system

Abstract

Provide a system. A user terminal for inputting text in dialect or standard Japanese; means for transmitting input text data to a server; means for identifying the received text data and determining whether it is a dialect or standard language; A means for converting dialects into standard language or converting standard language into dialects based on the identification results; means for transmitting the converted text data to a user terminal; A means for displaying the converted text data on a user terminal; A system including:

Description

[Technical Field]

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

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

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

[0004] In today's diverse regions, each has its own unique dialect, which can make it difficult to communicate smoothly with people who speak standard Japanese. This problem is particularly evident in situations where communication between different regions is required, such as business, education, and tourism. People who speak a dialect often encounter misunderstandings when interacting with standard Japanese speakers, and conversely, standard Japanese speakers often experience inconvenience when they cannot understand the dialect. Therefore, there is a need to naturally convert between dialects and standard Japanese while preserving regional characteristics, thereby achieving smooth communication both within and outside of the region. [Means for solving the problem]

[0005] In order to solve these problems, the present invention provides a system having the following configuration: A user terminal for inputting text in a dialect or standard language is provided, and the text data input from this terminal is sent to a server. The server has means for identifying the received text data and determining whether it is a dialect or standard language. The server further has means for converting the dialect into standard language or converting standard language into a dialect based on the identification result, and sends the converted text data to the user terminal. Finally, the user terminal has means for displaying the converted text data. The system also uses a natural language processing model for identifying the language form of the text data and includes a language conversion model that learns the correspondence between dialects and standard language using a specific regional language database, thereby achieving high accuracy in converting between dialects and standard language.

[0006] "User terminal" refers to a device for inputting text data and displaying the conversion results.

[0007] "Server" refers to a computer system that receives, processes, and converts text data sent from a user terminal.

[0008] "Text data" refers to character string information written in a dialect or standard language.

[0009] "Language identification means" refers to an algorithm or model for determining whether input text data is a dialect or standard language.

[0010] "Language conversion means" refers to an algorithm or model that has the function of converting dialects into standard language or converting standard language into dialects based on the identification results.

[0011] A "natural language processing model" refers to a model that uses machine learning or deep learning to analyze the linguistic form of text data and identify its content.

[0012] A "regional language database" refers to a database for learning the correspondence between dialects and standard Japanese used in a specific region. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] The present invention relates to a system for naturally converting between regional dialects and standard Japanese. The system consists of a user terminal, a server, and a series of processes that use natural language processing to identify and convert text data.

[0035] Program processing

[0036] Accepting input from the user

[0037] The user inputs text in a dialect or standard Japanese into the user terminal. This text can be a regional dialect such as Kansai dialect, such as "It's a nice day today," or standard Japanese, such as "It's a nice day today." By entering text into the input field and pressing the conversion button, the user terminal acquires this text data.

[0038] Sending Input

[0039] The user terminal transmits the input text data to the server. Specifically, it generates an HTTP request and transmits the request to the server together with the text data.

[0040] Language Identification

[0041] The server analyzes the received HTTP request and extracts the text data. It then uses a natural language processing model to automatically identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by the natural language processing model.

[0042] Conversion process

[0043] The server selects an appropriate conversion model based on the recognition results. Here, a model that converts Kansai dialect to standard Japanese is used. For example, "It's a nice day today" is converted to "It's a nice day today." Conversely, conversion from standard Japanese to a dialect is also possible, for example, "It's a nice day today" is converted to "It's a nice day today."

[0044] Sending the conversion results

[0045] The server generates an HTTP response including the converted text data and sends it to the user terminal. At this time, the response includes the converted text.

[0046] Displaying the results

[0047] The user device analyzes the received HTTP response and extracts the converted text data. Finally, the user device displays the conversion result on the screen and provides feedback to the user. For example, the conversion result "It's nice weather today" is displayed.

[0048] Specific examples

[0049] A specific example of use is as follows:

[0050] 1. User operations

[0051] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[0052] 2. Terminal Processing

[0053] The terminal transmits the input text data to the server.

[0054] 3. Server Processing

[0055] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[0056] The server converts the text data into standard Japanese, "It's nice weather today."

[0057] The converted text data is sent to the user terminal.

[0058] 4. Displaying the terminal

[0059] The terminal displays the conversion result "It's a nice day today" to the user.

[0060] In this way, this system achieves smooth communication by converting between dialects and standard Japanese while preserving the distinctive characteristics of the region. This system can be used in a variety of fields, including business, education, and tourism, and will help promote communication both within and outside the region.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The user inputs text in a dialect or standard language into the input field. The user terminal acquires the input text data and waits for the user to press the conversion button.

[0064] Step 2:

[0065] When the user presses the convert button, the device generates an HTTP request to send the text data to the server. Specifically, it sends a POST request to the server containing the text data to the URL endpoint / convert.

[0066] Step 3:

[0067] The server analyzes the received HTTP request and extracts the text data. At this time, it verifies whether the character encoding and format are correct, and passes the correctly extracted text on to the next process.

[0068] Step 4:

[0069] The server uses a natural language processing (NLP) model to identify whether the input text is a dialect or standard language. Specifically, the server inputs the text data into a pre-trained NLP model to identify the most probabilistic type of language form.

[0070] Step 5:

[0071] The server selects an appropriate conversion model based on the recognition result. For example, if the recognition result is Kansai dialect, it selects a model that converts Kansai dialect to standard Japanese. Conversely, if the recognition result is standard Japanese, it selects a model that converts it to the specified dialect.

[0072] Step 6:

[0073] The server converts the text data using the selected conversion model. Specifically, the text data is input into the conversion model and the converted text is obtained. For example, "It's a nice day today" is converted to "It's a nice day today."

[0074] Step 7:

[0075] The server generates an HTTP response containing the converted text data and sends it to the user terminal. The response contains the converted text.

[0076] Step 8:

[0077] The terminal analyzes the received HTTP response, extracts the converted text data, and prepares to display the converted text on the screen based on the response format.

[0078] Step 9:

[0079] The terminal displays the converted text data on the screen and provides feedback to the user. The user can check whether the conversion result is correct. For example, the conversion result "It's a nice day today" is displayed on the screen.

[0080] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, enabling smooth communication.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] In today's information society, the ability to convert between regional dialects and standard Japanese is crucial for smooth communication, especially between regions. However, existing systems rarely perform this conversion naturally, often losing the nuances and subtle meanings of dialects. Another issue is the lack of systems that can convert text entered by users in real time and provide appropriate feedback.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes means for analyzing received text data and identifying whether it is a dialect or standard language, means for selecting an appropriate language conversion model based on the identification result and converting the dialect into standard language or converting standard language into a dialect, and means for generating the converted text data as an HTTP response and sending it to the user terminal. This enables natural mutual conversion of text data and immediate feedback.

[0086] "User" refers to a person who uses the system to input text in dialect or standard Japanese and performs a series of operations to convert between them.

[0087] "Terminal" refers to a device used by a user to input and display text data, including computers, smartphones, tablets, etc.

[0088] "Server" refers to a computer system that receives data sent from a terminal, analyzes, converts, and returns the results.

[0089] "Text data" refers to character string information that a user inputs into a terminal. The input text data includes dialects and standard Japanese.

[0090] "HTTP request" refers to the protocol and request message format used when a user terminal sends data to a server.

[0091] "HTTP response" refers to the protocol and response message format used when the server sends the conversion result and other data to the user terminal.

[0092] "Natural language processing model" refers to a machine learning model for analyzing text data and identifying and converting dialects and standard Japanese. Examples include BERT and GPT-3 (registered trademark).

[0093] "Language conversion model" refers to a machine learning model used to convert text data between a specific dialect and standard Japanese.

[0094] "Parsing" refers to a series of computations performed to identify received text data.

[0095] "Conversion" refers to the process of changing text data into a specified format (dialect or standard language).

[0096] "Display" refers to the process in which the terminal displays the conversion result on the screen to provide it to the user.

[0097] The present invention relates to a system for naturally converting between regional dialects and standard Japanese. The system consists of a user terminal, a server, and a series of processes that use natural language processing to identify and convert text data.

[0098] User terminal

[0099] A user uses a terminal to input text and request conversion into the system. The terminal is a network-connected device such as a smartphone, computer, or tablet. This terminal acquires the text input by the user and sends it to the server when the user presses the conversion button. The input text can be a dialect such as "It's a nice day today" or standard Japanese such as "It's a nice day today."

[0100] server

[0101] The server receives text data sent from the user device and analyzes and converts it. Specifically, the server analyzes the HTTP request and extracts the text data. Next, it uses a natural language processing model to automatically identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by a natural language processing model (e.g., BERT, GPT-3).

[0102] Language Transformation Model

[0103] The server selects an appropriate language conversion model based on the identified language, and uses a model to convert dialects to standard Japanese and vice versa. For example, when converting from Kansai dialect to standard Japanese, "Kyo wa ii tenki ya naa" (It's a nice day today) is converted to "Kyo wa ii tenki da ne" (It's a nice day today). Conversely, conversion from standard Japanese to dialect is also possible, for example, "Kyo wa ii tenki da ne" (It's a nice day today) is converted to "Kyo wa ii tenki ya naa" (It's a nice day today).

[0104] Sending and displaying conversion results

[0105] The server generates an HTTP response containing the converted text data and sends it to the user's device. The device then analyzes the received HTTP response and extracts the converted text data. Finally, the device displays the conversion result on the screen and provides feedback to the user. For example, the conversion result might read, "It's nice weather today."

[0106] Specific examples

[0107] A specific example of how this system can be used is as follows:

[0108] 1. User operations

[0109] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[0110] 2. Terminal Processing

[0111] The terminal transmits the input text data to the server.

[0112] 3. Server Processing

[0113] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[0114] The server converts the text data into standard Japanese, "It's nice weather today."

[0115] The converted text data is sent to the user terminal.

[0116] 4. Displaying the terminal

[0117] The terminal displays the conversion result "It's a nice day today" to the user.

[0118] Through this example, the system can quickly and naturally convert text data entered by the user between dialect and standard Japanese, promoting communication between regions and enabling smooth information exchange.

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Step 1: User enters text and presses the convert button

[0121] The user enters text in a dialect or standard language into the input field of the terminal. For example, this input is "It's a nice day today." When the user presses the conversion button, the terminal acquires the text data. The input here is the text entered by the user, and the output is the text data acquired by the terminal.

[0122] Step 2: The device sends the text data to the server

[0123] The device generates an HTTP request including the acquired text data and sends it to the server. Specifically, it uses the JavaScript (registered trademark) fetch API to send the request to the appropriate endpoint. The input is the acquired text data, and the output is the HTTP request sent to the server.

[0124] Step 3: The server analyzes the text data and identifies dialects or standard languages.

[0125] The server receives an HTTP request and extracts the text data. It then uses a natural language processing model to identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect. The input is the text data received by the server, and the output is the identification result of dialect or standard Japanese.

[0126] Step 4: The server selects the appropriate language translation model and translates the text.

[0127] The server selects an appropriate conversion model based on the classification results. Using a model that converts Kansai dialect to standard Japanese, it converts "Kyo wa ii tenki yana" to "Kyo wa ii tenki da ne." The input is the classification result of dialect or standard Japanese, and the output is the converted text data.

[0128] Step 5: The server sends the converted text data to the device.

[0129] The server generates an HTTP response containing the converted text data and sends it to the terminal. This response is in JSON format. The input is the converted text data, and the output is the HTTP response sent to the user terminal.

[0130] Step 6: The terminal parses the HTTP response and displays the conversion result

[0131] The terminal analyzes the received HTTP response and extracts the converted text data. Finally, the terminal displays the converted result on the screen. For example, the converted result "It's nice weather today" is displayed to the user. The input is the HTTP response received from the server, and the output is the converted result that the terminal displays on the screen.

[0132] (Application example 1)

[0133] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0134] Food delivery services face the challenge of making it difficult for delivery staff and restaurants to accurately understand the orders of users who speak regional dialects and respond quickly and smoothly. There is also a need for an appropriate method to promote communication without compromising regional characteristics.

[0135] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0136] In this invention, the server includes terminal means for inputting text in a dialect or standard language, transmission means for transmitting the input text data to the server, identification means for identifying the received text data and determining whether it is a dialect or standard language, conversion means for converting the dialect into standard language or converting standard language into a dialect based on the identification result, transmission means for transmitting the converted text data to the terminal means, display means for displaying the converted text data on the terminal means, and display means for displaying the converted text data as food delivery order information to delivery personnel and stores. This enables accurate and smooth communication between users who speak a local dialect and delivery personnel and stores who speak standard language.

[0137] "Terminal means" refers to a device that allows a user to input text in dialect or standard Japanese and display it.

[0138] The "transmission means" is a function for transmitting input text data to a server.

[0139] The "identification means" is a function for analyzing received text data and determining whether it is a dialect or standard language.

[0140] The "conversion means" is a function for converting dialects into standard language or converting standard language into dialects based on the identification results.

[0141] The "display means" is a function for displaying the converted text data on a user terminal, a delivery person, or in a store.

[0142] "Food delivery" refers to the delivery of meals and beverages to customers through a delivery service.

[0143] A "natural language processing model" is an algorithm or model used to identify the linguistic form of text data and perform any necessary transformations.

[0144] A "regional language database" is a database for learning and storing the correspondence between dialects and standard Japanese in a specific region.

[0145] This invention is a system that naturally converts text between dialects and standard Japanese, and is particularly applicable to food delivery services. This system is designed so that delivery staff and stores can accurately understand and respond even if the user uses a dialect. Below is a concrete example of how this system can be implemented.

[0146] System Configuration

[0147] This system mainly consists of the following hardware and software:

[0148] User device: Smartphone, tablet, etc.

[0149] Server: The back-end system that handles the calculations.

[0150] Natural language processing models: Algorithms for identifying linguistic forms in text data (e.g., BERT and GPT-3).

[0151] Regional Language Database: A database that learns the correspondence between dialects and standard Japanese.

[0152] Front-end application: An app that provides a user interface (e.g., an iOS or ANDROID app).

[0153] Program processing explanation

[0154] User Interface

[0155] When a user places a food delivery order, they input text written in a dialect, such as "It's a nice day today, can I have one katsudon please?" This input text is sent from the device to the server.

[0156] Server Processing

[0157] The server analyzes the received text data and uses a natural language processing model (e.g., HuggingFace's BERT or GPT-3) to identify whether the text is in a dialect or standard Japanese. At this stage, the text is identified as Kansai dialect, such as "What a nice day today, can I have a katsudon please?"

[0158] After identification, the server refers to a regional language database and converts the dialect into standard Japanese. For example, the Kansai dialect "It's a nice day today, so I'll have one katsudon please" is converted to "It's a nice day today. I'll have one katsudon please." This allows delivery personnel and stores to accurately understand the order.

[0159] Displaying the results

[0160] The converted text data is then sent from the server to the user's device, the delivery person's device, and the store's device. Each device displays the converted text in standard Japanese. This converts the dialect entered by the user into standard Japanese, allowing the delivery person and store to respond accurately.

[0161] Examples and prompts

[0162] As a specific example, the following flow can be considered.

[0163] 1. User operation: The user enters "Thank you, I'd like one yakiniku set meal" and presses the order button.

[0164] 2. Server processing: The text is sent to the server, which converts it to "Thank you. I'd like one yakiniku set meal, please."

[0165] 3. Displaying the results: The app displays the conversion results and communicates the order details in standard Japanese to the delivery person or store.

[0166] Example prompt sentence:

[0167] User input: Thank you, I'll have a yakiniku set meal.

[0168] Model prompt: dialect -> standard Japanese

[0169] Translated: Thank you. I'd like one yakiniku set meal, please.

[0170] This series of processes enables accurate and smooth communication between users who speak local dialects and delivery people and stores who speak standard Japanese.

[0171] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0172] Step 1:

[0173] User Input

[0174] The user opens the application on the terminal, enters the order text in the dialect into the text input field, and presses the send button. This becomes the input data.

[0175] Input: The dialect text entered by the user.

[0176] Output: The device prepares this text to be sent.

[0177] Step 2:

[0178] Sending input data

[0179] The terminal sends the text data entered by the user to the server as an HTTP request. Specifically, it generates a POST request and sends a payload including the text data to the server.

[0180] Input: Dialect text data entered by the user.

[0181] Output: Text data wrapped in an HTTP request is sent to the server.

[0182] Step 3:

[0183] Receiving and analyzing text data

[0184] The server parses the received HTTP request and extracts text data, which is then analyzed using a natural language processing model (e.g., HuggingFace's BERT) to identify dialects and standard Japanese.

[0185] Input: Text data contained in the payload of the HTTP request.

[0186] Output: Identification of the text as dialect or standard.

[0187] Step 4:

[0188] Language Conversion

[0189] Based on the classification results, the server selects an appropriate conversion model (e.g., GPT-3) and converts the text data. Specifically, it converts the dialect "Thank you very much, I'd like a yakiniku set meal please" into standard Japanese "Thank you. I'd like a yakiniku set meal please."

[0190] Input: Dialect text data and its classification results.

[0191] Output: Converted standard Japanese text data.

[0192] Step 5:

[0193] Sending the conversion results

[0194] The server generates an HTTP response containing the converted text data and sends it to the user's device, the delivery person's device, and the store's device. Specifically, the HTTP response payload includes the converted text.

[0195] Input: Converted standard Japanese text data.

[0196] Output: Text data wrapped in an HTTP response and sent to the device.

[0197] Step 6:

[0198] Displaying the conversion results

[0199] The user device and the delivery person / store device analyze the received HTTP response and extract the converted standard Japanese text data. The user device displays the converted text to the user, and the delivery person / store device displays it to each employee. Specifically, the application's text view displays "Thank you. I'd like one yakiniku set meal, please."

[0200] Input: HTTP response containing the converted standard Japanese text data.

[0201] Output: The converted text displayed on the application screen.

[0202] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0203] This invention relates to a system that naturally converts between regional dialects and standard Japanese, and also combines it with an emotion engine that recognizes the user's emotions. This system consists of a series of processes that use a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine to identify and convert text data and perform appropriate conversion according to the emotion.

[0204] Program processing

[0205] Accepting input from the user

[0206] The user inputs text in a dialect or standard Japanese into the user terminal. This text can be a regional dialect such as Kansai dialect, such as "It's a nice day today," or standard Japanese, such as "It's a nice day today." By entering text into the input field and pressing the conversion button, the user terminal acquires this text data.

[0207] Sending Input

[0208] The user terminal transmits the input text data to the server. Specifically, it generates an HTTP request and transmits the request to the server together with the text data.

[0209] Language and Emotion Recognition

[0210] The server analyzes the received HTTP request and extracts the text data. It uses a natural language processing model to identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by the natural language processing model. At the same time, it uses an emotion engine to recognize the emotion of the text data. For example, the emotion engine recognizes positive emotion (joy) for "It's a nice day today."

[0211] Conversion process

[0212] The server selects an appropriate conversion model based on the recognition results. In this case, a model that converts Kansai dialect to standard Japanese is used. Furthermore, based on the recognition results of the emotion engine, the conversion is performed taking into account emotional information. For example, when the input text "It's a nice day today" is converted to "It's a nice day today," the conversion is adjusted to maintain a positive emotion.

[0213] Sending the conversion results

[0214] The server generates an HTTP response including the converted text data and sends it to the user terminal. At this time, the response includes the converted text and emotion information.

[0215] Displaying the results

[0216] The user device analyzes the received HTTP response and extracts the converted text data. It also acquires the emotion information and finally displays it on the screen along with the conversion result. The user can check the converted text and the result with the emotion information added.

[0217] Specific examples

[0218] A specific example of use is as follows:

[0219] 1. User operations

[0220] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[0221] 2. Terminal Processing

[0222] The terminal transmits the input text data to the server.

[0223] 3. Server Processing

[0224] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[0225] At the same time, it uses an emotion engine to recognize emotions as positive.

[0226] The server converts the text data into standard Japanese, "It's nice weather today."

[0227] Positive emotional information is added to generate converted text data.

[0228] The converted text data and emotion information are sent to the user terminal.

[0229] 4. Displaying the terminal

[0230] The device displays the conversion result, "It's nice weather today," as positive emotional information to the user.

[0231] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, and then adds emotional information to achieve richer communication.

[0232] The processing flow will be explained below.

[0233] Step 1:

[0234] The user inputs text in a dialect or standard language into the input field. The user terminal acquires the input text data and waits for the user to press the conversion button.

[0235] Step 2:

[0236] When the user presses the convert button, the device generates an HTTP request to send the text data to the server. Specifically, it sends a POST request to the server containing the text data to the URL endpoint / convert.

[0237] Step 3:

[0238] The server analyzes the received HTTP request and extracts the text data. At this time, it verifies whether the character encoding and format are correct, and passes the correctly extracted text on to the next process.

[0239] Step 4:

[0240] The server uses a natural language processing (NLP) model to identify whether the text is in a dialect or standard Japanese. Specifically, it uses a pre-trained NLP model to identify the linguistic form of the text data. For example, the text "It's a nice day today" is identified as Kansai dialect.

[0241] Step 5:

[0242] The server uses an emotion engine to recognize emotions in input text data, for example, recognizing positive emotions (joy) from the text "What a nice day today."

[0243] Step 6:

[0244] The server selects an appropriate conversion model based on the classification results. In this case, it selects a model that converts Kansai dialect to standard Japanese, and further considers the recognized emotion when converting.

[0245] Step 7:

[0246] The server converts the text data using the selected conversion model, for example, converting "It's a nice day today" to "It's a nice day today," and adds positive sentiment information to the converted text.

[0247] Step 8:

[0248] The server generates an HTTP response including the converted text data and emotion information, and sends it to the user terminal. The response includes the converted text and emotion information.

[0249] Step 9:

[0250] The device analyzes the received HTTP response, extracts the converted text data and emotion information, and prepares to display them on the screen based on the response format.

[0251] Step 10:

[0252] The device displays the converted text data and the emotion information on the screen and provides feedback to the user. For example, the conversion result "It's nice weather today (positive)" and the emotion information are displayed on the screen.

[0253] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, and then adds emotional information to achieve richer communication.

[0254] Example 2

[0255] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0256] In today's world, deepening mutual understanding between regional dialects and standard Japanese is important, but accurately conveying subtle emotional nuances in these languages ​​is difficult. Furthermore, conventional technologies for converting between dialects and standard Japanese have difficulty taking emotional information into account, resulting in a decline in the quality of communication. Furthermore, even when natural language processing technology is used, the recognition and reflection of emotional information is insufficient, making it impossible to accurately understand and convey the user's intentions. Therefore, the present invention aims to solve these problems by providing a system that appropriately recognizes and reflects emotional information when converting between dialects and standard Japanese.

[0257] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0258] In this invention, the server includes means for analyzing received text data and determining whether it is a dialect or standard language, means for applying a language conversion model to convert the dialect into standard language or convert standard language into the dialect based on the determination result, and means for recognizing emotions in the text data and reflecting them in the conversion result. This allows text entered by a user to be accurately converted into dialect or standard language and transmitted while retaining the emotional nuances.

[0259] An "information processing device" is a device that allows a user to input text data and has the function of processing and communicating the input data.

[0260] A "communication device" is a device that includes hardware and software for transmitting and receiving data between an information processing device and a server.

[0261] "Analysis" refers to the process of understanding the content of input text data and determining whether it is a dialect or standard language.

[0262] A "language conversion model" is an algorithm that converts between dialects and standard Japanese based on a specific regional language database.

[0263] An "emotion engine" is an algorithm that recognizes emotional information contained in text data and outputs that information.

[0264] A "generative AI model" is an algorithm that uses machine learning technology to perform natural language processing and emotion recognition.

[0265] A "natural language processing model" is an algorithm that includes techniques for computers to understand and manipulate human language.

[0266] A "regional language database" is a dataset that collects examples of dialects and standard languages ​​in a specific region and learns the correspondences between them.

[0267] An "HTTP request" is a protocol for sending data from a client to a server, and is a message format for requesting and sending data.

[0268] The "JSON format" is a lightweight data exchange format for structuring and expressing data, and is a text format that is easy to read for both humans and machines.

[0269] MODE FOR CARRYING OUT THE INVENTION

[0270] This invention relates to a system that naturally converts between regional dialects and standard Japanese, and also combines it with an emotion engine that recognizes the user's emotions. This system consists of a series of processes that use a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine to identify and convert text data and perform appropriate conversion according to the emotion.

[0271] Hardware and Software Use

[0272] The user terminal functions as an input device for users to input text in dialect or standard Japanese. Specifically, this includes information processing devices such as PCs, smartphones, and tablets. When a user inputs text into an input field and presses the conversion button, the user terminal temporarily stores the text data in memory and prepares to proceed to the next processing step.

[0273] The terminal includes the text data entered by the user in an HTTP request and sends it to the server. The communication device used for this purpose has the function of providing a network connection. It generates an HTTP request and sends the text data to the server's endpoint using the POST method.

[0274] The server processes the received HTTP request and extracts the text data. Using a natural language processing model (such as GPT-3 or BERT), the server identifies whether the text is in a dialect or standard Japanese. At the same time, it uses an emotion engine to recognize the emotion of the text data. For example, it recognizes that the text "What a nice day today" is in the Kansai dialect and contains positive emotion (joy).

[0275] Based on the results of the classification, the server applies a language conversion model trained using a specific regional language database to convert dialects to standard Japanese or vice versa. The server also takes into account the recognition results of the emotion engine, preserving emotional information during the conversion. For example, "It's a nice day today" is converted to "It's a nice day today."

[0276] The server generates an HTTP response containing the converted text data and emotion information, and sends it to the user's device.

[0277] The terminal analyzes the received HTTP response, extracts the converted text data and emotion information, and displays the converted text data and emotion information in a specific area of ​​the user interface, allowing the user to check the converted text and emotion information.

[0278] Specific examples

[0279] Specific usage examples are:

[0280] User operations

[0281] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[0282] Terminal handling

[0283] The device creates a JSON containing the input text data "It's nice weather today" and sends an HTTP POST request to the server.

[0284] Server Processing

[0285] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[0286] At the same time, it uses an emotion engine to recognize emotions as positive.

[0287] The server converts the text data into standard Japanese, such as "It's nice weather today," and adds positive emotional information.

[0288] The converted text data and emotion information are sent to the user terminal.

[0289] Terminal display

[0290] The device displays the conversion result, "It's nice weather today," as positive emotional information to the user.

[0291] This allows the system to convert text entered by the user between dialect and standard Japanese, and by adding emotional information, it is possible to achieve richer communication.

[0292] Prompt Sentence Examples

[0293] Example of Kansai dialect input text: "It's a nice day today."

[0294] Standard Japanese conversion example: "It's a nice day today."

[0295] Emotional information: Positive (joy)

[0296] As described above, the embodiments of the present invention provide a system that accurately converts text data entered by a user between dialect and standard Japanese, while preserving emotional nuances.

[0297] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0298] Step 1: Accepting input from the user

[0299] The user enters text data into the input field on the user terminal and presses the conversion button. Specifically, the following process is performed:

[0300] Get text data from the input field.

[0301] The text data is temporarily stored in memory in preparation for the next step.

[0302] Input: "What a nice day today" (Kansai dialect)

[0303] Output: Text data is stored in memory.

[0304] Step 2: Sending Input

[0305] The device generates an HTTP request containing the retrieved text data and sends it to the server. The specific operation is as follows:

[0306] Make an HTTP request using the POST method.

[0307] Add text data in JSON format to the request body.

[0308] Sends a request to the server at the specified endpoint.

[0309] Input: "What a nice day today" (text data stored in memory)

[0310] Output: An HTTP request containing text data is sent to the server.

[0311] Step 3: Language and emotion recognition

[0312] The server processes the received HTTP request and extracts the text data. Specifically, it does the following:

[0313] Parse the JSON data from the body of the HTTP request and extract the text data.

[0314] Use a natural language processing model (e.g., a generative AI model) to identify whether the text data is a dialect or standard language.

[0315] At the same time, an emotion engine is used to recognize emotions in the text data.

[0316] Input: "What a nice day today" (text data extracted from an HTTP request)

[0317] Output: Linguistic form (Kansai dialect) and emotional information (positive) are identified.

[0318] Step 4: Conversion process

[0319] The server then applies the appropriate language transformation model to convert the text based on the identified language form. The specific operations are as follows:

[0320] Select a model that converts Kansai dialect to standard Japanese.

[0321] Based on the results of the emotion engine, the text is appropriately converted while retaining emotional information.

[0322] Input: Language form (Kansai dialect) and emotional information (positive)

[0323] Output: Converted standard Japanese text "It's a nice day today" and emotional information (positive)

[0324] Step 5: Send the conversion results

[0325] The server generates an HTTP response containing the converted text data and emotion information, and sends it to the user's device. The specific operation is as follows:

[0326] The converted text data and emotion information are combined into a single JSON object.

[0327] Set the above JSON object in the body of the HTTP response.

[0328] An HTTP response is sent to the user terminal.

[0329] Input: Converted text "It's a nice day today" and emotional information (positive)

[0330] Output: JSON data is sent to the user device as an HTTP response.

[0331] Step 6: View the results

[0332] The device analyzes the received HTTP response and extracts the converted text data and emotion information. The specific operation is as follows:

[0333] Parse JSON data from an HTTP response.

[0334] The converted text data and emotional information are extracted and stored in separate variables.

[0335] The converted text data "It's a nice day today" and emotional information (positive) are displayed on the user interface.

[0336] Input: HTTP response (JSON data) received from the server

[0337] Output: The converted text data "It's a nice day today" and emotional information (positive) are displayed on the user's device screen.

[0338] (Application example 2)

[0339] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0340] While conventional text conversion systems can convert between dialects and standard Japanese, they are unable to take into account the user's emotional information, which means they are unable to properly convey the emotional nuances of the text. Furthermore, even in advertisements or customer service messages that utilize regional dialects, conversion that does not take emotional information into account makes it difficult to achieve effective communication. This poses a challenge, as it makes it difficult to increase the impact of advertisements or enhance relationships with customers.

[0341] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0342] In this invention, the server includes means for identifying input text data and determining whether it is a dialect or standard language, means for converting the dialect into standard language or converting the standard language into a dialect based on the identification result and emotional information, and further adjusting the language to correspond to the emotion, and means for transmitting the converted text data and emotional information to the user terminal. This allows the user's emotional information to be appropriately reflected in the text conversion, making it possible to generate more effective advertisements and customer service messages.

[0343] A "dialect" or "standard language" is a unique language form used in a particular region or cultural area within Japan, and has characteristics that differ from the general national language.

[0344] "Emotional information" refers to the emotional nuances and attitudes contained in the text entered by the user, and is information that includes emotional states such as positive, negative, and neutral.

[0345] A "user terminal" is a device on which a user inputs text and checks the converted text result, and includes a smartphone, tablet, PC, etc.

[0346] The "server" is a centralized management system that receives and processes text data sent from user terminals, and is the device that performs text conversion and emotion recognition processing.

[0347] A "natural language processing model" is an artificial intelligence model that analyzes input text data and identifies its linguistic form, and is a technology for understanding and classifying the content of the text.

[0348] An "emotion engine" is a technology for recognizing emotional information contained in text data, and is a model for analyzing the emotional nuances of text and evaluating emotional states.

[0349] A "language conversion model" is an algorithm that uses a specific regional language database to learn the correspondence between dialects and standard Japanese and convert between the two.

[0350] "Converted text data" refers to new text obtained by subjecting input text to a specified conversion process, and is the data resulting from conversion from standard Japanese to a dialect, or from a dialect to standard Japanese.

[0351] A "regional language database" is a database that compiles variations of dialects and standard Japanese used in various regions of Japan, and is a collection of data used to train language conversion models.

[0352] The "emotion database" is a database that classifies and organizes emotional information accompanying text data, and is a source of information to support the learning and evaluation of the emotion engine.

[0353] A specific embodiment for carrying out the present invention will now be described. The present invention is realized using a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine. The operation and interaction of each element will be described below.

[0354] User terminal

[0355] First, the user inputs text in a dialect or standard Japanese using a user terminal. User terminals include smartphones, tablets, and PCs. The user inputs text into an input field and confirms the input text by pressing the conversion button. The input text at this stage is then sent to the server.

[0356] server

[0357] The server receives input text data sent from the user's device. Specifically, it receives text data via an HTTP request. The server analyzes the received text data and uses a natural language processing model to identify whether the data is written in a dialect or standard Japanese. It also uses an emotion engine to simultaneously recognize the emotional information contained in the text data.

[0358] Natural language processing model and emotion engine

[0359] The natural language processing model uses Hugging Face's "transformers" library to analyze text data and identify linguistic forms, while the emotion engine uses Hugging Face's sentiment analysis pipeline to analyze the emotional state contained in the text.

[0360] Language Transformation Model

[0361] A language transformation model is then used to convert the text from dialect to standard or vice versa. This model uses a specific regional language database to transform the text according to the regional linguistic form, and is adjusted to preserve emotional information by taking into account the output of the emotion engine.

[0362] Return to user terminal

[0363] The converted text data and emotion information are then sent back to the user device as an HTTP response by the server. The user device receives this and displays the converted text and emotion information on the screen. This allows the user to check the conversion results and manually correct them if necessary.

[0364] Examples of concrete examples and prompts

[0365] For example, consider the case where a user inputs the standard Japanese text "The release of a new product has been decided. Please look forward to it!". The server receives this text and converts it into Kansai dialect, such as "It's a nice day today," and reflects the output of the emotion engine to maintain a positive emotion. As a result, the user device displays "The release of a new product has been decided. Please look forward to it!".

[0366] An example of a prompt sentence would be, "Please convert the following text into the local dialect and recognize the emotion: We've decided to launch a new product. Look forward to it!" By inputting this into the generative AI model, appropriate text conversion and emotion recognition can be performed.

[0367] In this way, this system realizes mutual conversion between dialects and standard Japanese and retains emotional information, enabling effective and emotionally rich communication, particularly in advertising and customer service messages.

[0368] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0369] Step 1:

[0370] A user inputs text in a dialect or standard Japanese into a user terminal. The user inputs text into an input field and confirms the input text by pressing the conversion button. In this case, the input text is a dialect such as "It's a nice day today" or standard Japanese such as "It's a nice day today."

[0371] Step 2:

[0372] The user terminal sends the entered text data to the server. Specifically, it generates an HTTP request and sends it to the server including the text data. The input at this time is the text data entered by the user, and the output is the data to be sent to the server.

[0373] Step 3:

[0374] The server analyzes the received HTTP request and extracts the text data. The analyzed text data is input into a natural language processing model to identify the language form. For example, "It's nice weather today" is identified as Kansai dialect. At the same time, an emotion engine is used to recognize the emotion of the text data. For example, for "It's nice weather today," the emotion engine recognizes a positive emotion (joy).

[0375] Step 4:

[0376] The server selects an appropriate language conversion model based on the identification results. The inputs are the identification results and emotion information, and the output is the selected conversion model. For example, using a model that converts Kansai dialect into standard Japanese, "Kyo wa ii tenki ya na" (It's a nice day today) is converted to "Kyo wa ii tenki da ne" (It's a nice day today). At the same time, the conversion is performed in a way that preserves positive emotion information based on the output of the emotion engine.

[0377] Step 5:

[0378] The server generates an HTTP response including the converted text data and emotion information, and sends it to the user terminal. The input at this time is the converted text data and emotion information, and the output is the data sent to the user terminal.

[0379] Step 6:

[0380] The user device analyzes the received HTTP response and extracts the converted text data and emotional information. The conversion results and emotional information are then displayed on the screen, allowing the user to check the converted text and emotional information. The input in this case is the response data from the server, and the output is the data displayed on the screen.

[0381] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0382] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0383] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0384] [Second embodiment]

[0385] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0386] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0387] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0388] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0389] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0390] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0391] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0392] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0393] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0394] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0395] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0396] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0397] The present invention relates to a system for naturally converting between regional dialects and standard Japanese. The system consists of a user terminal, a server, and a series of processes that use natural language processing to identify and convert text data.

[0398] Program processing

[0399] Accepting input from the user

[0400] The user inputs text in a dialect or standard Japanese into the user terminal. This text can be a regional dialect such as Kansai dialect, such as "It's a nice day today," or standard Japanese, such as "It's a nice day today." By entering text into the input field and pressing the conversion button, the user terminal acquires this text data.

[0401] Sending Input

[0402] The user terminal transmits the input text data to the server. Specifically, it generates an HTTP request and transmits the request to the server together with the text data.

[0403] Language Identification

[0404] The server analyzes the received HTTP request and extracts the text data. It then uses a natural language processing model to automatically identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by the natural language processing model.

[0405] Conversion process

[0406] The server selects an appropriate conversion model based on the recognition results. Here, a model that converts Kansai dialect to standard Japanese is used. For example, "It's a nice day today" is converted to "It's a nice day today." Conversely, conversion from standard Japanese to a dialect is also possible, for example, "It's a nice day today" is converted to "It's a nice day today."

[0407] Sending the conversion results

[0408] The server generates an HTTP response including the converted text data and sends it to the user terminal. At this time, the response includes the converted text.

[0409] Displaying the results

[0410] The user device analyzes the received HTTP response and extracts the converted text data. Finally, the user device displays the conversion result on the screen and provides feedback to the user. For example, the conversion result "It's nice weather today" is displayed.

[0411] Specific examples

[0412] A specific example of use is as follows:

[0413] 1. User operations

[0414] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[0415] 2. Terminal Processing

[0416] The terminal transmits the input text data to the server.

[0417] 3. Server Processing

[0418] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[0419] The server converts the text data into standard Japanese, "It's nice weather today."

[0420] The converted text data is sent to the user terminal.

[0421] 4. Displaying the terminal

[0422] The terminal displays the conversion result "It's a nice day today" to the user.

[0423] In this way, this system achieves smooth communication by converting between dialects and standard Japanese while preserving the distinctive characteristics of the region. This system can be used in a variety of fields, including business, education, and tourism, and will help promote communication both within and outside the region.

[0424] The processing flow will be explained below.

[0425] Step 1:

[0426] The user inputs text in a dialect or standard language into the input field. The user terminal acquires the input text data and waits for the user to press the conversion button.

[0427] Step 2:

[0428] When the user presses the convert button, the device generates an HTTP request to send the text data to the server. Specifically, it sends a POST request to the server containing the text data to the URL endpoint / convert.

[0429] Step 3:

[0430] The server analyzes the received HTTP request and extracts the text data. At this time, it verifies whether the character encoding and format are correct, and passes the correctly extracted text on to the next process.

[0431] Step 4:

[0432] The server uses a natural language processing (NLP) model to identify whether the input text is a dialect or standard language. Specifically, the server inputs the text data into a pre-trained NLP model to identify the most probabilistic type of language form.

[0433] Step 5:

[0434] The server selects an appropriate conversion model based on the recognition result. For example, if the recognition result is Kansai dialect, it selects a model that converts Kansai dialect to standard Japanese. Conversely, if the recognition result is standard Japanese, it selects a model that converts it to the specified dialect.

[0435] Step 6:

[0436] The server converts the text data using the selected conversion model. Specifically, the text data is input into the conversion model and the converted text is obtained. For example, "It's a nice day today" is converted to "It's a nice day today."

[0437] Step 7:

[0438] The server generates an HTTP response containing the converted text data and sends it to the user terminal. The response contains the converted text.

[0439] Step 8:

[0440] The terminal analyzes the received HTTP response, extracts the converted text data, and prepares to display the converted text on the screen based on the response format.

[0441] Step 9:

[0442] The terminal displays the converted text data on the screen and provides feedback to the user. The user can check whether the conversion result is correct. For example, the conversion result "It's a nice day today" is displayed on the screen.

[0443] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, enabling smooth communication.

[0444] Example 1

[0445] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0446] In today's information society, the ability to convert between regional dialects and standard Japanese is crucial for smooth communication, especially between regions. However, existing systems rarely perform this conversion naturally, often losing the nuances and subtle meanings of dialects. Another issue is the lack of systems that can convert text entered by users in real time and provide appropriate feedback.

[0447] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0448] In this invention, the server includes means for analyzing received text data and identifying whether it is a dialect or standard language, means for selecting an appropriate language conversion model based on the identification result and converting the dialect into standard language or converting standard language into a dialect, and means for generating the converted text data as an HTTP response and sending it to the user terminal. This enables natural mutual conversion of text data and immediate feedback.

[0449] "User" refers to a person who uses the system to input text in dialect or standard Japanese and performs a series of operations to convert between them.

[0450] "Terminal" refers to a device used by a user to input and display text data, including computers, smartphones, tablets, etc.

[0451] "Server" refers to a computer system that receives data sent from a terminal, analyzes, converts, and returns the results.

[0452] "Text data" refers to character string information that a user inputs into a terminal. The input text data includes dialects and standard Japanese.

[0453] "HTTP request" refers to the protocol and request message format used when a user terminal sends data to a server.

[0454] "HTTP response" refers to the protocol and response message format used when the server sends the conversion result and other data to the user terminal.

[0455] "Natural language processing model" refers to a machine learning model that analyzes text data and identifies and converts dialects and standard Japanese. Examples include BERT and GPT-3.

[0456] "Language conversion model" refers to a machine learning model used to convert text data between a specific dialect and standard Japanese.

[0457] "Parsing" refers to a series of computations performed to identify received text data.

[0458] "Conversion" refers to the process of changing text data into a specified format (dialect or standard language).

[0459] "Display" refers to the process in which the terminal displays the conversion result on the screen to provide it to the user.

[0460] The present invention relates to a system for naturally converting between regional dialects and standard Japanese. The system consists of a user terminal, a server, and a series of processes that use natural language processing to identify and convert text data.

[0461] User terminal

[0462] A user uses a terminal to input text and request conversion into the system. The terminal is a network-connected device such as a smartphone, computer, or tablet. This terminal acquires the text input by the user and sends it to the server when the user presses the conversion button. The input text can be a dialect such as "It's a nice day today" or standard Japanese such as "It's a nice day today."

[0463] server

[0464] The server receives text data sent from the user device and analyzes and converts it. Specifically, the server analyzes the HTTP request and extracts the text data. Next, it uses a natural language processing model to automatically identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by a natural language processing model (e.g., BERT, GPT-3).

[0465] Language Transformation Model

[0466] The server selects an appropriate language conversion model based on the identified language, and uses a model to convert dialects to standard Japanese and vice versa. For example, when converting from Kansai dialect to standard Japanese, "Kyo wa ii tenki ya naa" (It's a nice day today) is converted to "Kyo wa ii tenki da ne" (It's a nice day today). Conversely, conversion from standard Japanese to dialect is also possible, for example, "Kyo wa ii tenki da ne" (It's a nice day today) is converted to "Kyo wa ii tenki ya naa" (It's a nice day today).

[0467] Sending and displaying conversion results

[0468] The server generates an HTTP response containing the converted text data and sends it to the user's device. The device then analyzes the received HTTP response and extracts the converted text data. Finally, the device displays the conversion result on the screen and provides feedback to the user. For example, the conversion result might read, "It's nice weather today."

[0469] Specific examples

[0470] A specific example of how this system can be used is as follows:

[0471] 1. User operations

[0472] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[0473] 2. Terminal Processing

[0474] The terminal transmits the input text data to the server.

[0475] 3. Server Processing

[0476] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[0477] The server converts the text data into standard Japanese, "It's nice weather today."

[0478] The converted text data is sent to the user terminal.

[0479] 4. Displaying the terminal

[0480] The terminal displays the conversion result "It's a nice day today" to the user.

[0481] Through this example, the system can quickly and naturally convert text data entered by the user between dialect and standard Japanese, promoting communication between regions and enabling smooth information exchange.

[0482] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0483] Step 1: User enters text and presses the convert button

[0484] The user enters text in a dialect or standard language into the input field of the terminal. For example, this input is "It's a nice day today." When the user presses the conversion button, the terminal acquires the text data. The input here is the text entered by the user, and the output is the text data acquired by the terminal.

[0485] Step 2: The device sends the text data to the server

[0486] The device generates an HTTP request containing the retrieved text data and sends it to the server. Specifically, it uses the JavaScript fetch API to send a request to the appropriate endpoint. The input is the retrieved text data, and the output is the HTTP request sent to the server.

[0487] Step 3: The server analyzes the text data and identifies dialects or standard languages.

[0488] The server receives an HTTP request and extracts the text data. It then uses a natural language processing model to identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect. The input is the text data received by the server, and the output is the identification result of dialect or standard Japanese.

[0489] Step 4: The server selects the appropriate language translation model and translates the text.

[0490] The server selects an appropriate conversion model based on the classification results. Using a model that converts Kansai dialect to standard Japanese, it converts "Kyo wa ii tenki yana" to "Kyo wa ii tenki da ne." The input is the classification result of dialect or standard Japanese, and the output is the converted text data.

[0491] Step 5: The server sends the converted text data to the device.

[0492] The server generates an HTTP response containing the converted text data and sends it to the terminal. This response is in JSON format. The input is the converted text data, and the output is the HTTP response sent to the user terminal.

[0493] Step 6: The terminal parses the HTTP response and displays the conversion result

[0494] The terminal analyzes the received HTTP response and extracts the converted text data. Finally, the terminal displays the converted result on the screen. For example, the converted result "It's nice weather today" is displayed to the user. The input is the HTTP response received from the server, and the output is the converted result that the terminal displays on the screen.

[0495] (Application example 1)

[0496] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0497] Food delivery services face the challenge of making it difficult for delivery staff and restaurants to accurately understand the orders of users who speak regional dialects and respond quickly and smoothly. There is also a need for an appropriate method to promote communication without compromising regional characteristics.

[0498] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0499] In this invention, the server includes terminal means for inputting text in a dialect or standard language, transmission means for transmitting the input text data to the server, identification means for identifying the received text data and determining whether it is a dialect or standard language, conversion means for converting the dialect into standard language or converting standard language into a dialect based on the identification result, transmission means for transmitting the converted text data to the terminal means, display means for displaying the converted text data on the terminal means, and display means for displaying the converted text data as food delivery order information to delivery personnel and stores. This enables accurate and smooth communication between users who speak a local dialect and delivery personnel and stores who speak standard language.

[0500] "Terminal means" refers to a device that allows a user to input text in dialect or standard Japanese and display it.

[0501] The "transmission means" is a function for transmitting input text data to a server.

[0502] The "identification means" is a function for analyzing received text data and determining whether it is a dialect or standard language.

[0503] The "conversion means" is a function for converting dialects into standard language or converting standard language into dialects based on the identification results.

[0504] The "display means" is a function for displaying the converted text data on a user terminal, a delivery person, or in a store.

[0505] "Food delivery" refers to the delivery of meals and beverages to customers through a delivery service.

[0506] A "natural language processing model" is an algorithm or model used to identify the linguistic form of text data and perform any necessary transformations.

[0507] A "regional language database" is a database for learning and storing the correspondence between dialects and standard Japanese in a specific region.

[0508] This invention is a system that naturally converts text between dialects and standard Japanese, and is particularly applicable to food delivery services. This system is designed so that delivery staff and stores can accurately understand and respond even if the user uses a dialect. Below is a concrete example of how this system can be implemented.

[0509] System Configuration

[0510] This system mainly consists of the following hardware and software:

[0511] User device: Smartphone, tablet, etc.

[0512] Server: The back-end system that handles the calculations.

[0513] Natural language processing models: Algorithms for identifying linguistic forms in text data (e.g., BERT and GPT-3).

[0514] Regional Language Database: A database that learns the correspondence between dialects and standard Japanese.

[0515] Front-end application: An app that provides the user interface (e.g., an iOS or Android app).

[0516] Program processing explanation

[0517] User Interface

[0518] When a user places a food delivery order, they input text written in a dialect, such as "It's a nice day today, can I have one katsudon please?" This input text is sent from the device to the server.

[0519] Server Processing

[0520] The server analyzes the received text data and uses a natural language processing model (e.g., HuggingFace's BERT or GPT-3) to identify whether the text is in a dialect or standard Japanese. At this stage, the text is identified as Kansai dialect, such as "What a nice day today, can I have a katsudon please?"

[0521] After identification, the server refers to a regional language database and converts the dialect into standard Japanese. For example, the Kansai dialect "It's a nice day today, so I'll have one katsudon please" is converted to "It's a nice day today. I'll have one katsudon please." This allows delivery personnel and stores to accurately understand the order.

[0522] Displaying the results

[0523] The converted text data is then sent from the server to the user's device, the delivery person's device, and the store's device. Each device displays the converted text in standard Japanese. This converts the dialect entered by the user into standard Japanese, allowing the delivery person and store to respond accurately.

[0524] Examples and prompts

[0525] As a specific example, the following flow can be considered.

[0526] 1. User operation: The user enters "Thank you, I'd like one yakiniku set meal" and presses the order button.

[0527] 2. Server processing: The text is sent to the server, which converts it to "Thank you. I'd like one yakiniku set meal, please."

[0528] 3. Displaying the results: The app displays the conversion results and communicates the order details in standard Japanese to the delivery person or store.

[0529] Example prompt sentence:

[0530] User input: Thank you, I'll have a yakiniku set meal.

[0531] Model prompt: dialect -> standard Japanese

[0532] Translated: Thank you. I'd like one yakiniku set meal, please.

[0533] This series of processes enables accurate and smooth communication between users who speak local dialects and delivery people and stores who speak standard Japanese.

[0534] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0535] Step 1:

[0536] User Input

[0537] The user opens the application on the terminal, enters the order text in the dialect into the text input field, and presses the send button. This becomes the input data.

[0538] Input: The dialect text entered by the user.

[0539] Output: The device prepares this text to be sent.

[0540] Step 2:

[0541] Sending input data

[0542] The terminal sends the text data entered by the user to the server as an HTTP request. Specifically, it generates a POST request and sends a payload including the text data to the server.

[0543] Input: Dialect text data entered by the user.

[0544] Output: Text data wrapped in an HTTP request is sent to the server.

[0545] Step 3:

[0546] Receiving and analyzing text data

[0547] The server parses the received HTTP request and extracts text data, which is then analyzed using a natural language processing model (e.g., HuggingFace's BERT) to identify dialects and standard Japanese.

[0548] Input: Text data contained in the payload of the HTTP request.

[0549] Output: Identification of the text as dialect or standard.

[0550] Step 4:

[0551] Language Conversion

[0552] Based on the classification results, the server selects an appropriate conversion model (e.g., GPT-3) and converts the text data. Specifically, it converts the dialect "Thank you very much, I'd like a yakiniku set meal please" into standard Japanese "Thank you. I'd like a yakiniku set meal please."

[0553] Input: Dialect text data and its classification results.

[0554] Output: Converted standard Japanese text data.

[0555] Step 5:

[0556] Sending the conversion results

[0557] The server generates an HTTP response containing the converted text data and sends it to the user's device, the delivery person's device, and the store's device. Specifically, the HTTP response payload includes the converted text.

[0558] Input: Converted standard Japanese text data.

[0559] Output: Text data wrapped in an HTTP response and sent to the device.

[0560] Step 6:

[0561] Displaying the conversion results

[0562] The user device and the delivery person / store device analyze the received HTTP response and extract the converted standard Japanese text data. The user device displays the converted text to the user, and the delivery person / store device displays it to each employee. Specifically, the application's text view displays "Thank you. I'd like one yakiniku set meal, please."

[0563] Input: HTTP response containing the converted standard Japanese text data.

[0564] Output: The converted text displayed on the application screen.

[0565] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0566] This invention relates to a system that naturally converts between regional dialects and standard Japanese, and also combines it with an emotion engine that recognizes the user's emotions. This system consists of a series of processes that use a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine to identify and convert text data and perform appropriate conversion according to the emotion.

[0567] Program processing

[0568] Accepting input from the user

[0569] The user inputs text in a dialect or standard Japanese into the user terminal. This text can be a regional dialect such as Kansai dialect, such as "It's a nice day today," or standard Japanese, such as "It's a nice day today." By entering text into the input field and pressing the conversion button, the user terminal acquires this text data.

[0570] Sending Input

[0571] The user terminal transmits the input text data to the server. Specifically, it generates an HTTP request and transmits the request to the server together with the text data.

[0572] Language and Emotion Recognition

[0573] The server analyzes the received HTTP request and extracts the text data. It uses a natural language processing model to identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by the natural language processing model. At the same time, it uses an emotion engine to recognize the emotion of the text data. For example, the emotion engine recognizes positive emotion (joy) for "It's a nice day today."

[0574] Conversion process

[0575] The server selects an appropriate conversion model based on the recognition results. In this case, a model that converts Kansai dialect to standard Japanese is used. Furthermore, based on the recognition results of the emotion engine, the conversion is performed taking into account emotional information. For example, when the input text "It's a nice day today" is converted to "It's a nice day today," the conversion is adjusted to maintain a positive emotion.

[0576] Sending the conversion results

[0577] The server generates an HTTP response including the converted text data and sends it to the user terminal. At this time, the response includes the converted text and emotion information.

[0578] Displaying the results

[0579] The user device analyzes the received HTTP response and extracts the converted text data. It also acquires the emotion information and finally displays it on the screen along with the conversion result. The user can check the converted text and the result with the emotion information added.

[0580] Specific examples

[0581] A specific example of use is as follows:

[0582] 1. User operations

[0583] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[0584] 2. Terminal Processing

[0585] The terminal transmits the input text data to the server.

[0586] 3. Server Processing

[0587] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[0588] At the same time, it uses an emotion engine to recognize emotions as positive.

[0589] The server converts the text data into standard Japanese, "It's nice weather today."

[0590] Positive emotional information is added to generate converted text data.

[0591] The converted text data and emotion information are sent to the user terminal.

[0592] 4. Displaying the terminal

[0593] The device displays the conversion result, "It's nice weather today," as positive emotional information to the user.

[0594] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, and then adds emotional information to achieve richer communication.

[0595] The processing flow will be explained below.

[0596] Step 1:

[0597] The user inputs text in a dialect or standard language into the input field. The user terminal acquires the input text data and waits for the user to press the conversion button.

[0598] Step 2:

[0599] When the user presses the convert button, the device generates an HTTP request to send the text data to the server. Specifically, it sends a POST request to the server containing the text data to the URL endpoint / convert.

[0600] Step 3:

[0601] The server analyzes the received HTTP request and extracts the text data. At this time, it verifies whether the character encoding and format are correct, and passes the correctly extracted text on to the next process.

[0602] Step 4:

[0603] The server uses a natural language processing (NLP) model to identify whether the text is in a dialect or standard Japanese. Specifically, it uses a pre-trained NLP model to identify the linguistic form of the text data. For example, the text "It's a nice day today" is identified as Kansai dialect.

[0604] Step 5:

[0605] The server uses an emotion engine to recognize emotions in input text data, for example, recognizing positive emotions (joy) from the text "What a nice day today."

[0606] Step 6:

[0607] The server selects an appropriate conversion model based on the classification results. In this case, it selects a model that converts Kansai dialect to standard Japanese, and further considers the recognized emotion when converting.

[0608] Step 7:

[0609] The server converts the text data using the selected conversion model, for example, converting "It's a nice day today" to "It's a nice day today," and adds positive sentiment information to the converted text.

[0610] Step 8:

[0611] The server generates an HTTP response including the converted text data and emotion information, and sends it to the user terminal. The response includes the converted text and emotion information.

[0612] Step 9:

[0613] The device analyzes the received HTTP response, extracts the converted text data and emotion information, and prepares to display them on the screen based on the response format.

[0614] Step 10:

[0615] The device displays the converted text data and the emotion information on the screen and provides feedback to the user. For example, the conversion result "It's nice weather today (positive)" and the emotion information are displayed on the screen.

[0616] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, and then adds emotional information to achieve richer communication.

[0617] Example 2

[0618] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0619] In today's world, deepening mutual understanding between regional dialects and standard Japanese is important, but accurately conveying subtle emotional nuances in these languages ​​is difficult. Furthermore, conventional technologies for converting between dialects and standard Japanese have difficulty taking emotional information into account, resulting in a decline in the quality of communication. Furthermore, even when natural language processing technology is used, the recognition and reflection of emotional information is insufficient, making it impossible to accurately understand and convey the user's intentions. Therefore, the present invention aims to solve these problems by providing a system that appropriately recognizes and reflects emotional information when converting between dialects and standard Japanese.

[0620] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0621] In this invention, the server includes means for analyzing received text data and determining whether it is a dialect or standard language, means for applying a language conversion model to convert the dialect into standard language or convert standard language into the dialect based on the determination result, and means for recognizing emotions in the text data and reflecting them in the conversion result. This allows text entered by a user to be accurately converted into dialect or standard language and transmitted while retaining the emotional nuances.

[0622] An "information processing device" is a device that allows a user to input text data and has the function of processing and communicating the input data.

[0623] A "communication device" is a device that includes hardware and software for transmitting and receiving data between an information processing device and a server.

[0624] "Analysis" refers to the process of understanding the content of input text data and determining whether it is a dialect or standard language.

[0625] A "language conversion model" is an algorithm that converts between dialects and standard Japanese based on a specific regional language database.

[0626] An "emotion engine" is an algorithm that recognizes emotional information contained in text data and outputs that information.

[0627] A "generative AI model" is an algorithm that uses machine learning technology to perform natural language processing and emotion recognition.

[0628] A "natural language processing model" is an algorithm that includes techniques for computers to understand and manipulate human language.

[0629] A "regional language database" is a dataset that collects examples of dialects and standard languages ​​in a specific region and learns the correspondences between them.

[0630] An "HTTP request" is a protocol for sending data from a client to a server, and is a message format for requesting and sending data.

[0631] The "JSON format" is a lightweight data exchange format for structuring and expressing data, and is a text format that is easy to read for both humans and machines.

[0632] MODE FOR CARRYING OUT THE INVENTION

[0633] This invention relates to a system that naturally converts between regional dialects and standard Japanese, and also combines it with an emotion engine that recognizes the user's emotions. This system consists of a series of processes that use a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine to identify and convert text data and perform appropriate conversion according to the emotion.

[0634] Hardware and Software Use

[0635] The user terminal functions as an input device for users to input text in dialect or standard Japanese. Specifically, this includes information processing devices such as PCs, smartphones, and tablets. When a user inputs text into an input field and presses the conversion button, the user terminal temporarily stores the text data in memory and prepares to proceed to the next processing step.

[0636] The terminal includes the text data entered by the user in an HTTP request and sends it to the server. The communication device used for this purpose has the function of providing a network connection. It generates an HTTP request and sends the text data to the server's endpoint using the POST method.

[0637] The server processes the received HTTP request and extracts the text data. Using a natural language processing model (such as GPT-3 or BERT), the server identifies whether the text is in a dialect or standard Japanese. At the same time, it uses an emotion engine to recognize the emotion of the text data. For example, it recognizes that the text "What a nice day today" is in the Kansai dialect and contains positive emotion (joy).

[0638] Based on the results of the classification, the server applies a language conversion model trained using a specific regional language database to convert dialects to standard Japanese or vice versa. The server also takes into account the recognition results of the emotion engine, preserving emotional information during the conversion. For example, "It's a nice day today" is converted to "It's a nice day today."

[0639] The server generates an HTTP response containing the converted text data and emotion information, and sends it to the user's device.

[0640] The terminal analyzes the received HTTP response, extracts the converted text data and emotion information, and displays the converted text data and emotion information in a specific area of ​​the user interface, allowing the user to check the converted text and emotion information.

[0641] Specific examples

[0642] Specific usage examples are:

[0643] User operations

[0644] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[0645] Terminal handling

[0646] The device creates a JSON containing the input text data "It's nice weather today" and sends an HTTP POST request to the server.

[0647] Server Processing

[0648] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[0649] At the same time, it uses an emotion engine to recognize emotions as positive.

[0650] The server converts the text data into standard Japanese, such as "It's nice weather today," and adds positive emotional information.

[0651] The converted text data and emotion information are sent to the user terminal.

[0652] Terminal display

[0653] The device displays the conversion result, "It's nice weather today," as positive emotional information to the user.

[0654] This allows the system to convert text entered by the user between dialect and standard Japanese, and by adding emotional information, it is possible to achieve richer communication.

[0655] Prompt Sentence Examples

[0656] Example of Kansai dialect input text: "It's a nice day today."

[0657] Standard Japanese conversion example: "It's a nice day today."

[0658] Emotional information: Positive (joy)

[0659] As described above, the embodiments of the present invention provide a system that accurately converts text data entered by a user between dialect and standard Japanese, while preserving emotional nuances.

[0660] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0661] Step 1: Accepting input from the user

[0662] The user enters text data into the input field on the user terminal and presses the conversion button. Specifically, the following process is performed:

[0663] Get text data from the input field.

[0664] The text data is temporarily stored in memory in preparation for the next step.

[0665] Input: "What a nice day today" (Kansai dialect)

[0666] Output: Text data is stored in memory.

[0667] Step 2: Sending Input

[0668] The device generates an HTTP request containing the retrieved text data and sends it to the server. The specific operation is as follows:

[0669] Make an HTTP request using the POST method.

[0670] Add text data in JSON format to the request body.

[0671] Sends a request to the server at the specified endpoint.

[0672] Input: "What a nice day today" (text data stored in memory)

[0673] Output: An HTTP request containing text data is sent to the server.

[0674] Step 3: Language and emotion recognition

[0675] The server processes the received HTTP request and extracts the text data. Specifically, it does the following:

[0676] Parse the JSON data from the body of the HTTP request and extract the text data.

[0677] Use a natural language processing model (e.g., a generative AI model) to identify whether the text data is a dialect or standard language.

[0678] At the same time, an emotion engine is used to recognize emotions in the text data.

[0679] Input: "What a nice day today" (text data extracted from an HTTP request)

[0680] Output: Linguistic form (Kansai dialect) and emotional information (positive) are identified.

[0681] Step 4: Conversion process

[0682] The server then applies the appropriate language transformation model to convert the text based on the identified language form. The specific operations are as follows:

[0683] Select a model that converts Kansai dialect to standard Japanese.

[0684] Based on the results of the emotion engine, the text is appropriately converted while retaining emotional information.

[0685] Input: Language form (Kansai dialect) and emotional information (positive)

[0686] Output: Converted standard Japanese text "It's a nice day today" and emotional information (positive)

[0687] Step 5: Send the conversion results

[0688] The server generates an HTTP response containing the converted text data and emotion information, and sends it to the user's device. The specific operation is as follows:

[0689] The converted text data and emotion information are combined into a single JSON object.

[0690] Set the above JSON object in the body of the HTTP response.

[0691] An HTTP response is sent to the user terminal.

[0692] Input: Converted text "It's a nice day today" and emotional information (positive)

[0693] Output: JSON data is sent to the user device as an HTTP response.

[0694] Step 6: View the results

[0695] The device analyzes the received HTTP response and extracts the converted text data and emotion information. The specific operation is as follows:

[0696] Parse JSON data from an HTTP response.

[0697] The converted text data and emotional information are extracted and stored in separate variables.

[0698] The converted text data "It's a nice day today" and emotional information (positive) are displayed on the user interface.

[0699] Input: HTTP response (JSON data) received from the server

[0700] Output: The converted text data "It's a nice day today" and emotional information (positive) are displayed on the user's device screen.

[0701] (Application example 2)

[0702] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0703] While conventional text conversion systems can convert between dialects and standard Japanese, they are unable to take into account the user's emotional information, which means they are unable to properly convey the emotional nuances of the text. Furthermore, even in advertisements or customer service messages that utilize regional dialects, conversion that does not take emotional information into account makes it difficult to achieve effective communication. This poses a challenge, as it makes it difficult to increase the impact of advertisements or enhance relationships with customers.

[0704] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0705] In this invention, the server includes means for identifying input text data and determining whether it is a dialect or standard language, means for converting the dialect into standard language or converting the standard language into a dialect based on the identification result and emotional information, and further adjusting the language to correspond to the emotion, and means for transmitting the converted text data and emotional information to the user terminal. This allows the user's emotional information to be appropriately reflected in the text conversion, making it possible to generate more effective advertisements and customer service messages.

[0706] A "dialect" or "standard language" is a unique language form used in a particular region or cultural area within Japan, and has characteristics that differ from the general national language.

[0707] "Emotional information" refers to the emotional nuances and attitudes contained in the text entered by the user, and is information that includes emotional states such as positive, negative, and neutral.

[0708] A "user terminal" is a device on which a user inputs text and checks the converted text result, and includes a smartphone, tablet, PC, etc.

[0709] The "server" is a centralized management system that receives and processes text data sent from user terminals, and is the device that performs text conversion and emotion recognition processing.

[0710] A "natural language processing model" is an artificial intelligence model that analyzes input text data and identifies its linguistic form, and is a technology for understanding and classifying the content of the text.

[0711] An "emotion engine" is a technology for recognizing emotional information contained in text data, and is a model for analyzing the emotional nuances of text and evaluating emotional states.

[0712] A "language conversion model" is an algorithm that uses a specific regional language database to learn the correspondence between dialects and standard Japanese and convert between the two.

[0713] "Converted text data" refers to new text obtained by subjecting input text to a specified conversion process, and is the data resulting from conversion from standard Japanese to a dialect, or from a dialect to standard Japanese.

[0714] A "regional language database" is a database that compiles variations of dialects and standard Japanese used in various regions of Japan, and is a collection of data used to train language conversion models.

[0715] The "emotion database" is a database that classifies and organizes emotional information accompanying text data, and is a source of information to support the learning and evaluation of the emotion engine.

[0716] A specific embodiment for carrying out the present invention will now be described. The present invention is realized using a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine. The operation and interaction of each element will be described below.

[0717] User terminal

[0718] First, the user inputs text in a dialect or standard Japanese using a user terminal. User terminals include smartphones, tablets, and PCs. The user inputs text into an input field and confirms the input text by pressing the conversion button. The input text at this stage is then sent to the server.

[0719] server

[0720] The server receives input text data sent from the user's device. Specifically, it receives text data via an HTTP request. The server analyzes the received text data and uses a natural language processing model to identify whether the data is written in a dialect or standard Japanese. It also uses an emotion engine to simultaneously recognize the emotional information contained in the text data.

[0721] Natural language processing model and emotion engine

[0722] The natural language processing model uses Hugging Face's "transformers" library to analyze text data and identify linguistic forms, while the emotion engine uses Hugging Face's sentiment analysis pipeline to analyze the emotional state contained in the text.

[0723] Language Transformation Model

[0724] A language transformation model is then used to convert the text from dialect to standard or vice versa. This model uses a specific regional language database to transform the text according to the regional linguistic form, and is adjusted to preserve emotional information by taking into account the output of the emotion engine.

[0725] Return to user terminal

[0726] The converted text data and emotion information are then sent back to the user device as an HTTP response by the server. The user device receives this and displays the converted text and emotion information on the screen. This allows the user to check the conversion results and manually correct them if necessary.

[0727] Examples of concrete examples and prompts

[0728] For example, consider the case where a user inputs the standard Japanese text "The release of a new product has been decided. Please look forward to it!". The server receives this text and converts it into Kansai dialect, such as "It's a nice day today," and reflects the output of the emotion engine to maintain a positive emotion. As a result, the user device displays "The release of a new product has been decided. Please look forward to it!".

[0729] An example of a prompt sentence would be, "Please convert the following text into the local dialect and recognize the emotion: We've decided to launch a new product. Look forward to it!" By inputting this into the generative AI model, appropriate text conversion and emotion recognition can be performed.

[0730] In this way, this system realizes mutual conversion between dialects and standard Japanese and retains emotional information, enabling effective and emotionally rich communication, particularly in advertising and customer service messages.

[0731] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0732] Step 1:

[0733] A user inputs text in a dialect or standard Japanese into a user terminal. The user inputs text into an input field and confirms the input text by pressing the conversion button. In this case, the input text is a dialect such as "It's a nice day today" or standard Japanese such as "It's a nice day today."

[0734] Step 2:

[0735] The user terminal sends the entered text data to the server. Specifically, it generates an HTTP request and sends it to the server including the text data. The input at this time is the text data entered by the user, and the output is the data to be sent to the server.

[0736] Step 3:

[0737] The server analyzes the received HTTP request and extracts the text data. The analyzed text data is input into a natural language processing model to identify the language form. For example, "It's nice weather today" is identified as Kansai dialect. At the same time, an emotion engine is used to recognize the emotion of the text data. For example, for "It's nice weather today," the emotion engine recognizes a positive emotion (joy).

[0738] Step 4:

[0739] The server selects an appropriate language conversion model based on the identification results. The inputs are the identification results and emotion information, and the output is the selected conversion model. For example, using a model that converts Kansai dialect into standard Japanese, "Kyo wa ii tenki ya na" (It's a nice day today) is converted to "Kyo wa ii tenki da ne" (It's a nice day today). At the same time, the conversion is performed in a way that preserves positive emotion information based on the output of the emotion engine.

[0740] Step 5:

[0741] The server generates an HTTP response including the converted text data and emotion information, and sends it to the user terminal. The input at this time is the converted text data and emotion information, and the output is the data sent to the user terminal.

[0742] Step 6:

[0743] The user device analyzes the received HTTP response and extracts the converted text data and emotional information. The conversion results and emotional information are then displayed on the screen, allowing the user to check the converted text and emotional information. The input in this case is the response data from the server, and the output is the data displayed on the screen.

[0744] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0745] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0746] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0747] [Third embodiment]

[0748] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0749] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0750] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0751] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0752] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0753] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0754] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0755] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0756] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0757] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0758] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0759] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0760] The present invention relates to a system for naturally converting between regional dialects and standard Japanese. The system consists of a user terminal, a server, and a series of processes that use natural language processing to identify and convert text data.

[0761] Program processing

[0762] Accepting input from the user

[0763] The user inputs text in a dialect or standard Japanese into the user terminal. This text can be a regional dialect such as Kansai dialect, such as "It's a nice day today," or standard Japanese, such as "It's a nice day today." By entering text into the input field and pressing the conversion button, the user terminal acquires this text data.

[0764] Sending Input

[0765] The user terminal transmits the input text data to the server. Specifically, it generates an HTTP request and transmits the request to the server together with the text data.

[0766] Language Identification

[0767] The server analyzes the received HTTP request and extracts the text data. It then uses a natural language processing model to automatically identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by the natural language processing model.

[0768] Conversion process

[0769] The server selects an appropriate conversion model based on the recognition results. Here, a model that converts Kansai dialect to standard Japanese is used. For example, "It's a nice day today" is converted to "It's a nice day today." Conversely, conversion from standard Japanese to a dialect is also possible, for example, "It's a nice day today" is converted to "It's a nice day today."

[0770] Sending the conversion results

[0771] The server generates an HTTP response including the converted text data and sends it to the user terminal. At this time, the response includes the converted text.

[0772] Displaying the results

[0773] The user device analyzes the received HTTP response and extracts the converted text data. Finally, the user device displays the conversion result on the screen and provides feedback to the user. For example, the conversion result "It's nice weather today" is displayed.

[0774] Specific examples

[0775] A specific example of use is as follows:

[0776] 1. User operations

[0777] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[0778] 2. Terminal Processing

[0779] The terminal transmits the input text data to the server.

[0780] 3. Server Processing

[0781] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[0782] The server converts the text data into standard Japanese, "It's nice weather today."

[0783] The converted text data is sent to the user terminal.

[0784] 4. Displaying the terminal

[0785] The terminal displays the conversion result "It's a nice day today" to the user.

[0786] In this way, this system achieves smooth communication by converting between dialects and standard Japanese while preserving the distinctive characteristics of the region. This system can be used in a variety of fields, including business, education, and tourism, and will help promote communication both within and outside the region.

[0787] The processing flow will be explained below.

[0788] Step 1:

[0789] The user inputs text in a dialect or standard language into the input field. The user terminal acquires the input text data and waits for the user to press the conversion button.

[0790] Step 2:

[0791] When the user presses the convert button, the device generates an HTTP request to send the text data to the server. Specifically, it sends a POST request to the server containing the text data to the URL endpoint / convert.

[0792] Step 3:

[0793] The server analyzes the received HTTP request and extracts the text data. At this time, it verifies whether the character encoding and format are correct, and passes the correctly extracted text on to the next process.

[0794] Step 4:

[0795] The server uses a natural language processing (NLP) model to identify whether the input text is a dialect or standard language. Specifically, the server inputs the text data into a pre-trained NLP model to identify the most probabilistic type of language form.

[0796] Step 5:

[0797] The server selects an appropriate conversion model based on the recognition result. For example, if the recognition result is Kansai dialect, it selects a model that converts Kansai dialect to standard Japanese. Conversely, if the recognition result is standard Japanese, it selects a model that converts it to the specified dialect.

[0798] Step 6:

[0799] The server converts the text data using the selected conversion model. Specifically, the text data is input into the conversion model and the converted text is obtained. For example, "It's a nice day today" is converted to "It's a nice day today."

[0800] Step 7:

[0801] The server generates an HTTP response containing the converted text data and sends it to the user terminal. The response contains the converted text.

[0802] Step 8:

[0803] The terminal analyzes the received HTTP response, extracts the converted text data, and prepares to display the converted text on the screen based on the response format.

[0804] Step 9:

[0805] The terminal displays the converted text data on the screen and provides feedback to the user. The user can check whether the conversion result is correct. For example, the conversion result "It's a nice day today" is displayed on the screen.

[0806] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, enabling smooth communication.

[0807] Example 1

[0808] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0809] In today's information society, the ability to convert between regional dialects and standard Japanese is crucial for smooth communication, especially between regions. However, existing systems rarely perform this conversion naturally, often losing the nuances and subtle meanings of dialects. Another issue is the lack of systems that can convert text entered by users in real time and provide appropriate feedback.

[0810] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0811] In this invention, the server includes means for analyzing received text data and identifying whether it is a dialect or standard language, means for selecting an appropriate language conversion model based on the identification result and converting the dialect into standard language or converting standard language into a dialect, and means for generating the converted text data as an HTTP response and sending it to the user terminal. This enables natural mutual conversion of text data and immediate feedback.

[0812] "User" refers to a person who uses the system to input text in dialect or standard Japanese and performs a series of operations to convert between them.

[0813] "Terminal" refers to a device used by a user to input and display text data, including computers, smartphones, tablets, etc.

[0814] "Server" refers to a computer system that receives data sent from a terminal, analyzes, converts, and returns the results.

[0815] "Text data" refers to character string information that a user inputs into a terminal. The input text data includes dialects and standard Japanese.

[0816] "HTTP request" refers to the protocol and request message format used when a user terminal sends data to a server.

[0817] "HTTP response" refers to the protocol and response message format used when the server sends the conversion result and other data to the user terminal.

[0818] "Natural language processing model" refers to a machine learning model that analyzes text data and identifies and converts dialects and standard Japanese. Examples include BERT and GPT-3.

[0819] "Language conversion model" refers to a machine learning model used to convert text data between a specific dialect and standard Japanese.

[0820] "Parsing" refers to a series of computations performed to identify received text data.

[0821] "Conversion" refers to the process of changing text data into a specified format (dialect or standard language).

[0822] "Display" refers to the process in which the terminal displays the conversion result on the screen to provide it to the user.

[0823] The present invention relates to a system for naturally converting between regional dialects and standard Japanese. The system consists of a user terminal, a server, and a series of processes that use natural language processing to identify and convert text data.

[0824] User terminal

[0825] A user uses a terminal to input text and request conversion into the system. The terminal is a network-connected device such as a smartphone, computer, or tablet. This terminal acquires the text input by the user and sends it to the server when the user presses the conversion button. The input text can be a dialect such as "It's a nice day today" or standard Japanese such as "It's a nice day today."

[0826] server

[0827] The server receives text data sent from the user device and analyzes and converts it. Specifically, the server analyzes the HTTP request and extracts the text data. Next, it uses a natural language processing model to automatically identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by a natural language processing model (e.g., BERT, GPT-3).

[0828] Language Transformation Model

[0829] The server selects an appropriate language conversion model based on the identified language, and uses a model to convert dialects to standard Japanese and vice versa. For example, when converting from Kansai dialect to standard Japanese, "Kyo wa ii tenki ya naa" (It's a nice day today) is converted to "Kyo wa ii tenki da ne" (It's a nice day today). Conversely, conversion from standard Japanese to dialect is also possible, for example, "Kyo wa ii tenki da ne" (It's a nice day today) is converted to "Kyo wa ii tenki ya naa" (It's a nice day today).

[0830] Sending and displaying conversion results

[0831] The server generates an HTTP response containing the converted text data and sends it to the user's device. The device then analyzes the received HTTP response and extracts the converted text data. Finally, the device displays the conversion result on the screen and provides feedback to the user. For example, the conversion result might read, "It's nice weather today."

[0832] Specific examples

[0833] A specific example of how this system can be used is as follows:

[0834] 1. User operations

[0835] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[0836] 2. Terminal Processing

[0837] The terminal transmits the input text data to the server.

[0838] 3. Server Processing

[0839] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[0840] The server converts the text data into standard Japanese, "It's nice weather today."

[0841] The converted text data is sent to the user terminal.

[0842] 4. Displaying the terminal

[0843] The terminal displays the conversion result "It's a nice day today" to the user.

[0844] Through this example, the system can quickly and naturally convert text data entered by the user between dialect and standard Japanese, promoting communication between regions and enabling smooth information exchange.

[0845] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0846] Step 1: User enters text and presses the convert button

[0847] The user enters text in a dialect or standard language into the input field of the terminal. For example, this input is "It's a nice day today." When the user presses the conversion button, the terminal acquires the text data. The input here is the text entered by the user, and the output is the text data acquired by the terminal.

[0848] Step 2: The device sends the text data to the server

[0849] The device generates an HTTP request containing the retrieved text data and sends it to the server. Specifically, it uses the JavaScript fetch API to send a request to the appropriate endpoint. The input is the retrieved text data, and the output is the HTTP request sent to the server.

[0850] Step 3: The server analyzes the text data and identifies dialects or standard languages.

[0851] The server receives an HTTP request and extracts the text data. It then uses a natural language processing model to identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect. The input is the text data received by the server, and the output is the identification result of dialect or standard Japanese.

[0852] Step 4: The server selects the appropriate language translation model and translates the text.

[0853] The server selects an appropriate conversion model based on the classification results. Using a model that converts Kansai dialect to standard Japanese, it converts "Kyo wa ii tenki yana" to "Kyo wa ii tenki da ne." The input is the classification result of dialect or standard Japanese, and the output is the converted text data.

[0854] Step 5: The server sends the converted text data to the device.

[0855] The server generates an HTTP response containing the converted text data and sends it to the terminal. This response is in JSON format. The input is the converted text data, and the output is the HTTP response sent to the user terminal.

[0856] Step 6: The terminal parses the HTTP response and displays the conversion result

[0857] The terminal analyzes the received HTTP response and extracts the converted text data. Finally, the terminal displays the converted result on the screen. For example, the converted result "It's nice weather today" is displayed to the user. The input is the HTTP response received from the server, and the output is the converted result that the terminal displays on the screen.

[0858] (Application example 1)

[0859] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0860] Food delivery services face the challenge of making it difficult for delivery staff and restaurants to accurately understand the orders of users who speak regional dialects and respond quickly and smoothly. There is also a need for an appropriate method to promote communication without compromising regional characteristics.

[0861] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0862] In this invention, the server includes terminal means for inputting text in a dialect or standard language, transmission means for transmitting the input text data to the server, identification means for identifying the received text data and determining whether it is a dialect or standard language, conversion means for converting the dialect into standard language or converting standard language into a dialect based on the identification result, transmission means for transmitting the converted text data to the terminal means, display means for displaying the converted text data on the terminal means, and display means for displaying the converted text data as food delivery order information to delivery personnel and stores. This enables accurate and smooth communication between users who speak a local dialect and delivery personnel and stores who speak standard language.

[0863] "Terminal means" refers to a device that allows a user to input text in dialect or standard Japanese and display it.

[0864] The "transmission means" is a function for transmitting input text data to a server.

[0865] The "identification means" is a function for analyzing received text data and determining whether it is a dialect or standard language.

[0866] The "conversion means" is a function for converting dialects into standard language or converting standard language into dialects based on the identification results.

[0867] The "display means" is a function for displaying the converted text data on a user terminal, a delivery person, or in a store.

[0868] "Food delivery" refers to the delivery of meals and beverages to customers through a delivery service.

[0869] A "natural language processing model" is an algorithm or model used to identify the linguistic form of text data and perform any necessary transformations.

[0870] A "regional language database" is a database for learning and storing the correspondence between dialects and standard Japanese in a specific region.

[0871] This invention is a system that naturally converts text between dialects and standard Japanese, and is particularly applicable to food delivery services. This system is designed so that delivery staff and stores can accurately understand and respond even if the user uses a dialect. Below is a concrete example of how this system can be implemented.

[0872] System Configuration

[0873] This system mainly consists of the following hardware and software:

[0874] User device: Smartphone, tablet, etc.

[0875] Server: The back-end system that handles the calculations.

[0876] Natural language processing models: Algorithms for identifying linguistic forms in text data (e.g., BERT and GPT-3).

[0877] Regional Language Database: A database that learns the correspondence between dialects and standard Japanese.

[0878] Front-end application: An app that provides the user interface (e.g., an iOS or Android app).

[0879] Program processing explanation

[0880] User Interface

[0881] When a user places a food delivery order, they input text written in a dialect, such as "It's a nice day today, can I have one katsudon please?" This input text is sent from the device to the server.

[0882] Server Processing

[0883] The server analyzes the received text data and uses a natural language processing model (e.g., HuggingFace's BERT or GPT-3) to identify whether the text is in a dialect or standard Japanese. At this stage, the text is identified as Kansai dialect, such as "What a nice day today, can I have a katsudon please?"

[0884] After identification, the server refers to a regional language database and converts the dialect into standard Japanese. For example, the Kansai dialect "It's a nice day today, so I'll have one katsudon please" is converted to "It's a nice day today. I'll have one katsudon please." This allows delivery personnel and stores to accurately understand the order.

[0885] Displaying the results

[0886] The converted text data is then sent from the server to the user's device, the delivery person's device, and the store's device. Each device displays the converted text in standard Japanese. This converts the dialect entered by the user into standard Japanese, allowing the delivery person and store to respond accurately.

[0887] Examples and prompts

[0888] As a specific example, the following flow can be considered.

[0889] 1. User operation: The user enters "Thank you, I'd like one yakiniku set meal" and presses the order button.

[0890] 2. Server processing: The text is sent to the server, which converts it to "Thank you. I'd like one yakiniku set meal, please."

[0891] 3. Displaying the results: The app displays the conversion results and communicates the order details in standard Japanese to the delivery person or store.

[0892] Example prompt sentence:

[0893] User input: Thank you, I'll have a yakiniku set meal.

[0894] Model prompt: dialect -> standard Japanese

[0895] Translated: Thank you. I'd like one yakiniku set meal, please.

[0896] This series of processes enables accurate and smooth communication between users who speak local dialects and delivery people and stores who speak standard Japanese.

[0897] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0898] Step 1:

[0899] User Input

[0900] The user opens the application on the terminal, enters the order text in the dialect into the text input field, and presses the send button. This becomes the input data.

[0901] Input: The dialect text entered by the user.

[0902] Output: The device prepares this text to be sent.

[0903] Step 2:

[0904] Sending input data

[0905] The terminal sends the text data entered by the user to the server as an HTTP request. Specifically, it generates a POST request and sends a payload including the text data to the server.

[0906] Input: Dialect text data entered by the user.

[0907] Output: Text data wrapped in an HTTP request is sent to the server.

[0908] Step 3:

[0909] Receiving and analyzing text data

[0910] The server parses the received HTTP request and extracts text data, which is then analyzed using a natural language processing model (e.g., HuggingFace's BERT) to identify dialects and standard Japanese.

[0911] Input: Text data contained in the payload of the HTTP request.

[0912] Output: Identification of the text as dialect or standard.

[0913] Step 4:

[0914] Language Conversion

[0915] Based on the classification results, the server selects an appropriate conversion model (e.g., GPT-3) and converts the text data. Specifically, it converts the dialect "Thank you very much, I'd like a yakiniku set meal please" into standard Japanese "Thank you. I'd like a yakiniku set meal please."

[0916] Input: Dialect text data and its classification results.

[0917] Output: Converted standard Japanese text data.

[0918] Step 5:

[0919] Sending the conversion results

[0920] The server generates an HTTP response containing the converted text data and sends it to the user's device, the delivery person's device, and the store's device. Specifically, the HTTP response payload includes the converted text.

[0921] Input: Converted standard Japanese text data.

[0922] Output: Text data wrapped in an HTTP response and sent to the device.

[0923] Step 6:

[0924] Displaying the conversion results

[0925] The user device and the delivery person / store device analyze the received HTTP response and extract the converted standard Japanese text data. The user device displays the converted text to the user, and the delivery person / store device displays it to each employee. Specifically, the application's text view displays "Thank you. I'd like one yakiniku set meal, please."

[0926] Input: HTTP response containing the converted standard Japanese text data.

[0927] Output: The converted text displayed on the application screen.

[0928] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0929] This invention relates to a system that naturally converts between regional dialects and standard Japanese, and also combines it with an emotion engine that recognizes the user's emotions. This system consists of a series of processes that use a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine to identify and convert text data and perform appropriate conversion according to the emotion.

[0930] Program processing

[0931] Accepting input from the user

[0932] The user inputs text in a dialect or standard Japanese into the user terminal. This text can be a regional dialect such as Kansai dialect, such as "It's a nice day today," or standard Japanese, such as "It's a nice day today." By entering text into the input field and pressing the conversion button, the user terminal acquires this text data.

[0933] Sending Input

[0934] The user terminal transmits the input text data to the server. Specifically, it generates an HTTP request and transmits the request to the server together with the text data.

[0935] Language and Emotion Recognition

[0936] The server analyzes the received HTTP request and extracts the text data. It uses a natural language processing model to identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by the natural language processing model. At the same time, it uses an emotion engine to recognize the emotion of the text data. For example, the emotion engine recognizes positive emotion (joy) for "It's a nice day today."

[0937] Conversion process

[0938] The server selects an appropriate conversion model based on the recognition results. In this case, a model that converts Kansai dialect to standard Japanese is used. Furthermore, based on the recognition results of the emotion engine, the conversion is performed taking into account emotional information. For example, when the input text "It's a nice day today" is converted to "It's a nice day today," the conversion is adjusted to maintain a positive emotion.

[0939] Sending the conversion results

[0940] The server generates an HTTP response including the converted text data and sends it to the user terminal. At this time, the response includes the converted text and emotion information.

[0941] Displaying the results

[0942] The user device analyzes the received HTTP response and extracts the converted text data. It also acquires the emotion information and finally displays it on the screen along with the conversion result. The user can check the converted text and the result with the emotion information added.

[0943] Specific examples

[0944] A specific example of use is as follows:

[0945] 1. User operations

[0946] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[0947] 2. Terminal Processing

[0948] The terminal transmits the input text data to the server.

[0949] 3. Server Processing

[0950] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[0951] At the same time, it uses an emotion engine to recognize emotions as positive.

[0952] The server converts the text data into standard Japanese, "It's nice weather today."

[0953] Positive emotional information is added to generate converted text data.

[0954] The converted text data and emotion information are sent to the user terminal.

[0955] 4. Displaying the terminal

[0956] The device displays the conversion result, "It's nice weather today," as positive emotional information to the user.

[0957] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, and then adds emotional information to achieve richer communication.

[0958] The processing flow will be explained below.

[0959] Step 1:

[0960] The user inputs text in a dialect or standard language into the input field. The user terminal acquires the input text data and waits for the user to press the conversion button.

[0961] Step 2:

[0962] When the user presses the convert button, the device generates an HTTP request to send the text data to the server. Specifically, it sends a POST request to the server containing the text data to the URL endpoint / convert.

[0963] Step 3:

[0964] The server analyzes the received HTTP request and extracts the text data. At this time, it verifies whether the character encoding and format are correct, and passes the correctly extracted text on to the next process.

[0965] Step 4:

[0966] The server uses a natural language processing (NLP) model to identify whether the text is in a dialect or standard Japanese. Specifically, it uses a pre-trained NLP model to identify the linguistic form of the text data. For example, the text "It's a nice day today" is identified as Kansai dialect.

[0967] Step 5:

[0968] The server uses an emotion engine to recognize emotions in input text data, for example, recognizing positive emotions (joy) from the text "What a nice day today."

[0969] Step 6:

[0970] The server selects an appropriate conversion model based on the classification results. In this case, it selects a model that converts Kansai dialect to standard Japanese, and further considers the recognized emotion when converting.

[0971] Step 7:

[0972] The server converts the text data using the selected conversion model, for example, converting "It's a nice day today" to "It's a nice day today," and adds positive sentiment information to the converted text.

[0973] Step 8:

[0974] The server generates an HTTP response including the converted text data and emotion information, and sends it to the user terminal. The response includes the converted text and emotion information.

[0975] Step 9:

[0976] The device analyzes the received HTTP response, extracts the converted text data and emotion information, and prepares to display them on the screen based on the response format.

[0977] Step 10:

[0978] The device displays the converted text data and the emotion information on the screen and provides feedback to the user. For example, the conversion result "It's nice weather today (positive)" and the emotion information are displayed on the screen.

[0979] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, and then adds emotional information to achieve richer communication.

[0980] Example 2

[0981] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0982] In today's world, deepening mutual understanding between regional dialects and standard Japanese is important, but accurately conveying subtle emotional nuances in these languages ​​is difficult. Furthermore, conventional technologies for converting between dialects and standard Japanese have difficulty taking emotional information into account, resulting in a decline in the quality of communication. Furthermore, even when natural language processing technology is used, the recognition and reflection of emotional information is insufficient, making it impossible to accurately understand and convey the user's intentions. Therefore, the present invention aims to solve these problems by providing a system that appropriately recognizes and reflects emotional information when converting between dialects and standard Japanese.

[0983] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0984] In this invention, the server includes means for analyzing received text data and determining whether it is a dialect or standard language, means for applying a language conversion model to convert the dialect into standard language or convert standard language into the dialect based on the determination result, and means for recognizing emotions in the text data and reflecting them in the conversion result. This allows text entered by a user to be accurately converted into dialect or standard language and transmitted while retaining the emotional nuances.

[0985] An "information processing device" is a device that allows a user to input text data and has the function of processing and communicating the input data.

[0986] A "communication device" is a device that includes hardware and software for transmitting and receiving data between an information processing device and a server.

[0987] "Analysis" refers to the process of understanding the content of input text data and determining whether it is a dialect or standard language.

[0988] A "language conversion model" is an algorithm that converts between dialects and standard Japanese based on a specific regional language database.

[0989] An "emotion engine" is an algorithm that recognizes emotional information contained in text data and outputs that information.

[0990] A "generative AI model" is an algorithm that uses machine learning technology to perform natural language processing and emotion recognition.

[0991] A "natural language processing model" is an algorithm that includes techniques for computers to understand and manipulate human language.

[0992] A "regional language database" is a dataset that collects examples of dialects and standard languages ​​in a specific region and learns the correspondences between them.

[0993] An "HTTP request" is a protocol for sending data from a client to a server, and is a message format for requesting and sending data.

[0994] The "JSON format" is a lightweight data exchange format for structuring and expressing data, and is a text format that is easy to read for both humans and machines.

[0995] MODE FOR CARRYING OUT THE INVENTION

[0996] This invention relates to a system that naturally converts between regional dialects and standard Japanese, and also combines it with an emotion engine that recognizes the user's emotions. This system consists of a series of processes that use a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine to identify and convert text data and perform appropriate conversion according to the emotion.

[0997] Hardware and Software Use

[0998] The user terminal functions as an input device for users to input text in dialect or standard Japanese. Specifically, this includes information processing devices such as PCs, smartphones, and tablets. When a user inputs text into an input field and presses the conversion button, the user terminal temporarily stores the text data in memory and prepares to proceed to the next processing step.

[0999] The terminal includes the text data entered by the user in an HTTP request and sends it to the server. The communication device used for this purpose has the function of providing a network connection. It generates an HTTP request and sends the text data to the server's endpoint using the POST method.

[1000] The server processes the received HTTP request and extracts the text data. Using a natural language processing model (such as GPT-3 or BERT), the server identifies whether the text is in a dialect or standard Japanese. At the same time, it uses an emotion engine to recognize the emotion of the text data. For example, it recognizes that the text "What a nice day today" is in the Kansai dialect and contains positive emotion (joy).

[1001] Based on the results of the classification, the server applies a language conversion model trained using a specific regional language database to convert dialects to standard Japanese or vice versa. The server also takes into account the recognition results of the emotion engine, preserving emotional information during the conversion. For example, "It's a nice day today" is converted to "It's a nice day today."

[1002] The server generates an HTTP response containing the converted text data and emotion information, and sends it to the user's device.

[1003] The terminal analyzes the received HTTP response, extracts the converted text data and emotion information, and displays the converted text data and emotion information in a specific area of ​​the user interface, allowing the user to check the converted text and emotion information.

[1004] Specific examples

[1005] Specific usage examples are:

[1006] User operations

[1007] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[1008] Terminal handling

[1009] The device creates a JSON containing the input text data "It's nice weather today" and sends an HTTP POST request to the server.

[1010] Server Processing

[1011] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[1012] At the same time, it uses an emotion engine to recognize emotions as positive.

[1013] The server converts the text data into standard Japanese, such as "It's nice weather today," and adds positive emotional information.

[1014] The converted text data and emotion information are sent to the user terminal.

[1015] Terminal display

[1016] The device displays the conversion result, "It's nice weather today," as positive emotional information to the user.

[1017] This allows the system to convert text entered by the user between dialect and standard Japanese, and by adding emotional information, it is possible to achieve richer communication.

[1018] Prompt Sentence Examples

[1019] Example of Kansai dialect input text: "It's a nice day today."

[1020] Standard Japanese conversion example: "It's a nice day today."

[1021] Emotional information: Positive (joy)

[1022] As described above, the embodiments of the present invention provide a system that accurately converts text data entered by a user between dialect and standard Japanese, while preserving emotional nuances.

[1023] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1024] Step 1: Accepting input from the user

[1025] The user enters text data into the input field on the user terminal and presses the conversion button. Specifically, the following process is performed:

[1026] Get text data from the input field.

[1027] The text data is temporarily stored in memory in preparation for the next step.

[1028] Input: "What a nice day today" (Kansai dialect)

[1029] Output: Text data is stored in memory.

[1030] Step 2: Sending Input

[1031] The device generates an HTTP request containing the retrieved text data and sends it to the server. The specific operation is as follows:

[1032] Make an HTTP request using the POST method.

[1033] Add text data in JSON format to the request body.

[1034] Sends a request to the server at the specified endpoint.

[1035] Input: "What a nice day today" (text data stored in memory)

[1036] Output: An HTTP request containing text data is sent to the server.

[1037] Step 3: Language and emotion recognition

[1038] The server processes the received HTTP request and extracts the text data. Specifically, it does the following:

[1039] Parse the JSON data from the body of the HTTP request and extract the text data.

[1040] Use a natural language processing model (e.g., a generative AI model) to identify whether the text data is a dialect or standard language.

[1041] At the same time, an emotion engine is used to recognize emotions in the text data.

[1042] Input: "What a nice day today" (text data extracted from an HTTP request)

[1043] Output: Linguistic form (Kansai dialect) and emotional information (positive) are identified.

[1044] Step 4: Conversion process

[1045] The server then applies the appropriate language transformation model to convert the text based on the identified language form. The specific operations are as follows:

[1046] Select a model that converts Kansai dialect to standard Japanese.

[1047] Based on the results of the emotion engine, the text is appropriately converted while retaining emotional information.

[1048] Input: Language form (Kansai dialect) and emotional information (positive)

[1049] Output: Converted standard Japanese text "It's a nice day today" and emotional information (positive)

[1050] Step 5: Send the conversion results

[1051] The server generates an HTTP response containing the converted text data and emotion information, and sends it to the user's device. The specific operation is as follows:

[1052] The converted text data and emotion information are combined into a single JSON object.

[1053] Set the above JSON object in the body of the HTTP response.

[1054] An HTTP response is sent to the user terminal.

[1055] Input: Converted text "It's a nice day today" and emotional information (positive)

[1056] Output: JSON data is sent to the user device as an HTTP response.

[1057] Step 6: View the results

[1058] The device analyzes the received HTTP response and extracts the converted text data and emotion information. The specific operation is as follows:

[1059] Parse JSON data from an HTTP response.

[1060] The converted text data and emotional information are extracted and stored in separate variables.

[1061] The converted text data "It's a nice day today" and emotional information (positive) are displayed on the user interface.

[1062] Input: HTTP response (JSON data) received from the server

[1063] Output: The converted text data "It's a nice day today" and emotional information (positive) are displayed on the user's device screen.

[1064] (Application example 2)

[1065] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1066] While conventional text conversion systems can convert between dialects and standard Japanese, they are unable to take into account the user's emotional information, which means they are unable to properly convey the emotional nuances of the text. Furthermore, even in advertisements or customer service messages that utilize regional dialects, conversion that does not take emotional information into account makes it difficult to achieve effective communication. This poses a challenge, as it makes it difficult to increase the impact of advertisements or enhance relationships with customers.

[1067] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1068] In this invention, the server includes means for identifying input text data and determining whether it is a dialect or standard language, means for converting the dialect into standard language or converting the standard language into a dialect based on the identification result and emotional information, and further adjusting the language to correspond to the emotion, and means for transmitting the converted text data and emotional information to the user terminal. This allows the user's emotional information to be appropriately reflected in the text conversion, making it possible to generate more effective advertisements and customer service messages.

[1069] A "dialect" or "standard language" is a unique language form used in a particular region or cultural area within Japan, and has characteristics that differ from the general national language.

[1070] "Emotional information" refers to the emotional nuances and attitudes contained in the text entered by the user, and is information that includes emotional states such as positive, negative, and neutral.

[1071] A "user terminal" is a device on which a user inputs text and checks the converted text result, and includes a smartphone, tablet, PC, etc.

[1072] The "server" is a centralized management system that receives and processes text data sent from user terminals, and is the device that performs text conversion and emotion recognition processing.

[1073] A "natural language processing model" is an artificial intelligence model that analyzes input text data and identifies its linguistic form, and is a technology for understanding and classifying the content of the text.

[1074] An "emotion engine" is a technology for recognizing emotional information contained in text data, and is a model for analyzing the emotional nuances of text and evaluating emotional states.

[1075] A "language conversion model" is an algorithm that uses a specific regional language database to learn the correspondence between dialects and standard Japanese and convert between the two.

[1076] "Converted text data" refers to new text obtained by subjecting input text to a specified conversion process, and is the data resulting from conversion from standard Japanese to a dialect, or from a dialect to standard Japanese.

[1077] A "regional language database" is a database that compiles variations of dialects and standard Japanese used in various regions of Japan, and is a collection of data used to train language conversion models.

[1078] The "emotion database" is a database that classifies and organizes emotional information accompanying text data, and is a source of information to support the learning and evaluation of the emotion engine.

[1079] A specific embodiment for carrying out the present invention will now be described. The present invention is realized using a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine. The operation and interaction of each element will be described below.

[1080] User terminal

[1081] First, the user inputs text in a dialect or standard Japanese using a user terminal. User terminals include smartphones, tablets, and PCs. The user inputs text into an input field and confirms the input text by pressing the conversion button. The input text at this stage is then sent to the server.

[1082] server

[1083] The server receives input text data sent from the user's device. Specifically, it receives text data via an HTTP request. The server analyzes the received text data and uses a natural language processing model to identify whether the data is written in a dialect or standard Japanese. It also uses an emotion engine to simultaneously recognize the emotional information contained in the text data.

[1084] Natural language processing model and emotion engine

[1085] The natural language processing model uses Hugging Face's "transformers" library to analyze text data and identify linguistic forms, while the emotion engine uses Hugging Face's sentiment analysis pipeline to analyze the emotional state contained in the text.

[1086] Language Transformation Model

[1087] A language transformation model is then used to convert the text from dialect to standard or vice versa. This model uses a specific regional language database to transform the text according to the regional linguistic form, and is adjusted to preserve emotional information by taking into account the output of the emotion engine.

[1088] Return to user terminal

[1089] The converted text data and emotion information are then sent back to the user device as an HTTP response by the server. The user device receives this and displays the converted text and emotion information on the screen. This allows the user to check the conversion results and manually correct them if necessary.

[1090] Examples of concrete examples and prompts

[1091] For example, consider the case where a user inputs the standard Japanese text "The release of a new product has been decided. Please look forward to it!". The server receives this text and converts it into Kansai dialect, such as "It's a nice day today," and reflects the output of the emotion engine to maintain a positive emotion. As a result, the user device displays "The release of a new product has been decided. Please look forward to it!".

[1092] An example of a prompt sentence would be, "Please convert the following text into the local dialect and recognize the emotion: We've decided to launch a new product. Look forward to it!" By inputting this into the generative AI model, appropriate text conversion and emotion recognition can be performed.

[1093] In this way, this system realizes mutual conversion between dialects and standard Japanese and retains emotional information, enabling effective and emotionally rich communication, particularly in advertising and customer service messages.

[1094] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1095] Step 1:

[1096] A user inputs text in a dialect or standard Japanese into a user terminal. The user inputs text into an input field and confirms the input text by pressing the conversion button. In this case, the input text is a dialect such as "It's a nice day today" or standard Japanese such as "It's a nice day today."

[1097] Step 2:

[1098] The user terminal sends the entered text data to the server. Specifically, it generates an HTTP request and sends it to the server including the text data. The input at this time is the text data entered by the user, and the output is the data to be sent to the server.

[1099] Step 3:

[1100] The server analyzes the received HTTP request and extracts the text data. The analyzed text data is input into a natural language processing model to identify the language form. For example, "It's nice weather today" is identified as Kansai dialect. At the same time, an emotion engine is used to recognize the emotion of the text data. For example, for "It's nice weather today," the emotion engine recognizes a positive emotion (joy).

[1101] Step 4:

[1102] The server selects an appropriate language conversion model based on the identification results. The inputs are the identification results and emotion information, and the output is the selected conversion model. For example, using a model that converts Kansai dialect into standard Japanese, "Kyo wa ii tenki ya na" (It's a nice day today) is converted to "Kyo wa ii tenki da ne" (It's a nice day today). At the same time, the conversion is performed in a way that preserves positive emotion information based on the output of the emotion engine.

[1103] Step 5:

[1104] The server generates an HTTP response including the converted text data and emotion information, and sends it to the user terminal. The input at this time is the converted text data and emotion information, and the output is the data sent to the user terminal.

[1105] Step 6:

[1106] The user device analyzes the received HTTP response and extracts the converted text data and emotional information. The conversion results and emotional information are then displayed on the screen, allowing the user to check the converted text and emotional information. The input in this case is the response data from the server, and the output is the data displayed on the screen.

[1107] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1108] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1109] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1110] [Fourth embodiment]

[1111] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1112] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1113] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1114] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1115] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1118] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1119] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1120] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1121] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1122] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1123] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1124] The present invention relates to a system for naturally converting between regional dialects and standard Japanese. The system consists of a user terminal, a server, and a series of processes that use natural language processing to identify and convert text data.

[1125] Program processing

[1126] Accepting input from the user

[1127] The user inputs text in a dialect or standard Japanese into the user terminal. This text can be a regional dialect such as Kansai dialect, such as "It's a nice day today," or standard Japanese, such as "It's a nice day today." By entering text into the input field and pressing the conversion button, the user terminal acquires this text data.

[1128] Sending Input

[1129] The user terminal transmits the input text data to the server. Specifically, it generates an HTTP request and transmits the request to the server together with the text data.

[1130] Language Identification

[1131] The server analyzes the received HTTP request and extracts the text data. It then uses a natural language processing model to automatically identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by the natural language processing model.

[1132] Conversion process

[1133] The server selects an appropriate conversion model based on the recognition results. Here, a model that converts Kansai dialect to standard Japanese is used. For example, "It's a nice day today" is converted to "It's a nice day today." Conversely, conversion from standard Japanese to a dialect is also possible, for example, "It's a nice day today" is converted to "It's a nice day today."

[1134] Sending the conversion results

[1135] The server generates an HTTP response including the converted text data and sends it to the user terminal. At this time, the response includes the converted text.

[1136] Displaying the results

[1137] The user device analyzes the received HTTP response and extracts the converted text data. Finally, the user device displays the conversion result on the screen and provides feedback to the user. For example, the conversion result "It's nice weather today" is displayed.

[1138] Specific examples

[1139] A specific example of use is as follows:

[1140] 1. User operations

[1141] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[1142] 2. Terminal Processing

[1143] The terminal transmits the input text data to the server.

[1144] 3. Server Processing

[1145] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[1146] The server converts the text data into standard Japanese, "It's nice weather today."

[1147] The converted text data is sent to the user terminal.

[1148] 4. Displaying the terminal

[1149] The terminal displays the conversion result "It's a nice day today" to the user.

[1150] In this way, this system achieves smooth communication by converting between dialects and standard Japanese while preserving the distinctive characteristics of the region. This system can be used in a variety of fields, including business, education, and tourism, and will help promote communication both within and outside the region.

[1151] The processing flow will be explained below.

[1152] Step 1:

[1153] The user inputs text in a dialect or standard language into the input field. The user terminal acquires the input text data and waits for the user to press the conversion button.

[1154] Step 2:

[1155] When the user presses the convert button, the device generates an HTTP request to send the text data to the server. Specifically, it sends a POST request to the server containing the text data to the URL endpoint / convert.

[1156] Step 3:

[1157] The server analyzes the received HTTP request and extracts the text data. At this time, it verifies whether the character encoding and format are correct, and passes the correctly extracted text on to the next process.

[1158] Step 4:

[1159] The server uses a natural language processing (NLP) model to identify whether the input text is a dialect or standard language. Specifically, the server inputs the text data into a pre-trained NLP model to identify the most probabilistic type of language form.

[1160] Step 5:

[1161] The server selects an appropriate conversion model based on the recognition result. For example, if the recognition result is Kansai dialect, it selects a model that converts Kansai dialect to standard Japanese. Conversely, if the recognition result is standard Japanese, it selects a model that converts it to the specified dialect.

[1162] Step 6:

[1163] The server converts the text data using the selected conversion model. Specifically, the text data is input into the conversion model and the converted text is obtained. For example, "It's a nice day today" is converted to "It's a nice day today."

[1164] Step 7:

[1165] The server generates an HTTP response containing the converted text data and sends it to the user terminal. The response contains the converted text.

[1166] Step 8:

[1167] The terminal analyzes the received HTTP response, extracts the converted text data, and prepares to display the converted text on the screen based on the response format.

[1168] Step 9:

[1169] The terminal displays the converted text data on the screen and provides feedback to the user. The user can check whether the conversion result is correct. For example, the conversion result "It's a nice day today" is displayed on the screen.

[1170] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, enabling smooth communication.

[1171] Example 1

[1172] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1173] In today's information society, the ability to convert between regional dialects and standard Japanese is crucial for smooth communication, especially between regions. However, existing systems rarely perform this conversion naturally, often losing the nuances and subtle meanings of dialects. Another issue is the lack of systems that can convert text entered by users in real time and provide appropriate feedback.

[1174] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1175] In this invention, the server includes means for analyzing received text data and identifying whether it is a dialect or standard language, means for selecting an appropriate language conversion model based on the identification result and converting the dialect into standard language or converting standard language into a dialect, and means for generating the converted text data as an HTTP response and sending it to the user terminal. This enables natural mutual conversion of text data and immediate feedback.

[1176] "User" refers to a person who uses the system to input text in dialect or standard Japanese and performs a series of operations to convert between them.

[1177] "Terminal" refers to a device used by a user to input and display text data, including computers, smartphones, tablets, etc.

[1178] "Server" refers to a computer system that receives data sent from a terminal, analyzes, converts, and returns the results.

[1179] "Text data" refers to character string information that a user inputs into a terminal. The input text data includes dialects and standard Japanese.

[1180] "HTTP request" refers to the protocol and request message format used when a user terminal sends data to a server.

[1181] "HTTP response" refers to the protocol and response message format used when the server sends the conversion result and other data to the user terminal.

[1182] "Natural language processing model" refers to a machine learning model that analyzes text data and identifies and converts dialects and standard Japanese. Examples include BERT and GPT-3.

[1183] "Language conversion model" refers to a machine learning model used to convert text data between a specific dialect and standard Japanese.

[1184] "Parsing" refers to a series of computations performed to identify received text data.

[1185] "Conversion" refers to the process of changing text data into a specified format (dialect or standard language).

[1186] "Display" refers to the process in which the terminal displays the conversion result on the screen to provide it to the user.

[1187] The present invention relates to a system for naturally converting between regional dialects and standard Japanese. The system consists of a user terminal, a server, and a series of processes that use natural language processing to identify and convert text data.

[1188] User terminal

[1189] A user uses a terminal to input text and request conversion into the system. The terminal is a network-connected device such as a smartphone, computer, or tablet. This terminal acquires the text input by the user and sends it to the server when the user presses the conversion button. The input text can be a dialect such as "It's a nice day today" or standard Japanese such as "It's a nice day today."

[1190] server

[1191] The server receives text data sent from the user device and analyzes and converts it. Specifically, the server analyzes the HTTP request and extracts the text data. Next, it uses a natural language processing model to automatically identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by a natural language processing model (e.g., BERT, GPT-3).

[1192] Language Transformation Model

[1193] The server selects an appropriate language conversion model based on the identified language, and uses a model to convert dialects to standard Japanese and vice versa. For example, when converting from Kansai dialect to standard Japanese, "Kyo wa ii tenki ya naa" (It's a nice day today) is converted to "Kyo wa ii tenki da ne" (It's a nice day today). Conversely, conversion from standard Japanese to dialect is also possible, for example, "Kyo wa ii tenki da ne" (It's a nice day today) is converted to "Kyo wa ii tenki ya naa" (It's a nice day today).

[1194] Sending and displaying conversion results

[1195] The server generates an HTTP response containing the converted text data and sends it to the user's device. The device then analyzes the received HTTP response and extracts the converted text data. Finally, the device displays the conversion result on the screen and provides feedback to the user. For example, the conversion result might read, "It's nice weather today."

[1196] Specific examples

[1197] A specific example of how this system can be used is as follows:

[1198] 1. User operations

[1199] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[1200] 2. Terminal Processing

[1201] The terminal transmits the input text data to the server.

[1202] 3. Server Processing

[1203] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[1204] The server converts the text data into standard Japanese, "It's nice weather today."

[1205] The converted text data is sent to the user terminal.

[1206] 4. Displaying the terminal

[1207] The terminal displays the conversion result "It's a nice day today" to the user.

[1208] Through this example, the system can quickly and naturally convert text data entered by the user between dialect and standard Japanese, promoting communication between regions and enabling smooth information exchange.

[1209] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1210] Step 1: User enters text and presses the convert button

[1211] The user enters text in a dialect or standard language into the input field of the terminal. For example, this input is "It's a nice day today." When the user presses the conversion button, the terminal acquires the text data. The input here is the text entered by the user, and the output is the text data acquired by the terminal.

[1212] Step 2: The device sends the text data to the server

[1213] The device generates an HTTP request containing the retrieved text data and sends it to the server. Specifically, it uses the JavaScript fetch API to send a request to the appropriate endpoint. The input is the retrieved text data, and the output is the HTTP request sent to the server.

[1214] Step 3: The server analyzes the text data and identifies dialects or standard languages.

[1215] The server receives an HTTP request and extracts the text data. It then uses a natural language processing model to identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect. The input is the text data received by the server, and the output is the identification result of dialect or standard Japanese.

[1216] Step 4: The server selects the appropriate language translation model and translates the text.

[1217] The server selects an appropriate conversion model based on the classification results. Using a model that converts Kansai dialect to standard Japanese, it converts "Kyo wa ii tenki yana" to "Kyo wa ii tenki da ne." The input is the classification result of dialect or standard Japanese, and the output is the converted text data.

[1218] Step 5: The server sends the converted text data to the device.

[1219] The server generates an HTTP response containing the converted text data and sends it to the terminal. This response is in JSON format. The input is the converted text data, and the output is the HTTP response sent to the user terminal.

[1220] Step 6: The terminal parses the HTTP response and displays the conversion result

[1221] The terminal analyzes the received HTTP response and extracts the converted text data. Finally, the terminal displays the converted result on the screen. For example, the converted result "It's nice weather today" is displayed to the user. The input is the HTTP response received from the server, and the output is the converted result that the terminal displays on the screen.

[1222] (Application example 1)

[1223] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1224] Food delivery services face the challenge of making it difficult for delivery staff and restaurants to accurately understand the orders of users who speak regional dialects and respond quickly and smoothly. There is also a need for an appropriate method to promote communication without compromising regional characteristics.

[1225] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1226] In this invention, the server includes terminal means for inputting text in a dialect or standard language, transmission means for transmitting the input text data to the server, identification means for identifying the received text data and determining whether it is a dialect or standard language, conversion means for converting the dialect into standard language or converting standard language into a dialect based on the identification result, transmission means for transmitting the converted text data to the terminal means, display means for displaying the converted text data on the terminal means, and display means for displaying the converted text data as food delivery order information to delivery personnel and stores. This enables accurate and smooth communication between users who speak a local dialect and delivery personnel and stores who speak standard language.

[1227] "Terminal means" refers to a device that allows a user to input text in dialect or standard Japanese and display it.

[1228] The "transmission means" is a function for transmitting input text data to a server.

[1229] The "identification means" is a function for analyzing received text data and determining whether it is a dialect or standard language.

[1230] The "conversion means" is a function for converting dialects into standard language or converting standard language into dialects based on the identification results.

[1231] The "display means" is a function for displaying the converted text data on a user terminal, a delivery person, or in a store.

[1232] "Food delivery" refers to the delivery of meals and beverages to customers through a delivery service.

[1233] A "natural language processing model" is an algorithm or model used to identify the linguistic form of text data and perform any necessary transformations.

[1234] A "regional language database" is a database for learning and storing the correspondence between dialects and standard Japanese in a specific region.

[1235] This invention is a system that naturally converts text between dialects and standard Japanese, and is particularly applicable to food delivery services. This system is designed so that delivery staff and stores can accurately understand and respond even if the user uses a dialect. Below is a concrete example of how this system can be implemented.

[1236] System Configuration

[1237] This system mainly consists of the following hardware and software:

[1238] User device: Smartphone, tablet, etc.

[1239] Server: The back-end system that handles the calculations.

[1240] Natural language processing models: Algorithms for identifying linguistic forms in text data (e.g., BERT and GPT-3).

[1241] Regional Language Database: A database that learns the correspondence between dialects and standard Japanese.

[1242] Front-end application: An app that provides the user interface (e.g., an iOS or Android app).

[1243] Program processing explanation

[1244] User Interface

[1245] When a user places a food delivery order, they input text written in a dialect, such as "It's a nice day today, can I have one katsudon please?" This input text is sent from the device to the server.

[1246] Server Processing

[1247] The server analyzes the received text data and uses a natural language processing model (e.g., HuggingFace's BERT or GPT-3) to identify whether the text is in a dialect or standard Japanese. At this stage, the text is identified as Kansai dialect, such as "What a nice day today, can I have a katsudon please?"

[1248] After identification, the server refers to a regional language database and converts the dialect into standard Japanese. For example, the Kansai dialect "It's a nice day today, so I'll have one katsudon please" is converted to "It's a nice day today. I'll have one katsudon please." This allows delivery personnel and stores to accurately understand the order.

[1249] Displaying the results

[1250] The converted text data is then sent from the server to the user's device, the delivery person's device, and the store's device. Each device displays the converted text in standard Japanese. This converts the dialect entered by the user into standard Japanese, allowing the delivery person and store to respond accurately.

[1251] Examples and prompts

[1252] As a specific example, the following flow can be considered.

[1253] 1. User operation: The user enters "Thank you, I'd like one yakiniku set meal" and presses the order button.

[1254] 2. Server processing: The text is sent to the server, which converts it to "Thank you. I'd like one yakiniku set meal, please."

[1255] 3. Displaying the results: The app displays the conversion results and communicates the order details in standard Japanese to the delivery person or store.

[1256] Example prompt sentence:

[1257] User input: Thank you, I'll have a yakiniku set meal.

[1258] Model prompt: dialect -> standard Japanese

[1259] Translated: Thank you. I'd like one yakiniku set meal, please.

[1260] This series of processes enables accurate and smooth communication between users who speak local dialects and delivery people and stores who speak standard Japanese.

[1261] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1262] Step 1:

[1263] User Input

[1264] The user opens the application on the terminal, enters the order text in the dialect into the text input field, and presses the send button. This becomes the input data.

[1265] Input: The dialect text entered by the user.

[1266] Output: The device prepares this text to be sent.

[1267] Step 2:

[1268] Sending input data

[1269] The terminal sends the text data entered by the user to the server as an HTTP request. Specifically, it generates a POST request and sends a payload including the text data to the server.

[1270] Input: Dialect text data entered by the user.

[1271] Output: Text data wrapped in an HTTP request is sent to the server.

[1272] Step 3:

[1273] Receiving and analyzing text data

[1274] The server parses the received HTTP request and extracts text data, which is then analyzed using a natural language processing model (e.g., HuggingFace's BERT) to identify dialects and standard Japanese.

[1275] Input: Text data contained in the payload of the HTTP request.

[1276] Output: Identification of the text as dialect or standard.

[1277] Step 4:

[1278] Language Conversion

[1279] Based on the classification results, the server selects an appropriate conversion model (e.g., GPT-3) and converts the text data. Specifically, it converts the dialect "Thank you very much, I'd like a yakiniku set meal please" into standard Japanese "Thank you. I'd like a yakiniku set meal please."

[1280] Input: Dialect text data and its classification results.

[1281] Output: Converted standard Japanese text data.

[1282] Step 5:

[1283] Sending the conversion results

[1284] The server generates an HTTP response containing the converted text data and sends it to the user's device, the delivery person's device, and the store's device. Specifically, the HTTP response payload includes the converted text.

[1285] Input: Converted standard Japanese text data.

[1286] Output: Text data wrapped in an HTTP response and sent to the device.

[1287] Step 6:

[1288] Displaying the conversion results

[1289] The user device and the delivery person / store device analyze the received HTTP response and extract the converted standard Japanese text data. The user device displays the converted text to the user, and the delivery person / store device displays it to each employee. Specifically, the application's text view displays "Thank you. I'd like one yakiniku set meal, please."

[1290] Input: HTTP response containing the converted standard Japanese text data.

[1291] Output: The converted text displayed on the application screen.

[1292] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1293] This invention relates to a system that naturally converts between regional dialects and standard Japanese, and also combines it with an emotion engine that recognizes the user's emotions. This system consists of a series of processes that use a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine to identify and convert text data and perform appropriate conversion according to the emotion.

[1294] Program processing

[1295] Accepting input from the user

[1296] The user inputs text in a dialect or standard Japanese into the user terminal. This text can be a regional dialect such as Kansai dialect, such as "It's a nice day today," or standard Japanese, such as "It's a nice day today." By entering text into the input field and pressing the conversion button, the user terminal acquires this text data.

[1297] Sending Input

[1298] The user terminal transmits the input text data to the server. Specifically, it generates an HTTP request and transmits the request to the server together with the text data.

[1299] Language and Emotion Recognition

[1300] The server analyzes the received HTTP request and extracts the text data. It uses a natural language processing model to identify whether the text is in a dialect or standard Japanese. For example, the text "It's a nice day today" is identified as Kansai dialect by the natural language processing model. At the same time, it uses an emotion engine to recognize the emotion of the text data. For example, the emotion engine recognizes positive emotion (joy) for "It's a nice day today."

[1301] Conversion process

[1302] The server selects an appropriate conversion model based on the recognition results. In this case, a model that converts Kansai dialect to standard Japanese is used. Furthermore, based on the recognition results of the emotion engine, the conversion is performed taking into account emotional information. For example, when the input text "It's a nice day today" is converted to "It's a nice day today," the conversion is adjusted to maintain a positive emotion.

[1303] Sending the conversion results

[1304] The server generates an HTTP response including the converted text data and sends it to the user terminal. At this time, the response includes the converted text and emotion information.

[1305] Displaying the results

[1306] The user device analyzes the received HTTP response and extracts the converted text data. It also acquires the emotion information and finally displays it on the screen along with the conversion result. The user can check the converted text and the result with the emotion information added.

[1307] Specific examples

[1308] A specific example of use is as follows:

[1309] 1. User operations

[1310] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[1311] 2. Terminal Processing

[1312] The terminal transmits the input text data to the server.

[1313] 3. Server Processing

[1314] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[1315] At the same time, it uses an emotion engine to recognize emotions as positive.

[1316] The server converts the text data into standard Japanese, "It's nice weather today."

[1317] Positive emotional information is added to generate converted text data.

[1318] The converted text data and emotion information are sent to the user terminal.

[1319] 4. Displaying the terminal

[1320] The device displays the conversion result, "It's nice weather today," as positive emotional information to the user.

[1321] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, and then adds emotional information to achieve richer communication.

[1322] The processing flow will be explained below.

[1323] Step 1:

[1324] The user inputs text in a dialect or standard language into the input field. The user terminal acquires the input text data and waits for the user to press the conversion button.

[1325] Step 2:

[1326] When the user presses the convert button, the device generates an HTTP request to send the text data to the server. Specifically, it sends a POST request to the server containing the text data to the URL endpoint / convert.

[1327] Step 3:

[1328] The server analyzes the received HTTP request and extracts the text data. At this time, it verifies whether the character encoding and format are correct, and passes the correctly extracted text on to the next process.

[1329] Step 4:

[1330] The server uses a natural language processing (NLP) model to identify whether the text is in a dialect or standard Japanese. Specifically, it uses a pre-trained NLP model to identify the linguistic form of the text data. For example, the text "It's a nice day today" is identified as Kansai dialect.

[1331] Step 5:

[1332] The server uses an emotion engine to recognize emotions in input text data, for example, recognizing positive emotions (joy) from the text "What a nice day today."

[1333] Step 6:

[1334] The server selects an appropriate conversion model based on the classification results. In this case, it selects a model that converts Kansai dialect to standard Japanese, and further considers the recognized emotion when converting.

[1335] Step 7:

[1336] The server converts the text data using the selected conversion model, for example, converting "It's a nice day today" to "It's a nice day today," and adds positive sentiment information to the converted text.

[1337] Step 8:

[1338] The server generates an HTTP response including the converted text data and emotion information, and sends it to the user terminal. The response includes the converted text and emotion information.

[1339] Step 9:

[1340] The device analyzes the received HTTP response, extracts the converted text data and emotion information, and prepares to display them on the screen based on the response format.

[1341] Step 10:

[1342] The device displays the converted text data and the emotion information on the screen and provides feedback to the user. For example, the conversion result "It's nice weather today (positive)" and the emotion information are displayed on the screen.

[1343] In this way, through a series of steps, the system converts the text entered by the user into either dialect or standard Japanese, and then adds emotional information to achieve richer communication.

[1344] Example 2

[1345] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1346] In today's world, deepening mutual understanding between regional dialects and standard Japanese is important, but accurately conveying subtle emotional nuances in these languages ​​is difficult. Furthermore, conventional technologies for converting between dialects and standard Japanese have difficulty taking emotional information into account, resulting in a decline in the quality of communication. Furthermore, even when natural language processing technology is used, the recognition and reflection of emotional information is insufficient, making it impossible to accurately understand and convey the user's intentions. Therefore, the present invention aims to solve these problems by providing a system that appropriately recognizes and reflects emotional information when converting between dialects and standard Japanese.

[1347] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1348] In this invention, the server includes means for analyzing received text data and determining whether it is a dialect or standard language, means for applying a language conversion model to convert the dialect into standard language or convert standard language into the dialect based on the determination result, and means for recognizing emotions in the text data and reflecting them in the conversion result. This allows text entered by a user to be accurately converted into dialect or standard language and transmitted while retaining the emotional nuances.

[1349] An "information processing device" is a device that allows a user to input text data and has the function of processing and communicating the input data.

[1350] A "communication device" is a device that includes hardware and software for transmitting and receiving data between an information processing device and a server.

[1351] "Analysis" refers to the process of understanding the content of input text data and determining whether it is a dialect or standard language.

[1352] A "language conversion model" is an algorithm that converts between dialects and standard Japanese based on a specific regional language database.

[1353] An "emotion engine" is an algorithm that recognizes emotional information contained in text data and outputs that information.

[1354] A "generative AI model" is an algorithm that uses machine learning technology to perform natural language processing and emotion recognition.

[1355] A "natural language processing model" is an algorithm that includes techniques for computers to understand and manipulate human language.

[1356] A "regional language database" is a dataset that collects examples of dialects and standard languages ​​in a specific region and learns the correspondences between them.

[1357] An "HTTP request" is a protocol for sending data from a client to a server, and is a message format for requesting and sending data.

[1358] The "JSON format" is a lightweight data exchange format for structuring and expressing data, and is a text format that is easy to read for both humans and machines.

[1359] MODE FOR CARRYING OUT THE INVENTION

[1360] This invention relates to a system that naturally converts between regional dialects and standard Japanese, and also combines it with an emotion engine that recognizes the user's emotions. This system consists of a series of processes that use a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine to identify and convert text data and perform appropriate conversion according to the emotion.

[1361] Hardware and Software Use

[1362] The user terminal functions as an input device for users to input text in dialect or standard Japanese. Specifically, this includes information processing devices such as PCs, smartphones, and tablets. When a user inputs text into an input field and presses the conversion button, the user terminal temporarily stores the text data in memory and prepares to proceed to the next processing step.

[1363] The terminal includes the text data entered by the user in an HTTP request and sends it to the server. The communication device used for this purpose has the function of providing a network connection. It generates an HTTP request and sends the text data to the server's endpoint using the POST method.

[1364] The server processes the received HTTP request and extracts the text data. Using a natural language processing model (such as GPT-3 or BERT), the server identifies whether the text is in a dialect or standard Japanese. At the same time, it uses an emotion engine to recognize the emotion of the text data. For example, it recognizes that the text "What a nice day today" is in the Kansai dialect and contains positive emotion (joy).

[1365] Based on the results of the classification, the server applies a language conversion model trained using a specific regional language database to convert dialects to standard Japanese or vice versa. The server also takes into account the recognition results of the emotion engine, preserving emotional information during the conversion. For example, "It's a nice day today" is converted to "It's a nice day today."

[1366] The server generates an HTTP response containing the converted text data and emotion information, and sends it to the user's device.

[1367] The terminal analyzes the received HTTP response, extracts the converted text data and emotion information, and displays the converted text data and emotion information in a specific area of ​​the user interface, allowing the user to check the converted text and emotion information.

[1368] Specific examples

[1369] Specific usage examples are:

[1370] User operations

[1371] The user inputs "It's a nice day today" into the terminal and presses the conversion button.

[1372] Terminal handling

[1373] The device creates a JSON containing the input text data "It's nice weather today" and sends an HTTP POST request to the server.

[1374] Server Processing

[1375] The server analyzes the input text and identifies it as Kansai dialect using a natural language processing model.

[1376] At the same time, it uses an emotion engine to recognize emotions as positive.

[1377] The server converts the text data into standard Japanese, such as "It's nice weather today," and adds positive emotional information.

[1378] The converted text data and emotion information are sent to the user terminal.

[1379] Terminal display

[1380] The device displays the conversion result, "It's nice weather today," as positive emotional information to the user.

[1381] This allows the system to convert text entered by the user between dialect and standard Japanese, and by adding emotional information, it is possible to achieve richer communication.

[1382] Prompt Sentence Examples

[1383] Example of Kansai dialect input text: "It's a nice day today."

[1384] Standard Japanese conversion example: "It's a nice day today."

[1385] Emotional information: Positive (joy)

[1386] As described above, the embodiments of the present invention provide a system that accurately converts text data entered by a user between dialect and standard Japanese, while preserving emotional nuances.

[1387] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1388] Step 1: Accepting input from the user

[1389] The user enters text data into the input field on the user terminal and presses the conversion button. Specifically, the following process is performed:

[1390] Get text data from the input field.

[1391] The text data is temporarily stored in memory in preparation for the next step.

[1392] Input: "What a nice day today" (Kansai dialect)

[1393] Output: Text data is stored in memory.

[1394] Step 2: Sending Input

[1395] The device generates an HTTP request containing the retrieved text data and sends it to the server. The specific operation is as follows:

[1396] Make an HTTP request using the POST method.

[1397] Add text data in JSON format to the request body.

[1398] Sends a request to the server at the specified endpoint.

[1399] Input: "What a nice day today" (text data stored in memory)

[1400] Output: An HTTP request containing text data is sent to the server.

[1401] Step 3: Language and emotion recognition

[1402] The server processes the received HTTP request and extracts the text data. Specifically, it does the following:

[1403] Parse the JSON data from the body of the HTTP request and extract the text data.

[1404] Use a natural language processing model (e.g., a generative AI model) to identify whether the text data is a dialect or standard language.

[1405] At the same time, an emotion engine is used to recognize emotions in the text data.

[1406] Input: "What a nice day today" (text data extracted from an HTTP request)

[1407] Output: Linguistic form (Kansai dialect) and emotional information (positive) are identified.

[1408] Step 4: Conversion process

[1409] The server then applies the appropriate language transformation model to convert the text based on the identified language form. The specific operations are as follows:

[1410] Select a model that converts Kansai dialect to standard Japanese.

[1411] Based on the results of the emotion engine, the text is appropriately converted while retaining emotional information.

[1412] Input: Language form (Kansai dialect) and emotional information (positive)

[1413] Output: Converted standard Japanese text "It's a nice day today" and emotional information (positive)

[1414] Step 5: Send the conversion results

[1415] The server generates an HTTP response containing the converted text data and emotion information, and sends it to the user's device. The specific operation is as follows:

[1416] The converted text data and emotion information are combined into a single JSON object.

[1417] Set the above JSON object in the body of the HTTP response.

[1418] An HTTP response is sent to the user terminal.

[1419] Input: Converted text "It's a nice day today" and emotional information (positive)

[1420] Output: JSON data is sent to the user device as an HTTP response.

[1421] Step 6: View the results

[1422] The device analyzes the received HTTP response and extracts the converted text data and emotion information. The specific operation is as follows:

[1423] Parse JSON data from an HTTP response.

[1424] The converted text data and emotional information are extracted and stored in separate variables.

[1425] The converted text data "It's a nice day today" and emotional information (positive) are displayed on the user interface.

[1426] Input: HTTP response (JSON data) received from the server

[1427] Output: The converted text data "It's a nice day today" and emotional information (positive) are displayed on the user's device screen.

[1428] (Application example 2)

[1429] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1430] While conventional text conversion systems can convert between dialects and standard Japanese, they are unable to take into account the user's emotional information, which means they are unable to properly convey the emotional nuances of the text. Furthermore, even in advertisements or customer service messages that utilize regional dialects, conversion that does not take emotional information into account makes it difficult to achieve effective communication. This poses a challenge, as it makes it difficult to increase the impact of advertisements or enhance relationships with customers.

[1431] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1432] In this invention, the server includes means for identifying input text data and determining whether it is a dialect or standard language, means for converting the dialect into standard language or converting the standard language into a dialect based on the identification result and emotional information, and further adjusting the language to correspond to the emotion, and means for transmitting the converted text data and emotional information to the user terminal. This allows the user's emotional information to be appropriately reflected in the text conversion, making it possible to generate more effective advertisements and customer service messages.

[1433] A "dialect" or "standard language" is a unique language form used in a particular region or cultural area within Japan, and has characteristics that differ from the general national language.

[1434] "Emotional information" refers to the emotional nuances and attitudes contained in the text entered by the user, and is information that includes emotional states such as positive, negative, and neutral.

[1435] A "user terminal" is a device on which a user inputs text and checks the converted text result, and includes a smartphone, tablet, PC, etc.

[1436] The "server" is a centralized management system that receives and processes text data sent from user terminals, and is the device that performs text conversion and emotion recognition processing.

[1437] A "natural language processing model" is an artificial intelligence model that analyzes input text data and identifies its linguistic form, and is a technology for understanding and classifying the content of the text.

[1438] An "emotion engine" is a technology for recognizing emotional information contained in text data, and is a model for analyzing the emotional nuances of text and evaluating emotional states.

[1439] A "language conversion model" is an algorithm that uses a specific regional language database to learn the correspondence between dialects and standard Japanese and convert between the two.

[1440] "Converted text data" refers to new text obtained by subjecting input text to a specified conversion process, and is the data resulting from conversion from standard Japanese to a dialect, or from a dialect to standard Japanese.

[1441] A "regional language database" is a database that compiles variations of dialects and standard Japanese used in various regions of Japan, and is a collection of data used to train language conversion models.

[1442] The "emotion database" is a database that classifies and organizes emotional information accompanying text data, and is a source of information to support the learning and evaluation of the emotion engine.

[1443] A specific embodiment for carrying out the present invention will now be described. The present invention is realized using a user terminal, a server, a natural language processing model, a language conversion model, and an emotion engine. The operation and interaction of each element will be described below.

[1444] User terminal

[1445] First, the user inputs text in a dialect or standard Japanese using a user terminal. User terminals include smartphones, tablets, and PCs. The user inputs text into an input field and confirms the input text by pressing the conversion button. The input text at this stage is then sent to the server.

[1446] server

[1447] The server receives input text data sent from the user's device. Specifically, it receives text data via an HTTP request. The server analyzes the received text data and uses a natural language processing model to identify whether the data is written in a dialect or standard Japanese. It also uses an emotion engine to simultaneously recognize the emotional information contained in the text data.

[1448] Natural language processing model and emotion engine

[1449] The natural language processing model uses Hugging Face's "transformers" library to analyze text data and identify linguistic forms, while the emotion engine uses Hugging Face's sentiment analysis pipeline to analyze the emotional state contained in the text.

[1450] Language Transformation Model

[1451] A language transformation model is then used to convert the text from dialect to standard or vice versa. This model uses a specific regional language database to transform the text according to the regional linguistic form, and is adjusted to preserve emotional information by taking into account the output of the emotion engine.

[1452] Return to user terminal

[1453] The converted text data and emotion information are then sent back to the user device as an HTTP response by the server. The user device receives this and displays the converted text and emotion information on the screen. This allows the user to check the conversion results and manually correct them if necessary.

[1454] Examples of concrete examples and prompts

[1455] For example, consider the case where a user inputs the standard Japanese text "The release of a new product has been decided. Please look forward to it!". The server receives this text and converts it into Kansai dialect, such as "It's a nice day today," and reflects the output of the emotion engine to maintain a positive emotion. As a result, the user device displays "The release of a new product has been decided. Please look forward to it!".

[1456] An example of a prompt sentence would be, "Please convert the following text into the local dialect and recognize the emotion: We've decided to launch a new product. Look forward to it!" By inputting this into the generative AI model, appropriate text conversion and emotion recognition can be performed.

[1457] In this way, this system realizes mutual conversion between dialects and standard Japanese and retains emotional information, enabling effective and emotionally rich communication, particularly in advertising and customer service messages.

[1458] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1459] Step 1:

[1460] A user inputs text in a dialect or standard Japanese into a user terminal. The user inputs text into an input field and confirms the input text by pressing the conversion button. In this case, the input text is a dialect such as "It's a nice day today" or standard Japanese such as "It's a nice day today."

[1461] Step 2:

[1462] The user terminal sends the entered text data to the server. Specifically, it generates an HTTP request and sends it to the server including the text data. The input at this time is the text data entered by the user, and the output is the data to be sent to the server.

[1463] Step 3:

[1464] The server analyzes the received HTTP request and extracts the text data. The analyzed text data is input into a natural language processing model to identify the language form. For example, "It's nice weather today" is identified as Kansai dialect. At the same time, an emotion engine is used to recognize the emotion of the text data. For example, for "It's nice weather today," the emotion engine recognizes a positive emotion (joy).

[1465] Step 4:

[1466] The server selects an appropriate language conversion model based on the identification results. The inputs are the identification results and emotion information, and the output is the selected conversion model. For example, using a model that converts Kansai dialect into standard Japanese, "Kyo wa ii tenki ya na" (It's a nice day today) is converted to "Kyo wa ii tenki da ne" (It's a nice day today). At the same time, the conversion is performed in a way that preserves positive emotion information based on the output of the emotion engine.

[1467] Step 5:

[1468] The server generates an HTTP response including the converted text data and emotion information, and sends it to the user terminal. The input at this time is the converted text data and emotion information, and the output is the data sent to the user terminal.

[1469] Step 6:

[1470] The user device analyzes the received HTTP response and extracts the converted text data and emotional information. The conversion results and emotional information are then displayed on the screen, allowing the user to check the converted text and emotional information. The input in this case is the response data from the server, and the output is the data displayed on the screen.

[1471] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1472] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1473] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1474] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1475] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1476] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1477] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1478] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1479] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1480] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1481] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1482] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1483] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1484] 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.

[1485] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1486] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1487] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1488] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1489] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1490] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1491] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1492] The following is further disclosed regarding the above embodiment.

[1493] (Claim 1)

[1494] a user terminal for inputting text in dialect or standard language;

[1495] means for transmitting input text data to a server;

[1496] means for identifying the received text data and determining whether it is a dialect or standard language;

[1497] A means for converting dialects into standard language or standard language into dialects based on the identification results;

[1498] means for transmitting the converted text data to a user terminal;

[1499] A means for displaying the converted text data on a user terminal

[1500] A system including:

[1501] (Claim 2)

[1502] 10. The system of claim 1, which uses a natural language processing model to identify linguistic forms of the text data.

[1503] (Claim 3)

[1504] 10. The system of claim 1, including a language conversion model that uses a specific regional language database to learn correspondences between dialects and standard Japanese.

[1505] "Example 1"

[1506] (Claim 1)

[1507] a terminal where a user inputs text in dialect or standard language;

[1508] A means for transmitting input text data from the terminal to a server;

[1509] means for analyzing the text data received by the server and identifying whether it is a dialect or standard language;

[1510] A means for selecting an appropriate language conversion model based on the identification result and converting dialects into standard language or standard language into dialects;

[1511] means for generating the converted text data as an HTTP response and transmitting it to the user's terminal;

[1512] A means for analyzing the converted text data received by the terminal and displaying it on the screen

[1513] A system including:

[1514] (Claim 2)

[1515] 10. The system of claim 1, wherein the system uses a natural language processing model to identify the language of the text data.

[1516] (Claim 3)

[1517] 10. The system of claim 1, including a language conversion model that uses a specific regional language database to learn correspondences between dialects and standard Japanese.

[1518] "Application Example 1"

[1519] (Claim 1)

[1520] a terminal means for inputting text in dialect or standard language;

[1521] a transmitting means for transmitting the input text data to a server;

[1522] an identification means for identifying the received text data and determining whether the text data is a dialect or standard language;

[1523] A conversion means for converting a dialect into standard language or converting standard language into a dialect based on the identification result;

[1524] a transmitting means for transmitting the converted text data to a terminal means;

[1525] a display means for displaying the converted text data on the terminal means;

[1526] A display method that displays the converted text data as food delivery order information to delivery staff and stores.

[1527] A system including:

[1528] (Claim 2)

[1529] 10. The system of claim 1, which uses a natural language processing model to identify linguistic forms of the text data.

[1530] (Claim 3)

[1531] 10. The system of claim 1, including a language conversion model that uses a specific regional language database to learn correspondences between dialects and standard Japanese.

[1532] "Example 2: Combining Emotion Engines"

[1533] (Claim 1)

[1534] an information processing device for inputting a text in a dialect or standard language;

[1535] means for transmitting input text data to a communication device;

[1536] means for analyzing the received text data to determine whether it is a dialect or standard language;

[1537] A means for converting the dialect into standard language or converting standard language into the dialect by applying a language conversion model based on the determination result;

[1538] A means for recognizing emotions in text data and reflecting them in the conversion results;

[1539] means for transmitting the converted text data to an information processing device;

[1540] A means for displaying the converted text data on an information processing device

[1541] A system including:

[1542] (Claim 2)

[1543] 10. The system of claim 1, which uses a generative AI model to identify linguistic form and sentiment of text data.

[1544] (Claim 3)

[1545] 10. The system of claim 1, further comprising a language conversion model that uses a specific regional language database to learn correspondences between dialects, standard language, and emotional information.

[1546] "Application example 2 when combining emotion engines"

[1547] (Claim 1)

[1548] a user terminal for inputting text in dialect or standard language;

[1549] means for transmitting input text data to a server;

[1550] means for identifying the received text data and determining whether it is a dialect or standard language;

[1551] A means for converting dialects into standard language or converting standard language into dialects based on the identification result and emotion information, and further adjusting the dialects in a manner corresponding to the emotion;

[1552] means for transmitting the converted text data and emotion information to a user terminal;

[1553] A means for displaying the converted text data and emotion information on a user terminal.

[1554] A system including:

[1555] (Claim 2)

[1556] 10. The system of claim 1, which uses a natural language processing model and an emotion engine to identify linguistic forms and emotions in the text data.

[1557] (Claim 3)

[1558] 10. The system of claim 1, further comprising a language translation model and emotion engine that uses a specific regional language database and emotion database to learn correspondences between dialects and standard language and emotion information. [Explanation of symbols]

[1559] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a user terminal for inputting text in dialect or standard language; means for transmitting input text data to a server; means for identifying the received text data and determining whether it is a dialect or standard language; A means for converting dialects into standard language or converting standard language into dialects based on the identification results; means for transmitting the converted text data to a user terminal; A means for displaying the converted text data on a user terminal; A system including:

2. The system of claim 1 , which uses a natural language processing model to identify linguistic forms of the text data.

3. 10. The system of claim 1, further comprising a language conversion model that uses a specific regional language database to learn correspondences between dialects and standard Japanese.

Images