system

Abstract

We provide the system. [Solution] A means for reading existing data, A means of summarizing new approval information, A means of adding summarized approval information to existing data, A means of saving updated data, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a situation where multiple commercial products and mobile models have different offering prices, manually summarizing approval information and managing existing information requires a great deal of time and effort. As a result, the efficiency of business operations decreases, and human errors may occur. Also, it is difficult to quickly and accurately summarize a large amount of frequently updated data. In current technologies, appropriate management and automation of summarization of approval information are not sufficiently performed, and there is a need to improve this point.

Means for Solving the Problems

[0005] This invention provides a system that reads existing data, automatically summarizes new approval information, and adds the summarized information to the existing data. The system first includes means for reading existing data from a CSV file. Next, it provides means for summarizing the new approval information using a natural language processing engine. Furthermore, it includes means for integrating this summarized information into the existing data. Finally, it includes means for saving the updated data again as a CSV file. This streamlines the summarization and management of approval information, reducing time and effort.

[0006] "Existing data" refers to past information that has already been stored in databases or files.

[0007] "New decision information" refers to information regarding the latest business decisions and price changes.

[0008] "Summarizing" refers to shortening long texts or data, extracting only the important points, and expressing them in a concise format.

[0009] A "natural language processing engine" is a computer model for understanding and generating human language, and specifically refers to the technology used for text analysis and generation.

[0010] "Means of reading" refers to methods and devices for obtaining information from files or databases.

[0011] "Means of addition" refers to methods or devices for integrating new information into existing datasets.

[0012] "Means of storage" refers to methods or devices for holding data or information in physical or virtual storage.

[0013] A "CSV file" is a file format that uses comma-separated values ​​to represent data and is commonly used to store information structured in rows and columns. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system for efficiently managing the pricing of multiple products and mobile devices. The following describes a specific implementation of this system.

[0036] System Overview

[0037] This system enables a seamless workflow where users input new approval information via a terminal, and a server processes that information and integrates it with existing data. This system improves operational efficiency and data management accuracy.

[0038] System Configuration

[0039] The server has the following main features:

[0040] 1. Reading existing data: The server reads existing approval information from a CSV file. This reading is done using a data analysis library such as Pandas.

[0041] 2. Summarization of new approval information: The server uses a natural language processing engine (e.g., GPT-3®) to summarize the new approval information. This summarization makes it easier to select and filter the information.

[0042] 3. Adding summary information: The server integrates the summarized approval information into the existing DataFrame and generates an updated dataset.

[0043] 4. Data Storage: The server saves the updated data again as a CSV file. This ensures that the latest information is available when the data is read in the future.

[0044] The device has the following main features:

[0045] 1. User Input Reception: The terminal provides an interface for users to input new approval information. This interface is implemented through web forms or dedicated software applications.

[0046] 2. Sending Input Information: The terminal sends the information entered by the user to the server. This transmission is done using protocols such as HTTP requests.

[0047] 3. Display of updated data: The terminal receives the latest approval information data sent from the server and displays it to the user. This allows the user to check the latest information at any time.

[0048] Specific example

[0049] For example, consider a case where a user enters new payment information into their terminal, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is first sent to the server. The server reads the existing data and summarizes this new information using a natural language processing engine. The resulting summary is "Change the price of mobile device A from 1000 yen to 1200 yen." This summarized information is added to the existing DataFrame, and the updated dataset is saved in CSV format.

[0050] Users can later review this updated data through their devices. This saves work time and improves the accuracy of data management.

[0051] The system of the present invention functions based on the above components and processing flow, and streamlines the management of approval information.

[0052] The following describes the processing flow.

[0053] Step 1:

[0054] The user enters new payment information (for example, "Change the price of mobile device A from 1000 yen to 1200 yen") into the device. The device collects this information and prepares a request to send it to the server.

[0055] Step 2:

[0056] The terminal sends the prepared request to the server. This request is sent as data in JSON or XML format, containing the new approval information.

[0057] Step 3:

[0058] The server parses the received request and extracts new approval information. This new approval information is stored on the server in text format.

[0059] Step 4:

[0060] The server reads a CSV file containing existing approval information. This uses data analysis libraries such as Pandas to read the data from the CSV file in DataFrame format.

[0061] Step 5:

[0062] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The server sends the new approval information to the natural language processing engine as a prompt and receives the summary result.

[0063] Step 6:

[0064] The server integrates the received summary results into the existing data. This process adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[0065] Step 7:

[0066] The server saves the updated DataFrame again as a CSV file. By overwriting the existing file, a file is generated that reflects the latest approval information.

[0067] Step 8:

[0068] The user requests the latest approval information data stored on the server via their device. The device sends this request using a protocol such as an HTTP request.

[0069] Step 9:

[0070] The server rereads the updated CSV file to retrieve the latest data. It then prepares this data for transmission to the terminal.

[0071] Step 10:

[0072] The terminal displays the latest approval information data received from the server to the user. The user can then review this updated information and use it for necessary tasks.

[0073] This allows users to quickly manage new approval information in their daily work and check updates in real time. This process streamlines the summarization and data management of approval information, resulting in reduced working time and improved accuracy.

[0074] (Example 1)

[0075] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0076] A system is needed to properly manage existing approval information and efficiently input, summarize, integrate, and store new approval information. However, conventional systems have problems such as time-consuming information summarization, data integration, and storage processes, which increase the likelihood of manual input errors and data management omissions. Therefore, there is a need for a system that solves these problems and improves the efficiency and accuracy of approval information management.

[0077] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0078] In this invention, the server includes means for a user to input new approval information through a terminal, means for transmitting the new approval information to the server, means for reading existing data, means for summarizing the new approval information using a generative AI model, means for adding the summarized approval information to the existing data, means for saving the updated data, means for transmitting the updated data to the terminal, and means for the terminal to display the updated data to the user. This streamlines the management of approval information and enables accurate data updating and storage.

[0079] A "user" is the entity that operates the system and inputs new approval information.

[0080] A "terminal" is a device operated by a user that has the means to input new approval information and send that information to a server.

[0081] A "server" is a central management device that processes, stores, and manages approval information.

[0082] "Approval information" refers to data representing the pricing and approval information for products and mobile devices in a business context.

[0083] A "generative AI model" refers to an artificial intelligence algorithm that uses natural language processing technology to analyze and summarize text data.

[0084] "Summarization" refers to the process of extracting important information using a generative AI model and presenting it in a concise format.

[0085] A "data analysis library" is a software library used to manipulate and analyze data, and in this context, it specifically refers to Pandas.

[0086] A "CSV file" refers to a file format that stores data in comma-separated text format.

[0087] This invention is a system for efficiently managing the pricing of multiple products and mobile devices. This system implements a workflow in which users input new approval information via a terminal, and a server processes this information and integrates it with existing data. The specific implementation of this system is described below.

[0088] System configuration and operation

[0089] The device has the following features:

[0090] 1. User Input Reception: The terminal allows users to input new payment information through web forms or dedicated software. For example, it provides text boxes or selection menus for inputting information such as "Change the price of mobile model A from 1000 yen to 1200 yen."

[0091] 2. Sending Input Information: The terminal sends the approval information entered by the user to the server as an HTTP POST request. Specifically, the request library is used to send the information.

[0092] The server has the following functions:

[0093] 1. Reading existing data: The server uses the Pandas library to read existing approval information from a CSV file. This process allows the server to understand the current data state.

[0094] 2. Summarizing the new approval information: The server uses a generative AI model (e.g., GPT-3) to summarize the new approval information. The prompt will be text in the format of "Please summarize the new approval information. Example: 'Change the price of mobile model A from 1000 yen to 1200 yen'."

[0095] 3. Adding summary information: The server integrates the summarized approval information into the existing DataFrame and updates the dataset. This ensures that the new approval information is reflected in the existing data.

[0096] 4. Data Storage: The server saves the updated dataset again in CSV format. This ensures that the latest information is available the next time the data is read.

[0097] 5. Sending updated data: The server sends the updated approval data to the terminal as an HTTP response. Specifically, it converts the data into a dictionary format and sends it as a response.

[0098] The device has the following features:

[0099] 1. Receiving and displaying updated data: The terminal receives updated data sent from the server and displays it in the user interface. For example, it reflects the updated approval information in the HTML elements of a web page that displays it as a list.

[0100] Specific example

[0101] As a concrete example, consider the process when a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent from the device to the server. The server reads the existing data and summarizes this new information using a generation AI model. The generated summary information, "Change the price of mobile device A from 1000 yen to 1200 yen," is added to the existing data, and the updated dataset is saved in CSV format. Finally, the server sends the updated data to the device, which then displays it to the user.

[0102] In this way, this system can streamline the management of new approval information and improve the accuracy of data processing.

[0103] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0104] Step 1:

[0105] The user enters new approval information into the terminal.

[0106] Users enter new approval information using web forms or dedicated applications provided by their devices.

[0107] Input: New approval information (e.g., "Change the price of mobile device A from 1000 yen to 1200 yen").

[0108] Output: New approval information entered by the user on the terminal.

[0109] Specific operation: The user enters information into text boxes or selection menus and presses the "Submit" button.

[0110] Step 2:

[0111] The terminal sends the input information to the server.

[0112] The terminal sends the approval information entered by the user to the server as an HTTP POST request.

[0113] Input: Approval information entered by the user.

[0114] Output: Approval information received by the server.

[0115] Specific operation: The terminal uses the requests.post library to send the approval information to the specified server URL.

[0116] Step 3:

[0117] The server reads existing data.

[0118] The server uses the Pandas library to read existing approval information from a CSV file.

[0119] Input: A CSV file containing existing approval data.

[0120] Output: A DataFrame of existing data loaded into memory by the server.

[0121] Specific operation: The server executes `existing_df = pandas.read_csv("existing_data.csv")`.

[0122] Step 4:

[0123] The server summarizes the new approval information using a natural language processing engine.

[0124] The server uses a generative AI model (generative AI engine) to summarize the new approval information.

[0125] Input: Text for the new approval information.

[0126] Output: Text of the summarized approval information.

[0127] Specific operation: The server inputs the prompt message "Please summarize the new approval information. Example: 'Change the price of mobile model A from 1000 yen to 1200 yen'" into the generated AI model.

[0128] Step 5:

[0129] The server integrates the summary information into the existing data.

[0130] The server updates the dataset by adding the approval information summarized by the generated AI model to the existing DataFrame.

[0131] Input: DataFrame of existing data, summarized approval information.

[0132] Output: Updated DataFrame.

[0133] Specific action: The server executes existing_df = existing_df.append({"new_info": "Change the price of mobile model A from 1000 yen to 1200 yen"}, ignore_index=True).

[0134] Step 6:

[0135] The server saves the updated data.

[0136] The server saves the updated DataFrame again in CSV format.

[0137] Input: Updated DataFrame.

[0138] Output: Updated CSV file.

[0139] Specific action: The server executes existing_df.to_csv("updated_data.csv", index=False).

[0140] Step 7:

[0141] The server sends the update data to the terminal.

[0142] The server sends the updated approval data to the terminal as an HTTP response.

[0143] Input: Updated DataFrame.

[0144] Output: Update data received by the device.

[0145] Specific operation: The server converts the data using `updated_data = existing_df.to_dict()` and sends it as an HTTP response.

[0146] Step 8:

[0147] The device displays update data to the user.

[0148] The terminal displays the updated data received from the server on the user interface.

[0149] Input: Update data received from the server.

[0150] Output: Updated approval information displayed to the user.

[0151] Specific operation: The terminal executes document.getElementById("data-display").innerHTML = JSON.stringify(updated_data) to reflect the data in the HTML element of the web page.

[0152] (Application Example 1)

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

[0154] Modern e-commerce sites require the efficient management and timely updating of pricing information for numerous products and mobile devices. However, traditional manual data entry and management methods present challenges such as cumbersome information selection, wasted work time, and data management errors. Furthermore, the inability to immediately reflect new prices and payment information can lead to missed sales opportunities. To address these challenges, a more efficient and accurate information management system is necessary.

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

[0156] In this invention, the server includes means for reading existing information, means for summarizing new approval information, means for adding the summarized approval information to the existing information, means for storing the updated information, means for using a natural language processing engine to generate the new approval information, and means for displaying the updated information to the user. This streamlines the management of price information and products on e-commerce sites, enabling accurate data updates while significantly reducing labor. Furthermore, by utilizing a generation AI model, new approval information can be automatically summarized and quickly reflected in the data, which is expected to maximize sales opportunities.

[0157] "Means for reading existing information" refers to a function for retrieving previously recorded information from stored data files.

[0158] "Means for summarizing new approval information" refers to a function that uses a natural language processing engine to convert newly entered data into a concise format.

[0159] "Means of adding summarized approval information to existing information" refers to processing functions for integrating newly summarized data into existing datasets.

[0160] "Means for saving updated information" refers to a function that stores the dataset containing the new approval information in a file format, making it accessible the next time the data is read.

[0161] A "natural language processing engine that generates new approval information" is an engine that uses a generative AI model to shorten and summarize text data entered by the user.

[0162] "Means of displaying updated information to the user" refers to a function that visually provides the latest data sent from the server to the user's device or web interface.

[0163] A "generative AI model" is an artificial intelligence technology that learns from large amounts of data and generates natural language, and is primarily used for natural language processing and data summarization.

[0164] A "prompt" is input text used to give specific instructions or questions to a natural language processing engine.

[0165] This invention is a system for building an automated price management application for e-commerce websites. This system includes a server and user terminals and has the following main functions and processing steps:

[0166] System Overview

[0167] The server reads existing information, summarizes new approval information, integrates the summarized information with the existing data, and stores it. It also provides the updated information visually to the user. The user terminal provides an interface for entering the new approval information and allows the user to confirm the updated information.

[0168] Server Functions

[0169] 1. Means of reading existing information:

[0170] The server uses the Pandas library to read existing data (such as price information and product information) from a CSV file. This retrieves previously recorded information and prepares it for the next processing step.

[0171] 2. Means for summarizing new approval information:

[0172] The server uses a generative AI model to summarize the new approval information entered by the user using a natural language processing engine (e.g., GPT-3). This converts the input information into a concise and easy-to-handle format.

[0173] 3. Means for adding summarized approval information to existing information:

[0174] The summarized approval information is added to the existing dataframe, updating the dataset to its latest state. This process is performed using the Pandas library.

[0175] 4. Means for saving updated information:

[0176] The updated information will be saved again as a CSV file. This will ensure that the latest information is available the next time the data is read.

[0177] 5. Means for displaying updated information to the user:

[0178] The server sends updated information to the user's terminal, allowing for visual confirmation. This display can be accessed via a web interface or a dedicated application.

[0179] User terminal functions

[0180] 1. Receiving user input:

[0181] The user terminal provides an interface for entering new approval information (e.g., price changes for products). This information can be easily entered by the user through web forms or dedicated software applications.

[0182] 2. Submitting the entered information:

[0183] The user terminal sends the newly entered approval information to the server. This transmission is performed using protocols such as HTTP requests.

[0184] 3. Displaying update data:

[0185] Users can check updated data (for example, the latest price information) in real time through their devices.

[0186] Specific example

[0187] For example, when a user enters new payment information into their terminal, such as "Change the price of mobile device B from 800 yen to 850 yen," this information is sent to the server. The server reads the existing data and summarizes this new information using a natural language processing engine (GPT-3). The resulting summary information is "Change the price of mobile device B from 800 yen to 850 yen." This summary information is integrated into the existing data frame, and the updated dataset is saved in CSV format. The user can then view the updated data through their terminal.

[0188] Example of a prompt

[0189] "Please change the price of mobile model B from 800 yen to 850 yen."

[0190] Please summarize the new payment information: 'The price of mobile device B will be changed from 800 yen to 850 yen.'

[0191] This streamlines the management of pricing information and products on e-commerce sites, allowing for the immediate reflection of accurate information and ultimately maximizing sales opportunities.

[0192] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0193] Step 1:

[0194] The user enters new payment information. The user uses their device to enter information such as, for example, "Change the price of mobile device B from 800 yen to 850 yen." The device receives this input and sends it to the server via an HTTP request.

[0195] Step 2:

[0196] The server reads existing information. Using the Pandas library, the server reads existing price and product information from a CSV file. This read information forms the basis for the next processing step.

[0197] Step 3:

[0198] The server summarizes the new approval information. The server uses a generative AI model (e.g., GPT-3) to process the newly entered information. The input is text information sent by the user, and the output is summarized approval information. Specifically, the server inputs a prompt message such as "Please change the price of mobile model B from 800 yen to 850 yen" into the generative AI model and obtains the summarized result "Change the price of mobile model B from 800 yen to 850 yen".

[0199] Step 4:

[0200] The server adds the summarized approval information to the existing data. The server uses a Pandas DataFrame to add the summarized approval information to the existing DataFrame. Specifically, it inserts the new summarized information as a new record into the existing data. The input data is the summarized approval information, and the output is an updated DataFrame.

[0201] Step 5:

[0202] The server saves the updated information. The server uses the Pandas library to save the updated data as a CSV file. This saving process ensures that the latest information is available the next time the data is read. The input data is an updated dataframe, and the output is the saved CSV file.

[0203] Step 6:

[0204] The server displays updated information to the user. The server sends updated price and product information to the user's terminal via an HTTP response. The terminal receives this information and displays it for the user to visually confirm. Specifically, a web interface or a dedicated application is used. The input data is the updated information, and the output is the data displayed on the user's terminal.

[0205] Through the above processing steps, a system is realized in which new approval information entered by the user is efficiently processed, ultimately providing the user with the latest and most accurate information.

[0206] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0207] This invention is a data management system that combines an emotion engine and can efficiently process new decision information based on the recognition of user emotions. The following describes a specific implementation of this system.

[0208] System Overview

[0209] The system works by having users input new approval information via a terminal, with a server processing that information and integrating it with existing data. In addition, an emotion engine recognizes the user's emotions and adjusts information processing and display based on those emotions. This system improves operational efficiency, data management accuracy, and user experience.

[0210] System Configuration

[0211] The server has the following main features:

[0212] 1. Reading existing data: The server reads existing approval information from a CSV file. This is done using a data analysis library such as Pandas.

[0213] 2. Summarizing New Approval Information: The server uses a natural language processing engine (such as GPT-3) to summarize the new approval information. The server sends the new approval information as a prompt to the natural language processing engine and receives the summary result.

[0214] 3. Adding summary information: The server integrates the summarized approval information into the existing data. It adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[0215] 4. Data Storage: The server saves the updated DataFrame again as a CSV file. This generates a file that reflects the latest approval information.

[0216] 5. Emotion Recognition: The server uses an emotion engine to recognize the user's emotions in real time. The recognized emotions influence how information is processed and displayed.

[0217] The device has the following main features:

[0218] 1. User Input Reception: The terminal provides an interface for users to input new approval information. This interface is implemented through web forms or dedicated software applications.

[0219] 2. Sending Input Information: The terminal sends the information entered by the user to the server. This transmission is done using HTTP requests, etc.

[0220] 3. Transmission of emotion data: The device senses the user's facial expressions and tone of voice and sends this data to the server. The emotion engine analyzes this data and recognizes the user's emotions.

[0221] 4. Displaying updated data: The terminal displays the latest approval information data sent from the server to the user. The display method can also be adjusted based on sentiment data.

[0222] Specific example

[0223] For example, consider a scenario where a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent to the server, which reads the existing data. The server then uses a natural language processing engine to summarize the new payment information, generating a summary such as "Change the price of mobile device A from 1000 yen to 1200 yen." This summarized information is added to the existing DataFrame, and the updated dataset is saved in CSV format. Furthermore, an emotion engine recognizes the user's emotions (e.g., tension or anxiety) and adjusts the summary content and display method accordingly.

[0224] Users can later review this updated data through their devices. The display method may also be adjusted to a view that is relaxing for the user. In this way, new approval information can be managed quickly in daily operations, and an optimal user experience tailored to individual needs can be provided.

[0225] The system of the present invention functions based on the above components and processing flow, streamlining the management of approval information and realizing information processing and display that takes user emotions into consideration.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The user enters new payment information (for example, "Change the price of mobile device A from 1000 yen to 1200 yen") into the device. The device collects this information and prepares a request to send it to the server.

[0229] Step 2:

[0230] The terminal sends the prepared request to the server. This request is sent as data in JSON or XML format, containing the new approval information.

[0231] Step 3:

[0232] The server parses the received request and extracts new approval information. This new approval information is stored on the server in text format.

[0233] Step 4:

[0234] The server reads a CSV file containing existing approval information. This uses data analysis libraries such as Pandas to read the data from the CSV file in DataFrame format.

[0235] Step 5:

[0236] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The server sends the new approval information to the natural language processing engine as a prompt and receives the summary result.

[0237] Step 6:

[0238] The server integrates the received summary results into the existing data. This process adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[0239] Step 7:

[0240] The server saves the updated DataFrame again as a CSV file. By overwriting the existing file, a file is generated that reflects the latest approval information.

[0241] Step 8:

[0242] The device uses sensors to detect the user's facial expressions and voice tone, and sends this emotional data to a server. The emotion engine analyzes this data to recognize the user's emotions in real time.

[0243] Step 9:

[0244] The server adjusts how information is processed and displayed based on the recognized user's emotions. For example, if the user is stressed, it may add more detailed information, or conversely, if they are relaxed, it may display only summary information.

[0245] Step 10:

[0246] The user requests the latest approval information data stored on the server via their device. The device sends this request using a protocol such as an HTTP request.

[0247] Step 11:

[0248] The server rereads the updated CSV file to retrieve the latest data. The retrieved data is then formatted appropriately according to the user's sentiment and prepared for transmission to the terminal.

[0249] Step 12:

[0250] The terminal displays the latest approval information data received from the server to the user. The display method is adjusted based on the results processed by the emotion engine. For example, if the user is stressed, supplementary explanations and graphs are added for more detail; if relaxed, only a concise summary is displayed.

[0251] This process allows users to quickly manage new approval information in their daily work and obtain an optimal user experience through emotion-based information display. Furthermore, the introduction of an emotion engine is expected to improve both work efficiency and user satisfaction.

[0252] (Example 2)

[0253] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0254] Conventional data management systems have faced challenges in efficiently processing and integrating new approval information, as well as in displaying and processing information in a way that considers user emotions. In particular, there is a need to process large amounts of data quickly and accurately, while simultaneously making adjustments that respond to user emotions to reduce work stress.

[0255] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0256] In this invention, the server includes means for reading existing data, means for summarizing new approval information, means for adding the summarized approval information to the existing data, means for storing the updated data, means for recognizing the user's emotions, and means for adjusting information processing and display based on the recognized emotions. This streamlines the management of approval information and enables information processing and display that takes the user's emotions into consideration.

[0257] "Existing data" refers to information that is already stored within the data management system.

[0258] "New approval information" refers to information that has been newly entered into the system and needs to be managed.

[0259] A "summary" is a concise compilation of new approval information.

[0260] A "natural language processing engine" is an artificial intelligence technology that analyzes input text data and outputs it in a format that is easy for humans to understand.

[0261] "User emotions" refers to the feelings a user experiences while using the service (e.g., tension, relaxation, anxiety, etc.).

[0262] "Means of recognizing emotions" refers to methods or devices that use an emotion engine to analyze a user's emotional data and identify those emotions.

[0263] "Means for adjusting information processing and display" refers to methods or devices that change the way a system processes or displays information based on the perceived emotions of the user.

[0264] A "CSV file" is a text file format that uses comma-separated values ​​and is used for saving and reading data.

[0265] A "data frame" is a tabular data structure composed of rows and columns, used for storing and manipulating data.

[0266] An "HTTP request" is a protocol used to send requests from a client, such as a web browser, to a web server.

[0267] Modes for carrying out the invention

[0268] This invention is a data management system that incorporates an emotion engine, enabling efficient processing of new approval information based on user emotion recognition. This system can improve operational efficiency, data management accuracy, and user experience.

[0269] System Overview

[0270] This system allows users to input new approval information via a terminal, and a server processes that information and integrates it with existing data. In addition, a key feature is the emotion engine, which recognizes the user's emotions and adjusts information processing and display based on those emotions. This system enables rapid management of new approval information and optimizes the user experience in daily operations.

[0271] Server-based processing

[0272] The server has multiple functions and performs the following processes.

[0273] 1. Reading existing data:

[0274] The server uses data analysis libraries such as Pandas to read existing approval information from CSV files. This allows for accurate retrieval of existing data.

[0275] 2. Summary of new approval information:

[0276] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The following is an example of a prompt used for summarization.

[0277] New payment information: Change the price of mobile device A from 1000 yen to 1200 yen.

[0278] Please create a summary of this information.

[0279] 3. Add summary information:

[0280] The server adds the summarized approval information as new rows to the existing DataFrame, generating an updated dataset. This ensures a smooth integration of old and new data.

[0281] 4. Data storage:

[0282] The server saves the updated DataFrame as a CSV file again. This generates a data file with the latest approval information reflected.

[0283] 5. Emotion Recognition:

[0284] The server uses an emotion engine to recognize the user's emotions in real time. For example, when the user is nervous, the processing and display methods are adjusted based on that data.

[0285] Processing by the Terminal

[0286] The terminal provides the following functions.

[0287] 1. Reception of User Input:

[0288] The terminal provides an interface that allows the user to input new approval information through a dedicated web form or software application.

[0289] 2. Transmission of Input Information:

[0290] The terminal transmits the information input by the user to the server using an HTTP request. This ensures reliable data transmission.

[0291] 3. Transmission of Emotion Data:

[0292] The terminal senses the user's facial expressions and vocal tones and transmits that data to the server. The emotion engine analyzes the data to recognize the user's emotions.

[0293] 4. Display of Updated Data:

[0294] The terminal displays the latest approval information data transmitted from the server to the user. Furthermore, the display method can be adjusted based on the user's emotions.

[0295] Specific Example

[0296] When a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen," this information is sent from the device to the server using an HTTP request. The server uses Pandas to read the existing data and a natural language processing engine to summarize the new information. The summarized information is then added to the existing DataFrame, and the updated dataset is saved as a CSV file. Furthermore, an emotion engine recognizes the user's emotions (e.g., tension or anxiety) in real time, and the display method is adjusted according to the recognized emotions.

[0297] In this way, the system can efficiently manage and display approval information while taking user emotions into consideration.

[0298] Specific examples of hardware and software to be used

[0299] This system's implementation utilizes Pandas, a natural language processing engine (GPT-3), and an emotion recognition engine on the server side. On the terminal side, communication with the server is performed using HTTP requests via web forms or dedicated software applications.

[0300] With the above configuration, the present invention provides a system that enables efficient management of approval information and information processing and display that takes into consideration the user's feelings.

[0301] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0302] Step 1:

[0303] The user enters the new approval information into the terminal.

[0304] The user uses a dedicated web form or software application to input approval information (e.g., "Change the price of mobile model A from 1000 yen to 1200 yen"). This is the input data for Step 1. After input, the information is saved on the terminal.

[0305] Step 2:

[0306] The terminal sends the input information to the server.

[0307] The input approval information is sent from the terminal to the server using an HTTP request. This transmission is executed in a form such as requests.post('http: / / example.com / api', data={'information': 'Change the price of mobile model A from 1000 yen to 1200 yen'}). The server that receives the transmission receives the new approval information as the output of Step 2.

[0308] Step 3:

[0309] The server reads the existing data.

[0310] The server reads the existing approval information from a CSV - formatted file using the Pandas library. The input is the existing data file, and the output is data in the DataFrame format. Specifically, a DataFrame is obtained in the form of pd.read_csv('approval_information.csv').

[0311] Step 4:

[0312] The server summarizes the new approval information using a natural - language processing engine.

[0313] The server sends the newly received approval information as a prompt to a natural - language processing engine (e.g., GPT - 3) and receives the summarized information. Examples of prompt sentences are as follows.

[0314] New payment information: Change the price of mobile device A from 1000 yen to 1200 yen.

[0315] Please create a summary of this information.

[0316] The input data is the new approval information, and the output data is the summarized approval information.

[0317] Step 5:

[0318] The server integrates the summary information into the existing data.

[0319] Summarized approval information is added as a new row to an existing DataFrame. The data for the new row is added using the DataFrame.append() method. The input is the summary information and the existing DataFrame, and the output is the updated DataFrame.

[0320] Step 6:

[0321] The server saves the updated data.

[0322] The server saves the updated DataFrame again as a CSV file. The method used for saving is `df.to_csv('ApprovalInfo.csv', index=False)`. The input data is the updated DataFrame, and the output is the updated CSV file.

[0323] Step 7:

[0324] The device sends user emotion data to the server.

[0325] The device senses the user's facial expressions and tone of voice and sends that data to the server. The input data is emotional data, and the output data is the emotional data sent to the server.

[0326] Step 8:

[0327] The server analyzes the user's emotions using an emotion engine.

[0328] The server uses an emotion engine to analyze the transmitted emotion data. Based on the results of the emotion analysis, the way the information is displayed and processed is adjusted. The input data is emotion data, and the output data is the analysis result.

[0329] Step 9:

[0330] The device displays update data.

[0331] The terminal displays the latest approval information data sent from the server to the user. The display method is adjusted based on emotional data. For example, if the user is stressed, the content is displayed concisely; if they are relaxed, more detailed information is displayed. The input data consists of the updated approval information data and the results of the emotional analysis, while the output data is the adjusted display.

[0332] In this way, the system efficiently manages new approval information and displays it in a way that is considerate of the user's feelings.

[0333] (Application Example 2)

[0334] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0335] The problems that this invention aims to solve are the efficient management of electronic payment information and the improvement of the user experience. Conventional systems do not take into account the user's emotions when processing information, which can cause users to feel stressed. Therefore, it is necessary to adjust information processing and display methods based on the user's emotions so that users can make payments in a relaxed state.

[0336] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for reading existing data, means for summarizing new payment information, means for adding the summarized payment information to the existing data, means for storing the updated data, means for recognizing the user's emotions, and means for adjusting information processing and display based on the recognized emotions. This enables efficient management of electronic payment information and improvement of the user experience.

[0337] "Existing data" refers to past payment information and related data that is already stored in the system.

[0338] "New payment information" refers to payment information and transaction details that a user newly enters.

[0339] "Means of summarization" refers to processes or devices that use natural language processing engines or similar technologies to condense input payment information into a shorter format.

[0340] "Means of storing data" refers to mechanisms or devices for continuously storing updated data. This includes, for example, means of saving data in CSV format.

[0341] "Means of recognizing emotions" refers to technologies and devices that analyze a user's facial expressions and tone of voice to detect their emotional state.

[0342] "Means for adjusting information processing and display" refers to processes and devices for optimizing the operation of a system or the appearance of a user interface based on perceived emotions.

[0343] A "natural language processing engine" refers to machine learning models or software that analyze input text data and automatically perform processing such as summarization and translation.

[0344] A "CSV file" refers to a file format with comma-separated values, and it is a widely used data format for saving and transferring data.

[0345] Modes for carrying out the invention

[0346] The present invention provides a system for efficiently managing electronic payment information in response to user emotions. This system relies on the interaction between a server and a terminal; the user inputs new payment information through the terminal, and the server processes this information and recognizes the user's emotions. Specifically, the elements work together as follows:

[0347] Server configuration and operation

[0348] The server has the following main features:

[0349] 1. Existing data reading method: The server reads existing payment information from a CSV file. This is done using Pandas, a Python data analysis library.

[0350] 2. New payment information summarization method: New payment information is summarized using a natural language processing engine (e.g., GPT-3). The input payment information is sent to the natural language processing engine as a prompt, and the summarized case is received.

[0351] 3. Method for adding summary information: Integrate the summarized payment information into existing data. This process is performed by generating an updated DataFrame and adding it as new rows to an existing CSV file.

[0352] 4. Data storage method: The updated DataFrame is saved again as a CSV file to reflect the latest payment information.

[0353] 5. Emotion Recognition Method: An emotion engine is used to recognize the user's emotions in real time. Emotion data influences subsequent information processing and display methods.

[0354] Terminal configuration and operation

[0355] The device has the following main features:

[0356] 1. Means for receiving user input: Provide a user interface for users to input new payment information. This can be implemented using web forms or dedicated applications.

[0357] 2. Means of transmitting input information: Information entered by the user is sent to the server using HTTP requests, etc.

[0358] 3. Means of transmitting emotional data: The terminal senses the user's facial expressions and tone of voice and transmits that data to the server.

[0359] 4. Display method for updated data: The latest payment information data sent from the server is displayed to the user. It is also possible to adjust the display method based on sentiment data.

[0360] Specific example

[0361] As an example, consider a case where a user enters new payment information into their terminal, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent to the server, which reads the existing data. Then, using a natural language processing engine, the new payment information is summarized, and the summary "Change the price of mobile device A from 1000 yen to 1200 yen" is generated.

[0362] Example of a prompt

[0363] User input: "Change the price of the new monthly plan from 3000 yen to 2500 yen."

[0364] GPT-3 prompt: "Please summarize the entered payment information: Change the price of the new monthly plan from 3000 yen to 2500 yen."

[0365] Subsequently, this summary information is added to an existing DataFrame, and the updated dataset is saved in CSV format. Furthermore, the emotion engine can recognize the user's emotions (e.g., tension or anxiety) and adjust the summary content and display method accordingly.

[0366] Based on the above configuration and operation, the system of the present invention streamlines payment information management and realizes information processing and display that takes user emotions into consideration. As a result, users can perform payment transactions in a relaxed state.

[0367] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0368] Step 1:

[0369] The user enters new payment information into the terminal. On the terminal's user interface, the user enters the payment information into a text field and presses the "Submit Payment Information" button. The entered payment information is stored in text format.

[0370] Step 2:

[0371] The terminal sends the payment information entered by the user to the server. The entered payment information is sent to the server as an HTTP POST request. The data entered here is the payment information text entered by the user. The server receives this payment information text as output.

[0372] Step 3:

[0373] The server reads existing payment data from a CSV file. Using the Python Pandas library, it reads the CSV file containing the existing data and converts it to a DataFrame. The input is a CSV file, and the output is a DataFrame of the read existing payment data.

[0374] Step 4:

[0375] The server sends the new payment information to a natural language processing engine to generate a summary. The server sends the input payment information text as a prompt to the natural language processing engine (e.g., GPT-3) and receives the summary result. The input is the payment information text entered by the user, and the output is the summary result returned by the natural language processing engine.

[0376] Step 5:

[0377] The server adds the summarized payment information to the existing data. It adds the new summarized information as a new row to the updated DataFrame. At this time, it also adds user sentiment data if necessary. The input is the summarized payment information and the existing DataFrame, and the output is the updated DataFrame with the new payment information added.

[0378] Step 6:

[0379] The server saves the updated DataFrame again as a CSV file. The Pandas library is used to write the updated DataFrame to a CSV file. The input is the updated DataFrame, and the output is the new CSV file.

[0380] Step 7:

[0381] The device senses the user's facial expressions and tone of voice and sends this data to the server. The device's camera and microphone are used to collect data about the user's emotions. The collected data is sent to the server for analysis by the emotion recognition engine. The input is the user's emotion data, and the output is the emotion data sent to the server.

[0382] Step 8:

[0383] The server uses an emotion recognition engine to recognize the user's emotions in real time. Based on the received emotion data, it analyzes the user's emotional state. The input is the user's emotion data, and the output is information about the recognized emotions.

[0384] Step 9:

[0385] The server adjusts how summarized payment information is displayed based on the perceived emotions. For example, it changes the display method depending on whether the user is stressed or relaxed. The input is perceived emotion information and summarized payment information, and the output is the adjusted display information.

[0386] Step 10:

[0387] The terminal displays the latest payment information data sent from the server to the user. It adjusts the display method based on sentiment data, providing information through a user-friendly interface. The input is the adjusted display information received from the server, and the output is the actual displayed payment information.

[0388] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0389] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0390] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0391] [Second Embodiment]

[0392] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0393] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0394] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0395] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0396] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0397] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0398] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0399] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0400] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0401] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0402] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0403] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0404] This invention is a system for efficiently managing the pricing of multiple products and mobile devices. The following describes a specific implementation of this system.

[0405] System Overview

[0406] This system enables a seamless workflow where users input new approval information via a terminal, and a server processes that information and integrates it with existing data. This system improves operational efficiency and data management accuracy.

[0407] System Configuration

[0408] The server has the following main features:

[0409] 1. Reading existing data: The server reads existing approval information from a CSV file. This reading is done using a data analysis library such as Pandas.

[0410] 2. Summarizing new approval information: The server uses a natural language processing engine (e.g., GPT-3) to summarize new approval information. This summarization makes it easier to select and filter information.

[0411] 3. Adding summary information: The server integrates the summarized approval information into the existing DataFrame and generates an updated dataset.

[0412] 4. Data Storage: The server saves the updated data again as a CSV file. This ensures that the latest information is available when the data is read in the future.

[0413] The device has the following main features:

[0414] 1. User Input Reception: The terminal provides an interface for users to input new approval information. This interface is implemented through web forms or dedicated software applications.

[0415] 2. Sending Input Information: The terminal sends the information entered by the user to the server. This transmission is done using protocols such as HTTP requests.

[0416] 3. Display of updated data: The terminal receives the latest approval information data sent from the server and displays it to the user. This allows the user to check the latest information at any time.

[0417] Specific example

[0418] For example, consider a case where a user enters new payment information into their terminal, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is first sent to the server. The server reads the existing data and summarizes this new information using a natural language processing engine. The resulting summary is "Change the price of mobile device A from 1000 yen to 1200 yen." This summarized information is added to the existing DataFrame, and the updated dataset is saved in CSV format.

[0419] Users can later review this updated data through their devices. This saves work time and improves the accuracy of data management.

[0420] The system of the present invention functions based on the above components and processing flow, and streamlines the management of approval information.

[0421] The following describes the processing flow.

[0422] Step 1:

[0423] The user enters new payment information (for example, "Change the price of mobile device A from 1000 yen to 1200 yen") into the device. The device collects this information and prepares a request to send it to the server.

[0424] Step 2:

[0425] The terminal sends the prepared request to the server. This request is sent as data in JSON or XML format, containing the new approval information.

[0426] Step 3:

[0427] The server parses the received request and extracts new approval information. This new approval information is stored on the server in text format.

[0428] Step 4:

[0429] The server reads a CSV file containing existing approval information. This uses data analysis libraries such as Pandas to read the data from the CSV file in DataFrame format.

[0430] Step 5:

[0431] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The server sends the new approval information to the natural language processing engine as a prompt and receives the summary result.

[0432] Step 6:

[0433] The server integrates the received summary results into the existing data. This process adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[0434] Step 7:

[0435] The server saves the updated DataFrame again as a CSV file. By overwriting the existing file, a file is generated that reflects the latest approval information.

[0436] Step 8:

[0437] The user requests the latest approval information data stored on the server via their device. The device sends this request using a protocol such as an HTTP request.

[0438] Step 9:

[0439] The server rereads the updated CSV file to retrieve the latest data. It then prepares this data for transmission to the terminal.

[0440] Step 10:

[0441] The terminal displays the latest approval information data received from the server to the user. The user can then review this updated information and use it for necessary tasks.

[0442] This allows users to quickly manage new approval information in their daily work and check updates in real time. This process streamlines the summarization and data management of approval information, resulting in reduced working time and improved accuracy.

[0443] (Example 1)

[0444] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0445] A system is needed to properly manage existing approval information and efficiently input, summarize, integrate, and store new approval information. However, conventional systems have problems such as time-consuming information summarization, data integration, and storage processes, which increase the likelihood of manual input errors and data management omissions. Therefore, there is a need for a system that solves these problems and improves the efficiency and accuracy of approval information management.

[0446] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0447] In this invention, the server includes means for a user to input new approval information through a terminal, means for transmitting the new approval information to the server, means for reading existing data, means for summarizing the new approval information using a generative AI model, means for adding the summarized approval information to the existing data, means for saving the updated data, means for transmitting the updated data to the terminal, and means for the terminal to display the updated data to the user. This streamlines the management of approval information and enables accurate data updating and storage.

[0448] A "user" is the entity that operates the system and inputs new approval information.

[0449] A "terminal" is a device operated by a user that has the means to input new approval information and send that information to a server.

[0450] A "server" is a central management device that processes, stores, and manages approval information.

[0451] "Approval information" refers to data representing the pricing and approval information for products and mobile devices in a business context.

[0452] A "generative AI model" refers to an artificial intelligence algorithm that uses natural language processing technology to analyze and summarize text data.

[0453] "Summarization" refers to the process of extracting important information using a generative AI model and presenting it in a concise format.

[0454] A "data analysis library" is a software library used to manipulate and analyze data, and in this context, it specifically refers to Pandas.

[0455] A "CSV file" refers to a file format that stores data in comma-separated text format.

[0456] This invention is a system for efficiently managing the pricing of multiple products and mobile devices. This system implements a workflow in which users input new approval information via a terminal, and a server processes this information and integrates it with existing data. The specific implementation of this system is described below.

[0457] System configuration and operation

[0458] The device has the following features:

[0459] 1. User Input Reception: The terminal allows users to input new payment information through web forms or dedicated software. For example, it provides text boxes or selection menus for inputting information such as "Change the price of mobile model A from 1000 yen to 1200 yen."

[0460] 2. Sending Input Information: The terminal sends the approval information entered by the user to the server as an HTTP POST request. Specifically, the request library is used to send the information.

[0461] The server has the following functions:

[0462] 1. Reading existing data: The server uses the Pandas library to read existing approval information from a CSV file. This process allows the server to understand the current data state.

[0463] 2. Summarizing the new approval information: The server uses a generative AI model (e.g., GPT-3) to summarize the new approval information. The prompt will be in the format of "Please summarize the new approval information. Example: 'Change the price of mobile model A from 1000 yen to 1200 yen'."

[0464] 3. Adding summary information: The server integrates the summarized approval information into the existing DataFrame and updates the dataset. This ensures that the new approval information is reflected in the existing data.

[0465] 4. Data Storage: The server saves the updated dataset again in CSV format. This ensures that the latest information is available the next time the data is read.

[0466] 5. Sending updated data: The server sends the updated approval data to the terminal as an HTTP response. Specifically, it converts the data into a dictionary format and sends it as a response.

[0467] The device has the following features:

[0468] 1. Receiving and displaying updated data: The terminal receives updated data sent from the server and displays it in the user interface. For example, it reflects the updated approval information in the HTML elements of a web page that displays it as a list.

[0469] Specific example

[0470] As a concrete example, consider the process when a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent from the device to the server. The server reads the existing data and summarizes this new information using a generation AI model. The generated summary information, "Change the price of mobile device A from 1000 yen to 1200 yen," is added to the existing data, and the updated dataset is saved in CSV format. Finally, the server sends the updated data to the device, which then displays it to the user.

[0471] In this way, this system can streamline the management of new approval information and improve the accuracy of data processing.

[0472] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0473] Step 1:

[0474] The user enters new approval information into the terminal.

[0475] Users enter new approval information using web forms or dedicated applications provided by their devices.

[0476] Input: New approval information (e.g., "Change the price of mobile device A from 1000 yen to 1200 yen").

[0477] Output: New approval information entered by the user on the terminal.

[0478] Specific operation: The user enters information into text boxes or selection menus and presses the "Submit" button.

[0479] Step 2:

[0480] The terminal sends the input information to the server.

[0481] The terminal sends the approval information entered by the user to the server as an HTTP POST request.

[0482] Input: Approval information entered by the user.

[0483] Output: Approval information received by the server.

[0484] Specific operation: The terminal uses the requests.post library to send the approval information to the specified server URL.

[0485] Step 3:

[0486] The server reads existing data.

[0487] The server uses the Pandas library to read existing approval information from a CSV file.

[0488] Input: A CSV file containing existing approval data.

[0489] Output: A DataFrame of existing data loaded into memory by the server.

[0490] Specific operation: The server executes `existing_df = pandas.read_csv("existing_data.csv")`.

[0491] Step 4:

[0492] The server summarizes the new approval information using a natural language processing engine.

[0493] The server uses a generative AI model (generative AI engine) to summarize the new approval information.

[0494] Input: Text for the new approval information.

[0495] Output: Text of the summarized approval information.

[0496] Specific operation: The server inputs the prompt message "Please summarize the new approval information. Example: 'Change the price of mobile model A from 1000 yen to 1200 yen'" into the generated AI model.

[0497] Step 5:

[0498] The server integrates the summary information into the existing data.

[0499] The server updates the dataset by adding the approval information summarized by the generated AI model to the existing DataFrame.

[0500] Input: DataFrame of existing data, summarized approval information.

[0501] Output: Updated DataFrame.

[0502] Specific action: The server executes existing_df = existing_df.append({"new_info": "Change the price of mobile model A from 1000 yen to 1200 yen"}, ignore_index=True).

[0503] Step 6:

[0504] The server saves the updated data.

[0505] The server saves the updated DataFrame again in CSV format.

[0506] Input: Updated DataFrame.

[0507] Output: Updated CSV file.

[0508] Specific action: The server executes existing_df.to_csv("updated_data.csv", index=False).

[0509] Step 7:

[0510] The server sends the update data to the terminal.

[0511] The server sends the updated approval data to the terminal as an HTTP response.

[0512] Input: Updated DataFrame.

[0513] Output: Update data received by the device.

[0514] Specific operation: The server converts the data using `updated_data = existing_df.to_dict()` and sends it as an HTTP response.

[0515] Step 8:

[0516] The device displays update data to the user.

[0517] The terminal displays the updated data received from the server on the user interface.

[0518] Input: Update data received from the server.

[0519] Output: Updated approval information displayed to the user.

[0520] Specific operation: The terminal executes document.getElementById("data-display").innerHTML = JSON.stringify(updated_data) to reflect the data in the HTML element of the web page.

[0521] (Application Example 1)

[0522] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0523] Modern e-commerce sites require the efficient management and timely updating of pricing information for numerous products and mobile devices. However, traditional manual data entry and management methods present challenges such as cumbersome information selection, wasted work time, and data management errors. Furthermore, the inability to immediately reflect new prices and payment information can lead to missed sales opportunities. To address these challenges, a more efficient and accurate information management system is necessary.

[0524] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0525] In this invention, the server includes means for reading existing information, means for summarizing new approval information, means for adding the summarized approval information to the existing information, means for storing the updated information, means for using a natural language processing engine to generate the new approval information, and means for displaying the updated information to the user. This streamlines the management of price information and products on e-commerce sites, enabling accurate data updates while significantly reducing labor. Furthermore, by utilizing a generation AI model, new approval information can be automatically summarized and quickly reflected in the data, which is expected to maximize sales opportunities.

[0526] "Means for reading existing information" refers to a function for retrieving previously recorded information from stored data files.

[0527] "Means for summarizing new approval information" refers to a function that uses a natural language processing engine to convert newly entered data into a concise format.

[0528] "Means of adding summarized approval information to existing information" refers to processing functions for integrating newly summarized data into existing datasets.

[0529] "Means for saving updated information" refers to a function that stores the dataset containing the new approval information in a file format, making it accessible the next time the data is read.

[0530] A "natural language processing engine that generates new approval information" is an engine that uses a generative AI model to shorten and summarize text data entered by the user.

[0531] "Means of displaying updated information to the user" refers to a function that visually provides the latest data sent from the server to the user's device or web interface.

[0532] A "generative AI model" is an artificial intelligence technology that learns from large amounts of data and generates natural language, and is primarily used for natural language processing and data summarization.

[0533] A "prompt" is input text used to give specific instructions or questions to a natural language processing engine.

[0534] This invention is a system for building an automated price management application for e-commerce websites. This system includes a server and user terminals and has the following main functions and processing steps:

[0535] System Overview

[0536] The server reads existing information, summarizes new approval information, integrates the summarized information with the existing data, and stores it. It also provides the updated information visually to the user. The user terminal provides an interface for entering the new approval information and allows the user to confirm the updated information.

[0537] Server Functions

[0538] 1. Means of reading existing information:

[0539] The server uses the Pandas library to read existing data (such as price information and product information) from a CSV file. This retrieves previously recorded information and prepares it for the next processing step.

[0540] 2. Means for summarizing new approval information:

[0541] The server uses a generative AI model to summarize the new approval information entered by the user using a natural language processing engine (e.g., GPT-3). This converts the input information into a concise and easy-to-handle format.

[0542] 3. Means for adding summarized approval information to existing information:

[0543] The summarized approval information is added to the existing dataframe, updating the dataset to its latest state. This process is performed using the Pandas library.

[0544] 4. Means for saving updated information:

[0545] The updated information will be saved again as a CSV file. This will ensure that the latest information is available the next time the data is read.

[0546] 5. Means of displaying updated information to the user:

[0547] The server sends updated information to the user's terminal, allowing for visual confirmation. This display can be accessed via a web interface or a dedicated application.

[0548] User terminal functions

[0549] 1. Receiving user input:

[0550] The user terminal provides an interface for entering new approval information (e.g., changes in product prices). This information can be easily entered by the user through web forms or dedicated software applications.

[0551] 2. Submitting the entered information:

[0552] The user terminal sends the newly entered approval information to the server. This transmission is performed using protocols such as HTTP requests.

[0553] 3. Displaying update data:

[0554] Users can check updated data (for example, the latest price information) in real time through their devices.

[0555] Specific example

[0556] For example, when a user enters new payment information into their terminal, such as "Change the price of mobile device B from 800 yen to 850 yen," this information is sent to the server. The server reads the existing data and summarizes this new information using a natural language processing engine (GPT-3). The resulting summary information is "Change the price of mobile device B from 800 yen to 850 yen." This summary information is integrated into the existing data frame, and the updated dataset is saved in CSV format. The user can then view the updated data through their terminal.

[0557] Example of a prompt

[0558] "Please change the price of mobile model B from 800 yen to 850 yen."

[0559] Please summarize the new payment information: 'The price of mobile device B will be changed from 800 yen to 850 yen.'

[0560] This streamlines the management of pricing information and products on e-commerce sites, allowing for the immediate reflection of accurate information and ultimately maximizing sales opportunities.

[0561] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0562] Step 1:

[0563] The user enters new payment information. The user uses their device to enter information such as, for example, "Change the price of mobile device B from 800 yen to 850 yen." The device receives this input and sends it to the server via an HTTP request.

[0564] Step 2:

[0565] The server reads existing information. Using the Pandas library, the server reads existing price and product information from a CSV file. This read information forms the basis for the next processing step.

[0566] Step 3:

[0567] The server summarizes the new approval information. The server uses a generative AI model (e.g., GPT-3) to process the newly entered information. The input is text information sent by the user, and the output is summarized approval information. Specifically, the server inputs a prompt message such as "Please change the price of mobile model B from 800 yen to 850 yen" into the generative AI model and obtains the summarized result "Change the price of mobile model B from 800 yen to 850 yen".

[0568] Step 4:

[0569] The server adds the summarized approval information to the existing data. The server uses a Pandas DataFrame to add the summarized approval information to the existing DataFrame. Specifically, it inserts the new summarized information as a new record into the existing data. The input data is the summarized approval information, and the output is an updated DataFrame.

[0570] Step 5:

[0571] The server saves the updated information. The server uses the Pandas library to save the updated data as a CSV file. This saving process ensures that the latest information is available the next time the data is read. The input data is an updated dataframe, and the output is the saved CSV file.

[0572] Step 6:

[0573] The server displays updated information to the user. The server sends updated price and product information to the user's terminal via an HTTP response. The terminal receives this information and displays it for the user to visually confirm. Specifically, a web interface or a dedicated application is used. The input data is the updated information, and the output is the data displayed on the user's terminal.

[0574] Through the above processing steps, a system is realized in which new approval information entered by the user is efficiently processed, ultimately providing the user with the latest and most accurate information.

[0575] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0576] This invention is a data management system that combines an emotion engine and can efficiently process new decision information based on the recognition of user emotions. The following describes a specific implementation of this system.

[0577] System Overview

[0578] The system works by having users input new approval information via a terminal, with a server processing that information and integrating it with existing data. In addition, an emotion engine recognizes the user's emotions and adjusts information processing and display based on those emotions. This system improves operational efficiency, data management accuracy, and user experience.

[0579] System Configuration

[0580] The server has the following main features:

[0581] 1. Reading existing data: The server reads existing approval information from a CSV file. This is done using a data analysis library such as Pandas.

[0582] 2. Summarizing New Approval Information: The server uses a natural language processing engine (such as GPT-3) to summarize the new approval information. The server sends the new approval information as a prompt to the natural language processing engine and receives the summary result.

[0583] 3. Adding summary information: The server integrates the summarized approval information into the existing data. It adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[0584] 4. Data Storage: The server saves the updated DataFrame again as a CSV file. This generates a file that reflects the latest approval information.

[0585] 5. Emotion Recognition: The server uses an emotion engine to recognize the user's emotions in real time. The recognized emotions influence how information is processed and displayed.

[0586] The device has the following main features:

[0587] 1. User Input Reception: The terminal provides an interface for users to input new approval information. This interface is implemented through web forms or dedicated software applications.

[0588] 2. Sending Input Information: The terminal sends the information entered by the user to the server. This transmission is done using HTTP requests, etc.

[0589] 3. Transmission of emotion data: The device senses the user's facial expressions and tone of voice and sends this data to the server. The emotion engine analyzes this data and recognizes the user's emotions.

[0590] 4. Displaying updated data: The terminal displays the latest approval information data sent from the server to the user. The display method can also be adjusted based on sentiment data.

[0591] Specific example

[0592] For example, consider a scenario where a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent to the server, which reads the existing data. The server then uses a natural language processing engine to summarize the new payment information, generating a summary such as "Change the price of mobile device A from 1000 yen to 1200 yen." This summarized information is added to the existing DataFrame, and the updated dataset is saved in CSV format. Furthermore, an emotion engine recognizes the user's emotions (e.g., tension or anxiety) and adjusts the summary content and display method accordingly.

[0593] Users can later review this updated data through their devices. The display method may also be adjusted to a view that is relaxing for the user. In this way, new approval information can be managed quickly in daily operations, and an optimal user experience tailored to individual needs can be provided.

[0594] The system of the present invention functions based on the above components and processing flow, streamlining the management of approval information and realizing information processing and display that takes user emotions into consideration.

[0595] The following describes the processing flow.

[0596] Step 1:

[0597] The user enters new payment information (for example, "Change the price of mobile device A from 1000 yen to 1200 yen") into the device. The device collects this information and prepares a request to send it to the server.

[0598] Step 2:

[0599] The terminal sends the prepared request to the server. This request is sent as data in JSON or XML format, containing the new approval information.

[0600] Step 3:

[0601] The server parses the received request and extracts new approval information. This new approval information is stored on the server in text format.

[0602] Step 4:

[0603] The server reads a CSV file containing existing approval information. This uses data analysis libraries such as Pandas to read the data from the CSV file in DataFrame format.

[0604] Step 5:

[0605] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The server sends the new approval information to the natural language processing engine as a prompt and receives the summary result.

[0606] Step 6:

[0607] The server integrates the received summary results into the existing data. This process adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[0608] Step 7:

[0609] The server saves the updated DataFrame again as a CSV file. By overwriting the existing file, a file is generated that reflects the latest approval information.

[0610] Step 8:

[0611] The device uses sensors to detect the user's facial expressions and voice tone, and sends this emotional data to a server. The emotion engine analyzes this data to recognize the user's emotions in real time.

[0612] Step 9:

[0613] The server adjusts how information is processed and displayed based on the recognized user's emotions. For example, if the user is stressed, it may add more detailed information, or conversely, if they are relaxed, it may display only summary information.

[0614] Step 10:

[0615] The user requests the latest approval information data stored on the server via their device. The device sends this request using a protocol such as an HTTP request.

[0616] Step 11:

[0617] The server rereads the updated CSV file to retrieve the latest data. The retrieved data is then formatted appropriately according to the user's sentiment and prepared for transmission to the terminal.

[0618] Step 12:

[0619] The terminal displays the latest approval information data received from the server to the user. The display method is adjusted based on the results processed by the emotion engine. For example, if the user is stressed, supplementary explanations and graphs are added for more detail; if relaxed, only a concise summary is displayed.

[0620] This process allows users to quickly manage new approval information in their daily work and obtain an optimal user experience through emotion-based information display. Furthermore, the introduction of an emotion engine is expected to improve both work efficiency and user satisfaction.

[0621] (Example 2)

[0622] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0623] Conventional data management systems have faced challenges in efficiently processing and integrating new approval information, as well as in displaying and processing information in a way that considers user emotions. In particular, there is a need to process large amounts of data quickly and accurately, while simultaneously making adjustments that respond to user emotions to reduce work stress.

[0624] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0625] In this invention, the server includes means for reading existing data, means for summarizing new approval information, means for adding the summarized approval information to the existing data, means for storing the updated data, means for recognizing the user's emotions, and means for adjusting information processing and display based on the recognized emotions. This streamlines the management of approval information and enables information processing and display that takes the user's emotions into consideration.

[0626] "Existing data" refers to information that is already stored within the data management system.

[0627] "New approval information" refers to information that has been newly entered into the system and needs to be managed.

[0628] A "summary" is a concise compilation of new approval information.

[0629] A "natural language processing engine" is an artificial intelligence technology that analyzes input text data and outputs it in a format that is easy for humans to understand.

[0630] "User emotions" refers to the feelings a user experiences while using the service (e.g., tension, relaxation, anxiety, etc.).

[0631] "Means of recognizing emotions" refers to methods or devices that use an emotion engine to analyze a user's emotional data and identify those emotions.

[0632] "Means for adjusting information processing and display" refers to methods or devices that change the way a system processes or displays information based on the emotions of the recognized user.

[0633] A "CSV file" is a text file format that uses comma-separated values ​​and is used for saving and reading data.

[0634] A "data frame" is a tabular data structure composed of rows and columns, used for storing and manipulating data.

[0635] An "HTTP request" is a protocol used to send requests from a client, such as a web browser, to a web server.

[0636] Modes for carrying out the invention

[0637] This invention is a data management system that incorporates an emotion engine, enabling efficient processing of new approval information based on user emotion recognition. This system can improve operational efficiency, data management accuracy, and user experience.

[0638] System Overview

[0639] This system allows users to input new approval information via a terminal, and a server processes that information and integrates it with existing data. In addition, a key feature is the emotion engine, which recognizes the user's emotions and adjusts information processing and display based on those emotions. This system enables rapid management of new approval information and optimizes the user experience in daily operations.

[0640] Server-based processing

[0641] The server has multiple functions and performs the following processes.

[0642] 1. Reading existing data:

[0643] The server uses data analysis libraries such as Pandas to read existing approval information from a CSV file. This allows for accurate retrieval of existing data.

[0644] 2. Summary of new approval information:

[0645] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The following is an example of a prompt used for summarization.

[0646] New payment information: Change the price of mobile device A from 1000 yen to 1200 yen.

[0647] Please create a summary of this information.

[0648] 3. Add summary information:

[0649] The server adds the summarized approval information as new rows to the existing DataFrame, generating an updated dataset. This ensures a smooth integration of old and new data.

[0650] 4. Data storage:

[0651] The server saves the updated DataFrame again as a CSV file. This generates a data file that reflects the latest approval information.

[0652] 5. Emotion recognition:

[0653] The server uses an emotion engine to recognize the user's emotions in real time. For example, if the user is feeling anxious, the server adjusts its processing and display methods based on that data.

[0654] Processing by the terminal

[0655] The device provides the following functions:

[0656] 1. Receiving user input:

[0657] The terminal provides an interface that allows users to input new approval information through dedicated web forms or software applications.

[0658] 2. Submitting the entered information:

[0659] The terminal sends information entered by the user to the server using an HTTP request. This ensures reliable data transmission.

[0660] 3. Sending emotional data:

[0661] The device senses the user's facial expressions and tone of voice and sends that data to a server. The emotion engine analyzes this data and recognizes the user's emotions.

[0662] 4. Displaying update data:

[0663] The terminal displays the latest approval information data sent from the server to the user. Furthermore, the display method can be adjusted based on the user's emotions.

[0664] Specific example

[0665] When a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen," this information is sent from the device to the server using an HTTP request. The server uses Pandas to read the existing data and a natural language processing engine to summarize the new information. The summarized information is then added to the existing DataFrame, and the updated dataset is saved as a CSV file. Furthermore, an emotion engine recognizes the user's emotions (e.g., tension or anxiety) in real time, and the display method is adjusted according to the recognized emotions.

[0666] In this way, the system can efficiently manage and display approval information while taking user emotions into consideration.

[0667] Specific examples of hardware and software to be used

[0668] This system's implementation utilizes Pandas, a natural language processing engine (GPT-3), and an emotion recognition engine on the server side. On the terminal side, communication with the server is performed using HTTP requests via web forms or dedicated software applications.

[0669] With the above configuration, the present invention provides a system that enables efficient management of approval information and information processing and display that takes into consideration the user's feelings.

[0670] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0671] Step 1:

[0672] The user enters the new approval information into the terminal.

[0673] The user enters the approval information (e.g., "Change the price of mobile device A from 1000 yen to 1200 yen") using a dedicated web form or software application. This is the input data for Step 1. After input, the information is saved on the device.

[0674] Step 2:

[0675] The terminal sends the input information to the server.

[0676] The entered payment information is sent from the terminal to the server using an HTTP request. This transmission is performed in the form of, for example, requests.post('http: / / example.com / api', data={'Information': 'Change the price of mobile model A from 1000 yen to 1200 yen'}). The server that receives the transmission receives the new payment information as the output of step 2.

[0677] Step 3:

[0678] The server reads existing data.

[0679] The server uses the Pandas library to read existing approval information from a CSV file. The input is an existing data file, and the output is data in DataFrame format. Specifically, a DataFrame is obtained using pd.read_csv('approval information.csv').

[0680] Step 4:

[0681] The server uses a natural language processing engine to summarize the new approval information.

[0682] The server sends the newly received approval information as a prompt to a natural language processing engine (e.g., GPT-3) and receives the summarized information. An example of a prompt message is as follows:

[0683] New payment information: Change the price of mobile device A from 1000 yen to 1200 yen.

[0684] Please create a summary of this information.

[0685] The input data is the new approval information, and the output data is the summarized approval information.

[0686] Step 5:

[0687] The server integrates the summary information into the existing data.

[0688] Summarized approval information is added as a new row to an existing DataFrame. The data for the new row is added using the DataFrame.append() method. The input is the summary information and the existing DataFrame, and the output is the updated DataFrame.

[0689] Step 6:

[0690] The server saves the updated data.

[0691] The server saves the updated DataFrame again as a CSV file. The method used for saving is `df.to_csv('ApprovalInfo.csv', index=False)`. The input data is the updated DataFrame, and the output is the updated CSV file.

[0692] Step 7:

[0693] The device sends user emotion data to the server.

[0694] The device senses the user's facial expressions and tone of voice and sends that data to the server. The input data is emotional data, and the output data is the emotional data sent to the server.

[0695] Step 8:

[0696] The server analyzes the user's emotions using an emotion engine.

[0697] The server uses an emotion engine to analyze the transmitted emotion data. Based on the results of the emotion analysis, the way the information is displayed and processed is adjusted. The input data is emotion data, and the output data is the analysis result.

[0698] Step 9:

[0699] The device displays update data.

[0700] The terminal displays the latest approval information data sent from the server to the user. The display method is adjusted based on emotional data. For example, if the user is stressed, the content is displayed concisely; if they are relaxed, more detailed information is displayed. The input data consists of the updated approval information data and the results of the emotional analysis, while the output data is the adjusted display.

[0701] In this way, the system efficiently manages new approval information and displays it in a way that is considerate of the user's feelings.

[0702] (Application Example 2)

[0703] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0704] The problems that this invention aims to solve are the efficient management of electronic payment information and the improvement of the user experience. Conventional systems do not take into account the user's emotions when processing information, which can cause users to feel stressed. Therefore, it is necessary to adjust information processing and display methods based on the user's emotions so that users can make payments in a relaxed state.

[0705] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for reading existing data, means for summarizing new payment information, means for adding the summarized payment information to the existing data, means for storing the updated data, means for recognizing the user's emotions, and means for adjusting information processing and display based on the recognized emotions. This enables efficient management of electronic payment information and improvement of the user experience.

[0706] "Existing data" refers to past payment information and related data that is already stored in the system.

[0707] "New payment information" refers to payment information and transaction details that a user newly enters.

[0708] "Means of summarization" refers to processes or devices that use natural language processing engines or similar technologies to condense input payment information into a shorter format.

[0709] "Means of saving data" refers to mechanisms or devices for continuously storing updated data. This includes, for example, methods for saving data in CSV format files.

[0710] "Means of recognizing emotions" refers to technologies and devices that analyze a user's facial expressions and tone of voice to detect their emotional state.

[0711] "Means for adjusting information processing and display" refers to processes and devices for optimizing the operation of a system or the appearance of a user interface based on perceived emotions.

[0712] A "natural language processing engine" refers to machine learning models or software that analyze input text data and automatically perform processing such as summarization and translation.

[0713] A "CSV file" refers to a file format with comma-separated values, and it is a widely used data format for saving and transferring data.

[0714] Modes for carrying out the invention

[0715] The present invention provides a system for efficiently managing electronic payment information in response to user emotions. This system relies on the interaction between a server and a terminal; the user inputs new payment information through the terminal, and the server processes this information and recognizes the user's emotions. Specifically, the elements work together as follows:

[0716] Server configuration and operation

[0717] The server has the following main features:

[0718] 1. Existing data reading method: The server reads existing payment information from a CSV file. This is done using Pandas, a Python data analysis library.

[0719] 2. New payment information summarization method: New payment information is summarized using a natural language processing engine (e.g., GPT-3). The input payment information is sent to the natural language processing engine as a prompt, and the summarized case is received.

[0720] 3. Method for adding summary information: Integrate the summarized payment information into existing data. This process is performed by generating an updated DataFrame and adding it as new rows to an existing CSV file.

[0721] 4. Data storage method: The updated DataFrame is saved again as a CSV file to reflect the latest payment information.

[0722] 5. Emotion Recognition Method: An emotion engine is used to recognize the user's emotions in real time. Emotion data influences subsequent information processing and display methods.

[0723] Terminal configuration and operation

[0724] The device has the following main features:

[0725] 1. Means for receiving user input: Provide a user interface for users to input new payment information. This can be implemented using web forms or dedicated applications.

[0726] 2. Means of transmitting input information: Information entered by the user is sent to the server using HTTP requests, etc.

[0727] 3. Means of transmitting emotional data: The terminal senses the user's facial expressions and tone of voice and transmits that data to the server.

[0728] 4. Display method for updated data: The latest payment information data sent from the server is displayed to the user. It is also possible to adjust the display method based on sentiment data.

[0729] Specific example

[0730] As an example, consider a case where a user enters new payment information into their terminal, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent to the server, which reads the existing data. Then, using a natural language processing engine, the new payment information is summarized, and the summary "Change the price of mobile device A from 1000 yen to 1200 yen" is generated.

[0731] Example of a prompt

[0732] User input: "Change the price of the new monthly plan from 3000 yen to 2500 yen."

[0733] GPT-3 prompt: "Please summarize the entered payment information: Change the price of the new monthly plan from 3000 yen to 2500 yen."

[0734] Subsequently, this summary information is added to an existing DataFrame, and the updated dataset is saved in CSV format. Furthermore, the emotion engine can recognize the user's emotions (e.g., tension or anxiety) and adjust the summary content and display method accordingly.

[0735] Based on the above configuration and operation, the system of the present invention streamlines payment information management and realizes information processing and display that takes user emotions into consideration. As a result, users can perform payment transactions in a relaxed state.

[0736] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0737] Step 1:

[0738] The user enters new payment information into the terminal. On the terminal's user interface, the user enters the payment information into a text field and presses the "Submit Payment Information" button. The entered payment information is stored in text format.

[0739] Step 2:

[0740] The terminal sends the payment information entered by the user to the server. The entered payment information is sent to the server as an HTTP POST request. The data entered here is the payment information text entered by the user. The server receives this payment information text as output.

[0741] Step 3:

[0742] The server reads existing payment data from a CSV file. Using the Python Pandas library, it reads the CSV file containing the existing data and converts it to a DataFrame. The input is a CSV file, and the output is a DataFrame of the read existing payment data.

[0743] Step 4:

[0744] The server sends the new payment information to a natural language processing engine to generate a summary. The server sends the input payment information text as a prompt to the natural language processing engine (e.g., GPT-3) and receives the summary result. The input is the payment information text entered by the user, and the output is the summary result returned by the natural language processing engine.

[0745] Step 5:

[0746] The server adds the summarized payment information to the existing data. It adds the new summarized information as a new row to the updated DataFrame. At this time, it also adds user sentiment data if necessary. The input is the summarized payment information and the existing DataFrame, and the output is the updated DataFrame with the new payment information added.

[0747] Step 6:

[0748] The server saves the updated DataFrame again as a CSV file. The Pandas library is used to write the updated DataFrame to a CSV file. The input is the updated DataFrame, and the output is the new CSV file.

[0749] Step 7:

[0750] The device senses the user's facial expressions and tone of voice and sends this data to the server. The device's camera and microphone are used to collect data about the user's emotions. The collected data is sent to the server for analysis by the emotion recognition engine. The input is the user's emotion data, and the output is the emotion data sent to the server.

[0751] Step 8:

[0752] The server uses an emotion recognition engine to recognize the user's emotions in real time. Based on the received emotion data, it analyzes the user's emotional state. The input is the user's emotion data, and the output is information about the recognized emotions.

[0753] Step 9:

[0754] The server adjusts how summarized payment information is displayed based on the perceived emotions. For example, it changes the display method depending on whether the user is stressed or relaxed. The input is perceived emotion information and summarized payment information, and the output is the adjusted display information.

[0755] Step 10:

[0756] The terminal displays the latest payment information data sent from the server to the user. It adjusts the display method based on sentiment data, providing information through a user-friendly interface. The input is the adjusted display information received from the server, and the output is the actual displayed payment information.

[0757] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0758] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0759] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0760] [Third Embodiment]

[0761] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0762] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0763] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0764] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0765] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0766] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0767] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0768] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0769] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0770] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0771] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0772] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0773] This invention is a system for efficiently managing the pricing of multiple products and mobile devices. The following describes a specific implementation of this system.

[0774] System Overview

[0775] This system enables a seamless workflow where users input new approval information via a terminal, and a server processes that information and integrates it with existing data. This system improves operational efficiency and data management accuracy.

[0776] System Configuration

[0777] The server has the following main features:

[0778] 1. Reading existing data: The server reads existing approval information from a CSV file. This reading is done using a data analysis library such as Pandas.

[0779] 2. Summarizing new approval information: The server uses a natural language processing engine (e.g., GPT-3) to summarize new approval information. This summarization makes it easier to select and filter information.

[0780] 3. Adding summary information: The server integrates the summarized approval information into the existing DataFrame and generates an updated dataset.

[0781] 4. Data Storage: The server saves the updated data again as a CSV file. This ensures that the latest information is available when the data is read in the future.

[0782] The device has the following main features:

[0783] 1. User Input Reception: The terminal provides an interface for users to input new approval information. This interface is implemented through web forms or dedicated software applications.

[0784] 2. Sending Input Information: The terminal sends the information entered by the user to the server. This transmission is done using protocols such as HTTP requests.

[0785] 3. Display of updated data: The terminal receives the latest approval information data sent from the server and displays it to the user. This allows the user to check the latest information at any time.

[0786] Specific example

[0787] For example, consider a case where a user enters new payment information into their terminal, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is first sent to the server. The server reads the existing data and summarizes this new information using a natural language processing engine. The resulting summary is "Change the price of mobile device A from 1000 yen to 1200 yen." This summarized information is added to the existing DataFrame, and the updated dataset is saved in CSV format.

[0788] Users can later review this updated data through their devices. This saves work time and improves the accuracy of data management.

[0789] The system of the present invention functions based on the above components and processing flow, and streamlines the management of approval information.

[0790] The following describes the processing flow.

[0791] Step 1:

[0792] The user enters new payment information (for example, "Change the price of mobile device A from 1000 yen to 1200 yen") into the device. The device collects this information and prepares a request to send it to the server.

[0793] Step 2:

[0794] The terminal sends the prepared request to the server. This request is sent as data in JSON or XML format, containing the new approval information.

[0795] Step 3:

[0796] The server parses the received request and extracts new approval information. This new approval information is stored on the server in text format.

[0797] Step 4:

[0798] The server reads a CSV file containing existing approval information. This uses data analysis libraries such as Pandas to read the data from the CSV file in DataFrame format.

[0799] Step 5:

[0800] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The server sends the new approval information to the natural language processing engine as a prompt and receives the summary result.

[0801] Step 6:

[0802] The server integrates the received summary results into the existing data. This process adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[0803] Step 7:

[0804] The server saves the updated DataFrame again as a CSV file. By overwriting the existing file, a file is generated that reflects the latest approval information.

[0805] Step 8:

[0806] The user requests the latest approval information data stored on the server via their device. The device sends this request using a protocol such as an HTTP request.

[0807] Step 9:

[0808] The server rereads the updated CSV file to retrieve the latest data. It then prepares this data for transmission to the terminal.

[0809] Step 10:

[0810] The terminal displays the latest approval information data received from the server to the user. The user can then review this updated information and use it for necessary tasks.

[0811] This allows users to quickly manage new approval information in their daily work and check updates in real time. This process streamlines the summarization and data management of approval information, resulting in reduced working time and improved accuracy.

[0812] (Example 1)

[0813] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0814] A system is needed to properly manage existing approval information and efficiently input, summarize, integrate, and store new approval information. However, conventional systems have problems such as time-consuming information summarization, data integration, and storage processes, which increase the likelihood of manual input errors and data management omissions. Therefore, there is a need for a system that solves these problems and improves the efficiency and accuracy of approval information management.

[0815] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0816] In this invention, the server includes means for a user to input new approval information through a terminal, means for transmitting the new approval information to the server, means for reading existing data, means for summarizing the new approval information using a generative AI model, means for adding the summarized approval information to the existing data, means for saving the updated data, means for transmitting the updated data to the terminal, and means for the terminal to display the updated data to the user. This streamlines the management of approval information and enables accurate data updating and storage.

[0817] A "user" is the entity that operates the system and inputs new approval information.

[0818] A "terminal" is a device operated by a user that has the means to input new approval information and send that information to a server.

[0819] A "server" is a central management device that processes, stores, and manages approval information.

[0820] "Approval information" refers to data representing the pricing and approval information for products and mobile devices in a business context.

[0821] A "generative AI model" refers to an artificial intelligence algorithm that uses natural language processing technology to analyze and summarize text data.

[0822] "Summarization" refers to the process of extracting important information using a generative AI model and presenting it in a concise format.

[0823] A "data analysis library" is a software library used to manipulate and analyze data, and in this context, it specifically refers to Pandas.

[0824] A "CSV file" refers to a file format that stores data in comma-separated text format.

[0825] This invention is a system for efficiently managing the pricing of multiple products and mobile devices. This system implements a workflow in which users input new approval information via a terminal, and a server processes this information and integrates it with existing data. The specific implementation of this system is described below.

[0826] System configuration and operation

[0827] The device has the following features:

[0828] 1. User Input Reception: The terminal allows users to input new payment information through web forms or dedicated software. For example, it provides text boxes or selection menus for inputting information such as "Change the price of mobile model A from 1000 yen to 1200 yen."

[0829] 2. Sending Input Information: The terminal sends the approval information entered by the user to the server as an HTTP POST request. Specifically, the request library is used to send the information.

[0830] The server has the following functions:

[0831] 1. Reading existing data: The server uses the Pandas library to read existing approval information from a CSV file. This process allows the server to understand the current data state.

[0832] 2. Summarizing the new approval information: The server uses a generative AI model (e.g., GPT-3) to summarize the new approval information. The prompt will be text in the format of "Please summarize the new approval information. Example: 'Change the price of mobile model A from 1000 yen to 1200 yen'."

[0833] 3. Adding summary information: The server integrates the summarized approval information into the existing DataFrame and updates the dataset. This ensures that the new approval information is reflected in the existing data.

[0834] 4. Data Storage: The server saves the updated dataset again in CSV format. This ensures that the latest information is available the next time the data is read.

[0835] 5. Sending updated data: The server sends the updated approval data to the terminal as an HTTP response. Specifically, it converts the data into a dictionary format and sends it as a response.

[0836] The device has the following features:

[0837] 1. Receiving and displaying updated data: The terminal receives updated data sent from the server and displays it in the user interface. For example, it reflects the updated approval information in the HTML elements of a web page that displays it as a list.

[0838] Specific example

[0839] As a concrete example, consider the process when a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent from the device to the server. The server reads the existing data and summarizes this new information using a generation AI model. The generated summary information, "Change the price of mobile device A from 1000 yen to 1200 yen," is added to the existing data, and the updated dataset is saved in CSV format. Finally, the server sends the updated data to the device, which then displays it to the user.

[0840] In this way, this system can streamline the management of new approval information and improve the accuracy of data processing.

[0841] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0842] Step 1:

[0843] The user enters new approval information into the terminal.

[0844] Users enter new approval information using web forms or dedicated applications provided by their devices.

[0845] Input: New approval information (e.g., "Change the price of mobile device A from 1000 yen to 1200 yen").

[0846] Output: New approval information entered by the user on the terminal.

[0847] Specific operation: The user enters information into text boxes or selection menus and presses the "Submit" button.

[0848] Step 2:

[0849] The terminal sends the input information to the server.

[0850] The terminal sends the approval information entered by the user to the server as an HTTP POST request.

[0851] Input: Approval information entered by the user.

[0852] Output: Approval information received by the server.

[0853] Specific operation: The terminal uses the requests.post library to send the approval information to the specified server URL.

[0854] Step 3:

[0855] The server reads existing data.

[0856] The server uses the Pandas library to read existing approval information from a CSV file.

[0857] Input: A CSV file containing existing approval data.

[0858] Output: A DataFrame of existing data loaded into memory by the server.

[0859] Specific operation: The server executes `existing_df = pandas.read_csv("existing_data.csv")`.

[0860] Step 4:

[0861] The server summarizes the new approval information using a natural language processing engine.

[0862] The server uses a generative AI model (generative AI engine) to summarize the new approval information.

[0863] Input: Text for the new approval information.

[0864] Output: Text of the summarized approval information.

[0865] Specific operation: The server inputs the prompt message "Please summarize the new approval information. Example: 'Change the price of mobile model A from 1000 yen to 1200 yen'" into the generated AI model.

[0866] Step 5:

[0867] The server integrates the summary information into the existing data.

[0868] The server updates the dataset by adding the approval information summarized by the generated AI model to the existing DataFrame.

[0869] Input: DataFrame of existing data, summarized approval information.

[0870] Output: Updated DataFrame.

[0871] Specific action: The server executes existing_df = existing_df.append({"new_info": "Change the price of mobile model A from 1000 yen to 1200 yen"}, ignore_index=True).

[0872] Step 6:

[0873] The server saves the updated data.

[0874] The server saves the updated DataFrame again in CSV format.

[0875] Input: Updated DataFrame.

[0876] Output: Updated CSV file.

[0877] Specific action: The server executes existing_df.to_csv("updated_data.csv", index=False).

[0878] Step 7:

[0879] The server sends the update data to the terminal.

[0880] The server sends the updated approval data to the terminal as an HTTP response.

[0881] Input: Updated DataFrame.

[0882] Output: Update data received by the device.

[0883] Specific operation: The server converts the data using `updated_data = existing_df.to_dict()` and sends it as an HTTP response.

[0884] Step 8:

[0885] The device displays update data to the user.

[0886] The terminal displays the updated data received from the server on the user interface.

[0887] Input: Update data received from the server.

[0888] Output: Updated approval information displayed to the user.

[0889] Specific operation: The terminal executes document.getElementById("data-display").innerHTML = JSON.stringify(updated_data) to reflect the data in the HTML element of the web page.

[0890] (Application Example 1)

[0891] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0892] Modern e-commerce sites require the efficient management and timely updating of pricing information for numerous products and mobile devices. However, traditional manual data entry and management methods present challenges such as cumbersome information selection, wasted work time, and data management errors. Furthermore, the inability to immediately reflect new prices and payment information can lead to missed sales opportunities. To address these challenges, a more efficient and accurate information management system is necessary.

[0893] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0894] In this invention, the server includes means for reading existing information, means for summarizing new approval information, means for adding the summarized approval information to the existing information, means for storing the updated information, means for using a natural language processing engine to generate the new approval information, and means for displaying the updated information to the user. This streamlines the management of price information and products on e-commerce sites, enabling accurate data updates while significantly reducing labor. Furthermore, by utilizing a generation AI model, new approval information can be automatically summarized and quickly reflected in the data, which is expected to maximize sales opportunities.

[0895] "Means for reading existing information" refers to a function for retrieving previously recorded information from stored data files.

[0896] "Means for summarizing new approval information" refers to a function that uses a natural language processing engine to convert newly entered data into a concise format.

[0897] "Means of adding summarized approval information to existing information" refers to processing functions for integrating newly summarized data into existing datasets.

[0898] "Means for saving updated information" refers to a function that stores the dataset containing the new approval information in a file format, making it accessible the next time the data is read.

[0899] A "natural language processing engine that generates new approval information" is an engine that uses a generative AI model to shorten and summarize text data entered by the user.

[0900] "Means of displaying updated information to the user" refers to a function that visually provides the latest data sent from the server to the user's device or web interface.

[0901] A "generative AI model" is an artificial intelligence technology that learns from large amounts of data and generates natural language, and is primarily used for natural language processing and data summarization.

[0902] A "prompt" is input text used to give specific instructions or questions to a natural language processing engine.

[0903] This invention is a system for building an automated price management application for e-commerce websites. This system includes a server and user terminals and has the following main functions and processing steps:

[0904] System Overview

[0905] The server reads existing information, summarizes new approval information, integrates the summarized information with the existing data, and stores it. It also provides the updated information visually to the user. The user terminal provides an interface for entering the new approval information and allows the user to confirm the updated information.

[0906] Server Functions

[0907] 1. Means of reading existing information:

[0908] The server uses the Pandas library to read existing data (such as price information and product information) from a CSV file. This retrieves previously recorded information and prepares it for the next processing step.

[0909] 2. Means for summarizing new approval information:

[0910] The server uses a generative AI model to summarize the new approval information entered by the user using a natural language processing engine (e.g., GPT-3). This converts the input information into a concise and easy-to-handle format.

[0911] 3. Means for adding summarized approval information to existing information:

[0912] The summarized approval information is added to the existing dataframe, updating the dataset to its latest state. This process is performed using the Pandas library.

[0913] 4. Means for saving updated information:

[0914] The updated information will be saved again as a CSV file. This will ensure that the latest information is available the next time the data is read.

[0915] 5. Means for displaying updated information to the user:

[0916] The server sends updated information to the user's terminal, allowing for visual confirmation. This display can be accessed via a web interface or a dedicated application.

[0917] User terminal functions

[0918] 1. Receiving user input:

[0919] The user terminal provides an interface for entering new approval information (e.g., price changes for products). This information can be easily entered by the user through web forms or dedicated software applications.

[0920] 2. Submitting the entered information:

[0921] The user terminal sends the newly entered approval information to the server. This transmission is performed using protocols such as HTTP requests.

[0922] 3. Displaying update data:

[0923] Users can check updated data (for example, the latest price information) in real time through their devices.

[0924] Specific example

[0925] For example, when a user enters new payment information into their terminal, such as "Change the price of mobile device B from 800 yen to 850 yen," this information is sent to the server. The server reads the existing data and summarizes this new information using a natural language processing engine (GPT-3). The resulting summary information is "Change the price of mobile device B from 800 yen to 850 yen." This summary information is integrated into the existing data frame, and the updated dataset is saved in CSV format. The user can then view the updated data through their terminal.

[0926] Example of a prompt

[0927] "Please change the price of mobile model B from 800 yen to 850 yen."

[0928] Please summarize the new payment information: 'The price of mobile device B will be changed from 800 yen to 850 yen.'

[0929] This streamlines the management of pricing information and products on e-commerce sites, allowing for the immediate reflection of accurate information and ultimately maximizing sales opportunities.

[0930] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0931] Step 1:

[0932] The user enters new payment information. The user uses their device to enter information such as, for example, "Change the price of mobile device B from 800 yen to 850 yen." The device receives this input and sends it to the server via an HTTP request.

[0933] Step 2:

[0934] The server reads existing information. Using the Pandas library, the server reads existing price and product information from a CSV file. This read information forms the basis for the next processing step.

[0935] Step 3:

[0936] The server summarizes the new approval information. The server uses a generative AI model (e.g., GPT-3) to process the newly entered information. The input is text information sent by the user, and the output is summarized approval information. Specifically, the server inputs a prompt message such as "Please change the price of mobile model B from 800 yen to 850 yen" into the generative AI model and obtains the summarized result "Change the price of mobile model B from 800 yen to 850 yen".

[0937] Step 4:

[0938] The server adds the summarized approval information to the existing data. The server uses a Pandas DataFrame to add the summarized approval information to the existing DataFrame. Specifically, it inserts the new summarized information as a new record into the existing data. The input data is the summarized approval information, and the output is an updated DataFrame.

[0939] Step 5:

[0940] The server saves the updated information. The server uses the Pandas library to save the updated data as a CSV file. This saving process ensures that the latest information is available the next time the data is read. The input data is an updated dataframe, and the output is the saved CSV file.

[0941] Step 6:

[0942] The server displays updated information to the user. The server sends updated price and product information to the user's terminal via an HTTP response. The terminal receives this information and displays it for the user to visually confirm. Specifically, a web interface or a dedicated application is used. The input data is the updated information, and the output is the data displayed on the user's terminal.

[0943] Through the above processing steps, a system is realized in which new approval information entered by the user is efficiently processed, ultimately providing the user with the latest and most accurate information.

[0944] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0945] This invention is a data management system that combines an emotion engine and can efficiently process new decision information based on the recognition of user emotions. The following describes a specific implementation of this system.

[0946] System Overview

[0947] The system works by having users input new approval information via a terminal, with a server processing that information and integrating it with existing data. In addition, an emotion engine recognizes the user's emotions and adjusts information processing and display based on those emotions. This system improves operational efficiency, data management accuracy, and user experience.

[0948] System Configuration

[0949] The server has the following main features:

[0950] 1. Reading existing data: The server reads existing approval information from a CSV file. This is done using a data analysis library such as Pandas.

[0951] 2. Summarizing New Approval Information: The server uses a natural language processing engine (such as GPT-3) to summarize the new approval information. The server sends the new approval information as a prompt to the natural language processing engine and receives the summary result.

[0952] 3. Adding summary information: The server integrates the summarized approval information into the existing data. It adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[0953] 4. Data Storage: The server saves the updated DataFrame again as a CSV file. This generates a file that reflects the latest approval information.

[0954] 5. Emotion Recognition: The server uses an emotion engine to recognize the user's emotions in real time. The recognized emotions influence how information is processed and displayed.

[0955] The device has the following main features:

[0956] 1. User Input Reception: The terminal provides an interface for users to input new approval information. This interface is implemented through web forms or dedicated software applications.

[0957] 2. Sending Input Information: The terminal sends the information entered by the user to the server. This transmission is done using HTTP requests, etc.

[0958] 3. Transmission of emotion data: The device senses the user's facial expressions and tone of voice and sends this data to the server. The emotion engine analyzes this data and recognizes the user's emotions.

[0959] 4. Displaying updated data: The terminal displays the latest approval information data sent from the server to the user. The display method can also be adjusted based on sentiment data.

[0960] Specific example

[0961] For example, consider a scenario where a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent to the server, which reads the existing data. The server then uses a natural language processing engine to summarize the new payment information, generating a summary such as "Change the price of mobile device A from 1000 yen to 1200 yen." This summarized information is added to the existing DataFrame, and the updated dataset is saved in CSV format. Furthermore, an emotion engine recognizes the user's emotions (e.g., tension or anxiety) and adjusts the summary content and display method accordingly.

[0962] Users can later review this updated data through their devices. The display method may also be adjusted to a view that is relaxing for the user. In this way, new approval information can be managed quickly in daily operations, and an optimal user experience tailored to individual needs can be provided.

[0963] The system of the present invention functions based on the above components and processing flow, streamlining the management of approval information and realizing information processing and display that takes user emotions into consideration.

[0964] The following describes the processing flow.

[0965] Step 1:

[0966] The user enters new payment information (for example, "Change the price of mobile device A from 1000 yen to 1200 yen") into the device. The device collects this information and prepares a request to send it to the server.

[0967] Step 2:

[0968] The terminal sends the prepared request to the server. This request is sent as data in JSON or XML format, containing the new approval information.

[0969] Step 3:

[0970] The server parses the received request and extracts new approval information. This new approval information is stored on the server in text format.

[0971] Step 4:

[0972] The server reads a CSV file containing existing approval information. This uses data analysis libraries such as Pandas to read the data from the CSV file in DataFrame format.

[0973] Step 5:

[0974] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The server sends the new approval information to the natural language processing engine as a prompt and receives the summary result.

[0975] Step 6:

[0976] The server integrates the received summary results into the existing data. This process adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[0977] Step 7:

[0978] The server saves the updated DataFrame again as a CSV file. By overwriting the existing file, a file is generated that reflects the latest approval information.

[0979] Step 8:

[0980] The device uses sensors to detect the user's facial expressions and voice tone, and sends this emotional data to a server. The emotion engine analyzes this data to recognize the user's emotions in real time.

[0981] Step 9:

[0982] The server adjusts how information is processed and displayed based on the recognized user's emotions. For example, if the user is stressed, it may add more detailed information, or conversely, if they are relaxed, it may display only summary information.

[0983] Step 10:

[0984] The user requests the latest approval information data stored on the server via their device. The device sends this request using a protocol such as an HTTP request.

[0985] Step 11:

[0986] The server rereads the updated CSV file to retrieve the latest data. The retrieved data is then formatted appropriately according to the user's sentiment and prepared for transmission to the terminal.

[0987] Step 12:

[0988] The terminal displays the latest approval information data received from the server to the user. The display method is adjusted based on the results processed by the emotion engine. For example, if the user is stressed, supplementary explanations and graphs are added for more detail; if relaxed, only a concise summary is displayed.

[0989] This process allows users to quickly manage new approval information in their daily work and obtain an optimal user experience through emotion-based information display. Furthermore, the introduction of an emotion engine is expected to improve both work efficiency and user satisfaction.

[0990] (Example 2)

[0991] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0992] Conventional data management systems have faced challenges in efficiently processing and integrating new approval information, as well as in displaying and processing information in a way that considers user emotions. In particular, there is a need to process large amounts of data quickly and accurately, while simultaneously making adjustments that respond to user emotions to reduce work stress.

[0993] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0994] In this invention, the server includes means for reading existing data, means for summarizing new approval information, means for adding the summarized approval information to the existing data, means for storing the updated data, means for recognizing the user's emotions, and means for adjusting information processing and display based on the recognized emotions. This streamlines the management of approval information and enables information processing and display that takes the user's emotions into consideration.

[0995] "Existing data" refers to information that is already stored within the data management system.

[0996] "New approval information" refers to information that has been newly entered into the system and needs to be managed.

[0997] A "summary" is a concise compilation of new approval information.

[0998] A "natural language processing engine" is an artificial intelligence technology that analyzes input text data and outputs it in a format that is easy for humans to understand.

[0999] "User emotions" refers to the feelings a user experiences while using the service (e.g., tension, relaxation, anxiety, etc.).

[1000] "Means of recognizing emotions" refers to methods or devices that use an emotion engine to analyze a user's emotional data and identify those emotions.

[1001] "Means for adjusting information processing and display" refers to methods or devices that change the way a system processes or displays information based on the perceived emotions of the user.

[1002] A "CSV file" is a text file format that uses comma-separated values ​​and is used for saving and reading data.

[1003] A "data frame" is a tabular data structure composed of rows and columns, used for storing and manipulating data.

[1004] An "HTTP request" is a protocol used to send requests from a client, such as a web browser, to a web server.

[1005] Modes for carrying out the invention

[1006] This invention is a data management system that incorporates an emotion engine, enabling efficient processing of new approval information based on user emotion recognition. This system can improve operational efficiency, data management accuracy, and user experience.

[1007] System Overview

[1008] This system allows users to input new approval information via a terminal, and a server processes that information and integrates it with existing data. In addition, a key feature is the emotion engine, which recognizes the user's emotions and adjusts information processing and display based on those emotions. This system enables rapid management of new approval information and optimizes the user experience in daily operations.

[1009] Server-based processing

[1010] The server has multiple functions and performs the following processes.

[1011] 1. Reading existing data:

[1012] The server uses data analysis libraries such as Pandas to read existing approval information from CSV files. This allows for accurate retrieval of existing data.

[1013] 2. Summary of new approval information:

[1014] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The following is an example of a prompt used for summarization.

[1015] New payment information: Change the price of mobile device A from 1000 yen to 1200 yen.

[1016] Please create a summary of this information.

[1017] 3. Add summary information:

[1018] The server adds the summarized approval information as new rows to the existing DataFrame, generating an updated dataset. This ensures a smooth integration of old and new data.

[1019] 4. Data storage:

[1020] The server saves the updated DataFrame again as a CSV file. This generates a data file that reflects the latest approval information.

[1021] 5. Emotion recognition:

[1022] The server uses an emotion engine to recognize the user's emotions in real time. For example, if the user is feeling anxious, the server adjusts its processing and display methods based on that data.

[1023] Processing by the terminal

[1024] The device provides the following functions:

[1025] 1. Receiving user input:

[1026] The terminal provides an interface that allows users to input new approval information through dedicated web forms or software applications.

[1027] 2. Submitting the entered information:

[1028] The terminal sends information entered by the user to the server using an HTTP request. This ensures reliable data transmission.

[1029] 3. Sending emotional data:

[1030] The device senses the user's facial expressions and tone of voice and sends that data to a server. The emotion engine analyzes this data and recognizes the user's emotions.

[1031] 4. Displaying update data:

[1032] The terminal displays the latest approval information data sent from the server to the user. Furthermore, the display method can be adjusted based on the user's emotions.

[1033] Specific example

[1034] When a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen," this information is sent from the device to the server using an HTTP request. The server uses Pandas to read the existing data and a natural language processing engine to summarize the new information. The summarized information is then added to the existing DataFrame, and the updated dataset is saved as a CSV file. Furthermore, an emotion engine recognizes the user's emotions (e.g., tension or anxiety) in real time, and the display method is adjusted according to the recognized emotions.

[1035] In this way, the system can efficiently manage and display approval information while taking user emotions into consideration.

[1036] Specific examples of hardware and software to be used

[1037] This system's implementation utilizes Pandas, a natural language processing engine (GPT-3), and an emotion recognition engine on the server side. On the terminal side, communication with the server is performed using HTTP requests via web forms or dedicated software applications.

[1038] With the above configuration, the present invention provides a system that enables efficient management of approval information and information processing and display that takes into consideration the user's feelings.

[1039] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1040] Step 1:

[1041] The user enters the new approval information into the terminal.

[1042] The user enters the approval information (e.g., "Change the price of mobile model A from 1000 yen to 1200 yen") using a dedicated web form or software application. This is the input data for Step 1. After input, the information is saved on the device.

[1043] Step 2:

[1044] The terminal sends the input information to the server.

[1045] The entered payment information is sent from the terminal to the server using an HTTP request. This transmission is performed in the form of, for example, requests.post('http: / / example.com / api', data={'Information': 'Change the price of mobile model A from 1000 yen to 1200 yen'}). The server that receives the transmission receives the new payment information as the output of step 2.

[1046] Step 3:

[1047] The server reads existing data.

[1048] The server uses the Pandas library to read existing approval information from a CSV file. The input is an existing data file, and the output is data in DataFrame format. Specifically, a DataFrame is obtained using pd.read_csv('approval information.csv').

[1049] Step 4:

[1050] The server uses a natural language processing engine to summarize the new approval information.

[1051] The server sends the newly received approval information as a prompt to a natural language processing engine (e.g., GPT-3) and receives the summarized information. An example of a prompt message is as follows:

[1052] New payment information: Change the price of mobile device A from 1000 yen to 1200 yen.

[1053] Please create a summary of this information.

[1054] The input data is the new approval information, and the output data is the summarized approval information.

[1055] Step 5:

[1056] The server integrates the summary information into the existing data.

[1057] Summarized approval information is added as a new row to an existing DataFrame. The data for the new row is added using the DataFrame.append() method. The input is the summary information and the existing DataFrame, and the output is the updated DataFrame.

[1058] Step 6:

[1059] The server saves the updated data.

[1060] The server saves the updated DataFrame again as a CSV file. The method used for saving is `df.to_csv('ApprovalInfo.csv', index=False)`. The input data is the updated DataFrame, and the output is the updated CSV file.

[1061] Step 7:

[1062] The device sends user emotion data to the server.

[1063] The device senses the user's facial expressions and tone of voice and sends that data to the server. The input data is emotional data, and the output data is the emotional data sent to the server.

[1064] Step 8:

[1065] The server analyzes the user's emotions using an emotion engine.

[1066] The server uses an emotion engine to analyze the transmitted emotion data. Based on the results of the emotion analysis, the way the information is displayed and processed is adjusted. The input data is emotion data, and the output data is the analysis result.

[1067] Step 9:

[1068] The device displays update data.

[1069] The terminal displays the latest approval information data sent from the server to the user. The display method is adjusted based on emotional data. For example, if the user is stressed, the content is displayed concisely; if they are relaxed, more detailed information is displayed. The input data consists of the updated approval information data and the results of the emotional analysis, while the output data is the adjusted display.

[1070] In this way, the system efficiently manages new approval information and displays it in a way that is considerate of the user's feelings.

[1071] (Application Example 2)

[1072] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1073] The problems that this invention aims to solve are the efficient management of electronic payment information and the improvement of the user experience. Conventional systems do not take into account the user's emotions when processing information, which can cause users to feel stressed. Therefore, it is necessary to adjust information processing and display methods based on the user's emotions so that users can make payments in a relaxed state.

[1074] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for reading existing data, means for summarizing new payment information, means for adding the summarized payment information to the existing data, means for storing the updated data, means for recognizing the user's emotions, and means for adjusting information processing and display based on the recognized emotions. This enables efficient management of electronic payment information and improvement of the user experience.

[1075] "Existing data" refers to past payment information and related data that is already stored in the system.

[1076] "New payment information" refers to payment information and transaction details that a user newly enters.

[1077] "Means of summarization" refers to processes or devices that use natural language processing engines or similar technologies to condense input payment information into a shorter format.

[1078] "Means of saving data" refers to mechanisms or devices for continuously storing updated data. This includes, for example, methods for saving data in CSV format files.

[1079] "Means of recognizing emotions" refers to technologies and devices that analyze a user's facial expressions and tone of voice to detect their emotional state.

[1080] "Means of adjusting information processing and display" refers to processes and devices that optimize the operation of a system or the appearance of a user interface based on perceived emotions.

[1081] A "natural language processing engine" refers to a machine learning model or software that analyzes input text data and automatically performs processing such as summarization and translation.

[1082] A "CSV file" refers to a file format with comma-separated values, and it is a widely used data format for saving and transferring data.

[1083] Modes for carrying out the invention

[1084] The present invention provides a system for efficiently managing electronic payment information in response to user emotions. This system relies on the interaction between a server and a terminal; the user inputs new payment information through the terminal, and the server processes this information and recognizes the user's emotions. Specifically, the elements work together as follows:

[1085] Server configuration and operation

[1086] The server has the following main features:

[1087] 1. Existing data reading method: The server reads existing payment information from a CSV file. This is done using Pandas, a Python data analysis library.

[1088] 2. New payment information summarization method: New payment information is summarized using a natural language processing engine (e.g., GPT-3). The input payment information is sent to the natural language processing engine as a prompt, and the summarized case is received.

[1089] 3. Method for adding summary information: Integrate the summarized payment information into existing data. This process is performed by generating an updated DataFrame and adding it as new rows to an existing CSV file.

[1090] 4. Data storage method: The updated DataFrame is saved again as a CSV file to reflect the latest payment information.

[1091] 5. Emotion Recognition Method: An emotion engine is used to recognize the user's emotions in real time. Emotion data influences subsequent information processing and display methods.

[1092] Terminal configuration and operation

[1093] The device has the following main features:

[1094] 1. Means for receiving user input: Provide a user interface for users to input new payment information. This can be implemented using web forms or dedicated applications.

[1095] 2. Means of transmitting input information: Information entered by the user is sent to the server using HTTP requests, etc.

[1096] 3. Means of transmitting emotional data: The terminal senses the user's facial expressions and tone of voice and transmits that data to the server.

[1097] 4. Display method for updated data: The latest payment information data sent from the server is displayed to the user. It is also possible to adjust the display method based on sentiment data.

[1098] Specific example

[1099] As an example, consider a case where a user enters new payment information into their terminal, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent to the server, which reads the existing data. Then, using a natural language processing engine, the new payment information is summarized, and the summary "Change the price of mobile device A from 1000 yen to 1200 yen" is generated.

[1100] Example of a prompt

[1101] User input: "Change the price of the new monthly plan from 3000 yen to 2500 yen."

[1102] GPT-3 prompt: "Please summarize the entered payment information: Change the price of the new monthly plan from 3000 yen to 2500 yen."

[1103] Subsequently, this summary information is added to an existing DataFrame, and the updated dataset is saved in CSV format. Furthermore, the emotion engine can recognize the user's emotions (e.g., tension or anxiety) and adjust the summary content and display method accordingly.

[1104] Based on the above configuration and operation, the system of the present invention streamlines payment information management and realizes information processing and display that takes user emotions into consideration. As a result, users can perform payment transactions in a relaxed state.

[1105] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1106] Step 1:

[1107] The user enters new payment information into the terminal. On the terminal's user interface, the user enters the payment information into a text field and presses the "Submit Payment Information" button. The entered payment information is stored in text format.

[1108] Step 2:

[1109] The terminal sends the payment information entered by the user to the server. The entered payment information is sent to the server as an HTTP POST request. The data entered here is the payment information text entered by the user. The server receives this payment information text as output.

[1110] Step 3:

[1111] The server reads existing payment data from a CSV file. Using the Python Pandas library, it reads the CSV file containing the existing data and converts it to a DataFrame. The input is a CSV file, and the output is a DataFrame of the read existing payment data.

[1112] Step 4:

[1113] The server sends the new payment information to a natural language processing engine to generate a summary. The server sends the input payment information text as a prompt to the natural language processing engine (e.g., GPT-3) and receives the summary result. The input is the payment information text entered by the user, and the output is the summary result returned by the natural language processing engine.

[1114] Step 5:

[1115] The server adds the summarized payment information to the existing data. It adds the new summarized information as a new row to the updated DataFrame. At this time, it also adds user sentiment data if necessary. The input is the summarized payment information and the existing DataFrame, and the output is the updated DataFrame with the new payment information added.

[1116] Step 6:

[1117] The server saves the updated DataFrame again as a CSV file. The Pandas library is used to write the updated DataFrame to a CSV file. The input is the updated DataFrame, and the output is the new CSV file.

[1118] Step 7:

[1119] The device senses the user's facial expressions and tone of voice and sends this data to the server. The device's camera and microphone are used to collect data about the user's emotions. The collected data is sent to the server for analysis by the emotion recognition engine. The input is the user's emotion data, and the output is the emotion data sent to the server.

[1120] Step 8:

[1121] The server uses an emotion recognition engine to recognize the user's emotions in real time. Based on the received emotion data, it analyzes the user's emotional state. The input is the user's emotion data, and the output is information about the recognized emotions.

[1122] Step 9:

[1123] The server adjusts how summarized payment information is displayed based on the perceived emotions. For example, it changes the display method depending on whether the user is stressed or relaxed. The input is perceived emotion information and summarized payment information, and the output is the adjusted display information.

[1124] Step 10:

[1125] The terminal displays the latest payment information data sent from the server to the user. It adjusts the display method based on sentiment data, providing information through a user-friendly interface. The input is the adjusted display information received from the server, and the output is the actual displayed payment information.

[1126] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1127] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1128] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1129] [Fourth Embodiment]

[1130] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1131] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1133] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1134] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1137] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1138] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1139] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1140] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1141] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1142] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1143] This invention is a system for efficiently managing the pricing of multiple products and mobile devices. The following describes a specific implementation of this system.

[1144] System Overview

[1145] This system enables a seamless workflow where users input new approval information via a terminal, and a server processes that information and integrates it with existing data. This system improves operational efficiency and data management accuracy.

[1146] System Configuration

[1147] The server has the following main features:

[1148] 1. Reading existing data: The server reads existing approval information from a CSV file. This reading is done using a data analysis library such as Pandas.

[1149] 2. Summarizing new approval information: The server uses a natural language processing engine (e.g., GPT-3) to summarize new approval information. This summarization makes it easier to select and filter information.

[1150] 3. Adding summary information: The server integrates the summarized approval information into the existing DataFrame and generates an updated dataset.

[1151] 4. Data Storage: The server saves the updated data again as a CSV file. This ensures that the latest information is available when the data is read in the future.

[1152] The device has the following main features:

[1153] 1. User Input Reception: The terminal provides an interface for users to input new approval information. This interface is implemented through web forms or dedicated software applications.

[1154] 2. Sending Input Information: The terminal sends the information entered by the user to the server. This transmission is done using protocols such as HTTP requests.

[1155] 3. Display of updated data: The terminal receives the latest approval information data sent from the server and displays it to the user. This allows the user to check the latest information at any time.

[1156] Specific example

[1157] For example, consider a case where a user enters new payment information into their terminal, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is first sent to the server. The server reads the existing data and summarizes this new information using a natural language processing engine. The resulting summary is "Change the price of mobile device A from 1000 yen to 1200 yen." This summarized information is added to the existing DataFrame, and the updated dataset is saved in CSV format.

[1158] Users can later review this updated data through their devices. This saves work time and improves the accuracy of data management.

[1159] The system of the present invention functions based on the above components and processing flow, and streamlines the management of approval information.

[1160] The following describes the processing flow.

[1161] Step 1:

[1162] The user enters new payment information (for example, "Change the price of mobile device A from 1000 yen to 1200 yen") into the device. The device collects this information and prepares a request to send it to the server.

[1163] Step 2:

[1164] The terminal sends the prepared request to the server. This request is sent as data in JSON or XML format, containing the new approval information.

[1165] Step 3:

[1166] The server parses the received request and extracts new approval information. This new approval information is stored on the server in text format.

[1167] Step 4:

[1168] The server reads a CSV file containing existing approval information. This uses data analysis libraries such as Pandas to read the data from the CSV file in DataFrame format.

[1169] Step 5:

[1170] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The server sends the new approval information to the natural language processing engine as a prompt and receives the summary result.

[1171] Step 6:

[1172] The server integrates the received summary results into the existing data. This process adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[1173] Step 7:

[1174] The server saves the updated DataFrame again as a CSV file. By overwriting the existing file, a file is generated that reflects the latest approval information.

[1175] Step 8:

[1176] The user requests the latest approval information data stored on the server via their device. The device sends this request using a protocol such as an HTTP request.

[1177] Step 9:

[1178] The server rereads the updated CSV file to retrieve the latest data. It then prepares this data for transmission to the terminal.

[1179] Step 10:

[1180] The terminal displays the latest approval information data received from the server to the user. The user can then review this updated information and use it for necessary tasks.

[1181] This allows users to quickly manage new approval information in their daily work and check updates in real time. This process streamlines the summarization and data management of approval information, resulting in reduced working time and improved accuracy.

[1182] (Example 1)

[1183] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1184] A system is needed to properly manage existing approval information and efficiently input, summarize, integrate, and store new approval information. However, conventional systems have problems such as time-consuming information summarization, data integration, and storage processes, which increase the likelihood of manual input errors and data management omissions. Therefore, there is a need for a system that solves these problems and improves the efficiency and accuracy of approval information management.

[1185] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1186] In this invention, the server includes means for a user to input new approval information through a terminal, means for transmitting the new approval information to the server, means for reading existing data, means for summarizing the new approval information using a generative AI model, means for adding the summarized approval information to the existing data, means for saving the updated data, means for transmitting the updated data to the terminal, and means for the terminal to display the updated data to the user. This streamlines the management of approval information and enables accurate data updating and storage.

[1187] A "user" is the entity that operates the system and inputs new approval information.

[1188] A "terminal" is a device operated by a user that has the means to input new approval information and send that information to a server.

[1189] A "server" is a central management device that processes, stores, and manages approval information.

[1190] "Approval information" refers to data representing the pricing and approval information for products and mobile devices in a business context.

[1191] A "generative AI model" refers to an artificial intelligence algorithm that uses natural language processing technology to analyze and summarize text data.

[1192] "Summarization" refers to the process of extracting important information using a generative AI model and presenting it in a concise format.

[1193] A "data analysis library" is a software library used to manipulate and analyze data, and in this context, it specifically refers to Pandas.

[1194] A "CSV file" refers to a file format that stores data in comma-separated text format.

[1195] This invention is a system for efficiently managing the pricing of multiple products and mobile devices. This system implements a workflow in which users input new approval information via a terminal, and a server processes this information and integrates it with existing data. The specific implementation of this system is described below.

[1196] System configuration and operation

[1197] The device has the following features:

[1198] 1. User Input Reception: The terminal allows users to input new payment information through web forms or dedicated software. For example, it provides text boxes or selection menus for inputting information such as "Change the price of mobile model A from 1000 yen to 1200 yen."

[1199] 2. Sending Input Information: The terminal sends the approval information entered by the user to the server as an HTTP POST request. Specifically, the request library is used to send the information.

[1200] The server has the following functions:

[1201] 1. Reading existing data: The server uses the Pandas library to read existing approval information from a CSV file. This process allows the server to understand the current data state.

[1202] 2. Summarizing the new approval information: The server uses a generative AI model (e.g., GPT-3) to summarize the new approval information. The prompt will be text in the format of "Please summarize the new approval information. Example: 'Change the price of mobile model A from 1000 yen to 1200 yen'."

[1203] 3. Adding summary information: The server integrates the summarized approval information into the existing DataFrame and updates the dataset. This ensures that the new approval information is reflected in the existing data.

[1204] 4. Data Storage: The server saves the updated dataset again in CSV format. This ensures that the latest information is available the next time the data is read.

[1205] 5. Sending updated data: The server sends the updated approval data to the terminal as an HTTP response. Specifically, it converts the data into a dictionary format and sends it as a response.

[1206] The device has the following features:

[1207] 1. Receiving and displaying updated data: The terminal receives updated data sent from the server and displays it in the user interface. For example, it reflects the updated approval information in the HTML elements of a web page that displays it as a list.

[1208] Specific example

[1209] As a concrete example, consider the process when a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent from the device to the server. The server reads the existing data and summarizes this new information using a generation AI model. The generated summary information, "Change the price of mobile device A from 1000 yen to 1200 yen," is added to the existing data, and the updated dataset is saved in CSV format. Finally, the server sends the updated data to the device, which then displays it to the user.

[1210] In this way, this system can streamline the management of new approval information and improve the accuracy of data processing.

[1211] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1212] Step 1:

[1213] The user enters new approval information into the terminal.

[1214] Users enter new approval information using web forms or dedicated applications provided by their devices.

[1215] Input: New approval information (e.g., "Change the price of mobile device A from 1000 yen to 1200 yen").

[1216] Output: New approval information entered by the user on the terminal.

[1217] Specific operation: The user enters information into text boxes or selection menus and presses the "Submit" button.

[1218] Step 2:

[1219] The terminal sends the input information to the server.

[1220] The terminal sends the approval information entered by the user to the server as an HTTP POST request.

[1221] Input: Approval information entered by the user.

[1222] Output: Approval information received by the server.

[1223] Specific operation: The terminal uses the requests.post library to send the approval information to the specified server URL.

[1224] Step 3:

[1225] The server reads existing data.

[1226] The server uses the Pandas library to read existing approval information from a CSV file.

[1227] Input: A CSV file containing existing approval data.

[1228] Output: A DataFrame of existing data loaded into memory by the server.

[1229] Specific operation: The server executes `existing_df = pandas.read_csv("existing_data.csv")`.

[1230] Step 4:

[1231] The server summarizes the new approval information using a natural language processing engine.

[1232] The server uses a generative AI model (generative AI engine) to summarize the new approval information.

[1233] Input: Text for the new approval information.

[1234] Output: Text of the summarized approval information.

[1235] Specific operation: The server inputs the prompt message "Please summarize the new approval information. Example: 'Change the price of mobile model A from 1000 yen to 1200 yen'" into the generated AI model.

[1236] Step 5:

[1237] The server integrates the summary information into the existing data.

[1238] The server updates the dataset by adding the approval information summarized by the generated AI model to the existing DataFrame.

[1239] Input: DataFrame of existing data, summarized approval information.

[1240] Output: Updated DataFrame.

[1241] Specific action: The server executes existing_df = existing_df.append({"new_info": "Change the price of mobile model A from 1000 yen to 1200 yen"}, ignore_index=True).

[1242] Step 6:

[1243] The server saves the updated data.

[1244] The server saves the updated DataFrame again in CSV format.

[1245] Input: Updated DataFrame.

[1246] Output: Updated CSV file.

[1247] Specific action: The server executes existing_df.to_csv("updated_data.csv", index=False).

[1248] Step 7:

[1249] The server sends the update data to the terminal.

[1250] The server sends the updated approval data to the terminal as an HTTP response.

[1251] Input: Updated DataFrame.

[1252] Output: Update data received by the device.

[1253] Specific operation: The server converts the data using `updated_data = existing_df.to_dict()` and sends it as an HTTP response.

[1254] Step 8:

[1255] The device displays update data to the user.

[1256] The terminal displays the updated data received from the server on the user interface.

[1257] Input: Update data received from the server.

[1258] Output: Updated approval information displayed to the user.

[1259] Specific operation: The terminal executes document.getElementById("data-display").innerHTML = JSON.stringify(updated_data) to reflect the data in the HTML element of the web page.

[1260] (Application Example 1)

[1261] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1262] Modern e-commerce sites require the efficient management and timely updating of pricing information for numerous products and mobile devices. However, traditional manual data entry and management methods present challenges such as cumbersome information selection, wasted work time, and data management errors. Furthermore, the inability to immediately reflect new prices and payment information can lead to missed sales opportunities. To address these challenges, a more efficient and accurate information management system is necessary.

[1263] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1264] In this invention, the server includes means for reading existing information, means for summarizing new approval information, means for adding the summarized approval information to the existing information, means for storing the updated information, means for using a natural language processing engine to generate the new approval information, and means for displaying the updated information to the user. This streamlines the management of price information and products on e-commerce sites, enabling accurate data updates while significantly reducing labor. Furthermore, by utilizing a generation AI model, new approval information can be automatically summarized and quickly reflected in the data, which is expected to maximize sales opportunities.

[1265] "Means for reading existing information" refers to a function for retrieving previously recorded information from stored data files.

[1266] "Means for summarizing new approval information" refers to a function that uses a natural language processing engine to convert newly entered data into a concise format.

[1267] "Means of adding summarized approval information to existing information" refers to processing functions for integrating newly summarized data into existing datasets.

[1268] "Means for saving updated information" refers to a function that stores the dataset containing the new approval information in a file format, making it accessible the next time the data is read.

[1269] A "natural language processing engine that generates new approval information" is an engine that uses a generative AI model to shorten and summarize text data entered by the user.

[1270] "Means of displaying updated information to the user" refers to a function that visually provides the latest data sent from the server to the user's device or web interface.

[1271] A "generative AI model" is an artificial intelligence technology that learns from large amounts of data and generates natural language, and is primarily used for natural language processing and data summarization.

[1272] A "prompt" is input text used to give specific instructions or questions to a natural language processing engine.

[1273] This invention is a system for building an automated price management application for e-commerce websites. This system includes a server and user terminals and has the following main functions and processing steps:

[1274] System Overview

[1275] The server reads existing information, summarizes new approval information, integrates the summarized information with the existing data, and stores it. It also provides the updated information visually to the user. The user terminal provides an interface for entering the new approval information and allows the user to confirm the updated information.

[1276] Server Functions

[1277] 1. Means of reading existing information:

[1278] The server uses the Pandas library to read existing data (such as price information and product information) from a CSV file. This retrieves previously recorded information and prepares it for the next processing step.

[1279] 2. Means for summarizing new approval information:

[1280] The server uses a generative AI model to summarize the new approval information entered by the user using a natural language processing engine (e.g., GPT-3). This converts the input information into a concise and easy-to-handle format.

[1281] 3. Means for adding summarized approval information to existing information:

[1282] The summarized approval information is added to the existing dataframe, updating the dataset to its latest state. This process is performed using the Pandas library.

[1283] 4. Means for saving updated information:

[1284] The updated information will be saved again as a CSV file. This will ensure that the latest information is available the next time the data is read.

[1285] 5. Means for displaying updated information to the user:

[1286] The server sends updated information to the user's terminal, allowing for visual confirmation. This display can be accessed via a web interface or a dedicated application.

[1287] User terminal functions

[1288] 1. Receiving user input:

[1289] The user terminal provides an interface for entering new approval information (e.g., price changes for products). This information can be easily entered by the user through web forms or dedicated software applications.

[1290] 2. Submitting the entered information:

[1291] The user terminal sends the newly entered approval information to the server. This transmission is performed using protocols such as HTTP requests.

[1292] 3. Displaying update data:

[1293] Users can check updated data (for example, the latest price information) in real time through their devices.

[1294] Specific example

[1295] For example, when a user enters new payment information into their terminal, such as "Change the price of mobile device B from 800 yen to 850 yen," this information is sent to the server. The server reads the existing data and summarizes this new information using a natural language processing engine (GPT-3). The resulting summary information is "Change the price of mobile device B from 800 yen to 850 yen." This summary information is integrated into the existing data frame, and the updated dataset is saved in CSV format. The user can then view the updated data through their terminal.

[1296] Example of a prompt

[1297] "Please change the price of mobile model B from 800 yen to 850 yen."

[1298] Please summarize the new payment information: 'The price of mobile device B will be changed from 800 yen to 850 yen.'

[1299] This streamlines the management of pricing information and products on e-commerce sites, allowing for the immediate reflection of accurate information and ultimately maximizing sales opportunities.

[1300] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1301] Step 1:

[1302] The user enters new payment information. The user uses their device to enter information such as, for example, "Change the price of mobile device B from 800 yen to 850 yen." The device receives this input and sends it to the server via an HTTP request.

[1303] Step 2:

[1304] The server reads existing information. Using the Pandas library, the server reads existing price and product information from a CSV file. This read information forms the basis for the next processing step.

[1305] Step 3:

[1306] The server summarizes the new approval information. The server uses a generative AI model (e.g., GPT-3) to process the newly entered information. The input is text information sent by the user, and the output is summarized approval information. Specifically, the server inputs a prompt message such as "Please change the price of mobile model B from 800 yen to 850 yen" into the generative AI model and obtains the summarized result "Change the price of mobile model B from 800 yen to 850 yen".

[1307] Step 4:

[1308] The server adds the summarized approval information to the existing data. The server uses a Pandas DataFrame to add the summarized approval information to the existing DataFrame. Specifically, it inserts the new summarized information as a new record into the existing data. The input data is the summarized approval information, and the output is an updated DataFrame.

[1309] Step 5:

[1310] The server saves the updated information. The server uses the Pandas library to save the updated data as a CSV file. This saving process ensures that the latest information is available the next time the data is read. The input data is an updated dataframe, and the output is the saved CSV file.

[1311] Step 6:

[1312] The server displays updated information to the user. The server sends updated price and product information to the user's terminal via an HTTP response. The terminal receives this information and displays it for the user to visually confirm. Specifically, a web interface or a dedicated application is used. The input data is the updated information, and the output is the data displayed on the user's terminal.

[1313] Through the above processing steps, a system is realized in which new approval information entered by the user is efficiently processed, ultimately providing the user with the latest and most accurate information.

[1314] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1315] This invention is a data management system that combines an emotion engine and can efficiently process new decision information based on the recognition of user emotions. The following describes a specific implementation of this system.

[1316] System Overview

[1317] The system works by having users input new approval information via a terminal, with a server processing that information and integrating it with existing data. In addition, an emotion engine recognizes the user's emotions and adjusts information processing and display based on those emotions. This system improves operational efficiency, data management accuracy, and user experience.

[1318] System Configuration

[1319] The server has the following main features:

[1320] 1. Reading existing data: The server reads existing approval information from a CSV file. This is done using a data analysis library such as Pandas.

[1321] 2. Summarizing New Approval Information: The server uses a natural language processing engine (such as GPT-3) to summarize the new approval information. The server sends the new approval information as a prompt to the natural language processing engine and receives the summary result.

[1322] 3. Adding summary information: The server integrates the summarized approval information into the existing data. It adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[1323] 4. Data Storage: The server saves the updated DataFrame again as a CSV file. This generates a file that reflects the latest approval information.

[1324] 5. Emotion Recognition: The server uses an emotion engine to recognize the user's emotions in real time. The recognized emotions influence how information is processed and displayed.

[1325] The device has the following main features:

[1326] 1. User Input Reception: The terminal provides an interface for users to input new approval information. This interface is implemented through web forms or dedicated software applications.

[1327] 2. Sending Input Information: The terminal sends the information entered by the user to the server. This transmission is done using HTTP requests, etc.

[1328] 3. Transmission of emotion data: The device senses the user's facial expressions and tone of voice and sends this data to the server. The emotion engine analyzes this data and recognizes the user's emotions.

[1329] 4. Displaying updated data: The terminal displays the latest approval information data sent from the server to the user. The display method can also be adjusted based on sentiment data.

[1330] Specific example

[1331] For example, consider a scenario where a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent to the server, which reads the existing data. The server then uses a natural language processing engine to summarize the new payment information, generating a summary such as "Change the price of mobile device A from 1000 yen to 1200 yen." This summarized information is added to the existing DataFrame, and the updated dataset is saved in CSV format. Furthermore, an emotion engine recognizes the user's emotions (e.g., tension or anxiety) and adjusts the summary content and display method accordingly.

[1332] Users can later review this updated data through their devices. The display method may also be adjusted to a view that is relaxing for the user. In this way, new approval information can be managed quickly in daily operations, and an optimal user experience tailored to individual needs can be provided.

[1333] The system of the present invention functions based on the above components and processing flow, streamlining the management of approval information and realizing information processing and display that takes user emotions into consideration.

[1334] The following describes the processing flow.

[1335] Step 1:

[1336] The user enters new payment information (for example, "Change the price of mobile device A from 1000 yen to 1200 yen") into the device. The device collects this information and prepares a request to send it to the server.

[1337] Step 2:

[1338] The terminal sends the prepared request to the server. This request is sent as data in JSON or XML format, containing the new approval information.

[1339] Step 3:

[1340] The server parses the received request and extracts new approval information. This new approval information is stored on the server in text format.

[1341] Step 4:

[1342] The server reads a CSV file containing existing approval information. This uses data analysis libraries such as Pandas to read the data from the CSV file in DataFrame format.

[1343] Step 5:

[1344] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The server sends the new approval information to the natural language processing engine as a prompt and receives the summary result.

[1345] Step 6:

[1346] The server integrates the received summary results into the existing data. This process adds the summary results as new rows to the existing DataFrame, generating an updated DataFrame.

[1347] Step 7:

[1348] The server saves the updated DataFrame again as a CSV file. By overwriting the existing file, a file is generated that reflects the latest approval information.

[1349] Step 8:

[1350] The device uses sensors to detect the user's facial expressions and voice tone, and sends this emotional data to a server. The emotion engine analyzes this data to recognize the user's emotions in real time.

[1351] Step 9:

[1352] The server adjusts how information is processed and displayed based on the recognized user's emotions. For example, if the user is stressed, it may add more detailed information, or conversely, if they are relaxed, it may display only summary information.

[1353] Step 10:

[1354] The user requests the latest approval information data stored on the server via their device. The device sends this request using a protocol such as an HTTP request.

[1355] Step 11:

[1356] The server rereads the updated CSV file to retrieve the latest data. The retrieved data is then formatted appropriately according to the user's sentiment and prepared for transmission to the terminal.

[1357] Step 12:

[1358] The terminal displays the latest approval information data received from the server to the user. The display method is adjusted based on the results processed by the emotion engine. For example, if the user is stressed, supplementary explanations and graphs are added for more detail; if relaxed, only a concise summary is displayed.

[1359] This process allows users to quickly manage new approval information in their daily work and obtain an optimal user experience through emotion-based information display. Furthermore, the introduction of an emotion engine is expected to improve both work efficiency and user satisfaction.

[1360] (Example 2)

[1361] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1362] Conventional data management systems have faced challenges in efficiently processing and integrating new approval information, as well as in displaying and processing information in a way that considers user emotions. In particular, there is a need to process large amounts of data quickly and accurately, while simultaneously making adjustments that respond to user emotions to reduce work stress.

[1363] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1364] In this invention, the server includes means for reading existing data, means for summarizing new approval information, means for adding the summarized approval information to the existing data, means for storing the updated data, means for recognizing the user's emotions, and means for adjusting information processing and display based on the recognized emotions. This streamlines the management of approval information and enables information processing and display that takes the user's emotions into consideration.

[1365] "Existing data" refers to information that is already stored within the data management system.

[1366] "New approval information" refers to information that has been newly entered into the system and needs to be managed.

[1367] A "summary" is a concise compilation of new approval information.

[1368] A "natural language processing engine" is an artificial intelligence technology that analyzes input text data and outputs it in a format that is easy for humans to understand.

[1369] "User emotions" refers to the feelings a user experiences while using the service (e.g., tension, relaxation, anxiety, etc.).

[1370] "Means of recognizing emotions" refers to methods or devices that use an emotion engine to analyze a user's emotional data and identify those emotions.

[1371] "Means for adjusting information processing and display" refers to methods or devices that change the way a system processes or displays information based on the perceived emotions of the user.

[1372] A "CSV file" is a text file format that uses comma-separated values ​​and is used for saving and reading data.

[1373] A "data frame" is a tabular data structure composed of rows and columns, used for storing and manipulating data.

[1374] An "HTTP request" is a protocol used to send requests from a client, such as a web browser, to a web server.

[1375] Modes for carrying out the invention

[1376] This invention is a data management system that incorporates an emotion engine, enabling efficient processing of new approval information based on user emotion recognition. This system can improve operational efficiency, data management accuracy, and user experience.

[1377] System Overview

[1378] This system allows users to input new approval information via a terminal, and a server processes that information and integrates it with existing data. In addition, a key feature is the emotion engine, which recognizes the user's emotions and adjusts information processing and display based on those emotions. This system enables rapid management of new approval information and optimizes the user experience in daily operations.

[1379] Server-based processing

[1380] The server has multiple functions and performs the following processes.

[1381] 1. Reading existing data:

[1382] The server uses data analysis libraries such as Pandas to read existing approval information from CSV files. This allows for accurate retrieval of existing data.

[1383] 2. Summary of new approval information:

[1384] The server uses a natural language processing engine (e.g., GPT-3) to summarize the new approval information. The following is an example of a prompt used for summarization.

[1385] New payment information: Change the price of mobile device A from 1000 yen to 1200 yen.

[1386] Please create a summary of this information.

[1387] 3. Add summary information:

[1388] The server adds the summarized approval information as new rows to the existing DataFrame, generating an updated dataset. This ensures a smooth integration of old and new data.

[1389] 4. Data storage:

[1390] The server saves the updated DataFrame again as a CSV file. This generates a data file that reflects the latest approval information.

[1391] 5. Emotion recognition:

[1392] The server uses an emotion engine to recognize the user's emotions in real time. For example, if the user is feeling anxious, the server adjusts its processing and display methods based on that data.

[1393] Processing by the terminal

[1394] The device provides the following functions:

[1395] 1. Receiving user input:

[1396] The terminal provides an interface that allows users to input new approval information through dedicated web forms or software applications.

[1397] 2. Submitting the entered information:

[1398] The terminal sends information entered by the user to the server using an HTTP request. This ensures reliable data transmission.

[1399] 3. Sending emotional data:

[1400] The device senses the user's facial expressions and tone of voice and sends that data to a server. The emotion engine analyzes this data and recognizes the user's emotions.

[1401] 4. Displaying update data:

[1402] The terminal displays the latest approval information data sent from the server to the user. Furthermore, the display method can be adjusted based on the user's emotions.

[1403] Specific example

[1404] When a user enters new payment information into their device, such as "Change the price of mobile device A from 1000 yen to 1200 yen," this information is sent from the device to the server using an HTTP request. The server uses Pandas to read the existing data and a natural language processing engine to summarize the new information. The summarized information is then added to the existing DataFrame, and the updated dataset is saved as a CSV file. Furthermore, an emotion engine recognizes the user's emotions (e.g., tension or anxiety) in real time, and the display method is adjusted according to the recognized emotions.

[1405] In this way, the system can efficiently manage and display approval information while taking user emotions into consideration.

[1406] Specific examples of hardware and software to be used

[1407] This system's implementation utilizes Pandas, a natural language processing engine (GPT-3), and an emotion recognition engine on the server side. On the terminal side, communication with the server is performed using HTTP requests via web forms or dedicated software applications.

[1408] With the above configuration, the present invention provides a system that enables efficient management of approval information and information processing and display that takes into consideration the user's feelings.

[1409] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1410] Step 1:

[1411] The user enters the new approval information into the terminal.

[1412] The user enters the approval information (e.g., "Change the price of mobile model A from 1000 yen to 1200 yen") using a dedicated web form or software application. This is the input data for Step 1. After input, the information is saved on the device.

[1413] Step 2:

[1414] The terminal sends the input information to the server.

[1415] The entered payment information is sent from the terminal to the server using an HTTP request. This transmission is performed in the form of, for example, requests.post('http: / / example.com / api', data={'Information': 'Change the price of mobile model A from 1000 yen to 1200 yen'}). The server that receives the transmission receives the new payment information as the output of step 2.

[1416] Step 3:

[1417] The server reads existing data.

[1418] The server uses the Pandas library to read existing approval information from a CSV file. The input is an existing data file, and the output is data in DataFrame format. Specifically, a DataFrame is obtained using pd.read_csv('approval information.csv').

[1419] Step 4:

[1420] The server uses a natural language processing engine to summarize the new approval information.

[1421] The server sends the newly received approval information as a prompt to a natural language processing engine (e.g., GPT-3) and receives the summarized information. An example of a prompt message is as follows:

[1422] New payment information: Change the price of mobile device A from 1000 yen to 1200 yen.

[1423] Please create a summary of this information.

[1424] The input data is the new approval information, and the output data is the summarized approval information.

[1425] Step 5:

[1426] The server integrates the summary information into the existing data.

[1427] Summarized approval information is added as a new row to an existing DataFrame. The data for the new row is added using the DataFrame.append() method. The input is the summary information and the existing DataFrame, and the output is the updated DataFrame.

[1428] Step 6:

[1429] The server saves the updated data.

[1430] The server saves the updated DataFrame again as a CSV file. The method used for saving is `df.to_csv('ApprovalInfo.csv', index=False)`. The input data is the updated DataFrame, and the output is the updated CSV file.

[1431] Step 7:

[1432] The device sends user emotion data to the server.

[1433] The device senses the user's facial expressions and tone of voice and sends that data to the server. The input data is emotional data, and the output data is the emotional data sent to the server.

[1434] Step 8:

[1435] The server analyzes the user's emotions using an emotion engine.

[1436] The server uses an emotion engine to analyze the transmitted emotion data. Based on the results of the emotion analysis, the way the information is displayed and processed is adjusted. The input data is emotion data, and the output data is the analysis result.

[1437] Step 9:

[1438] The device displays update data.

[1439] The terminal displays the latest approval information data sent from the server to the user. The display method is adjusted based on emotional data. For example, if the user is stressed, the content is displayed concisely; if they are relaxed, more detailed information is displayed. The input data consists of the updated approval information data and the results of the emotional analysis, while the output data is the adjusted display.

[1440] In this way, the system efficiently manages new approval information and displays it in a way that is considerate of the user's feelings.

[1441] (Application Example 2)

[1442] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1443] The problems that this invention aims to solve are the efficient management of electronic payment information and the improvement of the user experience. Conventional systems do not take into account the user's emotions when processing information, which can cause users to feel stressed. Therefore, it is necessary to adjust information processing and display methods based on the user's emotions so that users can make payments in a relaxed state.

[1444] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for reading existing data, means for summarizing new payment information, means for adding the summarized payment information to the existing data, means for storing the updated data, means for recognizing the user's emotions, and means for adjusting information processing and display based on the recognized emotions. This enables efficient management of electronic payment information and improvement of the user experience.

[1445] "Existing data" refers to past payment information and related data that is already stored in the system.

[1446] "New payment information" refers to payment information and transaction details that a user newly enters.

[1447] "Means of summarization" refers to processes or devices that use natural language processing engines or similar technologies to condense input payment information into a shorter format.

[1448] "Means of saving data" refers to mechanisms or devices for continuously storing updated data. This includes, for example, methods for saving data in CSV format files.

[1449] "Means of recognizing emotions" refers to technologies and devices that analyze a user's facial expressions and tone of voice to detect their emotional state.

[1450] "Means of adjusting information processing and display" refers to processes and devices that optimize the operation of a system or the appearance of a user interface based on perceived emotions.

[1451] A "natural language processing engine" refers to a machine learning model or software that analyzes input text data and automatically performs processing such as summarization and translation.

[1452] A "CSV file" refers to a file format with comma-separated values, and it is a widely used data format for saving and transferring data.

[1453] Modes for carrying out the invention

[1454] The present invention provides a system for efficiently managing electronic payment information in response to user emotions. This system relies on the interaction between a server and a terminal; the user inputs new payment information through the terminal, and the server processes this information and recognizes the user's emotions. Specifically, the elements work together as follows:

[1455] Server configuration and operation

[1456] The server has the following main features:

[1457] 1. Existing data reading method: The server reads existing payment information from a CSV file. This is done using Pandas, a Python data analysis library.

[1458] 2. New payment information summarization method: New payment information is summarized using a natural language processing engine (e.g., GPT-3). The input payment information is sent to the natural language processing engine as a prompt, and the summarized case is received.

[1459] 3. Method for adding summary information: Integrate the summarized payment information into existing data. This process is performed by generating an updated DataFrame and adding it as new rows to an existing CSV file.

[1460] 4. Data storage method: The updated DataFrame is saved again as a CSV file to reflect the latest payment information.

[1461] 5. Emotion Recognition Method: An emotion engine is used to recognize the user's emotions in real time. Emotion data influences subsequent information processing and display methods.

[1462] Terminal configuration and operation

[1463] The device has the following main features:

[1464] 1. Means for receiving user input: Provide a user interface for users to input new payment information. This can be implemented using web forms or dedicated applications.

[1465] 2. Means of transmitting input information: Information entered by the user is sent to the server using HTTP requests, etc.

[1466] 3. Means of transmitting emotional data: The terminal senses the user's facial expressions and tone of voice and transmits that data to the server.

[1467] 4. Display method for updated data: The latest payment information data sent from the server is displayed to the user. It is also possible to adjust the display method based on sentiment data.

[1468] Specific example

[1469] As an example, consider a case where a user enters new payment information into their terminal, such as "Change the price of mobile device A from 1000 yen to 1200 yen." This information is sent to the server, which reads the existing data. Then, using a natural language processing engine, the new payment information is summarized, and the summary "Change the price of mobile device A from 1000 yen to 1200 yen" is generated.

[1470] Example of a prompt

[1471] User input: "Change the price of the new monthly plan from 3000 yen to 2500 yen."

[1472] GPT-3 prompt: "Please summarize the entered payment information: Change the price of the new monthly plan from 3000 yen to 2500 yen."

[1473] Subsequently, this summary information is added to an existing DataFrame, and the updated dataset is saved in CSV format. Furthermore, the emotion engine can recognize the user's emotions (e.g., tension or anxiety) and adjust the summary content and display method accordingly.

[1474] Based on the above configuration and operation, the system of the present invention streamlines payment information management and realizes information processing and display that takes user emotions into consideration. As a result, users can perform payment transactions in a relaxed state.

[1475] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1476] Step 1:

[1477] The user enters new payment information into the terminal. On the terminal's user interface, the user enters the payment information into a text field and presses the "Submit Payment Information" button. The entered payment information is stored in text format.

[1478] Step 2:

[1479] The terminal sends the payment information entered by the user to the server. The entered payment information is sent to the server as an HTTP POST request. The data entered here is the payment information text entered by the user. The server receives this payment information text as output.

[1480] Step 3:

[1481] The server reads existing payment data from a CSV file. Using the Python Pandas library, it reads the CSV file containing the existing data and converts it to a DataFrame. The input is a CSV file, and the output is a DataFrame of the read existing payment data.

[1482] Step 4:

[1483] The server sends the new payment information to a natural language processing engine to generate a summary. The server sends the input payment information text as a prompt to the natural language processing engine (e.g., GPT-3) and receives the summary result. The input is the payment information text entered by the user, and the output is the summary result returned by the natural language processing engine.

[1484] Step 5:

[1485] The server adds the summarized payment information to the existing data. It adds the new summarized information as a new row to the updated DataFrame. At this time, it also adds user sentiment data if necessary. The input is the summarized payment information and the existing DataFrame, and the output is the updated DataFrame with the new payment information added.

[1486] Step 6:

[1487] The server saves the updated DataFrame again as a CSV file. The Pandas library is used to write the updated DataFrame to a CSV file. The input is the updated DataFrame, and the output is the new CSV file.

[1488] Step 7:

[1489] The device senses the user's facial expressions and tone of voice and sends this data to the server. The device's camera and microphone are used to collect data about the user's emotions. The collected data is sent to the server for analysis by the emotion recognition engine. The input is the user's emotion data, and the output is the emotion data sent to the server.

[1490] Step 8:

[1491] The server uses an emotion recognition engine to recognize the user's emotions in real time. Based on the received emotion data, it analyzes the user's emotional state. The input is the user's emotion data, and the output is information about the recognized emotions.

[1492] Step 9:

[1493] The server adjusts how summarized payment information is displayed based on the perceived emotions. For example, it changes the display method depending on whether the user is stressed or relaxed. The input is perceived emotion information and summarized payment information, and the output is the adjusted display information.

[1494] Step 10:

[1495] The terminal displays the latest payment information data sent from the server to the user. It adjusts the display method based on sentiment data, providing information through a user-friendly interface. The input is the adjusted display information received from the server, and the output is the actual displayed payment information.

[1496] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1497] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1498] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1499] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1500] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1501] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1502] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1503] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1504] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1505] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1506] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1507] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1508] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1509] 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.

[1510] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1511] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1512] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1513] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1514] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1515] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1516] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1517] The following is further disclosed regarding the embodiments described above.

[1518] (Claim 1)

[1519] Means for reading existing data,

[1520] A means of summarizing new approval information,

[1521] A means of adding summarized approval information to existing data,

[1522] A means of saving updated data,

[1523] A system that includes this.

[1524] (Claim 2)

[1525] The system according to claim 1, comprising means for summarizing new approval information using a natural language processing engine.

[1526] (Claim 3)

[1527] The system according to claim 1, comprising means for reading and storing existing data using a CSV file.

[1528] "Example 1"

[1529] (Claim 1)

[1530] A means for the user to enter new payment information via a terminal,

[1531] A means of sending new approval information to the server,

[1532] Means for reading existing data,

[1533] A means of summarizing new decision information using a generative AI model,

[1534] A means of adding summarized approval information to existing data,

[1535] A means of saving updated data,

[1536] A means of sending update data to the terminal,

[1537] A means by which the device displays update data to the user,

[1538] A system that includes this.

[1539] (Claim 2)

[1540] The system according to claim 1, comprising means for summarizing new approval information using a generative AI model.

[1541] (Claim 3)

[1542] The system according to claim 1, comprising means for reading and saving files in CSV format using a data analysis library.

[1543] "Application Example 1"

[1544] (Claim 1)

[1545] Means of reading existing information,

[1546] A means of summarizing new approval information,

[1547] A means of adding summarized approval information to existing information,

[1548] A means of saving updated information,

[1549] A means of using a natural language processing engine to generate new approval information,

[1550] A means of displaying updated information to the user,

[1551] A system that includes this.

[1552] (Claim 2)

[1553] The system according to claim 1, comprising means of using a generative AI model as a natural language processing engine for summarizing new approval information.

[1554] (Claim 3)

[1555] The system according to claim 1, comprising means for reading and storing existing information using a CSV file.

[1556] "Example 2 of combining an emotion engine"

[1557] (Claim 1)

[1558] Means for reading existing data,

[1559] A means of summarizing new approval information,

[1560] A means of adding summarized approval information to existing data,

[1561] A means of saving updated data,

[1562] Means of recognizing user emotions,

[1563] Means for adjusting information processing and display based on recognized emotions,

[1564] A system that includes this.

[1565] (Claim 2)

[1566] The system according to claim 1, comprising means for summarizing new approval information using a natural language processing engine.

[1567] (Claim 3)

[1568] The system according to claim 1, comprising means for reading and storing existing data using a CSV file.

[1569] (Claim 4)

[1570] The system according to claim 1, comprising means for collecting user sentiment data and transmitting the data to a server.

[1571] (Claim 5)

[1572] The system according to claim 1, comprising means for adjusting the method of displaying information according to the user's emotions.

[1573] "Application example 2 when combining with an emotional engine"

[1574] (Claim 1)

[1575] Means for reading existing data,

[1576] A means of summarizing new payment information,

[1577] A means of adding summarized payment information to existing data,

[1578] A means of saving updated data,

[1579] Means of recognizing user emotions,

[1580] Means for adjusting information processing and display based on recognized emotions,

[1581] A system that includes this.

[1582] (Claim 2)

[1583] The system according to claim 1, comprising means for summarizing new payment information using a natural language processing engine.

[1584] (Claim 3)

[1585] The system according to claim 1, comprising means for reading and storing existing data using a CSV file. [Explanation of Symbols]

[1586] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for reading existing data, A means of summarizing new approval information, A means of adding summarized approval information to existing data, A means of saving updated data, A system that includes this.

2. The system according to claim 1, comprising means for summarizing new approval information using a natural language processing engine.

3. The system according to claim 1, comprising means for reading and saving existing data using a CSV file.

Images