartphone) transmits the data entered by the user to the server in real time.

[1674] Calculation execution

[1675] The server receives the data and uses Google Apps Script (GAS) to retrieve the data in the specified range. For example, extracting data in a specified cell range from a spreadsheet.

[1676] The server performs calculations using GAS, such as calculating the average number of outgoing orders and the total inventory amount.

[1677] Formatting and sending the calculation results

[1678] The server formats the calculation results and stores them in a cloud database.

[1679] The server pushes the formatted results to the user's device in real time.

[1680] Proposals for improving business efficiency

[1681] The server systematically aggregates business efficiency data collected from each department.

[1682] Generative AI on the server (for example, OpenAI's API) generates business efficiency improvement proposals based on the collected data, such as adjusting work shifts or changing inventory management methods.

[1683] Based on the proposals, the server automatically generates new standard calculation programs and stores and shares them in a central repository.

[1684] Emotion engine integration

[1685] The device uses an emotion engine (such as Emotion API) to recognize the user's emotions in real time.

[1686] The server can then use the recognized emotion data to adjust the priority of the user's feedback and computational processes. For example, if the user is under high stress, it can postpone certain processes and send encouraging messages.

[1687] Specific examples

[1688] After completing a shipping task, a logistics center staff member enters the details of the task and their emotional state into a smartphone app. The device sends the input data to a server, which then retrieves a specified range of spreadsheet data and performs calculations based on the data. For example, it calculates the average number of shipping tasks per day and stores the results in a cloud database. The server then pushes the results to the device and uses an emotion engine to analyze the employee's stress level, sending an encouraging message if stress levels are high. Furthermore, the generative AI uses the collected data to make suggestions for efficiency improvements, such as "dividing shifts into morning and afternoon shifts to reduce the number of shipping tasks by 15%."

[1689] Example prompts to input to the generative AI model

[1690] Please provide suggestions for improving the efficiency of shipping operations at a logistics center. The input data is as follows:

[1691] 1. Number of shipping operations: 30

[1692] 2. Stock: 5000 items

[1693] 3. Staff emotional data: High stress level, medium fatigue level

[1694] Examples of suggestions: adjusting work shifts, changing inventory management methods, specific methods to maintain staff motivation, etc.

[1695] This approach improves work efficiency at the logistics center and reduces the burden on staff, optimizing overall operations.

[1696] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1697] Step 1:

[1698] The user inputs work data and emotional data into a smartphone app. At this time, the user inputs specific data about delivery work and inventory checks, and the emotion engine automatically detects the user's current emotional state (such as stress level and fatigue level). Examples of input data include the number of delivery work tasks, inventory volume, and stress level.

[1699] Step 2:

[1700] The device transmits the input task data and emotion data to the server in real time. The smartphone app then transmits the data to the cloud server via an internet connection. The transmitted data includes the task details, inventory information, and the user's emotion data.

[1701] Step 3:

[1702] The server parses the received data and retrieves the data in the specified range using Google Apps Script (GAS). In this step, the data in the required cell range (e.g., A1:D10) is read from the spreadsheet. This allows for consistent retrieval of working data.

[1703] Step 4:

[1704] The server performs calculations on the acquired spreadsheet data. For example, it uses Google Apps Script (GAS) to calculate the number of shipping operations per day, the average inventory amount, and the total amount. This process provides the user with the necessary statistical information.

[1705] Step 5:

[1706] The server formats the results and stores them in a cloud database. The formatting process converts the results into an easy-to-read format and then registers them in the database. At this stage, the results of the calculation are persisted.

[1707] Step 6:

[1708] The server then pushes the formatted results to the user's device in real time. The notification includes the calculation results (e.g., the average number of outgoing shipments), and the user can immediately check the results.

[1709] Step 7:

[1710] Generative AI on the server (for example, OpenAI's API) generates business efficiency improvement proposals based on the collected data, including specific suggestions such as "Review shifts to reduce the workload of shipping work by 15%."

[1711] Step 8:

[1712] The server automatically generates new standard calculation programs based on the suggestions of the generative AI. The generated programs are written as scripts and stored in a central repository. These scripts can then be shared with other departments.

[1713] Step 9:

[1714] The device's emotion engine (such as Emotion API) recognizes the user's emotions in real time and sends the data to the server. Emotion data indicates the user's stress level, fatigue level, etc.

[1715] Step 10:

[1716] The server uses the emotion data to provide feedback to the user and adjust the priority of computational processing. For example, if the user is in a high-stress state, it may lower the priority of stressful tasks or send encouraging messages.

[1717] Step 11:

[1718] The server accumulates emotional and operational data over the long term and reflects it in the generative AI's proposals. This data is used in monthly reports and for specific operational improvement plans.

[1719] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1720] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1721] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1722] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1723] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1724] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1725] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1726] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1727] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1728] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1729] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1730] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1731] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1732] 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.

[1733] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1734] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1735] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1736] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1737] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1738] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1739] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1740] The following is further disclosed regarding the above embodiment.

[1741] (Claim 1)

[1742] means for receiving input data from a user and performing computations;

[1743] means for automatically transmitting the results of the calculation process via a designated communication means;

[1744] A means of collecting data on business efficiency from multiple departments and using generative AI to propose further improvements in efficiency.

[1745] A means to generate standard calculation programs based on the proposals and share them among the supervisory departments,

[1746] A system including:

[1747] (Claim 2)

[1748] 10. The system of claim 1, further comprising means for setting triggers to periodically execute the calculations based on date and time.

[1749] (Claim 3)

[1750] 10. The system of claim 1, further comprising means for retrieving a specified range of spreadsheet data and performing a plurality of scripted calculations on the data.

[1751] (Claim 4)

[1752] The system of claim 1, further comprising means for generating an efficiency improvement program by a generative AI based on business efficiency improvement data collected from the management department.

[1753] (Claim 5)

[1754] The system of claim 1, further comprising means for sending the calculation results by email or a communication tool using a program suggested by the generative AI.

[1755] "Example 1"

[1756] (Claim 1)

[1757] means for receiving input data from a user and performing computations;

[1758] means for automatically transmitting the results of the calculation process via a designated communication means;

[1759] A means of collecting data on business efficiency from multiple departments and using generative AI to propose further improvements in efficiency.

[1760] A means to generate standard calculation programs based on the proposals and share them among the supervisory departments,

[1761] A means for using software to process and calculate data based on user input data;

[1762] A means for utilizing a communication means for automatically formatting and transmitting the calculation results;

[1763] means for executing a calculation process set by a user;

[1764] A system including:

[1765] (Claim 2)

[1766] 10. The system of claim 1, further comprising means for setting triggers to periodically execute the calculations based on date and time.

[1767] (Claim 3)

[1768] 10. The system of claim 1, further comprising means for retrieving a specified range of spreadsheet data and performing a plurality of scripted calculations on the data.

[1769] "Application Example 1"

[1770] (Claim 1)

[1771] means for receiving input data from a user and performing computations;

[1772] means for automatically transmitting the results of the calculation process via a designated communication means;

[1773] A means of collecting data on business efficiency from multiple departments and using generative AI to propose further improvements in efficiency.

[1774] A means to generate standard calculation programs based on the proposals and share them among the supervisory departments,

[1775] A system including:

[1776] (Claim 2)

[1777] 10. The system of claim 1, further comprising means for setting triggers to periodically execute the calculations based on date and time.

[1778] (Claim 3)

[1779] 10. The system of claim 1, further comprising means for retrieving a specified range of spreadsheet data and performing a plurality of scripted calculations on the data.

[1780]

[1781] (Claim 1)

[1782] means for receiving input data from a user and performing computations;

[1783] means for automatically transmitting the results of the calculation process via a designated communication means;

[1784] A means of collecting data on business efficiency from multiple management departments and using generative AI to propose further efficiency improvements.

[1785] A means to generate standard calculation programs based on the proposals and share them among management departments;

[1786] A means of applying data collection and computational processing to inventory management and work analysis in logistics centers;

[1787] A means to generate new scripts and macros based on efficiency suggestions, and to analyze and report data;

[1788] A system including:

[1789] (Claim 2)

[1790] 10. The system of claim 1, further comprising means for setting triggers to periodically execute the calculations based on date and time.

[1791] (Claim 3)

[1792] 10. The system of claim 1, further comprising means for retrieving a specified range of spreadsheet data and performing a plurality of scripted calculations on the data.

[1793] "Example 2: Combining Emotion Engines"

[1794] (Claim 1)

[1795] means for receiving input data from a user and performing computations;

[1796] means for automatically transmitting the results of the calculation process via a designated communication means;

[1797] A means to collect operational efficiency data from multiple departments and use generative AI models to make further efficiency recommendations;

[1798] A means to generate standard calculation programs based on the proposals and share them among departments,

[1799] means for recognizing a user's emotion and adjusting processing priorities based on the emotion;

[1800] A means of ac...

Claims

1. means for receiving input data from a user and performing computations; means for automatically transmitting the results of the calculation process via a designated communication means; A means of collecting data on business efficiency from multiple departments and using generative AI to propose further improvements in efficiency. A means to generate standard calculation programs based on the proposals and share them among the supervisory departments, A system including:

2. 10. The system of claim 1, further comprising means for setting triggers for periodically executing calculations based on date and time.

3. 10. The system of claim 1, further comprising means for retrieving a specified range of spreadsheet data and performing a plurality of scripted calculations on the data.

4. The system according to claim 1, further comprising a means for generating an efficiency improvement program by a generative AI based on business efficiency improvement data collected from the management department.

5. The system according to claim 1, further comprising means for transmitting the calculation results by email or a communication tool using a program proposed by the generative AI.

Images